diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index 58b9255c33d57bf53fe4b434dc1a9ba6a2a7b721..5c4b1ed8c10f297fdb405a1e1a0e2a95dbd1dfc0 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": "20260515T060029Z", - "generated_at": "2026-05-15T06:04:51Z", + "snapshot_id": "20260515T120027Z", + "generated_at": "2026-05-15T12:09:10Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1620,6 +1620,56 @@ } ] }, + { + "cluster_id": "cluster-45853-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45853.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45853, + "canonical_pr_number": 45863, + "issue_numbers": [ + 45853 + ], + "pr_numbers": [ + 45863, + 45986 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45863, + "right_pr_number": 45986, + "code_similarity": 0.141, + "size_similarity": 0.156, + "file_overlap": 0.333, + "area_overlap": 0.0, + "patch_similarity": 0.066, + "shared_filenames": [ + "src/transformers/utils/import_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/utils/import_utils.py", + "left_ranges": [ + [ + 1315, + 1321 + ] + ], + "right_ranges": [ + [ + 1338, + 1345 + ] + ] + } + ] + } + ] + }, { "cluster_id": "cluster-45081-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", @@ -2188,6 +2238,15 @@ ], "target_issue_number": 45647, "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-45853-3", + "canonical_pr_number": 45863, + "duplicate_pr_numbers": [ + 45986 + ], + "target_issue_number": 45853, + "reason": "PRs in cluster-45853-3 are treated as duplicates because they converge on issue #45853 with closing_reference, shared_issue_target evidence." } ], "best_issue": { diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index fe13419bf490f489af924c38ba39cd1442ff3d4d..a520933bbff8491c8237052fecc6554722cdc998 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": "20260515T060029Z", - "generated_at": "2026-05-15T06:04:51Z", + "snapshot_id": "20260515T120027Z", + "generated_at": "2026-05-15T12:09:10Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -13,10 +13,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:24643", "issue:30277", @@ -131,262 +131,406 @@ "issue:41093|issue:43638", "issue:43792|issue:45901" ], - "prepared_review_unit_hash": "ca841ab4584d65cd09eac411188d38fbd226e3f152249a9752dd7fc47802c51f", + "prepared_review_unit_hash": "07fbf3057b486d500f7af51353f393cc719d1228ad7d54daddf8cebcd2f36987", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 62, - "serialized_chars": 46363, - "estimated_input_tokens": 11591, - "estimated_eval_tokens": 23438 + "serialized_chars": 46378, + "estimated_input_tokens": 11595, + "estimated_eval_tokens": 23446 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a mix of unrelated issue families, with only a few true duplicates: a ZeRO-3/Bert zero-size index bug and a broader AutoTokenizer v5 regression, plus one possible Qwen3_5Moe rotary-embedding duplicate. Most soft edges are false positives from broad semantic similarity.", - "confidence": 0.62, - "canonical_issue_reason": "issue:45920 is the broadest, most representative issue here: a silent AutoTokenizer v5 regression affecting many model families, which is the best anchor for the tokenizer-related duplicate set.", + "summary": "Most pairs are only loosely related by subsystem or error shape. I accepted just two true duplicate clusters: the BertModel/DeepSpeed ZeRO-3 index-0 OOB reports, and the AutoTokenizer v4\u2192v5 token-id regression reports. There are no PRs in this set.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45920 is the best canonical issue: it is an open, broad report of the AutoTokenizer wrong-token-IDs regression across multiple model families, so it best anchors the accepted tokenizer duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45920 has the widest blast radius and clearest regression framing, making it the best overall issue candidate in this cluster.", + "best_issue_reason": "issue:45920 is the strongest issue candidate overall because it is open, broad, and captures the underlying tokenizer regression more generally than the narrower Granite-only report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different problems: a missing config attribute vs a streaming chat/completions failure." + "reason": "Different models and failure modes: missing Qwen3_5Config field vs streaming chat/completions failure." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Unrelated model/runtime failures on different hardware paths; not the same bug." + "reason": "Unrelated hardware/backend errors: AMD GPU model load vs MPS histogram op not implemented." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Different model paths and symptoms: vision dtype mismatch vs GPT-OSS AMD execution failure." + "reason": "Different bug: dtype mismatch in image preprocessing/model vs AMD GPU load failure." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Both are runtime errors, but they involve different models and different device/dtype code paths." + "reason": "Both are dtype-related, but they affect different models and code paths; not the same underlying bug." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "No shared underlying code path; one is AMD GPU loading, the other is an invalid method call in GraniteMoEHybrid." + "reason": "Different MoE/model-specific failures; not the same concrete error path." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Different model families and failure modes; not plausibly one fix." + "reason": "Different models and symptoms; no clear shared underlying bug." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch and ONNX export are unrelated code paths." + "reason": "DeepSpeed collective mismatch is unrelated to ModernBERT ONNX export." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "ONNX export error vs FP8 model loading failure; no common bug." + "reason": "Both involve model loading/export issues, but these are different models and distinct failures." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "Different subsystems: export tooling vs device mapping runtime crash." + "reason": "ONNX export error is unrelated to Qwen3 auto device mapping cudaErrorAssert." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are stale v5 docs, but they cover different removed features and should be triaged separately." + "reason": "Both are v5 docs cleanups, but they target different removed references and are not the same change." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "Export failure and GenerationMixin import regression are unrelated." + "reason": "ONNX export failure is unrelated to the GenerationMixin import error." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Mask shape mismatch and Gemma4 device mismatch do not point to the same bug." + "reason": "Generic mask-shape mismatch is not the same as Gemma4 PLE device mismatch." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Both are index/shape errors, but they arise in different model and execution contexts." + "reason": "Different failures: DeepSpeed ZeRO-3 index error vs mask/tensor shape mismatch." }, { "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "Same broad error class, but the model/setup differs enough that a shared fix is not clear." + "reason": "Different symptoms and code paths; the shared 'IndexError' wording is too broad to treat as duplicate." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Different models and failure mechanisms; not a duplicate." + "reason": "Mask-shape IndexError and GPT-OSS tensor-parallel issue are unrelated." }, { "left": "issue:44805", "right": "issue:44918", "accept": false, - "reason": "Mask indexing failure vs TRL embedding unpacking failure are distinct issues." + "reason": "Different model/trainer path; no evidence of the same bug." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "Processor voice_preset bug is unrelated to ModernBERT ONNX export." + "reason": "BarkProcessor voice preset bug is unrelated to ModernBERT ONNX export." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Both mention DeepSpeed, but one is a collective mismatch and the other is a zero-sized index error; different bugs." + "reason": "Both mention DeepSpeed, but one is a collective mismatch and the other is a BertModel index error." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3/Bert index-0-out-of-bounds failure pattern, with the same loading/training path and likely one fix." + "reason": "Same ZeRO-3/BertModel out-of-bounds index failure; only the wording differs (init/training, pretrained/non-pretrained)." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger kernel cross-entropy routing and GPT-OSS tensor-parallel failure are different problems." + "reason": "Liger Kernel cross-entropy call issue is unrelated to GPT-OSS tensor-parallel failure." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Detokenization regression and LoRA merge/save inconsistency do not share the same underlying bug." + "reason": "Different problems: detokenization regression vs LoRA merge/save/reload mismatch." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "NVFP4 execution error vs LoRA reload mismatch are unrelated." + "reason": "Unrelated model execution error vs LoRA weight merge inconsistency." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "FSDP activation-checkpointing size mismatch is not the same as this mask indexing bug." + "reason": "Activation-checkpointing/FSDP recomputation error is unrelated to the mask-shape IndexError." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "Both involve DeepSpeed, but they are different errors in different training scenarios." + "reason": "Both are DeepSpeed-related, but they are different runtime errors on different code paths." }, { "left": "issue:45859", "right": "issue:45902", - "accept": true, - "reason": "Same Qwen3_5MoeTextRotaryEmbedding device/materialization path; both point to the same buffer initialization/offload bug." + "accept": false, + "reason": "Both involve Qwen3_5MoeTextRotaryEmbedding, but one is CPU offload compatibility and the other is uninitialized-memory materialization; not the same bug." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Different model/setup and different error shape." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "FSDP checkpointing tensor-size mismatch is unrelated to the CustomTrainer signature change." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "DeepSpeed/BertModel index error is unrelated to GPT-OSS tensor-parallel behavior." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model families and failures; not the same underlying bug." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3 vLLM config attribute error is unrelated to the Mistral tokenizer regex crash." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Different Gemma4 issues: device mismatch in forward vs expensive reverse embedding lookup." }, { "left": "issue:43425", "right": "issue:44292", "accept": false, - "reason": "Torch version incompatibility and Qwen NVFP4 runtime failure are separate issues." + "reason": "Torch version incompatibility is unrelated to Qwen-3-8B-NVFP4 runtime error." }, { "left": "issue:43828", "right": "issue:45161", "accept": false, - "reason": "Autocast dtype mismatch and GPT-OSS-only tensor parallel failure are unrelated." + "reason": "Both are MoE-related, but the actual failures and code paths differ." }, { - "left": "issue:34928", - "right": "issue:41720", + "left": "issue:44918", + "right": "issue:45161", "accept": false, - "reason": "FSDP checkpointing mismatch and auto-device-map CUDA assert are different problems." + "reason": "TRL SFT input-embedding unpacking issue is unrelated to GPT-OSS TP failure." }, { - "left": "issue:44918", - "right": "issue:45161", + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different model/backend errors; no shared concrete bug." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Mixtral torch-dynamo grouped_mm tracing failure is unrelated to Mistral-3 dtype mismatch." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Both are dtype/model execution issues, but they are different models and distinct failures." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Invalid method call in GraniteMoEHybrid is unrelated to the MPS histogram op issue." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model-specific runtime failures." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Different model families and failure modes." + }, + { + "left": "issue:43039", + "right": "issue:44918", "accept": false, - "reason": "TRL SFT embedding unpacking failure is not the same as GPT-OSS tensor-parallel failure." + "reason": "Liger Kernel cross-entropy call vs TRL SFT embedding unpacking are unrelated." }, { "left": "issue:41762", "right": "issue:43638", "accept": false, - "reason": "Both are ZeRO-3 index errors, but the model contexts differ enough that a shared root cause is not established." + "reason": "Both mention ZeRO-3 and index errors, but Gemma3 loading and BertModel training are different concrete bugs." }, { "left": "issue:43827", "right": "issue:44512", "accept": false, - "reason": "Both are documentation regressions from v5 removals, but they cover different removed entry points." + "reason": "Both are docs regressions, but they refer to different removed v5 artifacts and different pages." }, { "left": "issue:43716", "right": "issue:44560", "accept": false, - "reason": "Different multimodal failures: image-preprocessor dtype mismatch vs video StopIteration." + "reason": "Different model-specific errors: image-preprocessor dtype mismatch vs video StopIteration." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different code paths and backends; no duplicate evidence." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Video embedding StopIteration and MPS histogram implementation error are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Both are model/runtime issues, but not the same bug or change." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch is unrelated to the trainer signature TypeError." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Activation checkpointing/FSDP error is unrelated to GenerationMixin import failure." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger Kernel cross-entropy invocation is unrelated to mask/tensor shape IndexError." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": false, + "reason": "Both are ZeRO-3 loading/index issues, but they affect different models and likely different root causes." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "TextClassificationPipeline docs issue is unrelated to the removed transformers run command docs issue." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different models and errors: Gemma3 config attribute missing vs Qwen3 device-mapping assert." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "GPT-OSS AMD GPU failure is unrelated to table-question-answering crash." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral is unrelated to Gemma4 device mismatch." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger Kernel cross-entropy issue is unrelated to Qwen3-vl video StopIteration." }, { "left": "issue:45812", "right": "issue:45920", "accept": true, - "reason": "Same AutoTokenizer v5 regression; 45920 is the broader multi-model report, and 45812 is a specific affected subset." + "reason": "Same AutoTokenizer v4\u2192v5 wrong-token-ID regression affecting multiple model families; 45920 is the broader report." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Checkpoint corruption and load failure for a different model are not the same bug." + "reason": "Corrupted Ovis2 checkpoint and NemotronH checkpoint-loading failure are different issues." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "Different models and different load symptoms; no clear shared fix." + "reason": "Different models and failure types; no shared root cause." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Both are shape/index errors, but they involve different tensor operations and model setups." + "reason": "Both are IndexErrors, but mask/tensor mismatch is not the same as the ZeRO-3 BertModel zero-size index error." }, { "left": "issue:43792", "right": "issue:45901", "accept": false, - "reason": "Whisper inference failure and table-question-answering crash are unrelated." + "reason": "Whisper run failure and table-question-answering crash are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative: it distinguishes the broad unrelated issue families, identifies the clearly related AutoTokenizer v5 regression cluster, and treats the Qwen3_5Moe pair as only a possible duplicate. The accepted soft-edge pairs are plausible and not overstated based on the available titles/body signals." + "feedback": "Grounded and conservative overall. The two accepted duplicate pairs are well supported by the packet: issue:43596/issue:43638 share the same ZeRO-3/BertModel index-out-of-bounds pattern, and issue:45812/issue:45920 clearly match the same AutoTokenizer v4\u2192v5 regression with 45920 being the broader canonical issue. The remaining pairs are mostly appropriately rejected on differing model, backend, or error-path evidence. No PR pairs are present." }, "evaluator_used": true, "retried": false, @@ -402,10 +546,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36010", "issue:39186", @@ -496,272 +640,269 @@ "issue:44530|issue:45005", "issue:42915|issue:45399" ], - "prepared_review_unit_hash": "181cd044c2ce24d415ec50f27f69f21c7149553d939d945cb2b5883741f964f8", + "prepared_review_unit_hash": "3d8e8814e89a6c3e00f5b875435285b92d3c5b0534bcfba2067a918879de8a30", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 38, - "serialized_chars": 38760, - "estimated_input_tokens": 9690, - "estimated_eval_tokens": 19636 + "serialized_chars": 38764, + "estimated_input_tokens": 9691, + "estimated_eval_tokens": 19638 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous and not a single duplicate set. I only see two true duplicate pairs: SigLIP2 bad-output reports, and the trust_remote_code/custom-module cache-collision reports. Everything else is at best thematic similarity, not the same underlying bug.", - "confidence": 0.79, - "canonical_issue_reason": "Issue 45698 is the clearest concrete bug report in the strongest duplicate subcluster: it describes the wrong custom module being loaded after save_pretrained, which matches the cache/path collision symptom in 45632.", + "summary": "The set is mostly a collection of distinct Transformers regression reports spanning different models, backends, and failure modes. The soft-similarity edges are largely false positives; at most they share broad themes like version compatibility, dtype issues, or loading problems, but not the same concrete bug.", + "confidence": 0.39, + "canonical_issue_reason": "issue:45020 is the broadest umbrella-style report in the set, centered on recent-version breakage for remote-code/custom models, so it is the best anchor for this heterogeneous cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45698 is the best representative issue overall because it is specific, actionable, and captures the underlying custom-code loading failure more cleanly than the broader symptom report.", + "best_issue_reason": "issue:45020 is the most general and reusable representative among these issues; it can subsume nearby custom-loading/version-regression reports better than the model-specific crashes.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Both mention sliding_window-related failures, but they affect different model families and different config fields; this is similarity, not the same bug." + "reason": "Both mention sliding window, but they hit different models and different failure modes; not the same bug." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "One is a torch-version incompatibility report and the other is a PretrainedConfig/pydantic break; too different in root cause and code path." + "reason": "One is a torch-version compatibility complaint, the other is a PretrainedConfig/pydantic regression; unrelated." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "Different failure modes and causes: ZeRO-3/BERT loading index error vs torch/transformers incompatibility." + "reason": "DeepSpeed ZeRO-3 loading error and a torch/transformers version incompatibility are distinct problems." }, { "left": "issue:43975", "right": "issue:45901", "accept": false, - "reason": "Detokenization corruption and table QA crashing are unrelated symptoms and do not point to the same code path." + "reason": "Detokenization on DeepSeek Coder and a table-question-answering crash are unrelated code paths." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Both involve Qwen3.5 and chat-like flows, but one is a transformers chat crash and the other is a streaming chat/completions failure; not the same concrete bug." + "reason": "Both involve Qwen3.5 chat usage, but one is a model crash and the other is a streaming API failure; not clearly the same defect." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "Whisper runtime failure and a pydantic/config field regression are unrelated." + "reason": "Whisper inference failure and a pydantic PretrainedConfig breakage do not match." }, { "left": "issue:44292", "right": "issue:45901", "accept": false, - "reason": "Qwen-3 NVFP4 runtime failure and table-question-answering crashes are different bugs in different paths." + "reason": "Qwen NVFP4 loading/runtime issues are unrelated to table-question-answering crashes." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "A tied lm_head bug in Mistral3 is not the same as a corrupted Ovis checkpoint." + "reason": "Missing tied weights in Mistral3 and a corrupted Ovis2 checkpoint are different root causes." }, { "left": "issue:39290", "right": "issue:45823", "accept": false, - "reason": "Gemma3 missing sliding_window_pattern and Gemma4 device mismatch are different issues, despite both being model-integration regressions." + "reason": "Gemma3 sliding_window_pattern and Gemma4 device_map mismatch are separate model bugs." }, { "left": "issue:45464", "right": "issue:45685", "accept": false, - "reason": "Chat streaming failure and an MPS Int histogram kernel error are unrelated." + "reason": "Qwen3.5 streaming API failure and an MPS int histogram error are unrelated." }, { "left": "issue:43541", "right": "issue:45685", "accept": false, - "reason": "Grouped_mm tracing failure in Mixtral and an MPS histogram kernel limitation are different code paths." + "reason": "Mixtral torch-dynamo grouped_mm failure and an MPS backend error are different code paths." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Both are dtype-related, but one is grouped_mm tracing and the other is autocast mismatch in Phi-tiny-MoE; not the same underlying bug." + "reason": "Both mention numeric/dtype problems, but they affect different models and operations; not the same bug." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Processor failure for Voxtral and a template-node compilation TypeError are unrelated." + "reason": "PaddleOCR-VL processor failure and a template-node compilation error are unrelated." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "ImportError for GenerationMixin and a Gemma3 sliding_window config error are not the same issue." + "reason": "Importing GenerationMixin and Gemma3 sliding_window_pattern are separate issues." }, { "left": "issue:41093", "right": "issue:41762", "accept": false, - "reason": "Both are IndexErrors, but one is a mask shape mismatch and the other is a zero-sized tensor during ZeRO-3 loading; different root causes." + "reason": "Both are IndexError-shaped failures, but one is a mask/tensor size mismatch and the other is zero-sized loading with ZeRO-3; not the same bug." }, { "left": "issue:45800", "right": "issue:45823", "accept": false, - "reason": "Torch/transformers version incompatibility and Gemma4 device-mismatch during forward are different problems." + "reason": "A torch/transformers version incompatibility is not the same as a Gemma4 device placement mismatch." }, { "left": "issue:43296", "right": "issue:43366", "accept": false, - "reason": "PaddleOCR-VL load failure in vLLM and gpt-oss GGUF support are not the same bug." + "reason": "PaddleOCR-VL loading failure and GGUF gpt-oss support are different feature areas." }, { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "Missing pad_token_idx after 5.0 update and a pydantic model-field regression are unrelated." + "reason": "Missing pad_token_idx in StableLmConfig is a specific config regression, not the pydantic PretrainedConfig field issue." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "CUDA memory regression under int4 quantization is not the same as tied-weight translation-model behavior in v5." + "reason": "Int4 memory growth/OOM and tied-weights handling are different problems." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Mixtral grouped_mm tracing and GPT-OSS TP-only failure are different model/runtime issues." + "reason": "Grouped_mm tracing failure in Mixtral and GPT-OSS tensor-parallel issues do not share the same code path." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "Autocast dtype mismatch in Phi-tiny-MoE and Qwen3.5 streaming API failure are different bugs." + "reason": "Phi dtype mismatch under autocast and Qwen3.5 streaming API failures are unrelated." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "Unexpected _is_hf_initialized argument in init_empty_weights is unrelated to the pydantic PretrainedConfig regression." + "reason": "init_empty_weights argument handling and a pydantic PretrainedConfig regression are distinct." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "GGUF gpt-oss support and Qwen3.5 streaming inference failures are not the same underlying issue." + "reason": "GGUF architecture support and streaming chat failures on Qwen3.5 are different issues." }, { "left": "issue:45020", "right": "issue:45800", "accept": false, - "reason": "Broad remote_code breakage and a specific torch/transformers incompatibility are too broad and different to treat as duplicates." + "reason": "Remote-code breakage and torch version incompatibility are only loosely related compatibility reports, not the same bug." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "A Qwen3-MoE sliding_window issue and a pydantic PretrainedConfig issue do not share a concrete code path." + "reason": "Qwen3-MoE sliding_window behavior and a pydantic config-field regression do not match." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Both are loading-time IndexErrors, but they come from different shapes, models, and initialization paths." + "reason": "Both are IndexErrors, but the model context and failure mechanics differ too much to be the same defect." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Grouped_mm tracing in Mixtral and missing Float8 storage support are different runtime failures." + "reason": "Mixtral grouped_mm tracing and missing Float8 storage are different backend/runtime problems." }, { "left": "issue:43054", "right": "issue:43994", - "accept": true, - "reason": "Both report SigLIP2 producing bad/nonsensical outputs, pointing to the same model-quality or implementation regression." + "accept": false, + "reason": "Both concern SigLIP2 quality, but one is embedding quality and the other is nonsensical AutoModel/pipeline outputs; not enough to treat as the same bug." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "TensorBoard-without-TensorFlow backend errors are unrelated to torch/transformers version incompatibility." + "reason": "TensorBoard-without-TensorFlow backend error and torch/transformers incompatibility are unrelated." }, { "left": "issue:45759", "right": "issue:45902", "accept": false, - "reason": "Composite Qwen config unwrapping and uninitialized-memory in rotary embedding are different bugs." + "reason": "Composite config unwrapping and uninitialized rotary frequency after to_empty(cuda) are different bugs." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "High perplexity on gpt-oss and a GLM5 issue do not describe the same failure." + "reason": "High perplexity on gpt-oss and a GLM5 issue are not the same underlying problem." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Gemma-3 multimodal dtype mismatch and Qwen3.5 embedding unpacking under TRL are different problems." + "reason": "Mistral-3 image-preprocessor dtype mismatch and Qwen3.5 embedding unpacking in TRL are separate failures." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP weight dimensionality and Qwen3.5/TRL embedding unpacking are unrelated." + "reason": "FSDP weight-shape error and Qwen3.5 embedding unpacking are different code paths." }, { "left": "issue:45632", "right": "issue:45698", - "accept": true, - "reason": "Both describe the same trust_remote_code/custom-code cache collision: local models with the same leaf name can resolve to the wrong loaded module." + "accept": false, + "reason": "Both involve custom code loading, but one is a cache-path collision and the other is wrong module selection after save/load; not the same concrete bug." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Mistral3 lm_head tying and translation-model tied-weight issues are similar only at a high level, not the same concrete bug." + "reason": "Both mention tied weights, but they concern different model families and likely different tie-weight regressions." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Jupyter custom model initialization and flash-attn fallback blocking are unrelated." + "reason": "Custom-model notebook initialization and flash-attn fallback gating are unrelated." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "PagedAttentionCache linear_attention failure and tied-weight translation-model issues are different subsystems and causes." + "reason": "PagedAttentionCache linear_attention support and translation-model tied weights are distinct issues." }, { "left": "issue:42915", "right": "issue:45399", "accept": false, - "reason": "Qwen3Moe FP8 failure and flash-attn fallback blocking are not the same underlying problem." + "reason": "FineGrainedFP8Config failure on Qwen3Moe and flash-attn fallback blocking are different configuration problems." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The two accepted duplicate pairs are supported by the issue titles, and the rejected soft-edge pairs are mostly framed as similarity rather than identity of bugs. No obvious overstatement of evidence." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -773,10 +914,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36331", "issue:38175", @@ -835,12 +976,12 @@ "issue:43975|issue:44292", "issue:43950|issue:44534", "issue:44292|issue:45507", - "issue:43644|issue:43950", "issue:39692|issue:43054", + "issue:43644|issue:43950", "issue:43828|issue:44928", "issue:36331|issue:41762", - "issue:43866|issue:44403", "issue:41628|issue:45800", + "issue:43866|issue:44403", "issue:43950|issue:45902", "issue:43872|issue:44589", "issue:43054|issue:45701", @@ -857,242 +998,242 @@ "issue:43975|issue:45237", "issue:44403|issue:44488", "issue:42947|issue:43856", - "issue:43782|issue:44960", "issue:43881|issue:43883", - "issue:41762|issue:42915" + "issue:41762|issue:42915", + "issue:43782|issue:44960" ], - "prepared_review_unit_hash": "8e89dea8719ecc725c18a5089445c5b8f28e69d3d521ae2973eda00b81899356", + "prepared_review_unit_hash": "2a861e141f00c9594184fd25c446b41d681a31a55bf395f76f53980e0ccb6dae", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 36583, - "estimated_input_tokens": 9146, - "estimated_eval_tokens": 18548 + "serialized_chars": 36585, + "estimated_input_tokens": 9147, + "estimated_eval_tokens": 18550 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a mix of unrelated issues, but it does contain a clear duplicate subcluster around the Transformers 5.x non-persistent buffer regression. A smaller SigLIP2-related subcluster also looks related, but not every SigLIP2 report is the same underlying bug.", - "confidence": 0.41, - "canonical_issue_reason": "Issue 43950 is the cleanest representative of the strongest duplicate subcluster: it describes the underlying non-persistent-buffer regression directly and matches multiple related reports (43644, 44534, 45902).", + "summary": "This set is mostly a loose mix of unrelated Transformers issues. The only clear duplicate family is the non-persistent-buffer regression; the rest are separate model-, loading-, or environment-specific bugs.", + "confidence": 0.87, + "canonical_issue_reason": "issue:43950 is the clearest umbrella report for the non-persistent-buffer regression, and the nearby reports (43644, 44534, 45902) read like narrower manifestations of the same bug.", "canonical_pr_reason": null, - "best_issue_reason": "43950 is the best issue to anchor the cluster because it captures the core bug in a concrete, reusable way rather than a single symptom.", + "best_issue_reason": "issue:43950 has the strongest, most general title and explicitly frames the problem as a Transformers 5.x regression, making it the best representative issue in this cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "Unrelated: one is about a DSA indexer ReLU discussion, the other is docs mentioning a removed command." + "reason": "Completely different topics: DSA indexer behavior vs docs mentioning a removed command." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Different problems: quantization/offloading behavior versus tied-weights handling in v5." + "reason": "Quantization/offloading behavior and tied-weights translation-model issues are unrelated bugs." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "Different failures: NemotronH checkpoint loading versus translation-model tied weights in v5." + "reason": "Model checkpoint loading failure does not match the tied-weights translation-model regression." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A typo in cache strategies is not the same as outdated docs about the removed transformers run command." + "reason": "A cache-strategy typo and a removed-command docs issue are not the same bug." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "Different code paths and symptoms: Qwen3.5 embedding unpacking with TRL versus GraniteMoEHybrid invalid method calls." + "reason": "Different model/code paths: TRL SFT embedding unpacking vs a GraniteMoEHybrid method call error." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "Different model-specific failures: detokenization bug versus runtime error on Qwen-3-8B-NVFP4." + "reason": "Detokenization regression and Qwen NVFP4 runtime failure are distinct issues." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Same underlying regression: both report non-persistent buffers being incorrectly populated with junk in Transformers 5.x." + "reason": "Both report the same non-persistent-buffer corruption/junk regression in Transformers 5.x." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "No shared concrete bug; one is a Qwen inference/runtime issue and the other is a model-method implementation problem." - }, - { - "left": "issue:43644", - "right": "issue:43950", - "accept": true, - "reason": "Same bug: both describe the Transformers 5.x regression where non-persistent buffers are filled/corrupted on load." + "reason": "Unrelated model failures with different symptoms and likely different root causes." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "Both involve SigLIP2, but one is a docs example/model-processor mismatch and quantization failure, while the other is a text-embedding quality regression." + "reason": "Both mention SigLIP2, but one is a docs/example error and the other is a model quality complaint." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Same underlying regression: non-persistent buffers being filled or returned with junk in Transformers 5.x." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Related to Qwen3.5 dtype/attention behavior, but the concrete failures differ: autocast dtype mismatch versus RLHF gradient explosion." + "reason": "Both involve precision/memory symptoms, but they are different models and different failure mechanisms." }, { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "Different training/loading errors with no clear shared code-path bug." + "reason": "Trainer API signature mismatch and DeepSpeed loading IndexError are unrelated." }, { - "left": "issue:43866", - "right": "issue:44403", + "left": "issue:41628", + "right": "issue:45800", "accept": false, - "reason": "Different topics: corrupted checkpoint versus generic loading noise." + "reason": "Import/export issue for AutoImageProcessor is unrelated to torch-version compatibility loading problems." }, { - "left": "issue:41628", - "right": "issue:45800", + "left": "issue:43866", + "right": "issue:44403", "accept": false, - "reason": "Not the same bug: import/export issue for AutoImageProcessor versus broad torch/transformers incompatibility." + "reason": "Checkpoint corruption and loading-log noise are not the same underlying bug." }, { "left": "issue:43950", "right": "issue:45902", "accept": true, - "reason": "Same regression: 45902 is a specific manifestation of the non-persistent buffer materialization bug covered by 43950." + "reason": "45902 appears to be a specific manifestation of the same non-persistent-buffer materialization corruption described in 43950." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "Both are compatibility/type errors, but they involve different objects and different failure modes." + "reason": "Different incompatibilities: bitsandbytes parameter handling vs missing Float8 storage support." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "SigLIP2 embedding quality is unrelated to a generic tokenization change report." + "reason": "SigLIP2 embedding quality and tokenization changes are different problems." }, { "left": "issue:41553", "right": "issue:43883", "accept": false, - "reason": "Different model-loading issues with no shared bug or fix path." + "reason": "Bad AutoTokenizer error handling for Voxtral is unrelated to a Molmo attribute error." }, { "left": "issue:38175", "right": "issue:43054", - "accept": true, - "reason": "Likely same SigLIP2 implementation bug family: both describe bad/incorrect SigLIP2 outputs rather than distinct subsystems." + "accept": false, + "reason": "Both are SigLIP2-related, but zero probabilities and worse embeddings are not clearly the same defect." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "Different problems: flash-attention crash from packed-sequence misinterpretation versus CPU-offload incompatibility in Qwen3_5MoeTextRotaryEmbedding." + "reason": "FlashAttention crash from 3D position_ids is unrelated to CPU-offload incompatibility in Qwen3_5MoeTextRotaryEmbedding." }, { "left": "issue:45663", "right": "issue:45902", "accept": false, - "reason": "Different models and failures: Gemma4 FSDP2 shared_kv_states issue versus Qwen3_5MoeTextRotaryEmbedding buffer materialization." + "reason": "A per-layer shared_kv_states KeyError is a different code path from uninitialized rotary-embedding memory." }, { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "Different loading failures for different models; no evidence of the same underlying bug." + "reason": "Different models and errors: Voxtral tokenizer loading vs GLM4V loading failure." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "Both are memory-related, but one is gradient checkpointing with LoRA and the other is int4 quantization reserved-memory/OOM." + "reason": "Gradient checkpointing with LoRA and int4 quantization OOM are separate memory-related issues." }, { "left": "issue:43054", "right": "issue:43493", - "accept": true, - "reason": "Likely same SigLIP2 discrepancy family: one report is poor text embeddings, the other explicitly compares HF and JAX implementations." + "accept": false, + "reason": "SigLIP2 embedding quality complaint and HF-vs-JAX discrepancy are related in theme but not clearly the same bug." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "Generic loading noise is not the same as failure to load a specific model." + "reason": "Docs/noise when loading a transformer does not match a specific model loading failure." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "Both involve remote_code-style loading, but the concrete issues differ too much to merge as one bug." + "reason": "A specific trust_remote_code AutoConfig field-loss bug is broader than, and not identical to, general remote_code breakage." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "Different bugs: detokenization versus Python 3.13 flash_attn import handling." + "reason": "Detokenization behavior and a Python 3.13 flash_attn import KeyError are unrelated." }, { "left": "issue:43975", "right": "issue:45237", "accept": false, - "reason": "No shared bug; one is a detokenization issue and the other is an AMD GPU runtime problem." + "reason": "DeepSeek detokenization and AMD GPU support are unrelated issues." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Both mention loading, but they concern different models and likely different causes." + "reason": "A generic loading-noise complaint is not the same as a model-specific loading failure." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "Different performance/memory topics with no concrete shared code-path problem." - }, - { - "left": "issue:43782", - "right": "issue:44960", - "accept": false, - "reason": "Different model families and failure modes; not the same underlying bug." + "reason": "Both mention memory, but LoRA checkpointing inefficiency and Qwen3 MoE training memory usage are different problems." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "Different model-loading failures with distinct root causes." + "reason": "Different models and failures: GLM4V loading failure vs Molmo missing all_tied_weights_keys." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Different issues: DeepSpeed ZeRO-3 loading crash versus Qwen3Moe FP8 config failure." + "reason": "Gemma3 ZeRO-3 loading IndexError and Qwen3 MoE FP8 failure are unrelated." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and GLM5 are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays mostly conservative. The non-persistent-buffer subcluster is well supported by the titles, and the SigLIP2 links are framed as likely/related rather than certain. I did not see an overstatement that would require rejection." + "feedback": "The analyst output is grounded in the packet and stays conservative on the soft-edge pairs. The non-persistent-buffer regression family is the only clearly supported duplicate cluster, and the other pairings are mostly reasonable rejections based on distinct titles and bug surfaces." }, "evaluator_used": true, "retried": false, @@ -1108,10 +1249,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:24643", "issue:30064", @@ -1185,8 +1326,8 @@ "issue:41553|issue:44991", "issue:43854|issue:44863", "issue:36331|issue:41093", - "issue:43257|issue:45305", "issue:42947|issue:45923", + "issue:43257|issue:45305", "issue:44928|issue:45588", "issue:41093|issue:44805", "issue:43872|issue:45538", @@ -1197,20 +1338,20 @@ "issue:45325|issue:45902", "issue:43366|issue:43828" ], - "prepared_review_unit_hash": "0b50d24dc60dedbc7da1304521d25dbbe2dd7434a284c794748a1d046bfbc3b2", + "prepared_review_unit_hash": "2f0ff435e57b6ca7fe6d0425da9e5fbf7d1e469a01a9d47d5510d4183333fd4c", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 38066, + "serialized_chars": 38065, "estimated_input_tokens": 9517, "estimated_eval_tokens": 19290 }, @@ -1219,216 +1360,216 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly heterogeneous issue cluster. I only found a few likely true duplicates/same-bug pairs; the rest are different model, training, tokenizer, or docs regressions that should stay separate.", - "confidence": 0.89, - "canonical_issue_reason": "issue:43827 is the clearest canonical anchor: issue:44509 is the same v5 docs regression about removed pipeline tasks, just phrased differently.", + "summary": "Most pairs are unrelated model-specific regressions; only a few soft edges look like true duplicates, mainly exact error matches or the same docs cleanup.", + "confidence": 0.76, + "canonical_issue_reason": "issue:45020 is the broadest umbrella-style report in the set and best matches the recurring theme of recent-version compatibility regressions across model loading paths.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43827 is the best issue to keep as the representative duplicate target because it is the earlier, cleaner report of the confirmed docs regression.", + "best_issue_reason": "issue:45020 is the most representative issue overall: it is high-signal, broadly scoped, and can serve as the anchor for adjacent model-loading breakages.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "Different failures: MPS histogram on Int vs Gemma4 device-mapping mismatch." + "reason": "Different failures: MPS int-histogram support vs Gemma4 device placement mismatch." }, { "left": "issue:42491", "right": "issue:44368", "accept": false, - "reason": "Both involve Qwen/LoRA, but one is a HF4.x/HF5.x compatibility break and the other is a tie_word_embeddings warning." + "reason": "Related Qwen3-MoE naming, but one is a LoRA compatibility break and the other is a config warning about tied embeddings." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Same keyword appears, but this is a model import error vs a bitsandbytes quantization constructor error." + "reason": "Different bugs: missing Qwen2.5-VL import vs bitsandbytes/_is_hf_initialized incompatibility." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "General remote_code breakage vs a specific Gemma4 forward device mismatch; not the same bug." + "reason": "Broad remote_code regression vs a specific Gemma4 forward device mismatch; not the same bug." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Tokenizer mapping helper failure vs remote_code model breakage; different code paths." + "reason": "Tokenizer-mapping edge case vs remote_code loading regressions; different code paths." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading failure vs flash-attn2 fallback gating; unrelated subsystems." + "reason": "Tokenizer loading failure vs flash-attn fallback gating; unrelated issues." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Autocast dtype mismatch is not the same as a device-placement error." + "reason": "Different symptoms and subsystems: autocast dtype mismatch vs device-map forward mismatch." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Mistral tokenizer regex crash vs flash-attn fallback checks; unrelated." + "reason": "Tokenizer regex patch crash vs flash-attn fallback logic; not the same underlying bug." }, { "left": "issue:43827", "right": "issue:44509", "accept": true, - "reason": "Same docs regression about removed pipeline tasks in v5; 44509 is a reworded duplicate of 43827." + "reason": "Same docs regression: both report obsolete pipeline-task references after v5 removals." }, { "left": "issue:45020", "right": "issue:45356", "accept": false, - "reason": "Remote_code regression vs Kimi-K2.5 tokenizer codec/warning regression; different model-specific bugs." + "reason": "Generic remote_code compatibility break vs a specific Kimi-K2.5 tokenizer regression." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Tied lm_head weights bug vs silent non-persistent buffer corruption; different issues." + "reason": "Weight tying bug in Mistral3 vs from_pretrained buffer corruption; different mechanisms." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "Different load-path failures: MobileLLM key error vs flash-attn fallback gating." + "reason": "Model load/key error vs flash-attn fallback gating; not the same issue." }, { "left": "issue:42915", "right": "issue:45020", "accept": false, - "reason": "Both are broad compatibility complaints, but one is LoRA/Qwen3-MOE specific and the other is a remote_code regression." + "reason": "LoRA model compatibility across versions vs broad remote_code breakage; different problems." }, { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MOE weight-conversion failure vs Ovis2 checkpoint corruption; unrelated models and causes." + "reason": "DeepSpeed weight conversion failure vs corrupted Ovis2 checkpoint; different failure modes." }, { "left": "issue:43638", "right": "issue:45823", "accept": false, - "reason": "DeepSpeed ZeRO-3 weight init error vs Gemma4 device mismatch; different problems." + "reason": "Zero3 index-out-of-bounds on Bert vs Gemma4 device mismatch; unrelated." }, { "left": "issue:43792", "right": "issue:44220", "accept": false, - "reason": "Whisper load failure and fbank helper issue may be adjacent, but the titles do not indicate the same concrete bug." + "reason": "Whisper runtime failure is too broad to equate to the specific fbank-feature helper issue." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Both describe the same unexpected `_is_hf_initialized` kwarg leaking into model-loading/init code paths." + "reason": "Same `_is_hf_initialized` / init_empty_weights incompatibility, just described from different entry points." }, { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Both are ZeRO-3 load failures, but the model families and reported symptoms differ too much to merge." + "reason": "Both are ZeRO-3 weight-loading failures, but for different Qwen model variants and reported at different submodules." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "LoRA/Qwen3-MOE compatibility issue vs bitsandbytes constructor kwarg bug; different paths." + "reason": "LoRA/version incompatibility vs bitsandbytes init argument error; different code paths." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "Different tokenizer-loading failures for different models; only the symptom is generic." + "reason": "Tokenizer error messaging for Voxtral vs tokenizer loading failure for EMBEDDIA/est-roberta; unrelated." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "GLM-4.7-Flash unit-test load failure vs NemotronH checkpoint loading; unrelated." + "reason": "Different model-load failures with different causes; no shared concrete bug is evident." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Trainer API signature change vs tensor mask shape mismatch; unrelated." + "reason": "Different TypeErrors/IndexErrors with unrelated triggers." }, { - "left": "issue:43257", - "right": "issue:45305", + "left": "issue:42947", + "right": "issue:45923", "accept": false, - "reason": "DeepSpeed weight conversion bug vs DeepSpeed gradient averaging bug; different training stages." + "reason": "Gradient checkpointing symptom vs missing supports_gradient_checkpointing flag; not the same bug." }, { - "left": "issue:42947", - "right": "issue:45923", + "left": "issue:43257", + "right": "issue:45305", "accept": false, - "reason": "Gradient checkpointing behavior issue vs missing support flag on a remote_code model; related theme, different bug." + "reason": "DeepSpeed weight conversion bug vs gradient averaging bug; different training failures." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "RLHF NaN/SDPA fallback issue vs flash-attn crash on `s_aux=None`; different attention-path failures." + "reason": "RLHF NaN/SDPA fallback problem vs flash-attn auxiliary-state AttributeError; different failure modes." }, { "left": "issue:41093", "right": "issue:44805", "accept": true, - "reason": "Same mask/index shape-mismatch exception pattern; these look like the same bug with different sample sizes." + "reason": "Same mask-vs-tensor shape mismatch IndexError; titles differ only in the concrete dimensions shown." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "bitsandbytes `_is_hf_initialized` error vs CLIPTokenizer max-length constant; unrelated." + "reason": "bitsandbytes init-arg incompatibility vs CLIPTokenizer max-length bug; unrelated." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Bad error message for Voxtral vs a different tokenizer load failure for sleng-bert; not the same issue." + "reason": "Both are tokenizer/model loading complaints, but for different models and likely different root causes." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "PagedAttentionCache linear_attention crash vs NemotronH checkpoint loading; unrelated." + "reason": "PagedAttentionCache linear_attention crash vs NemotronH checkpoint loading failure; different bugs." }, { "left": "issue:44479", "right": "issue:44560", "accept": true, - "reason": "44560 is a specific Qwen3-VL video error that fits the broader video-input regression reported in 44479." + "reason": "Both describe the same v5.3.0 Qwen video-input regression; one is the broader family report, the other a specific model manifestation." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "Training DeepSpeed weight shape error vs image-processor segmentation-map failure; unrelated." + "reason": "DeepSpeed training weight-shape runtime error vs image processor void-segmentation-map failure; unrelated." }, { "left": "issue:45325", "right": "issue:45902", "accept": false, - "reason": "Different rotary-embedding defects: rope-index scaling vs uninitialized memory after materialization." + "reason": "Both touch Qwen rotary/position-id internals, but one is a video rope-scaling regression and the other is uninitialized-memory after to_empty()." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF architecture support vs autocast dtype mismatch; unrelated." + "reason": "GGUF gpt-oss architecture support vs Phi-tiny-MoE autocast dtype mismatch; different issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays mostly conservative. The accepted duplicate pairs are plausible from the titles alone, especially 43827/44509, 43872/44291, and 41093/44805. The remaining soft-edge rejections are appropriately cautious rather than overstated." + "feedback": "The analysis is grounded in the packet: the canonical issue choice is defensible, the summary stays conservative, and the accepted soft edges are supported by the issue titles (docs cleanup, identical `_is_hf_initialized` incompatibility, matching mask-shape IndexErrors, and the Qwen video regression family). Rejected pairs also read as appropriately cautious rather than overstated." }, "evaluator_used": true, "retried": false, @@ -1444,10 +1585,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36010", "issue:38175", @@ -1469,6 +1610,8 @@ "issue:43708", "issue:43720", "issue:43824", + "issue:43854", + "issue:43931", "issue:43950", "issue:43957", "issue:43994", @@ -1491,10 +1634,8 @@ "issue:45276", "issue:45313", "issue:45357", - "issue:45488", "issue:45584", "issue:45663", - "issue:45812", "issue:45823", "issue:45834" ], @@ -1525,242 +1666,224 @@ "issue:44960|issue:44977", "issue:42491|issue:43720", "issue:45313|issue:45357", - "issue:44451|issue:44488", "issue:41720|issue:42915", + "issue:44451|issue:44488", "issue:42491|issue:45276", "issue:42915|issue:44756", "issue:43708|issue:44075", - "issue:45488|issue:45812" + "issue:43854|issue:43931" ], - "prepared_review_unit_hash": "cfa9cb1a9a587f13152c245eaa3e74ef15733c1440600747fcbca9b81f26592f", + "prepared_review_unit_hash": "7b3da719f3300b3ad40bbef27e9ce16301be60a882346540ef0e0dfe6c5e26d4", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37263, - "estimated_input_tokens": 9316, - "estimated_eval_tokens": 18888 + "serialized_chars": 37193, + "estimated_input_tokens": 9299, + "estimated_eval_tokens": 18854 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a grab-bag of unrelated model-specific regressions, not one tight duplicate cluster. The clearest duplicate is the Transformers 5 non-persistent-buffer bug (43644/44534), with one additional plausible duplicate around broken SigLIP2 outputs (38175/43994).", - "confidence": 0.64, - "canonical_issue_reason": "Issue 43644 is the cleanest canonical representative: it states the regression clearly and is effectively duplicated by 44534. The rest of the items are too heterogeneous to serve as one shared root issue.", + "summary": "Mostly a Transformers v5 regression cluster, with a few strong same-bug pairs around buffer corruption and some closely related model-specific failures; I kept the duplicate language conservative where the packet only shows similarity, not proof of identity.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43644 is the clearest representative of the non-persistent-buffer regression cluster: its title is concise and specific, and issue:44534 repeats essentially the same symptom wording, so 43644 is a good anchor without claiming an exact duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "43644 is the best issue to anchor the cluster because it is the most precise, broadly reusable description of the only exact duplicate pair in the set.", + "best_issue_reason": "issue:43644 is the best overall issue anchor because it is the most concise and generalizable report of the Transformers v5 non-persistent-buffer bug; nearby reports read as related variants or follow-ups rather than a separate class.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Different Gemma4 failures: one is an FSDP2 KeyError from per-layer shared_kv_states rebuilding, the other is a device-mapping mismatch during forward." + "reason": "Same model family only; one is an FSDP2 KeyError, the other is a device-map mismatch. Different code paths." }, { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "AudioFlamingo3 cross-track embedding leak and Whisper empty-transcription handling are unrelated code paths." + "reason": "Different models and failures: AudioFlamingo3 track leakage vs Whisper empty-transcription generation." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "gpt-oss GGUF support and Qwen3-MoE sliding_window behavior are different features/issues." + "reason": "Both are Qwen/LLM-adjacent, but one is GGUF architecture support and the other is a sliding-window bug." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "from_pretrained non-persistent buffer corruption is unrelated to the Kosmos2.5 long-OCR index error." + "reason": "Both are loading problems, but one is non-persistent buffers and the other is long OCR index handling." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "These are different attention/compiler bugs: SDPA+torch.compile on Bamba versus Flash Attention with Qwen3.5 position_ids packing." + "reason": "Different models and distinct failure modes: torch.compile/SDPA vs flash-attention illegal memory access." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Missing Qwen2_5_VL export and meta-device loading failures are distinct regressions." + "reason": "ImportError for a specific class vs meta-device loading failures; no clear shared bug." }, { "left": "issue:43645", "right": "issue:43646", - "accept": false, - "reason": "Both involve custom model init in v5, but the notebook-specific redefinition case and the general initialization failure are not clearly the same underlying bug." + "accept": true, + "reason": "Very likely the same custom-model initialization regression, with one report adding Jupyter as the environment." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "GGUF architecture support and Float8 storage lookup errors are unrelated." + "reason": "Unrelated issues: GGUF architecture support vs missing Float8 storage during load." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3-MoE FP8 config failure and meta-device model loading are separate problems." + "reason": "Different regressions: Qwen3Moe FP8 failure vs generic meta-device model loading breakage." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "A Qwen3-vl video StopIteration and a TRL SFT unpacking failure are different code paths." + "reason": "Both mention Qwen3.x and embeddings, but the concrete failures are different (video StopIteration vs TRL SFT 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 runtime failure and GGUF gpt-oss support are unrelated." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "GenerationMixin import regression and Qwen3-MoE FineGrainedFP8 failure are unrelated." + "reason": "Import path breakage for GenerationMixin vs Qwen3Moe FP8 runtime failure." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer-mapping lookup failure and Gemma4 device mismatch are different issues." + "reason": "Tokenizer-mapping edge case and Gemma4 device mismatch are different bugs." }, { "left": "issue:38175", "right": "issue:43994", "accept": true, - "reason": "Same SigLIP2 symptom family: both report broken outputs for google/siglip2-base-patch16-224 and point to the same model/processor regression." + "reason": "Same SigLIP2 base model and overlapping incorrect-output symptom; this looks like a closely related same-model regression, though the packet does not prove an exact duplicate." }, { "left": "issue:43632", "right": "issue:45834", "accept": false, - "reason": "_is_hf_initialized flag breakage and Kosmos2.5 OCR indexing are unrelated." + "reason": "General _is_hf_initialized regression vs Kosmos2.5 long-input index error; no shared code path is evident." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Qwen3-vl StopIteration and a mask/tensor shape IndexError are different failures." + "reason": "Both are tensor-shape failures, but the affected models and mechanisms differ." }, { "left": "issue:44877", "right": "issue:45030", - "accept": false, - "reason": "Strict config loading for granite_speech and glm4v config validation are not the same bug." + "accept": true, + "reason": "Both point to overly strict config validation blocking model loading; likely the same root cause." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "ZeRO-3 Bert initialization and add-new-model-like tokenizer-mapping handling are unrelated." + "reason": "Different failures: DeepSpeed ZeRO-3 on non-pretrained BertModel vs add-new-model-like/tokenizer mapping behavior." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Another ZeRO-3 Bert initialization failure; not the same as the tokenizer-mapping issue." + "reason": "IndexError during ZeRO-3 init is unrelated to TOKENIZER_MAPPING_NAMES handling." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer-mapping logic and mask-shape indexing are different code paths." + "reason": "Tokenizer-mapping registration bug vs mask/tensor shape mismatch; no duplicate evidence." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "gpu+cpu offload loading failure and Strix Halo mmap OOM are not the same underlying bug." + "reason": "Both involve loading/offload, but one is dequantized model offload and the other is mmap OOM on Strix Halo." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "Exact duplicate regression: both describe the same Transformers 5 non-persistent-buffer junk corruption issue." + "reason": "Very close same-symptom Transformers v5 non-persistent-buffer report; the titles are nearly identical, but the metadata alone doesn't prove an exact duplicate." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "Both are about SigLIP2, but one is bad inference outputs while the other is a docs-example model/processor mismatch and quantization failure; not clearly the same bug." + "reason": "Same model family, but one is bad outputs and the other is a documentation example with multiple separate errors." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "GLM5 is too vague and unrelated to the Qwen3.5 flash-attention generation failure." + "reason": "Different GLM/Qwen3.5 generation issues with no evidence of a shared bug." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Qwen3-MoE hf4.x/hf5.x LoRA compatibility and BitNet packed-weight loading are different problems." + "reason": "LoRA/Qwen3_moe incompatibility and BitNet packed-weight loading are unrelated." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "ZeRO-3 loading for Qwen3.5 language_model and incorrect visual-encoder save_pretrained keys affect different components." - }, - { - "left": "issue:44451", - "right": "issue:44488", - "accept": false, - "reason": "Two similar BERT loading reports, but the specific models and failure details are not enough to confirm one shared root cause." + "reason": "Same model family, but one is ZeRO-3 weight loading and the other is save_pretrained visual-encoder key regression." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Qwen3 auto device mapping on A800 and Qwen3-MoE FP8 issues are unrelated." - }, - { - "left": "issue:42491", - "right": "issue:45276", - "accept": false, - "reason": "LoRA hf4.x/hf5.x compatibility is unrelated to Gemma4 resize_token_embeddings propagation." - }, - { - "left": "issue:42915", - "right": "issue:44756", - "accept": false, - "reason": "Qwen3-MoE FP8 config failure and Strix Halo mmap OOM are unrelated." + "reason": "Qwen3 auto device-map CUDA assert and Qwen3Moe FP8 failure are different problems." }, { - "left": "issue:43708", - "right": "issue:44075", + "left": "issue:44451", + "right": "issue:44488", "accept": false, - "reason": "Checkpoint max_steps math and SGD argument handling are separate trainer/optimizer bugs." + "reason": "Both are model-loading failures, but the specific models differ and the bug mechanism is not shown to be the same." }, { - "left": "issue:45488", - "right": "issue:45812", + "left": "issue:43854", + "right": "issue:43931", "accept": false, - "reason": "Different tokenizer regressions: LlamaTokenizer pre-tokenizer override versus Granite token-ID corruption." + "reason": "Distinct model-loading errors: unit-test failure for GLM-4.7-Flash vs Qwen3-VL weight-shape mismatch." } ] }, "evaluator_result": { - "accept": true, - "feedback": "Grounded and conservative overall. The 43644/44534 duplicate is well supported, and the SigLIP2 pair is stated as only a plausible duplicate rather than overclaimed. The remaining rejections stay close to the packet and avoid stretching across unrelated regressions." + "accept": false, + "feedback": "The cluster summary is broadly grounded, but a few claims are too strong for the packet. In particular, calling issue:44534 an \"exact duplicate\" of issue:43644 is not supported by the metadata shown, and \"reproducible\" is also not evidenced in the packet. The accepted soft pair issue:38175/issue:43994 is similarly a bit strong for the available evidence; it should be softened to something like \"closely related same-model regression\" rather than \"same underlying regression.\" Please keep the canonical/best-issue wording more conservative and based only on the observed similarity and titles." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -1773,10 +1896,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36010", "issue:39404", @@ -1786,7 +1909,6 @@ "issue:42947", "issue:43257", "issue:43335", - "issue:43381", "issue:43404", "issue:43425", "issue:43454", @@ -1809,7 +1931,6 @@ "issue:44756", "issue:44910", "issue:44912", - "issue:44928", "issue:44960", "issue:44991", "issue:45216", @@ -1818,23 +1939,25 @@ "issue:45335", "issue:45362", "issue:45406", + "issue:45488", "issue:45588", "issue:45663", "issue:45684", "issue:45698", "issue:45704", "issue:45759", + "issue:45812", "issue:45823", "issue:45859" ], "soft_pairs": [ - "issue:43854|issue:43931", + "issue:45488|issue:45812", "issue:39692|issue:43994", "issue:43257|issue:43854", "issue:44488|issue:44991", "issue:42491|issue:43931", - "issue:43644|issue:43645", "issue:43856|issue:43873", + "issue:43644|issue:43645", "issue:45362|issue:45406", "issue:43856|issue:44387", "issue:44910|issue:45588", @@ -1849,276 +1972,252 @@ "issue:43425|issue:43957", "issue:42947|issue:45704", "issue:45663|issue:45759", - "issue:43335|issue:45663", "issue:43873|issue:44387", + "issue:43335|issue:45663", "issue:45663|issue:45859", "issue:44291|issue:44756", "issue:44155|issue:45823", - "issue:43854|issue:45216", "issue:44292|issue:44912", "issue:44387|issue:44756", + "issue:43854|issue:45216", "issue:44743|issue:44960", "issue:43957|issue:44756", "issue:45276|issue:45292", - "issue:45684|issue:45698", - "issue:43381|issue:44928", - "issue:44164|issue:44756", - "issue:42947|issue:43381" + "issue:45684|issue:45698" ], - "prepared_review_unit_hash": "69ed056041d6186415d50a870e7b94d6619339214007d5a94d41d484d9eb5897", + "prepared_review_unit_hash": "ed0cb8e771db94991ca45cc6934afc841c9f5f17403d8587a07ac9f60a2542e6", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 36, - "serialized_chars": 38618, - "estimated_input_tokens": 9655, - "estimated_eval_tokens": 19566 + "soft_pair_count": 33, + "serialized_chars": 37767, + "estimated_input_tokens": 9442, + "estimated_eval_tokens": 19140 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most candidate pairs are only loosely related by subsystem or symptom. The only clear duplicate-like pair is the resize_token_embeddings/output_embeddings regression around Gemma4/T5Gemma, where the broader generic report is the better representative.", - "confidence": 0.83, - "canonical_issue_reason": "Issue 45292 is the clearest broad report of the resize_token_embeddings \u2192 output_embeddings regression; 45276 looks like a Gemma4-specific manifestation of the same defect.", - "canonical_pr_reason": null, - "best_issue_reason": "45292 best captures the underlying bug in a reusable, general form and is the strongest canonical issue for this duplicate cluster.", - "best_pr_reason": null, + "summary": "This cluster is mostly heterogeneous: tokenizer regressions, quantization/offload issues, save/load bugs, and several model-specific generation/loading failures. A few pairs are superficially similar, especially the resize_token_embeddings reports, but none are safe duplicate merges on the evidence provided.", + "confidence": 0.84, + "canonical_issue_reason": "No single canonical issue is safe here; the cluster spans multiple unrelated code paths and model families, so there isn\u2019t a trustworthy umbrella duplicate target.", + "canonical_pr_reason": "No PRs in the cluster.", + "best_issue_reason": "Issue 45276 is the strongest local representative of the only weak mini-cluster (resize_token_embeddings propagation), because it is specific and actionable, but it still does not safely subsume the broader cluster.", + "best_pr_reason": "No PRs in the cluster.", "soft_edge_verdicts": [ { - "left": "issue:43854", - "right": "issue:43931", + "left": "issue:45488", + "right": "issue:45812", "accept": false, - "reason": "Both are model-loading failures, but they affect different models and different failure modes." + "reason": "Both are tokenizer regressions, but they affect different model families and failure modes; not the same bug." }, { "left": "issue:39692", "right": "issue:43994", "accept": false, - "reason": "Both involve SigLIP2, but one is a docs/example problem with multiple issues and the other is a runtime inference quality report; not the same concrete bug." + "reason": "Both mention SigLIP2, but one is a docs/example mismatch and the other is a model/pipeline correctness issue." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Different models and different root causes: Qwen3 MoE conversion vs GLM loading." + "reason": "Different models and different loading paths; no sign of a shared underlying defect." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer/load failures, but the reported models and symptoms are too different to treat as the same bug." + "reason": "Both are tokenizer-loading problems, but they hit different checkpoints and likely different model-specific fixes." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Different model families and unrelated loading failures." + "reason": "Both involve Qwen3, but one is LoRA/hf4.x compatibility and the other is a Qwen3-VL weight-shape mismatch." }, { - "left": "issue:43644", - "right": "issue:43645", + "left": "issue:43856", + "right": "issue:43873", "accept": false, - "reason": "Both are Transformers 5.0 regressions, but one is buffer initialization and the other is notebook custom-model initialization." + "reason": "Both are memory-related, but one is Qwen3 MoE training efficiency and the other is quantization/offloading behavior." }, { - "left": "issue:43856", - "right": "issue:43873", + "left": "issue:43644", + "right": "issue:43645", "accept": false, - "reason": "Both mention memory/quantization, but one is Qwen3 MoE training memory use and the other is offloading behavior." + "reason": "Both are Transformers 5.0 regressions, but they describe unrelated bugs in different subsystems." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Different components and different models; both are crashes only at a very high level." + "reason": "Different models and different failures: chat crashing for Qwen3.5 versus a Gemma4 processor attribute error." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both are memory-related, but the underlying causes and reproduction paths differ." + "reason": "Both touch memory usage, but one is training inefficiency and the other is int4 quantization causing OOM." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both are flash-attention crashes, but the code paths and failure signatures are unrelated." + "reason": "Both involve flash attention, but the concrete bug and trigger are different." }, { "left": "issue:42491", "right": "issue:45292", "accept": false, - "reason": "LoRA/Qwen3 MoE compatibility is unrelated to resize_token_embeddings behavior." + "reason": "LoRA/branch compatibility and resize_token_embeddings propagation are unrelated bugs." }, { "left": "issue:45276", "right": "issue:45335", - "accept": true, - "reason": "Both report resize_token_embeddings failing to update model-specific output/input embeddings; 45276 is the Gemma4-specific form of the same defect." + "accept": false, + "reason": "These are similar at a high level, but they affect different model families and different embedding members, so not a safe duplicate." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Different state-handling/loading regressions with different triggers and error types." + "reason": "One is extra_state handling in save/from_pretrained, the other is init_empty_weights passing an unexpected argument." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both are lm_head tying issues, but they are on different architectures and not clearly the same bug." + "reason": "Both are weight-tying complaints, but they concern different models and likely distinct implementation paths." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "Completely different issues: an import error vs Whisper pipeline behavior." + "reason": "An import error for GenerationMixin is unrelated to Whisper return_language pipeline behavior." }, { "left": "issue:41720", "right": "issue:44155", "accept": false, - "reason": "Different model families and unrelated failure mechanisms." + "reason": "Different models and unrelated runtime failures; no common code-path bug." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Both concern tokenization/model loading, but there is no evidence they are the same underlying tokenizer bug." + "reason": "Tokenizer vocab-size mismatch versus a model loading failure; not the same issue." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "Different models and unrelated topics." + "reason": "Both mention model examples, but the affected models and failures are entirely different." }, { "left": "issue:43425", "right": "issue:43957", "accept": false, - "reason": "General Torch version incompatibility is not the same as meta-device loading breakage." + "reason": "One is a Torch version compatibility complaint, the other is a meta-device loading regression." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Gradient checkpointing/LoRA and apex RMSNorm memory leak are unrelated." + "reason": "Gradient checkpointing/LoRA and an apex RMSNorm memory leak are unrelated." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "Different model classes and different forward/configuration bugs." + "reason": "Both involve composite models, but one is an FSDP2 KeyError and the other is AutoModel config unwrapping." }, { - "left": "issue:43335", - "right": "issue:45663", + "left": "issue:43873", + "right": "issue:44387", "accept": false, - "reason": "Different configuration/forward-path issues in unrelated models." + "reason": "Both are memory/quantization themed, but the symptoms and code paths differ." }, { - "left": "issue:43873", - "right": "issue:44387", + "left": "issue:43335", + "right": "issue:45663", "accept": false, - "reason": "Both can lead to memory problems, but the mechanisms are different: offloading vs quantization memory overhead." + "reason": "SwitchTransformers sparse-layer construction is unrelated to Gemma4 FSDP2 shared_kv_states rebuilding." }, { "left": "issue:45663", "right": "issue:45859", "accept": false, - "reason": "Different Qwen/Gemma subsystems and different offload compatibility issues." + "reason": "Both are model-internal bugs, but one is Gemma4 FSDP2 and the other is Qwen3 MoE CPU offload." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "Init-empty-weights argument handling is unrelated to mmap/OOM on Strix Halo." + "reason": "Meta-initialization argument handling and Strix Halo mmap OOM are unrelated." }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "Different models and different runtime failures." - }, - { - "left": "issue:43854", - "right": "issue:45216", - "accept": false, - "reason": "Different models and different save/load regressions." + "reason": "Different model families and different runtime errors; no duplicate evidence." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Different quantization formats, models, and failure modes." + "reason": "Both are quantization load issues, but they involve different models and quantization formats." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "Both are OOM-related, but the causes are distinct and not mergeable into one fix." + "reason": "Int4 quantization OOM and mmap-related OOM are different underlying problems." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "A model loading/test failure and a save_pretrained regression are different bugs." }, { "left": "issue:44743", "right": "issue:44960", "accept": false, - "reason": "Unrelated model behavior reports." + "reason": "Recurrent-state caching in modular_qwen3_5 is unrelated to GLM5." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "Meta-device loading and Strix Halo mmap OOM are unrelated." + "reason": "Meta-device loading regressions are unrelated to disabling mmap for Strix Halo." }, { "left": "issue:45276", "right": "issue:45292", - "accept": true, - "reason": "Same underlying resize_token_embeddings regression; 45292 is the broader, cleaner duplicate target." + "accept": false, + "reason": "Both are resize_token_embeddings regressions, but the affected outputs/components differ and there is no evidence of one shared code-path bug." }, { "left": "issue:45684", "right": "issue:45698", "accept": false, - "reason": "One is file permission propagation, the other is wrong custom-module resolution after save/load." - }, - { - "left": "issue:43381", - "right": "issue:44928", - "accept": false, - "reason": "Both mention gradient/checkpointing behavior, but they are different problems with different causes." - }, - { - "left": "issue:44164", - "right": "issue:44756", - "accept": false, - "reason": "Different bugs in unrelated code paths." - }, - { - "left": "issue:42947", - "right": "issue:43381", - "accept": false, - "reason": "Both involve gradient checkpointing, but the reported failures are distinct." + "reason": "Both concern save_pretrained/from_pretrained with custom modules, but one is permissions propagation and the other is wrong module loading." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The canonical issue choice is grounded in the packet: 45292 is the broad resize_token_embeddings/output_embeddings report, and the Gemma4/T5Gemma issues read as specific manifestations of that same regression. The soft-edge verdicts are appropriately conservative overall, with no obvious overreach beyond the evidence in the titles and summaries." - }, - "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 }, @@ -2130,16 +2229,17 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ - "issue:32090", "issue:36032", "issue:39404", + "issue:42947", "issue:43257", "issue:43299", + "issue:43381", "issue:43425", "issue:43452", "issue:43596", @@ -2149,7 +2249,6 @@ "issue:43708", "issue:43716", "issue:43828", - "issue:43856", "issue:43901", "issue:43906", "issue:43931", @@ -2173,8 +2272,8 @@ "issue:44898", "issue:44912", "issue:44918", + "issue:44928", "issue:44991", - "issue:45081", "issue:45084", "issue:45292", "issue:45335", @@ -2185,13 +2284,16 @@ "issue:45823" ], "soft_pairs": [ + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:42947|issue:43381", "issue:44479|issue:44877", "issue:43646|issue:43708", "issue:45588|issue:45663", "issue:45292|issue:45335", "issue:43645|issue:44164", - "issue:44402|issue:44451", "issue:43257|issue:44863", + "issue:44402|issue:44451", "issue:43828|issue:43957", "issue:43425|issue:43828", "issue:44589|issue:44756", @@ -2210,98 +2312,113 @@ "issue:43994|issue:44079", "issue:43299|issue:43931", "issue:43425|issue:44918", - "issue:44589|issue:45084", "issue:39404|issue:44671", + "issue:44589|issue:45084", "issue:44164|issue:45759", "issue:36032|issue:43452", "issue:43596|issue:44683", - "issue:44671|issue:44991", - "issue:32090|issue:39404", - "issue:43856|issue:44756", - "issue:44991|issue:45081" + "issue:44671|issue:44991" ], - "prepared_review_unit_hash": "3b7cd63dd85484ecac9db69d604e0273178be214bdc0e2e2b1d459263bcb273a", + "prepared_review_unit_hash": "9a838c87bdddb78bb342934dea77559ef8e1548a93a3b8429eed72f4262300ea", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 38057, - "estimated_input_tokens": 9515, - "estimated_eval_tokens": 19286 + "serialized_chars": 37971, + "estimated_input_tokens": 9493, + "estimated_eval_tokens": 19242 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a loose thematic cluster of Transformers v5 regressions, not a true duplicate set. One pair looks like the same resize_token_embeddings bug; the rest are separate failures affecting different model families or code paths.", - "confidence": 0.68, - "canonical_issue_reason": "Issue 43611 is the broadest, most central regression report in the set: a Transformers 5 loading break around `base_model_prefix` that fits the cluster\u2019s main theme of model-initialization/loading regressions.", + "summary": "Mostly unrelated issues with one likely duplicate pair around resize_token_embeddings behavior. No PRs were provided. Best representative issue is the broader embedding-resize report.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45292 is the broadest and clearest representative of the resize_token_embeddings propagation bug, and issue:45335 looks like the same defect in the t5gemma path.", "canonical_pr_reason": null, - "best_issue_reason": "43611 is the best single issue to anchor the cluster because it describes a clear, general API regression with wide impact and a concrete failure mode.", + "best_issue_reason": "issue:45292 has the most general title and would best anchor a fix that also covers the narrower t5gemma-specific report.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Both mention training/gradient topics, but one is eval-mode checkpointing and the other is a Qwen3.5 RLHF NaN issue with a different root cause." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "save/from_pretrained extra_state handling and Strix Halo mmap OOM are unrelated bugs." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both involve gradient checkpointing, but LoRA ineffectiveness and eval-mode incompatibility are different problems." + }, { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Different failures: video-input regression for Qwen-family models vs strict config loading for granite_speech." + "reason": "Video input regression in Qwen VL models and strict config loading for granite_speech are unrelated." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom model initialization in notebooks is unrelated to Trainer resume/max_steps calculation." + "reason": "Custom model initialization in notebooks is unrelated to Trainer max_steps recalculation on checkpoint resume." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "Different code paths: flash_attention `s_aux=None` crash vs Gemma4 FSDP2 shared_kv_states rebuild bug." + "reason": "One is a flash_attention None-handling crash; the other is a Gemma4 FSDP2 shared_kv_states KeyError." }, { "left": "issue:45292", "right": "issue:45335", "accept": true, - "reason": "Same underlying bug: `resize_token_embeddings` not propagating to tied output embeddings; 45335 is a T5Gemma-specific manifestation." + "reason": "Both report resize_token_embeddings failing to update the output-side embeddings; 45335 is a model-specific manifestation of the same bug." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Notebook custom model init regression is not the same as save/from_pretrained handling of `extra_state`." + "reason": "Jupyter custom-model initialization and extra_state save/load failure do not describe the same code path." }, { - "left": "issue:44402", - "right": "issue:44451", + "left": "issue:43257", + "right": "issue:44863", "accept": false, - "reason": "Tokenizer vocab-size mismatch vs a separate tokenizer loading failure for a different model." + "reason": "Qwen3 MOE conversion under accelerate/deepspeed and NemotronH checkpoint loading are distinct model-loading issues." }, { - "left": "issue:43257", - "right": "issue:44863", + "left": "issue:44402", + "right": "issue:44451", "accept": false, - "reason": "Both are model-loading issues, but they involve different architectures and different failure mechanisms." + "reason": "Both are tokenizer-loading complaints, but they concern different models and likely different tokenizer defects." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Autocast dtype mismatch is not the same as meta-device loading breakage." + "reason": "Autocast dtype mismatch on Phi-tiny-MoE and meta-device loading failures are different loading/runtime issues." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch version incompatibility is too broad and distinct from the Phi-tiny-MoE autocast dtype mismatch." + "reason": "Torch 2.10 incompatibility and an autocast dtype mismatch are not the same defect." }, { "left": "issue:44589", @@ -2313,133 +2430,133 @@ "left": "issue:44683", "right": "issue:45823", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 is a different bug from Gemma4 device-map mismatch." + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device-map mismatch are separate issues." }, { "left": "issue:39404", "right": "issue:45701", "accept": false, - "reason": "Whisper `return_language` regression is unrelated to tokenization changes across versions." + "reason": "Whisper return_language pipeline regression and tokenization changes across versions are different problems." }, { "left": "issue:43931", "right": "issue:44863", "accept": false, - "reason": "Qwen3-VL shape-mismatch loading failure is not the same as NemotronH checkpoint loading failure." + "reason": "Qwen3-VL weight-shape mismatch and NemotronH checkpoint loading are unrelated model-loading bugs." }, { "left": "issue:43906", "right": "issue:44530", "accept": false, - "reason": "An isolated reproduction of another issue is not the same as the PagedAttentionCache linear_attention crash." + "reason": "An isolated reproduction of another issue and a PagedAttentionCache linear_attention crash do not match." }, { "left": "issue:43425", "right": "issue:45823", "accept": false, - "reason": "Torch compatibility and Gemma4 forward device mismatch are different problems." + "reason": "Torch version incompatibility and Gemma4 forward device mismatch are different defects." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Both are Transformers 5 custom-model regressions, but one is about `base_model_prefix` loading and the other about notebook-defined model initialization." + "reason": "base_model_prefix loading breakage and custom model initialization in notebooks are not the same root cause." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch 2.10 incompatibility is not the same as the Mistral-3 image-preprocessor dtype mismatch." + "reason": "General Torch incompatibility and a specific Mistral-3 dtype mismatch are unrelated." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "PagedAttentionCache group-type failure and template-node compilation failure are separate code paths." + "reason": "PagedAttentionCache linear_attention crash and non-template-node compile TypeError are different code paths." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "These are both docs-related, but they cover different removed/changed pipeline-task documentation issues." + "reason": "Both are docs-related, but they cover different deprecated pipeline/task references." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline `return_language` regression is unrelated to MXFP4 quantization fallback." + "reason": "Whisper pipeline language return regression and MXFP4 quantization fallback are unrelated." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "`torch.export`/`torch_compilable_check` failure is unrelated to Perceiver non-default-resolution classification." + "reason": "torch.export/torch_compilable_check failure and Perceiver interpolation failure are different model/export issues." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Video-input regression and mask-shape IndexError are different failure modes." + "reason": "Qwen VL video-input regression and a generic mask-shape IndexError are not the same bug." }, { "left": "issue:43994", "right": "issue:44079", "accept": false, - "reason": "Siglip2 bad outputs are not the same bug as `ModelOutput` key assignment with prior `None` values." + "reason": "SigLIP2 nonsensical outputs and ModelOutput key assignment are unrelated." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "Both mention Qwen3-VL loading, but one is a v5 break for MoE models and the other is a specific weight-shape mismatch; not enough evidence of the same bug." + "reason": "Both touch Qwen3-VL loading, but one is a version-specific MoE loading regression and the other is a specific weight-shape mismatch report; not enough evidence they are the same bug." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch incompatibility is unrelated to the Qwen3.5 input-embedding unpacking issue." + "reason": "Torch 2.10 incompatibility and Qwen3.5 embedding unpacking in TRL are different problems." }, { - "left": "issue:44589", - "right": "issue:45084", + "left": "issue:39404", + "right": "issue:44671", "accept": false, - "reason": "Missing float8 storage and non-template-node compilation are unrelated." + "reason": "Whisper pipeline language handling and CamemBERT masked LM prediction errors are unrelated." }, { - "left": "issue:39404", - "right": "issue:44671", + "left": "issue:44589", + "right": "issue:45084", "accept": false, - "reason": "Whisper pipeline regression is unrelated to CamemBERT masked-LM prediction errors." + "reason": "Float8 storage lookup and non-template-node compile errors do not match." }, { "left": "issue:44164", "right": "issue:45759", "accept": false, - "reason": "`extra_state` save/load handling is separate from `from_config` text_config unwrapping for composite Qwen configs." + "reason": "extra_state save/load failure and AutoModelForCausalLM.from_config text_config unwrapping are different loading behaviors." }, { "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "T5Tokenizer special-token method conflict is unrelated to gguf_file loading failures." + "reason": "T5Tokenizer special-tokens conflict and gguf_file breaking from_pretrained are unrelated tokenizer/model-loading issues." }, { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "Deepspeed ZeRO-3 zero-sized tensor indexing is unrelated to compiled flex_attention on newer torch versions." + "reason": "Zero3 init IndexError with BertModel and compiled flex_attention torch>=2.9 are unrelated." }, { - "left": "issue:44991", - "right": "issue:45081", + "left": "issue:44671", + "right": "issue:44991", "accept": false, - "reason": "Tokenizer loading failure for est-roberta and Mistral regex patch backend-tokenizer access are different bugs." + "reason": "CamemBERT MLM prediction regression and tokenizer loading failure for EMBEDDIA/est-roberta are different bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded and conservative overall. The canonical issue choice is reasonable, and the summary correctly frames this as a loose Transformers v5 regression cluster rather than a true duplicate set. The one accepted soft-edge pair (45292/45335) is well supported by the issue titles and stays within the evidence." + "feedback": "The summary is grounded in the packet, and the one accepted soft-edge pair (45292/45335) is a conservative duplicate call based on the shared resize_token_embeddings propagation failure. The other verdicts stay appropriately negative given the titles alone, and no PR mergeability issue applies because no PRs were provided." }, "evaluator_used": true, "retried": false, @@ -2455,25 +2572,24 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ + "issue:32090", "issue:34567", "issue:36032", + "issue:39404", "issue:40444", "issue:40990", "issue:42915", - "issue:43262", + "issue:43089", "issue:43317", - "issue:43322", - "issue:43377", "issue:43404", "issue:43421", "issue:43452", "issue:43482", - "issue:43540", "issue:43541", "issue:43582", "issue:43611", @@ -2483,21 +2599,21 @@ "issue:43645", "issue:43646", "issue:43716", + "issue:43856", "issue:43883", - "issue:43994", "issue:44164", "issue:44206", "issue:44220", "issue:44451", + "issue:44464", "issue:44466", "issue:44479", "issue:44488", "issue:44530", - "issue:44534", - "issue:44610", "issue:44661", "issue:44683", "issue:44737", + "issue:44756", "issue:44811", "issue:44849", "issue:44987", @@ -2507,9 +2623,13 @@ "issue:45325", "issue:45507", "issue:45584", - "issue:45859" + "issue:45859", + "issue:45987" ], "soft_pairs": [ + "issue:32090|issue:39404", + "issue:43856|issue:44756", + "issue:44991|issue:45081", "issue:44737|issue:45859", "issue:44164|issue:44479", "issue:43582|issue:43632", @@ -2522,9 +2642,10 @@ "issue:43716|issue:45084", "issue:43883|issue:44488", "issue:43643|issue:44530", + "issue:36032|issue:42915", "issue:44811|issue:45584", "issue:34567|issue:40444", - "issue:36032|issue:42915", + "issue:44464|issue:45987", "issue:43644|issue:43646", "issue:44451|issue:44987", "issue:43452|issue:43482", @@ -2536,233 +2657,229 @@ "issue:44987|issue:44991", "issue:43883|issue:44991", "issue:43404|issue:44466", - "issue:45084|issue:45507", - "issue:43262|issue:43377", - "issue:43994|issue:44610", - "issue:43646|issue:44534", - "issue:43322|issue:43540", - "issue:43645|issue:44534" + "issue:43089|issue:45987", + "issue:45084|issue:45507" ], - "prepared_review_unit_hash": "b6c8734c85a5d40f89c97d8b3c6990902cf78ec89bdede0a9c0e034614bfc47a", + "prepared_review_unit_hash": "935733371e0282169a8f50808adc185ebaf51fbd4f63d5ea2c1dd9c8ba5dcae9", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37334, - "estimated_input_tokens": 9334, - "estimated_eval_tokens": 18924 + "serialized_chars": 37262, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly heterogeneous cluster of unrelated Transformers issues. A small subset concerns v5/custom-model initialization regressions, but the paired artifacts still describe different concrete failures, so no soft edges are accepted.", + "summary": "Mostly a heterogeneous set of Transformers issue reports with overlapping buzzwords (v5 regressions, loading, tokenizers, device/offload), but no pair looks like the same concrete bug/change. No PRs were present.", "confidence": 0.71, - "canonical_issue_reason": "issue:43646 is the broadest, most representative issue in the cluster's main v5/custom-model-init regression theme, with a generic title that can encompass nearby initialization failures more cleanly than the more specific model- or buffer-related reports.", + "canonical_issue_reason": "issue:43644 is the broadest, most central regression report in the set (v5.0.0 non-persistent buffer corruption) and is the best umbrella anchor among these mostly unrelated issues.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the best single issue representative because it is the most general and central to the repeated Transformers v5 initialization regression pattern in this set.", + "best_issue_reason": "issue:43644 is the best global issue candidate because it describes a core, actionable v5 regression with potential downstream impact on model initialization/loading paths.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Different failures: Trainer GPU broadcast NoneType error vs Whisper pipeline return_language regression." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both are memory-related, but one is Qwen3 MoE training efficiency and the other is Strix Halo mmap OOM; not the same bug." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both concern tokenizer loading, but one is an est-roberta tokenizer failure and the other is a Mistral regex patch crash; different code paths." + }, { "left": "issue:44737", "right": "issue:45859", "accept": false, - "reason": "Different model families and different bugs: XLNet CPU placement in a forward pass vs Qwen3.5 MoE CPU-offload incompatibility." + "reason": "Both involve device placement, but XLNet CPU arange overhead and Qwen3_5Moe CPU offload incompatibility are distinct issues." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "Serialization/extra_state handling is unrelated to a video-input regression in Qwen multimodal models." + "reason": "save/from_pretrained extra_state handling is unrelated to the Qwen video-input regression." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and the _is_hf_initialized flag regression are distinct failures." + "reason": "Apple Silicon caching_allocator_warmup TypeError and the _is_hf_initialized regression are separate failures." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Both are loading/tokenizer issues, but they hit different code paths and different models; not the same concrete bug." + "reason": "Different model-loading bugs; shared tokenization context is too broad to treat as one defect." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "Model-registration failure in add-new-model-like is unrelated to compiled flex_attention compatibility on torch >= 2.9." + "reason": "Tokenizer mapping/add-new-model-like failure is unrelated to compiled flex_attention on torch>=2.9." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "High perplexity on a model is not the same bug as runtime special-token post-processor updates." + "reason": "Perplexity regression on gpt-oss-20b is not the same as runtime post-processor updates for special tokens." }, { "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Different loading failures for different models; no evidence they share the same underlying tokenizer/model bug." + "reason": "Both are model-loading complaints, but they target different models and failure modes." }, { "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; separate code paths." + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer junk are different code-path bugs." }, { "left": "issue:44206", "right": "issue:44220", "accept": false, - "reason": "Audio feature extraction failures are too vague here to conclude the same underlying bug; the titles point to different symptoms." + "reason": "FeatureExtractor center-arg regression and _torch_extract_fbank_features problems are related audio code, but not the same concrete issue." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Mistral-3 dtype mismatch in image preprocessing is unrelated to a template compilation TypeError." + "reason": "Mistral image dtype mismatch is unrelated to the template-node compilation TypeError." }, { "left": "issue:43883", "right": "issue:44488", "accept": false, - "reason": "Missing all_tied_weights_keys in Molmo is unrelated to tokenizer loading for cjvt/sleng-bert." + "reason": "Missing all_tied_weights_keys in Molmo is unrelated to loading sleng-bert." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "AutoConfig trust_remote_code field loss and PagedAttentionCache linear_attention failure are unrelated." + "reason": "AutoConfig trust_remote_code field loss and Qwen3.5 PagedAttentionCache invalid group type are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer special-token conflict and Qwen3Moe FP8 config failure are different bugs." }, { "left": "issue:44811", "right": "issue:45584", "accept": false, - "reason": "Whisper decode skip_special_tokens behavior and empty-transcription generation after align_special_tokens are related to the same area but not clearly the same concrete bug." + "reason": "Both are Whisper/special-token themed, but batch_decode skip_special_tokens is distinct from empty-transcription generation failure." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "TrainerState token counting and Qwen2.5-VL iterable-dataset multi-image failure are unrelated." + "reason": "TrainerState token counter bug and Qwen2.5-VL iterable dataset multi-image finetuning failure are unrelated." }, { - "left": "issue:36032", - "right": "issue:42915", + "left": "issue:44464", + "right": "issue:45987", "accept": false, - "reason": "T5 tokenizer special-token method conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." + "reason": "Chunked generation inconsistency with compiled forward is not the same as StaticCache.get_seq_length returning a tensor." }, { "left": "issue:43644", "right": "issue:43646", "accept": false, - "reason": "Both are Transformers v5 regressions, but one concerns non-persistent buffers and the other custom model initialization; not the same fix target." + "reason": "Related v5 initialization complaints, but one is buffer corruption and the other is custom model initialization; not the same defect." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Different model-loading failures with no clear shared code path." + "reason": "Different model-loading failures for different repositories; no evidence of one shared underlying bug." }, { "left": "issue:43452", "right": "issue:43482", "accept": false, - "reason": "Both mention GGUF/loading, but one is a broad gguf_file from_pretrained breakage and the other is a specific Qwen2.5-GGUF failure; insufficient evidence they are the same bug." + "reason": "Both involve GGUF loading, but one is a general gguf_file API break and the other is a Qwen2.5-GGUF-specific failure." }, { "left": "issue:43541", "right": "issue:45084", "accept": false, - "reason": "Torch dynamo grouped_mm tracing error and non-template node compilation error are different failures." + "reason": "Mixtral grouped_mm tracing error and template-node compile TypeError are distinct compiler/runtime problems." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "Different Qwen variants and different failure modes: FineGrainedFP8Config vs linear_attention cache group handling." + "reason": "Different Qwen-family issues: FP8 training failure vs PagedAttentionCache linear_attention crash." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "Device-map/offload dequantized-model loading issue is unrelated to a Qwen2.5-GGUF loading regression." + "reason": "device_map auto offload loading failure and Qwen2.5-GGUF v5 loading failure are not the same code path." }, { "left": "issue:44849", "right": "issue:45325", "accept": false, - "reason": "Qwen3.5 hidden-state output bug and Qwen2.5-VL rope-index scaling bug are distinct issues." + "reason": "Qwen3.5 output_hidden_states bug and Qwen2.5-VL rope indexing bug are unrelated model-specific regressions." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Tokenizer method-name conflict is unrelated to custom model initialization in Jupyter notebooks." + "reason": "T5 tokenizer special-token conflict is unrelated to custom model initialization in notebooks." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Different models and likely different failure mechanisms; not the same underlying loading bug." + "reason": "Different model/tokenizer loading failures for different checkpoints; no shared concrete bug." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "Missing tied-weight attribute in Molmo is unrelated to tokenizer loading for EMBEDDIA/est-roberta." + "reason": "Molmo tied-weights attribute error is unrelated to tokenizer loading for EMBEDDIA/est-roberta." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Mistral3 lm_head tying bug and device-dependent serialization of lm_head.weight are related in broad theme only; not enough to call them the same bug." - }, - { - "left": "issue:45084", - "right": "issue:45507", - "accept": false, - "reason": "Template compilation failure and GraniteMoEHybrid invalid method call are unrelated." - }, - { - "left": "issue:43262", - "right": "issue:43377", - "accept": false, - "reason": "Audio sampling-rate defaulting and MIMI batching/padding-mask mismatch are separate issues." - }, - { - "left": "issue:43994", - "right": "issue:44610", - "accept": false, - "reason": "Bad SIGLIP2 outputs and OmDet-Turbo resolution mismatch are different model/preprocessing problems." - }, - { - "left": "issue:43646", - "right": "issue:44534", - "accept": false, - "reason": "Custom model initialization regression and non-persistent buffer junk are different concrete failures despite both being v5-related." + "reason": "Mistral3 lm_head tying bug and lm_head serialization inconsistency are related to weights, but not the same failure mode." }, { - "left": "issue:43322", - "right": "issue:43540", + "left": "issue:43089", + "right": "issue:45987", "accept": false, - "reason": "Llava Next loading segfault and Qwen3OmniMoe video-input ValueError are unrelated multimodal failures." + "reason": "Generation GPU sync/dispatch overhead is unrelated to StaticCache.get_seq_length return type." }, { - "left": "issue:43645", - "right": "issue:44534", + "left": "issue:45084", + "right": "issue:45507", "accept": false, - "reason": "Jupyter custom model initialization and non-persistent buffer initialization are not the same bug." + "reason": "Template compilation error and GraniteMoEHybrid invalid method calls are different bugs in different subsystems." } ] }, @@ -2781,10 +2898,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36032", "issue:40444", @@ -2793,19 +2910,22 @@ "issue:41720", "issue:42175", "issue:42915", + "issue:43262", "issue:43296", + "issue:43322", "issue:43377", "issue:43404", - "issue:43421", "issue:43425", "issue:43531", + "issue:43540", "issue:43582", "issue:43611", "issue:43632", + "issue:43645", + "issue:43646", "issue:43742", - "issue:43792", - "issue:43818", "issue:43819", + "issue:43994", "issue:44062", "issue:44079", "issue:44220", @@ -2815,7 +2935,6 @@ "issue:44451", "issue:44479", "issue:44534", - "issue:44568", "issue:44589", "issue:44610", "issue:44683", @@ -2823,8 +2942,6 @@ "issue:44811", "issue:44877", "issue:44987", - "issue:44991", - "issue:45020", "issue:45081", "issue:45084", "issue:45127", @@ -2835,6 +2952,11 @@ "issue:45663" ], "soft_pairs": [ + "issue:43262|issue:43377", + "issue:43994|issue:44610", + "issue:43646|issue:44534", + "issue:43322|issue:43540", + "issue:43645|issue:44534", "issue:44403|issue:45081", "issue:43377|issue:43819", "issue:42915|issue:45084", @@ -2844,252 +2966,244 @@ "issue:44987|issue:45081", "issue:44220|issue:44683", "issue:43404|issue:45127", - "issue:43632|issue:44756", "issue:42915|issue:44291", + "issue:43632|issue:44756", "issue:44062|issue:44987", "issue:44479|issue:45325", "issue:36032|issue:43742", - "issue:43296|issue:43531", "issue:42915|issue:44589", + "issue:43296|issue:43531", "issue:40444|issue:45325", "issue:43531|issue:44877", "issue:43611|issue:44534", "issue:36032|issue:41720", "issue:43425|issue:44403", - "issue:44079|issue:45663", "issue:41553|issue:43582", + "issue:44079|issue:45663", "issue:40990|issue:44811", "issue:43632|issue:44534", - "issue:42175|issue:45542", - "issue:43421|issue:44568", - "issue:43818|issue:45357", - "issue:43792|issue:44589", - "issue:44683|issue:45020", - "issue:44403|issue:44991" + "issue:42175|issue:45542" ], - "prepared_review_unit_hash": "0ce5cec36108bc038daf49caf19b5f64ba7ddf167eebbc6b62d1de9e726f4252", + "prepared_review_unit_hash": "a989dbb9af60ea95d02438feb2c78afe783af51168a5c35f029f8d3d36996c42", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 31, - "serialized_chars": 36435, - "estimated_input_tokens": 9109, - "estimated_eval_tokens": 18474 + "serialized_chars": 36391, + "estimated_input_tokens": 9098, + "estimated_eval_tokens": 18452 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is still mostly heterogeneous: many issues are broad Transformers v5 regressions, but most soft-edge pairs are only loosely related by subsystem or model family rather than the same concrete bug. The two previously accepted pairs are better treated as related follow-ups/regressions, not confirmed duplicates, from the evidence shown.", - "confidence": 0.62, - "canonical_issue_reason": "issue:45020 is the best broad open umbrella for the cluster\u2019s main theme: recent Transformers versions breaking model loading/behavior, especially around remote_code and adjacent initialization paths.", + "summary": "The set is mostly a collection of unrelated bug reports with only broad topical overlap (especially around Transformers v5 and Qwen variants). None of the soft pairs look like the same concrete underlying bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "issue:43646 is the broadest, most umbrella-like Transformers v5 regression in the set, so it is the best canonical issue anchor if one must be chosen.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the strongest representative issue because it is broad, still open, and best captures the recurring version-regression pattern across the cluster.", + "best_issue_reason": "issue:43646 is the most generally framed issue and the most plausible duplicate target among the items, even though the cluster is not truly a duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44403", - "right": "issue:45081", + "left": "issue:43262", + "right": "issue:43377", "accept": false, - "reason": "Both are loader-related, but this is generic load noise vs a specific Mistral regex crash; different bug paths." + "reason": "Different subsystems and failure modes: audio chat template sample-rate handling vs MIMI encoder padding-mask batching." }, { - "left": "issue:43377", - "right": "issue:43819", + "left": "issue:43994", + "right": "issue:44610", "accept": false, - "reason": "Different model families and mechanisms: padding-mask batching bug vs DAC forward/from_latents mismatch." + "reason": "Both are vision/model-quality reports, but one is nonsensical outputs from AutoModel/pipeline and the other is a processor size mismatch for OmDet-Turbo." }, { - "left": "issue:42915", - "right": "issue:45084", + "left": "issue:43646", + "right": "issue:44534", "accept": false, - "reason": "Qwen3Moe FP8 config handling and a template-node compilation TypeError are unrelated." + "reason": "Both touch Transformers v5 init/load behavior, but one is custom-model initialization and the other is non-persistent buffer corruption; not the same bug." }, { - "left": "issue:44265", - "right": "issue:44610", + "left": "issue:43322", + "right": "issue:43540", "accept": false, - "reason": "Torch export/check issues are unrelated to an OmDet processor size mismatch." + "reason": "Llava Next loading segfault and Qwen3OmniMoe video ValueError are unrelated code paths." }, { - "left": "issue:44451", - "right": "issue:45081", + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook/custom model initialization breakage is a different issue from junk-filled non-persistent buffers." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic loading noise and a Mistral tokenizer regex patch crash are not the same defect." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI batching/padding-mask mismatch is unrelated to DAC latent decoding without STE." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and template-compilation errors have different root causes and code paths." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export with torch_compilable_check and OmDet processor resolution mismatch are distinct issues." + }, + { + "left": "issue:44451", + "right": "issue:45081", "accept": false, - "reason": "Different tokenizers/models and different failure modes; not the same underlying bug." + "reason": "Model loading failure for ScandiBERT and tokenizer backend attribute crash are unrelated." }, { "left": "issue:45216", "right": "issue:45357", "accept": false, - "reason": "They are both Qwen3.5 save_pretrained regressions, but 45357 looks like a follow-up about visual encoder keys rather than a confirmed duplicate root cause." + "reason": "Both concern Qwen3.5 save_pretrained regressions, but one is incorrect checkpointing generally and the other is specific visual encoder key naming; not clearly the same bug." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "One is a model-loading failure for a remote_code package; the other is a Mistral tokenizer regex crash." + "reason": "Physical-intelligence/fast loading regression and Mistral tokenizer regex patch crash are different problems." }, { "left": "issue:44220", "right": "issue:44683", "accept": false, - "reason": "Audio feature extraction and compiled flex_attention are unrelated." + "reason": "Audio feature extraction bug and compiled flex_attention failure on newer torch are unrelated." }, { "left": "issue:43404", "right": "issue:45127", "accept": false, - "reason": "Both mention weights/tie_word_embeddings, but the concrete bugs are different: Mistral3 weight tying vs LoRA merge with extended vocab." + "reason": "Untied lm_head weights in Mistral3 and LoRA merge collapse after vocab extension are different model-state issues." }, { - "left": "issue:43632", - "right": "issue:44756", + "left": "issue:42915", + "right": "issue:44291", "accept": false, - "reason": "A v5 initialization-flag regression is not the same as a Strix Halo mmap OOM issue." + "reason": "FineGrainedFP8Config failure and unexpected _is_hf_initialized argument during init_empty_weights are distinct Transformers v5 regressions." }, { - "left": "issue:42915", - "right": "issue:44291", + "left": "issue:43632", + "right": "issue:44756", "accept": false, - "reason": "Different loading/initialization failures with no clear shared code path." + "reason": "_is_hf_initialized flag breakage and mmap/OOM on Strix Halo are unrelated." }, { "left": "issue:44062", "right": "issue:44987", "accept": false, - "reason": "The AddedToken special-argument TypeError is not clearly the same as the physical-intelligence/fast load failure." + "reason": "Tokenizers AddedToken special-flag conflict does not match the physical-intelligence/fast loading regression." }, { "left": "issue:44479", "right": "issue:45325", "accept": false, - "reason": "Related by Qwen VL family/version, but the titles do not clearly establish one root cause; this looks more like an adjacent video-input regression than a confirmed duplicate." + "reason": "Video-input regression across Qwen models and still-image temporal position scaling are separate Qwen2.5-VL/Qwen3-VL bugs." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "Tokenizer add_special_tokens conflict and MobileLLM key error are different loading bugs." + "reason": "T5Tokenizer special-token method conflict and MobileLLM key error are different loading failures." }, { - "left": "issue:43296", - "right": "issue:43531", + "left": "issue:42915", + "right": "issue:44589", "accept": false, - "reason": "Different model families and different failure modes." + "reason": "Qwen3Moe FP8 config failure and missing Float8 storage lookup are not the same error path." }, { - "left": "issue:42915", - "right": "issue:44589", + "left": "issue:43296", + "right": "issue:43531", "accept": false, - "reason": "FP8 config failure and missing Float8 storage are not the same underlying issue." + "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window behavior are unrelated." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "Both involve Qwen2.5-VL multimodal handling, but one is multi-image prompt iteration and the other is temporal position scaling; not clearly the same bug." + "reason": "IterableDataset multi-image finetuning failure and Qwen2.5-VL still-image rope scaling are different multimodal bugs." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to strict config loading for granite_speech." + "reason": "Qwen3-MoE sliding_window bug and granite_speech strict-config loading failure do not share a concrete root cause." }, { "left": "issue:43611", "right": "issue:44534", "accept": false, - "reason": "Base_model_prefix loading breakage and junk-filled non-persistent buffers are different v5 regressions." + "reason": "base_model_prefix loading regression is not the same as non-persistent buffer corruption." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer load conflict and Qwen3 auto-device-map cuda assert are unrelated." + "reason": "Tokenizer attribute conflict and Qwen3 auto device mapping cudaErrorAssert are unrelated." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch version compatibility and generic transformer-load noise are not the same bug." + "reason": "Torch version incompatibility and generic loading noise are not duplicates." }, { - "left": "issue:44079", - "right": "issue:45663", + "left": "issue:41553", + "right": "issue:43582", "accept": false, - "reason": "ModelOutput key assignment and Gemma4 FSDP2 shared_kv_states reconstruction are unrelated." + "reason": "Bad AutoTokenizer error for Voxtral and AppleSilicon caching_allocator_warmup TypeError are unrelated." }, { - "left": "issue:41553", - "right": "issue:43582", + "left": "issue:44079", + "right": "issue:45663", "accept": false, - "reason": "A bad AutoTokenizer error message and an Apple Silicon caching allocator TypeError are unrelated." + "reason": "ModelOutput key assignment bug and Gemma4 FSDP2 shared_kv_states rebuild failure are different issues." }, { "left": "issue:40990", "right": "issue:44811", "accept": false, - "reason": "Perplexity regression on GPT-OSS is unrelated to Whisper batch_decode skip_special_tokens behavior." + "reason": "High perplexity on gpt-oss-20b and Whisper batch_decode skip_special_tokens behavior are unrelated." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "These are different v5 regressions affecting different internals." + "reason": "The _is_hf_initialized flag regression and non-persistent buffer junk issue are separate Transformers v5 breakages." }, { "left": "issue:42175", "right": "issue:45542", "accept": false, - "reason": "Both concern TensorFlow availability, but one is missing TF in the torch extra and the other is tensorboard-only backend detection; not the same fix." - }, - { - "left": "issue:43421", - "right": "issue:44568", - "accept": false, - "reason": "Both involve special tokens, but one is runtime post-processor refresh and the other is add_special_tokens not adding BOS/EOS for a specific tokenizer." - }, - { - "left": "issue:43818", - "right": "issue:45357", - "accept": false, - "reason": "Video-LLaVA temporal-attention/weight-sharing bug is unrelated to Qwen3.5 save_pretrained key serialization." - }, - { - "left": "issue:43792", - "right": "issue:44589", - "accept": false, - "reason": "Whisper runtime failure and Float8 storage lookup error are different issues." - }, - { - "left": "issue:44683", - "right": "issue:45020", - "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and remote_code model-loading regressions are separate problems." - }, - { - "left": "issue:44403", - "right": "issue:44991", - "accept": false, - "reason": "Generic loading noise and a specific tokenizer load failure for EMBEDDIA/est-roberta are not the same underlying bug." + "reason": "TensorFlow missing from a torch-only install and undefined tf backend from tensorboard-only install are related packaging themes but not the same defect." } ] }, - "evaluator_result": { - "accept": false, - "feedback": "The summary is broadly grounded, but the soft-edge accepts are a bit too assertive for the evidence shown. In particular, issue:44479 vs issue:45325 looks related by model family/version, but the packet does not clearly establish a single root cause from titles alone, and issue:45216 vs issue:45357 likewise reads more like a continuing/follow-up regression than a confirmed duplicate. The rest of the rejects are appropriately conservative." - }, - "evaluator_used": true, - "retried": true, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -3102,21 +3216,21 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:33666", "issue:35707", "issue:40444", "issue:41720", "issue:42175", - "issue:42915", "issue:43296", "issue:43317", "issue:43377", "issue:43381", + "issue:43421", "issue:43454", "issue:43482", "issue:43525", @@ -3125,38 +3239,43 @@ "issue:43632", "issue:43644", "issue:43646", - "issue:43701", "issue:43749", "issue:43792", + "issue:43818", "issue:43856", - "issue:43957", "issue:43994", "issue:44079", "issue:44265", "issue:44291", - "issue:44387", + "issue:44403", "issue:44462", "issue:44466", - "issue:44479", "issue:44534", + "issue:44568", "issue:44589", - "issue:44617", + "issue:44683", "issue:44829", "issue:44898", + "issue:44991", + "issue:45020", "issue:45072", "issue:45081", "issue:45325", + "issue:45357", "issue:45381", "issue:45479", "issue:45491", "issue:45538", - "issue:45800", "issue:45812", - "issue:45823", "issue:45834", "issue:45923" ], "soft_pairs": [ + "issue:43421|issue:44568", + "issue:43792|issue:44589", + "issue:43818|issue:45357", + "issue:44683|issue:45020", + "issue:44403|issue:44991", "issue:44462|issue:45812", "issue:33666|issue:40444", "issue:44829|issue:45479", @@ -3165,8 +3284,8 @@ "issue:43381|issue:45923", "issue:35707|issue:40444", "issue:44079|issue:44534", - "issue:43482|issue:43525", "issue:44291|issue:44589", + "issue:43482|issue:43525", "issue:43377|issue:45491", "issue:43749|issue:44079", "issue:40444|issue:45381", @@ -3174,238 +3293,223 @@ "issue:41720|issue:45081", "issue:43531|issue:44291", "issue:44265|issue:45072", - "issue:43632|issue:45072", "issue:45325|issue:45381", + "issue:43632|issue:45072", "issue:43994|issue:44898", "issue:43611|issue:43646", "issue:42175|issue:43296", "issue:43454|issue:44466", - "issue:45325|issue:45834", - "issue:43792|issue:43957", - "issue:42915|issue:43482", - "issue:43296|issue:45800", - "issue:44387|issue:44617", - "issue:43701|issue:45325", - "issue:44479|issue:45823" + "issue:45325|issue:45834" ], - "prepared_review_unit_hash": "033315bcf69e709c1019b06823a140019358ecb6c8cf1b01cfc5def71b2f636e", + "prepared_review_unit_hash": "d008e177a7ef4168cbc1f22b10d2fcbd333f817f4f08d893bd171aece99f1e4b", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36752, - "estimated_input_tokens": 9188, - "estimated_eval_tokens": 18632 + "soft_pair_count": 29, + "serialized_chars": 36580, + "estimated_input_tokens": 9145, + "estimated_eval_tokens": 18546 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is mostly a loose mix of Transformers v5 / model-specific regression reports, not one tight duplicate set. The only strong soft-edge match is the Qwen2.5-VL position-id regression pair; the rest are related by subsystem but appear to be distinct bugs.", - "confidence": 0.57, - "canonical_issue_reason": "Best umbrella representative of the cluster\u2019s recurring Transformers v5 loading/initialization regressions; broad enough to anchor triage better than the more model-specific tickets.", + "summary": "These items are mostly unrelated issue reports, many around Transformers v5 regressions. None of the proposed soft pairs look like true duplicates of the same concrete bug. The broadest umbrella issue in the set is the remote_code regression report.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45020 is the broadest, most umbrella-style report and has active discussion/references; it best represents the cluster if one issue must be chosen.", "canonical_pr_reason": null, - "best_issue_reason": "Most central single issue in the set: it captures the generic v5 init/loading breakage theme that several of the other issues orbit, without being overly narrow.", + "best_issue_reason": "issue:45020 is the most suitable representative issue because it spans multiple affected models and a common regression class rather than a narrow model-specific failure.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer-related, but one is about updating the post-processor after runtime special-token changes while the other is about add_special_tokens not adding BOS/EOS; different bugs." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated failure modes: Whisper model loading versus missing Float8 storage handling." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Different models and defects: Video-LLaVA tower architecture issue versus Qwen3.5 save_pretrained key serialization." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Both involve recent version regressions, but one is a torch.compile/flex_attention breakage and the other is a remote_code model-loading regression." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "One is generic loading noise, the other is a tokenizer-loading regression for a specific model; not the same bug." + }, { "left": "issue:44462", "right": "issue:45812", "accept": false, - "reason": "Both are AutoTokenizer regressions, but one is about ignoring tokenizer.json while the other is a Granite-specific wrong-token-IDs bug; related area, different failure mode." + "reason": "Both concern AutoTokenizer behavior, but one ignores tokenizer.json while the other returns wrong token IDs for Granite models." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Both are Qwen VL training problems, but one is multi-GPU training and the other is IterableDataset handling with multiple images per prompt; not the same bug." + "reason": "Different scenarios: multi-GPU training for Qwen2-VL versus IterableDataset failures with multiple images per prompt." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "Both mention degenerate training, but the reported causes differ: flash_attention_3 behavior vs. single-label classification with num_labels=1." + "reason": "Both affect classification training, but the triggers differ: flash_attention_3 degeneration versus num_labels=1 zero-loss behavior." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "One is device_map/offload loading failure, the other is Qwen3 MoE memory inefficiency; same broad area, different issue." + "reason": "Different problems: device_map/offload loading failure versus inefficient memory usage during Qwen3 MoE training." }, { "left": "issue:43482", "right": "issue:45538", "accept": false, - "reason": "Qwen2.5-GGUF loading on transformers v5 and CLIPTokenizer model_max_length are unrelated bugs." + "reason": "Different tokenizer/model-loading issues: GGUF loading failure versus CLIPTokenizer max_length behavior." }, { "left": "issue:43381", "right": "issue:45923", "accept": false, - "reason": "Gradient checkpointing in eval mode is a runtime-mode bug; missing supports_gradient_checkpointing on trust_remote_code is a model config capability issue." + "reason": "One is eval-mode gradient checkpointing usage, the other is a missing supports_gradient_checkpointing flag on a remote-code variant." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen VL finetuning with multi-image iterable data." + "reason": "Different generation/training contexts and different root causes; not the same bug." }, { "left": "issue:44079", "right": "issue:44534", "accept": false, - "reason": "Both are Transformers v5 regressions, but one is ModelOutput key assignment and the other is non-persistent buffer initialization; different code paths." + "reason": "Different internal behaviors: ModelOutput key assignment versus non-persistent buffer serialization." }, { - "left": "issue:43482", - "right": "issue:43525", + "left": "issue:44291", + "right": "issue:44589", "accept": false, - "reason": "GGUF loading failure and Llama4Config missing pad_token_id are separate model/load issues." + "reason": "Both are v5 compatibility issues, but one is init_empty_weights argument handling and the other is Float8 storage resolution." }, { - "left": "issue:44291", - "right": "issue:44589", + "left": "issue:43482", + "right": "issue:43525", "accept": false, - "reason": "Both occur in model loading, but one is unexpected _is_hf_initialized handling and the other is Float8 storage lookup; not the same bug." + "reason": "Both are loading issues, but one is GGUF/v5 compatibility and the other is missing pad_token_id on Llama4Config." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "Both involve batch-vs-single discrepancies, but one is MIMI encoder padding masks and the other is Gemma3 sliding-window all-padding NaNs; different models and mechanisms." + "reason": "Both mention batched/padding-related failures, but they affect different models and code paths." }, { "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP_CPU_RAM_EFFICIENT_LOADING and ModelOutput key assignment are unrelated." + "reason": "FSDP RAM-efficient loading and ModelOutput key assignment are unrelated." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Qwen2.5-VL multi-image finetuning failure is not the same as the video position-id regression in v5.3.0." + "reason": "Different Qwen2.5-VL bugs: multi-image IterableDataset finetuning versus video vision_position_ids." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Non-persistent buffer junk and ModelOutput key assignment are distinct v5 regressions." + "reason": "Non-persistent buffer junk filling is unrelated to ModelOutput key bookkeeping." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert and Mistral regex patch crash are unrelated." + "reason": "Different failures in different models: cudaErrorAssert on Qwen3 auto device mapping versus Mistral tokenizer regex patch crash." }, { "left": "issue:43531", "right": "issue:44291", "accept": false, - "reason": "Sliding_window behavior in Qwen3-MoE and init_empty_weights/_is_hf_initialized are different issues." + "reason": "Sliding-window handling in Qwen3-MoE is not the same as unexpected _is_hf_initialized argument in init_empty_weights." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "torch.export with torch_compilable_check and dtype mismatches in bfloat16 inference do not share the same root cause." + "reason": "torch.export with torch_compilable_check and bfloat16 dtype mismatches are different bugs." }, { - "left": "issue:43632", - "right": "issue:45072", + "left": "issue:45325", + "right": "issue:45381", "accept": false, - "reason": "_is_hf_initialized breakage and bfloat16 dtype mismatch are separate Transformers v5 regressions." + "reason": "Same model family, but one is still-image temporal position scaling and the other is video vision_position_ids; not the same concrete defect." }, { - "left": "issue:45325", - "right": "issue:45381", - "accept": true, - "reason": "Both describe Qwen2.5-VL v5.3.0 position-id generation bugs in the same code path; a single fix could plausibly cover image and video variants." + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "Different v5 regressions: _is_hf_initialized flag handling versus bfloat16 dtype mismatch." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "SigLIP2 nonsensical outputs and Perceiver non-default resolution failure are different model-specific bugs." + "reason": "Different vision-model failures: siglip2 nonsensical outputs versus Perceiver resolution/interpolation issue." }, { "left": "issue:43611", "right": "issue:43646", "accept": false, - "reason": "Both are broad v5 loading/init regressions, but one is base_model_prefix handling and the other is custom model initialization; too different to merge confidently." + "reason": "Both are v5 model-init regressions, but one is base_model_prefix loading and the other is custom initialization behavior." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "TensorFlow packaging/backend inclusion and PaddleOCR-VL model loading are unrelated." + "reason": "Package backend inclusion and PaddleOCR-VL load failure are unrelated." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "AyaVision lm_head tying and inconsistent lm_head serialization are related by weights, but they are not clearly the same defect." + "reason": "One is a specific AyaVision weight-tying bug; the other is inconsistent lm_head serialization across devices." }, { "left": "issue:45325", "right": "issue:45834", "accept": false, - "reason": "Qwen2.5-VL position IDs and Kosmos2.5 OCR long-input index errors are different model bugs." - }, - { - "left": "issue:43792", - "right": "issue:43957", - "accept": false, - "reason": "Whisper model load failure and torch.device('meta') loading regressions are separate issues." - }, - { - "left": "issue:42915", - "right": "issue:43482", - "accept": false, - "reason": "Qwen3MoE FineGrainedFP8Config failure and Qwen2.5-GGUF loading failure are different model/config paths." - }, - { - "left": "issue:43296", - "right": "issue:45800", - "accept": false, - "reason": "PaddleOCR-VL loading on transformers 4.53.0/vLLM and torch 2.4.1 vs transformers 5.8.0 incompatibility are unrelated." - }, - { - "left": "issue:44387", - "right": "issue:44617", - "accept": false, - "reason": "Int4 memory regression and Sam3Video OOM are both memory-related but not the same bug or code path." - }, - { - "left": "issue:43701", - "right": "issue:45325", - "accept": false, - "reason": "resume_from_checkpoint key mismatch is unrelated to Qwen2.5-VL rope/position-id scaling." - }, - { - "left": "issue:44479", - "right": "issue:45823", - "accept": false, - "reason": "Qwen video input regression and Gemma4 PLE device mismatch are different model-specific failures." + "reason": "Both involve Qwen2.5-VL OCR/position behavior, but one is temporal position scaling and the other is long OCR input index errors." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays appropriately conservative: it frames the set as a mixed cluster with a recurring v5 loading/init theme without overclaiming a single root cause. The only accepted soft-edge pair, issue:45325 and issue:45381, is a plausible same-code-path Qwen2.5-VL position-id regression. The remaining pairs are rejected with cautious, bug-specific distinctions rather than overstating duplication." - }, - "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 }, @@ -3417,10 +3521,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:34634", "issue:35707", @@ -3428,52 +3532,58 @@ "issue:40444", "issue:40990", "issue:41720", + "issue:42915", "issue:42947", "issue:43257", "issue:43262", "issue:43296", "issue:43317", - "issue:43322", "issue:43377", - "issue:43404", "issue:43454", + "issue:43482", "issue:43526", "issue:43550", "issue:43572", "issue:43606", - "issue:43720", + "issue:43701", "issue:43746", - "issue:43749", + "issue:43792", "issue:43819", "issue:43873", "issue:43881", "issue:43883", - "issue:44008", + "issue:43957", "issue:44186", "issue:44265", "issue:44291", - "issue:44466", + "issue:44387", + "issue:44479", "issue:44488", - "issue:44534", "issue:44568", "issue:44610", + "issue:44617", "issue:44877", "issue:44898", - "issue:44977", - "issue:44991", "issue:45072", - "issue:45357", + "issue:45325", "issue:45584", "issue:45701", "issue:45759", + "issue:45800", "issue:45823", "issue:45920", "issue:45923" ], "soft_pairs": [ + "issue:43792|issue:43957", + "issue:42915|issue:43482", + "issue:43296|issue:45800", + "issue:44387|issue:44617", + "issue:43701|issue:45325", + "issue:44479|issue:45823", "issue:43881|issue:44488", - "issue:44291|issue:44877", "issue:43606|issue:44265", + "issue:44291|issue:44877", "issue:44568|issue:45920", "issue:43262|issue:43746", "issue:40990|issue:45584", @@ -3489,234 +3599,207 @@ "issue:39692|issue:40444", "issue:43572|issue:45759", "issue:43454|issue:45072", - "issue:43377|issue:44898", "issue:43257|issue:45923", + "issue:43377|issue:44898", "issue:43526|issue:43883", - "issue:40990|issue:42947", - "issue:44466|issue:45357", - "issue:43881|issue:44991", - "issue:43749|issue:44534", - "issue:43454|issue:43720", - "issue:41720|issue:43322", - "issue:43296|issue:44877", - "issue:41720|issue:44977", - "issue:44008|issue:45823", - "issue:43404|issue:45357" + "issue:40990|issue:42947" ], - "prepared_review_unit_hash": "0c8521e0374cf97aa71e6872374642779e418a5a1f7c222cd174d7277dfe01a9", + "prepared_review_unit_hash": "06c12f4633bba68c0ccf7ddfe73859d54b9c8f1fc2dd090180f41cb05c3944ba", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36703, - "estimated_input_tokens": 9176, - "estimated_eval_tokens": 18608 + "soft_pair_count": 28, + "serialized_chars": 35605, + "estimated_input_tokens": 8902, + "estimated_eval_tokens": 18060 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is not a true duplicate cluster: the items span unrelated failures across loading, tokenization, device mapping, quantization, audio, vision, and serialization. A few are superficially adjacent, but none look like the same underlying bug/change with enough certainty to merge.", - "confidence": 0.94, + "summary": "These items are a heterogeneous mix of unrelated bugs/regressions across model loading, tokenization, offloading, multimodal processors, and training utilities. None of the soft pairs look like the same concrete underlying issue, so there is no single canonical duplicate to keep for this cluster.", + "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the broadest and most central to the only recurring theme in the set (offloading/quantization/device-map behavior), but it still does not represent the full mix of unrelated issues.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43881", - "right": "issue:44488", + "left": "issue:43792", + "right": "issue:43957", "accept": false, - "reason": "Both are model-loading failures, but they involve different models and different failure modes; not the same underlying bug." + "reason": "Both involve loading/runtime failures, but one is Whisper-specific and the other is a broad meta-device loading issue affecting different models; not the same bug." }, { - "left": "issue:44291", - "right": "issue:44877", + "left": "issue:42915", + "right": "issue:43482", "accept": false, - "reason": "Both touch loading/config handling in v5, but one is an init_empty_weights argument issue and the other is strict config loading; different root causes." + "reason": "Qwen3 MoE FP8 config failure and Qwen2.5 GGUF load failure under v5 are different code paths and symptoms." }, { - "left": "issue:43606", + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "One is a PaddleOCR-VL load problem in vLLM; the other is a general torch/transformers version incompatibility. Too broad to be the same fix." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both mention OOM, but one is an int4 quantization reserved-memory regression and the other is a video model memory issue." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL rope index scaling for still-image temporal positions." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Video-input regression in Qwen VL models and Gemma4 PLE device mismatch are separate forward-path bugs." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different model families and failure modes: glm-4v-9b load failure versus sleng-bert load failure." + }, + { + "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "CPU-offload device mismatch for Bark is unrelated to torch.export failures with torch_compilable_check." + "reason": "CPU offload device mismatch for Bark is unrelated to torch.export failures caused by torch_compilable_check." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Unexpected init_empty_weights argument and strict config loading for granite_speech are distinct loading/config issues." }, { "left": "issue:44568", "right": "issue:45920", "accept": false, - "reason": "Both are tokenizer-related regressions, but one is missing special tokens and the other is wrong token IDs across models; not the same bug." + "reason": "Specific special-token insertion regression for one tokenizer is not the same as wrong token IDs across several models." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting and PEFT local checkpoint loading are unrelated." + "reason": "Audio chat-template sampling-rate default is unrelated to PEFT checkpoint loading for GraniteSpeech." }, { "left": "issue:40990", "right": "issue:45584", "accept": false, - "reason": "A perplexity regression and an empty-transcription generation failure are different issues." + "reason": "High perplexity on gpt-oss-20b and Whisper empty-transcription failure are unrelated generation issues." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "BarkProcessor voice_preset and progressive generation with inputs_embeds/past_key_values are unrelated." + "reason": "BarkProcessor voice_preset malfunction and progressive generation with inputs_embeds/past_key_values are different APIs and bugs." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Offloading/quantization behavior is unrelated to tokenizer changes across versions." + "reason": "Quantization/offloading behavior and tokenizer-version changes do not share the same concrete failing code path." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "Tokenizer batching/padding crashes and torch.export check failures are different code paths." + "reason": "Tokenizer crash on NER/padding is unrelated to torch.export with torch_compilable_check." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Progressive generation with caches and an auto device-map CUDA assert are not the same bug." + "reason": "Progressive generation with inputs_embeds is unrelated to Qwen3 auto device mapping cudaErrorAssert." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "Both mention model behavior bugs, but one is offload/device mismatch and the other is DAC latent conversion mismatch." + "reason": "Both are model-runtime bugs, but CPU offload device mismatch and DAC.from_latents/STE mismatch are separate implementations." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Both involve device_map=auto, but the model-specific forward/device mismatch problems are different." + "reason": "Auto device mapping assert on Qwen3 and Gemma4 PLE device mismatch are different model-specific failures." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "Weight tying in AyaVision is unrelated to Bamba SDPA/torch.compile failures." + "reason": "Weight tying/generation corruption in AyaVision is unrelated to Bamba-9B-v2 torch.compile SDPA failure." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "Missing padding-mask support in MIMI and image-size mismatch in OmDet-Turbo are different preprocessing bugs." + "reason": "Missing padding-mask support in MIMI encoder and OmDet-Turbo processor image-size mismatch are different bugs." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "These are adjacent around offload/quantization, but one is dequantized-model loading on gpu+cpu offload and the other is generic offloading behavior; too broad to merge." + "reason": "Loading dequantized models with device_map=auto and general offloading-not-working reports are related in theme but not the same concrete issue." }, { "left": "issue:39692", "right": "issue:40444", "accept": false, - "reason": "A doc/example error plus quantization failure is unrelated to iterable-dataset multi-image finetuning failure." + "reason": "SigLIP2 doc-example/model-processor mismatch and Qwen2.5-VL iterable multi-image finetuning failure are unrelated." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "Missing pad_token_idx in one config and not unwrapping text_config in another are distinct config bugs." + "reason": "Missing pad_token_idx in StableLmConfig and text_config unwrapping for composite Qwen multimodal configs are distinct config issues." }, { "left": "issue:43454", "right": "issue:45072", "accept": false, - "reason": "Weight-tying and bfloat16 dtype mismatches are unrelated." + "reason": "AyaVision lm_head tying bug and bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel are different failures." }, { - "left": "issue:43377", - "right": "issue:44898", + "left": "issue:43257", + "right": "issue:45923", "accept": false, - "reason": "Both are vision/multimodal preprocessing issues, but one is padding-mask consistency and the other is non-default resolution handling." + "reason": "Qwen3 MoE weight conversion with accelerate+deepspeed is unrelated to a missing supports_gradient_checkpointing flag." }, { - "left": "issue:43257", - "right": "issue:45923", + "left": "issue:43377", + "right": "issue:44898", "accept": false, - "reason": "MOE weight conversion under accelerate/deepspeed and a missing gradient_checkpointing flag are unrelated." + "reason": "MIMI padding-mask divergence and Perceiver non-default-resolution failure are separate model/processor problems." }, { "left": "issue:43526", "right": "issue:43883", "accept": false, - "reason": "Label reduction in BeitImageProcessorFast and a missing all_tied_weights_keys attribute are unrelated." + "reason": "BeitImageProcessorFast reduce_labels bug and Molmo missing all_tied_weights_keys are unrelated." }, { "left": "issue:40990", "right": "issue:42947", "accept": false, - "reason": "Perplexity on a benchmark and gradient checkpointing with LoRA are different problem areas." - }, - { - "left": "issue:44466", - "right": "issue:45357", - "accept": false, - "reason": "Both concern serialization, but one is tied lm_head.weight consistency and the other is incorrect visual encoder keys; not the same fix." - }, - { - "left": "issue:43881", - "right": "issue:44991", - "accept": false, - "reason": "Model loading failure for one model and tokenizer loading failure for a different model are unrelated." - }, - { - "left": "issue:43749", - "right": "issue:44534", - "accept": false, - "reason": "FSDP CPU-efficient loading and non-persistent buffer initialization are separate v5 regressions." - }, - { - "left": "issue:43454", - "right": "issue:43720", - "accept": false, - "reason": "Weight tying in AyaVision and BitNet packed-weight unpacking are unrelated." - }, - { - "left": "issue:41720", - "right": "issue:43322", - "accept": false, - "reason": "Both are severe load/runtime failures, but they are model-specific and do not share a concrete code-path problem." - }, - { - "left": "issue:43296", - "right": "issue:44877", - "accept": false, - "reason": "PaddleOCR-VL loading in vLLM and granite_speech strict-config loading are unrelated." - }, - { - "left": "issue:41720", - "right": "issue:44977", - "accept": false, - "reason": "Both involve Qwen models, but one is an auto device-map crash and the other is flash-attention generation behavior; not the same bug." - }, - { - "left": "issue:44008", - "right": "issue:45823", - "accept": false, - "reason": "Gemma3n variable-name collision in forward is unrelated to Gemma4 PLE device mismatch." - }, - { - "left": "issue:43404", - "right": "issue:45357", - "accept": false, - "reason": "lm_head weight tying in Mistral3 and Qwen3.5 visual key serialization are different regressions." + "reason": "High perplexity evaluation issue and ineffective gradient checkpointing with PEFT LoRA are unrelated training/inference bugs." } ] }, @@ -3735,40 +3818,40 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ - "issue:36010", "issue:36331", "issue:40990", "issue:41720", "issue:42617", "issue:42915", "issue:43295", + "issue:43296", "issue:43316", "issue:43317", "issue:43322", - "issue:43421", + "issue:43404", "issue:43450", + "issue:43454", "issue:43526", - "issue:43531", - "issue:43540", "issue:43550", - "issue:43572", "issue:43577", "issue:43606", "issue:43708", "issue:43720", - "issue:43782", + "issue:43749", "issue:43873", "issue:43881", + "issue:44008", "issue:44186", - "issue:44361", "issue:44387", "issue:44423", + "issue:44466", "issue:44479", + "issue:44534", "issue:44610", "issue:44671", "issue:44743", @@ -3777,30 +3860,40 @@ "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:44466|issue:45357", + "issue:43881|issue:44991", + "issue:43749|issue:44534", + "issue:43454|issue:43720", + "issue:41720|issue:43322", + "issue:43296|issue:44877", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:43404|issue:45357", "issue:42617|issue:42915", "issue:40990|issue:45701", - "issue:45632|issue:45684", "issue:44186|issue:45072", - "issue:43577|issue:43708", + "issue:45632|issue:45684", "issue:44423|issue:45406", + "issue:43577|issue:43708", "issue:44387|issue:45704", "issue:43873|issue:44756", - "issue:44877|issue:44991", "issue:36331|issue:42617", - "issue:43550|issue:43720", + "issue:44877|issue:44991", "issue:36331|issue:42915", + "issue:43550|issue:43720", "issue:43450|issue:45701", "issue:44610|issue:44898", "issue:44186|issue:44610", @@ -3812,229 +3905,240 @@ "issue:43295|issue:45701", "issue:43526|issue:43881", "issue:44671|issue:44743", - "issue:41720|issue:45161", - "issue:45081|issue:45812", - "issue:43531|issue:43572", - "issue:43540|issue:43782", - "issue:36010|issue:42617", - "issue:43421|issue:45812", - "issue:44186|issue:44361", - "issue:42915|issue:43322" + "issue:41720|issue:45161" ], - "prepared_review_unit_hash": "1c6c256ef97eeda4ebbaa53e9b85a3b434b91bc691d7ca2708e26b4516cc1800", + "prepared_review_unit_hash": "75511809c79ebbb90733b24087c08a93c04f6557362370d47acfe4cc46c3f1d2", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36462, - "estimated_input_tokens": 9116, - "estimated_eval_tokens": 18488 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37665, + "estimated_input_tokens": 9417, + "estimated_eval_tokens": 19090 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose similarity bucket of mostly unrelated Transformers issues. The pairs share broad themes like tokenization, loading, offloading, or multimodal serving, but they do not look like the same underlying bug/change, so none should be merged as duplicates.", - "confidence": 0.94, - "canonical_issue_reason": "No true duplicate cluster is present. If a single anchor is needed, issue 43873 is the most representative cross-cutting report because it has the highest activity and broadest framing, but it is not a duplicate of the others.", + "summary": "The cluster is dominated by superficially similar Transformers issues, but the paired items mostly describe distinct bugs, models, or code paths. I do not see any soft pair that is a safe duplicate merge candidate.", + "confidence": 0.91, + "canonical_issue_reason": "Best representative is issue 43873: it is open, has the most discussion/inbound references, and covers a broad, active offloading+quantization problem.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43873 is the best standalone issue to keep as a representative anchor: it has strong discussion/reference activity and a broad, actionable symptom description.", + "best_issue_reason": "Issue 43873 is the strongest cluster anchor because it is current, broadly scoped, and appears to be the most central active regression in the set.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both mention save/pretrained and tied weights, but they target different models and different failures (serialization inconsistency vs incorrect visual encoder keys)." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Unrelated problems: one is a model loading failure for glm-4v-9b, the other is tokenizer loading for est-roberta." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "Different bugs: FSDP CPU-efficient loading regression versus non-persistent buffers being filled with junk." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different code paths and symptoms: weight tying in AyaVision versus unpacking packed BitNet weights during accelerate loading." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Both are model-load failures, but they are different models and failure modes (cuda assert on A800 vs segmentation fault on Llava Next)." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "Different issues: vLLM/PaddleOCR-VL load failure versus strict config blocking granite_speech config loading." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Same general Qwen area, but the concrete bugs differ: auto device mapping assert versus flash-attention generation regression." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Different Gemma models and different failures: variable-name collision in Gemma3n versus device mismatch in Gemma4 PLE." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Both involve save_pretrained/tied weights, but one is about lm_head tying in Mistral3ForConditionalGeneration and the other about visual encoder keys in Qwen3.5." + }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "Different bugs: 3d_parallel.py execution failure vs Qwen3Moe loading failure with FineGrainedFP8Config." + "reason": "Different failures: running 3d_parallel.py versus FineGrainedFP8Config on Qwen3Moe." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "One is a perplexity quality report; the other is a tokenizer-version regression. Same area, not the same bug." - }, - { - "left": "issue:45632", - "right": "issue:45684", - "accept": false, - "reason": "Cache-path collision for trust_remote_code is unrelated to save_pretrained permission propagation." + "reason": "Tokenization may affect perplexity, but these are not the same underlying bug; one is a perplexity report, the other is a tokenizer-version behavior change." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Tokenizer crashes on NER/padding vs dtype mismatches in bfloat16 inference are unrelated failure modes." + "reason": "Different subsystems entirely: tokenizer padding/NER crashes versus dtype mismatches in bfloat16 inference." }, { - "left": "issue:43577", - "right": "issue:43708", + "left": "issue:45632", + "right": "issue:45684", "accept": false, - "reason": "Blip2 dtype loading bug vs Trainer resume/max_steps calculation bug are different code paths." + "reason": "Both touch save/load workflows, but one is a cache-path collision and the other is permission propagation from custom-model source files." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Both involve serve/multimodal crashes, but the errors and likely code paths are model-specific and distinct." + "reason": "Both are serve-time multimodal crashes, but the actual root causes differ (string `.to()` misuse vs missing `_tokenizer` on Gemma4Processor)." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "Unrelated: BLIP2 dtype loading bug versus resume_from_checkpoint max_steps calculation." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "Int4 quantization memory growth/OOM is unrelated to T5 using apex.FusedRMSNorm memory leak." + "reason": "Both are memory-related, but one is int4 quantization OOM behavior and the other is an apex RMSNorm leak in T5." }, { "left": "issue:43873", "right": "issue:44756", "accept": false, - "reason": "Quantized offloading behavior and Strix Halo mmap OOM are both memory-related but not the same underlying bug." + "reason": "Different memory/offload issues: quantization offloading failure versus disabling mmap on Strix Halo to avoid OOM." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Completely different failures: CustomTrainer API break versus 3d_parallel.py runtime issue." }, { "left": "issue:44877", "right": "issue:44991", "accept": false, - "reason": "Strict config loading for granite_speech is unrelated to tokenizer loading for EMBEDDIA/est-roberta." + "reason": "Different config/loading bugs: strict Granite config handling versus tokenizer loading for est-roberta." }, { "left": "issue:36331", - "right": "issue:42617", + "right": "issue:42915", "accept": false, - "reason": "CustomTrainer compute_loss signature breakage is unrelated to 3d_parallel.py runtime failure." + "reason": "No shared underlying bug; trainer keyword-argument regression is unrelated to Qwen3Moe FP8 loading." }, { "left": "issue:43550", "right": "issue:43720", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is a different issue from accelerate loading of packed BitNet weights." - }, - { - "left": "issue:36331", - "right": "issue:42915", - "accept": false, - "reason": "Trainer compute_loss API change and Qwen3Moe FP8 loading failure are unrelated." + "reason": "Different problems in different execution paths: torch.compile+SDPA on Bamba versus accelerate loading of packed BitNet weights." }, { "left": "issue:43450", "right": "issue:45701", "accept": false, - "reason": "Batched video processor shape bug is unrelated to a tokenizer-version regression." + "reason": "Video processor batch-shape bug is unrelated to tokenization-version differences." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "Both involve image size expectations, but OmDet-Turbo and Perceiver have different model-specific preprocessing bugs." + "reason": "Both involve image size/processor expectations, but they affect different models and are not the same defect." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "Tokenizer padding/truncation crash and processor output-size mismatch are different components and failures." + "reason": "Tokenizer NER/padding crash and OmDet-Turbo image-size mismatch are different issues." }, { "left": "issue:44479", "right": "issue:44918", "accept": false, - "reason": "Video-input regression in Qwen VL models is unrelated to SFT trainer embedding unpacking." + "reason": "Different Qwen3.5-related bugs: video-input regression versus unpacking embeddings with trl SFT trainer." }, { "left": "issue:43550", "right": "issue:43606", "accept": false, - "reason": "Bamba torch.compile/SDPA failure is unrelated to Bark CPU offload device mismatch." + "reason": "Different device/execution problems: torch.compile+SDPA versus CPU-offload device mismatch." }, { "left": "issue:41720", "right": "issue:42617", "accept": false, - "reason": "Auto device mapping cudaErrorAssert and 3d_parallel.py startup failure are different problems." + "reason": "Different models and failure modes; no shared code-path bug is evident." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Gemma3TextConfig API discrepancy is unrelated to GPTNeoX rotary_pct reload behavior." + "reason": "Both concern config behavior, but one is an API discrepancy and the other is a rotary_pct reload regression." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "Qwen3Moe FP8 loading failure and dequantized model offload failure are both loading-related but not the same bug." + "reason": "Different issues: Qwen3Moe FineGrainedFP8Config failure versus dequantized model loading with gpu+cpu offload." }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "Processor/tokenizer regression for custom multimodal code is not the same as a general tokenization-version change report." + "reason": "Processor/tokenizer regression in v4.57.5 is not the same as version-dependent tokenization changes." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug is unrelated to GLM-4V model loading failure." + "reason": "Different models and different defects: BeitImageProcessorFast label reduction versus glm-4v-9b loading failure." }, { "left": "issue:44671", "right": "issue:44743", "accept": false, - "reason": "CamemBERT masked LM prediction regression and Qwen recurrent-state reset bug are completely different model behaviors." - }, - { - "left": "issue:41720", - "right": "issue:45161", - "accept": false, - "reason": "Auto device mapping failure on Qwen3 and TP-only failure on GPT-OSS MoE are different distributed-inference issues." - }, - { - "left": "issue:45081", - "right": "issue:45812", - "accept": false, - "reason": "Mistral regex patch crash and Granite tokenizer wrong IDs are both tokenizer bugs, but they affect different mechanisms and models." - }, - { - "left": "issue:43531", - "right": "issue:43572", - "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and StableLm pad_token_idx config regression are unrelated." - }, - { - "left": "issue:43540", - "right": "issue:43782", - "accept": false, - "reason": "Video-processing ValueError in Qwen3OmniMoe and from_pretrained weight_only error in Qwen3VL are different bugs." - }, - { - "left": "issue:36010", - "right": "issue:42617", - "accept": false, - "reason": "GenerationMixin import failure is unrelated to 3d_parallel.py execution failure." - }, - { - "left": "issue:43421", - "right": "issue:45812", - "accept": false, - "reason": "Special-token post-processor update bug and Granite token-ID regression are distinct tokenizer issues." + "reason": "Masked LM prediction bug in CamemBERT is unrelated to Qwen3.5 recurrent-state reset behavior." }, { - "left": "issue:44186", - "right": "issue:44361", + "left": "issue:43873", + "right": "issue:44756", "accept": false, - "reason": "LayoutLMv2Tokenizer NER/padding crash and MLukeTokenizer AttributeError are different tokenizer implementations and failures." + "reason": "The memory symptoms differ enough that they are not the same underlying bug; one is quantization offload, the other is mmap-induced OOM." }, { - "left": "issue:42915", - "right": "issue:43322", + "left": "issue:41720", + "right": "issue:45161", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8 loading failure is unrelated to Llava Next segmentation fault." + "reason": "Both mention Qwen/GPT-OSS style loading/runtime issues, but the concrete bug here is auto device mapping on Qwen3, not TP on GPT-OSS MoE." } ] }, @@ -4053,24 +4157,29 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:30064", "issue:33357", "issue:34567", "issue:34634", "issue:35707", - "issue:39692", + "issue:36010", "issue:41720", "issue:42490", + "issue:42617", + "issue:42915", + "issue:43322", "issue:43329", "issue:43388", "issue:43421", "issue:43531", + "issue:43540", "issue:43550", + "issue:43572", "issue:43606", "issue:43653", "issue:43720", @@ -4078,23 +4187,20 @@ "issue:43782", "issue:43873", "issue:43927", - "issue:44062", - "issue:44077", + "issue:44186", + "issue:44361", "issue:44368", "issue:44451", "issue:44492", "issue:44509", "issue:44514", "issue:44545", - "issue:44589", - "issue:44610", "issue:44625", "issue:44898", - "issue:44987", "issue:44991", - "issue:45042", "issue:45059", "issue:45072", + "issue:45081", "issue:45357", "issue:45381", "issue:45406", @@ -4103,18 +4209,24 @@ "issue:45701", "issue:45704", "issue:45759", - "issue:45859", - "issue:45923" + "issue:45812" ], "soft_pairs": [ + "issue:45081|issue:45812", + "issue:43531|issue:43572", + "issue:43540|issue:43782", + "issue:36010|issue:42617", + "issue:43421|issue:45812", + "issue:44186|issue:44361", + "issue:42915|issue:43322", "issue:43388|issue:45059", "issue:45406|issue:45464", "issue:33357|issue:35707", "issue:44492|issue:44509", "issue:43421|issue:45701", - "issue:41720|issue:43746", "issue:43606|issue:43720", "issue:30064|issue:34634", + "issue:41720|issue:43746", "issue:43550|issue:43653", "issue:43873|issue:45704", "issue:44514|issue:44545", @@ -4128,226 +4240,219 @@ "issue:44368|issue:45357", "issue:43782|issue:45381", "issue:44898|issue:45072", - "issue:44451|issue:44991", - "issue:44077|issue:44625", - "issue:44987|issue:45042", - "issue:45759|issue:45859", - "issue:43531|issue:44589", - "issue:44062|issue:44451", - "issue:45704|issue:45923", - "issue:39692|issue:44610" + "issue:44451|issue:44991" ], - "prepared_review_unit_hash": "b38c460e60fb064fb2815ae4eb46bbc9d315767e9a0191c21a676116d66d14ac", + "prepared_review_unit_hash": "a41525236d4f2eb9e8c505fc5d0514aa1567eda3841a9b76a40850b1232467e7", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36145, - "estimated_input_tokens": 9037, - "estimated_eval_tokens": 18330 + "serialized_chars": 36655, + "estimated_input_tokens": 9164, + "estimated_eval_tokens": 18584 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous issue reports from different code paths. The only clear duplicate pair is the Qwen2_5_VLProcessor batched apply_chat_template crash with padding=False (issues 44514 and 44545).", - "confidence": 0.96, - "canonical_issue_reason": "Issue 44514 is the best canonical issue because it has an exact duplicate counterpart (44545) with the same title, same failure mode, and same affected API.", - "canonical_pr_reason": null, - "best_issue_reason": "Issue 44514 is the strongest representative issue in this set because it is a confirmed duplicate target; the rest of the cluster does not form a coherent duplicate group.", - "best_pr_reason": null, + "summary": "The cluster is still mostly a set of unrelated Transformers issues that only share broad thematic similarity. The only clear duplicate pair is issue:44514/issue:44545. For the tokenization-regression subset, issue:45812 is a strong representative, but it should be described as one of the more referenced issues rather than the most referenced one.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45812 is a strong canonical issue because it is open, specific, and describes a concrete silent AutoTokenizer regression in Granite models; it is one of the more referenced issues in the packet.", + "canonical_pr_reason": "No PRs are present in this cluster.", + "best_issue_reason": "issue:45812 is the best issue representative because it is the clearest concrete regression in the tokenization subset and can anchor that theme without overgeneralizing.", + "best_pr_reason": "No PRs are present in this cluster.", "soft_edge_verdicts": [ + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Different tokenizer bugs: Mistral regex/backend-tokenizer crash vs Granite token-ID regression." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different config/model bugs: Qwen3-MoE sliding_window vs StableLmConfig pad_token_idx." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Different Qwen failures and code paths: video-input processing vs weight_only loading." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to the 3d_parallel.py runtime failure." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer-related, but runtime post-processor updates and Granite wrong token IDs are different bugs." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer crashes affecting different models and inputs." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "FP8Config behavior in Qwen3Moe is unrelated to the Llava Next load-time segfault." + }, { "left": "issue:43388", "right": "issue:45059", "accept": false, - "reason": "Different subsystems and failure modes: metric gathering/last-batch label handling vs SAM3 text+box behavior." + "reason": "Trainer metric label handling and SAM3 text/bbox behavior are unrelated." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Unrelated bugs: Gemma4Processor missing _tokenizer vs streaming chat/completions failure on Qwen3.5." + "reason": "Different processors and failures: Gemma4Processor missing _tokenizer vs Qwen3.5 streaming API crash." }, { "left": "issue:33357", "right": "issue:35707", "accept": false, - "reason": "Different problems and code paths: MacOS bus error loading CLIP vs generation with inputs_embeds/past_key_values." + "reason": "MacOS bus error with CLIP is unrelated to progressive generation with inputs_embeds/past_key_values." }, { "left": "issue:44492", "right": "issue:44509", "accept": false, - "reason": "A typo docs issue is not the same as stale pipeline-task documentation; both concern docs, but not the same bug." + "reason": "A typo in cache strategy text is not the same as stale docs for removed pipeline tasks." }, { "left": "issue:43421", "right": "issue:45701", "accept": false, - "reason": "Both relate to tokenization behavior, but one is runtime post-processor updating and the other is a version-dependent tokenization change." - }, - { - "left": "issue:41720", - "right": "issue:43746", - "accept": false, - "reason": "Different model families and failure types: CUDA assert during device mapping vs PEFT local-checkpoint loading." + "reason": "Generic tokenization changes and runtime special-token post-processing are too broad to be the same bug." }, { "left": "issue:43606", "right": "issue:43720", "accept": false, - "reason": "Both touch accelerate/offload/loading, but one is a CPU offload device mismatch and the other is packed-weight unpacking during loading." + "reason": "Different accelerate/offload bugs affecting different models and loading paths." }, { "left": "issue:30064", "right": "issue:34634", "accept": false, - "reason": "Completely different components: image processor segmentation maps vs BarkProcessor voice_preset handling." + "reason": "Image segmentation-map processing and BarkProcessor voice_preset are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "CUDA assert during auto device mapping is unrelated to PEFT checkpoint loading for GraniteSpeech." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "Unrelated bugs: torch.compile+SDPA in Bamba vs tokenizer special-token registration in BigBirdTokenizer." + "reason": "Torch.compile/SDPA failure and tokenizer special-token registration are unrelated." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Different underlying issues: quantization/offloading behavior vs T5 using apex.FusedRMSNorm with a memory leak." + "reason": "Quantization offloading behavior is unrelated to the T5 apex RMSNorm memory leak." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Exact duplicate: same title, same API, same batched padding=False crash." + "reason": "Same concrete crash in Qwen2_5_VLProcessor.apply_chat_template with batched input and padding=False." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "One is config propagation of num_labels; the other is a zero-loss bug for single_label_classification across models." + "reason": "Different classification bugs: num_labels propagation vs degenerate zero loss for num_labels=1." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "Device mismatch during CPU offload is not the same as a tokenizer special-token decode bug." + "reason": "CPU offload device mismatch is unrelated to BigBirdTokenizer mask token registration." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "Different Qwen-related issues: sliding_window behavior in MoE models vs from_config text_config unwrapping for multimodal configs." + "reason": "Sliding_window behavior in Qwen3-MoE is unrelated to from_config not unwrapping text_config." }, { "left": "issue:42490", "right": "issue:43329", "accept": false, - "reason": "Local-path trailing-slash import warning is unrelated to undefined video-token helper/merge_size in multimodal token counting." + "reason": "Trailing-slash import warning is unrelated to the undefined-name video branch bug." }, { "left": "issue:34634", "right": "issue:41720", "accept": false, - "reason": "Different failures in different models: BarkProcessor voice preset vs Qwen3 device-mapping CUDA assert." + "reason": "BarkProcessor voice_preset bug is unrelated to Qwen3 auto device mapping CUDA asserts." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "TrainerState token accounting bug is unrelated to progressive generation with inputs_embeds and past_key_values." + "reason": "TrainerState token counting and progressive generation are different subsystems and failures." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Runtime special-token/post-processor update bug is different from DiaConfig losing custom token IDs on save/load." + "reason": "Runtime special-token post-processing and save/load losing custom token IDs are different bugs." }, { "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "Different Qwen3.5 issues: tie_word_embeddings warning during LoRA fine-tuning vs incorrect visual encoder keys on save_pretrained." + "reason": "A tie_word_embeddings warning during LoRA fine-tuning is unrelated to incorrect visual encoder keys in save_pretrained." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Different VL bugs: weight_only load failure vs incorrect video vision_position_ids." + "reason": "Different Qwen VL bugs: weight_only loading error vs video vision_position_ids mismatch." }, { "left": "issue:44898", "right": "issue:45072", "accept": false, - "reason": "Different components and symptoms: Perceiver non-default-resolution image classification vs dtype mismatch in inference wrappers." + "reason": "Perceiver resolution handling and dtype mismatch in inference are unrelated." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "Both are model-loading regressions, but they affect different tokenizers/models and are not the same concrete bug." - }, - { - "left": "issue:44077", - "right": "issue:44625", - "accept": false, - "reason": "PatchTSMixer post_init policy is unrelated to Qwen3.5 num_labels propagation." - }, - { - "left": "issue:44987", - "right": "issue:45042", - "accept": false, - "reason": "Different root causes: loading a specific model fails vs PIL image processors requiring torchvision." - }, - { - "left": "issue:45759", - "right": "issue:45859", - "accept": false, - "reason": "Unrelated Qwen3.5 issues: multimodal config unwrapping vs rotary embedding CPU-offload compatibility." - }, - { - "left": "issue:43531", - "right": "issue:44589", - "accept": false, - "reason": "Sliding_window behavior in Qwen3-MoE is unrelated to missing Float8 storage registration." - }, - { - "left": "issue:44062", - "right": "issue:44451", - "accept": false, - "reason": "AddedToken special-argument duplication is unrelated to failing to load a specific model." - }, - { - "left": "issue:45704", - "right": "issue:45923", - "accept": false, - "reason": "Memory leak in T5 RMSNorm is unrelated to missing supports_gradient_checkpointing on a trust_remote_code variant." - }, - { - "left": "issue:39692", - "right": "issue:44610", - "accept": false, - "reason": "SigLIP2 docs/model mismatch and quantization errors are different from OmDet-Turbo processor size mismatch." + "reason": "Different tokenizer-loading regressions for different models; not the same underlying bug." } ] }, "evaluator_result": { - "accept": true, - "feedback": "Grounded and conservative. The packet supports exactly one clear duplicate pair: issue 44514 and 44545 share the same title and same bug description. The remaining soft pairs are plausibly non-duplicates and the reasons stay within the evidence provided." + "accept": false, + "feedback": "The cluster summary is mostly conservative, but the canonical/best-issue rationale overstates the evidence: issue:45812 does not have the most inbound references in the packet (issue:45701 has 6 vs 45812\u2019s 5). Please revise the representative selection or soften that claim. The duplicate call on issue:44514/44545 looks grounded." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -4360,45 +4465,47 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:30064", "issue:36010", "issue:39692", "issue:40444", "issue:42886", - "issue:43295", - "issue:43335", "issue:43381", "issue:43421", "issue:43525", "issue:43531", "issue:43540", - "issue:43550", "issue:43596", "issue:43618", "issue:43653", "issue:43697", - "issue:43716", "issue:43720", "issue:43746", - "issue:43756", "issue:43819", "issue:43844", "issue:43873", "issue:43994", "issue:44008", + "issue:44062", + "issue:44077", "issue:44186", "issue:44220", + "issue:44451", + "issue:44589", + "issue:44610", + "issue:44625", "issue:44661", "issue:44671", "issue:44843", "issue:44918", "issue:44936", - "issue:45072", + "issue:44987", + "issue:45042", "issue:45081", "issue:45183", "issue:45356", @@ -4408,15 +4515,21 @@ "issue:45663", "issue:45704", "issue:45759", - "issue:45834", "issue:45859", "issue:45907", "issue:45923" ], "soft_pairs": [ + "issue:44077|issue:44625", + "issue:44987|issue:45042", + "issue:45759|issue:45859", + "issue:43531|issue:44589", + "issue:44062|issue:44451", + "issue:45704|issue:45923", + "issue:39692|issue:44610", "issue:44918|issue:44936", - "issue:45663|issue:45923", "issue:43421|issue:43653", + "issue:45663|issue:45923", "issue:45588|issue:45759", "issue:42886|issue:44843", "issue:43381|issue:43844", @@ -4427,231 +4540,238 @@ "issue:45081|issue:45356", "issue:45356|issue:45907", "issue:39692|issue:43873", - "issue:43596|issue:44220", "issue:43746|issue:43873", + "issue:43596|issue:44220", "issue:40444|issue:43746", "issue:43746|issue:45381", - "issue:43540|issue:44008", "issue:43720|issue:43819", - "issue:45183|issue:45479", + "issue:43540|issue:44008", "issue:44220|issue:44661", + "issue:45183|issue:45479", "issue:43618|issue:43697", "issue:30064|issue:36010", - "issue:43653|issue:43720", - "issue:43335|issue:43756", - "issue:43716|issue:44008", - "issue:43295|issue:45834", - "issue:43550|issue:45072", - "issue:43550|issue:43819" + "issue:43653|issue:43720" ], - "prepared_review_unit_hash": "5b331124060c3d965a9dbcbc3a0bc35fc09bd008525cd780464686701497352e", + "prepared_review_unit_hash": "aa8273ba0c49a27ab7db44218cd286c8526dc51224cc6f35f92dc353e37fadd3", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 36297, - "estimated_input_tokens": 9075, - "estimated_eval_tokens": 18406 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37377, + "estimated_input_tokens": 9345, + "estimated_eval_tokens": 18946 }, "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. Only one soft pair looks like the same underlying regression: the HF_HUB_OFFLINE tokenizer/cache failure in the Mistral regex patch path.", - "confidence": 0.71, - "canonical_issue_reason": "Issue 44843 is the best anchor for the only clear duplicate-like theme: it names the root cause directly (`_patch_mistral_regex` unconditionally calling `model_info()` and breaking HF_HUB_OFFLINE).", + "summary": "Most candidates are unrelated model/tokenizer bugs. The only strong duplicate-looking pair is the offline tokenizer regression in 42886 and 44843; the rest are distinct issues in different code paths.", + "confidence": 0.79, + "canonical_issue_reason": "44843 most directly identifies the root cause: `_patch_mistral_regex` unconditionally calling `model_info()`, which matches the offline/cache failure described in 42886.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44843 is the most concrete and root-cause-oriented issue in the set, and it best represents the accepted offline-tokenizer regression pair.", + "best_issue_reason": "44843 is the clearest representative of the one real overlap in this cluster and gives the most actionable root-cause description.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44918", - "right": "issue:44936", + "left": "issue:44077", + "right": "issue:44625", "accept": false, - "reason": "Different failures: SFT embedding unpacking vs trainer state after train/evaluate. No shared code-path bug." + "reason": "Different models and failures: patchtsmixer `post_init` policy vs Qwen3.5 `num_labels` propagation." }, { - "left": "issue:45663", + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Both are loading/processor issues, but they describe different bugs and code paths; not the same underlying change." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Different Qwen 3.5/3.6 problems: config unwrapping vs CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated failures: Qwen3-MoE sliding window logic vs Float8 storage deserialization." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "A tokenizer constructor argument conflict is not the same bug as a model-specific load failure for ScandiBERT." + }, + { + "left": "issue:45704", "right": "issue:45923", "accept": false, - "reason": "Unrelated model-specific bugs: FSDP2 shared_kv_states KeyError vs missing supports_gradient_checkpointing flag." + "reason": "T5 RMSNorm memory leak and missing gradient-checkpointing flag are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both involve vision processors, but the specific model mismatch and failure modes differ." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer failures: embedding unpacking with SFT trainer vs evaluate-after-train lifecycle issue." }, { "left": "issue:43421", "right": "issue:43653", "accept": false, - "reason": "Both tokenizer-related, but one is runtime post-processor updates and the other is BigBird special-token registration; not the same bug." + "reason": "Both mention special tokens, but one is runtime post-processor updates and the other is BigBird mask-token registration." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "FSDP2 shared-kv state rebuilding and a trust_remote_code checkpointing flag are not the same bug." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "Different subsystems and symptoms: flash-attention sink handling vs Qwen config unwrapping." + "reason": "Flash-attention sink handling and multimodal config unwrapping are different code paths." }, { "left": "issue:42886", "right": "issue:44843", "accept": true, - "reason": "Same underlying HF_HUB_OFFLINE regression in tokenizer loading: both point to the Mistral regex patch path triggering network metadata lookup and breaking cache-only loads." + "reason": "Same offline tokenizer regression: both point to tokenizer loading failing because `_patch_mistral_regex`/`model_info()` is invoked in offline mode." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Gradient checkpointing eval-mode behavior is unrelated to ZeRO-3 gradient growth under DeepSpeed." + "reason": "Eval-mode checkpointing restriction is unrelated to ZeRO-3 gradient inflation during training." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Both touch tokenization, but one is post-processor updates and the other is LayoutLMv2 NER/padding crash; different bugs." + "reason": "Both are tokenizer bugs, but the concrete failures differ and do not look like one fix." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different model families and problems: SigLIP2 pipeline output issues vs CamemBERT MLM prediction regression." + "reason": "Different models and behaviors: SigLIP2 bad outputs vs CamemBERT MLM regression." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "Both are model-config bugs, but pad_token_id missing on Llama4 is unrelated to sliding_window handling in Qwen3-MoE." + "reason": "Different subsystems: missing `pad_token_id` on Llama4Config vs Qwen3-MoE sliding-window handling." }, { "left": "issue:45704", "right": "issue:45859", "accept": false, - "reason": "T5 apex fused RMSNorm memory leak is unrelated to Qwen3_5Moe CPU offload compatibility." + "reason": "RMSNorm memory leak and CPU-offload rotary embedding are unrelated." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Both mention Mistral regex, but one is a backend_tokenizer AttributeError and the other is a Kimi codec/regression warning issue; not clearly the same bug." + "reason": "Both touch `_patch_mistral_regex`, but one is a crash on loading Mistral tokenizer and the other is a Kimi-K2.5 regression/warning issue; not clearly the same bug." }, { "left": "issue:45356", "right": "issue:45907", "accept": false, - "reason": "Kimi tokenizer regression is unrelated to `list_repo_files` needing to forward revision." + "reason": "Tokenizer-regex regression vs `list_repo_files` revision forwarding are unrelated." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "Documentation/example mismatch is unrelated to quantization/offloading behavior." + "reason": "SigLIP2 example issues and quantization offloading are different problems." }, { - "left": "issue:43596", - "right": "issue:44220", + "left": "issue:43746", + "right": "issue:43873", "accept": false, - "reason": "Different low-level errors: Deepspeed ZeRO-3/BertModel init vs `_torch_extract_fbank_features()`." + "reason": "Local checkpoint loading with PEFT adapters is unrelated to quantized offloading behavior." }, { - "left": "issue:43746", - "right": "issue:43873", + "left": "issue:43596", + "right": "issue:44220", "accept": false, - "reason": "Local PEFT checkpoint loading for GraniteSpeech is unrelated to offloading with quantization." + "reason": "DeepSpeed/BertModel initialization error vs audio feature extraction bug." }, { "left": "issue:40444", "right": "issue:43746", "accept": false, - "reason": "Multi-image iterable dataset finetuning failure is unrelated to GraniteSpeech checkpoint loading." + "reason": "Multimodal iterable dataset training failure is unrelated to GraniteSpeech checkpoint loading." }, { "left": "issue:43746", "right": "issue:45381", "accept": false, - "reason": "Different model paths: GraniteSpeech local checkpoint loading vs Qwen2.5-VL video vision_position_ids." - }, - { - "left": "issue:43540", - "right": "issue:44008", - "accept": false, - "reason": "Video processing ValueError in Qwen3OmniMoe is unrelated to Gemma 3n variable name collision." + "reason": "PEFT local checkpoint loading and Qwen2.5-VL video position IDs are different issues." }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "BitNet packed-weight loading and DAC.from_latents/STE mismatch are distinct bugs." + "reason": "BitNet packed-weight loading and DAC `from_latents`/STE mismatch are unrelated." }, { - "left": "issue:45183", - "right": "issue:45479", + "left": "issue:43540", + "right": "issue:44008", "accept": false, - "reason": "Different validation/loss problems: input_ids/inputs_embeds XOR messaging vs single-label classification degeneracy." + "reason": "Qwen3OmniMoe video-processing error and Gemma 3n variable collision are different bugs." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio fbank extraction issue is unrelated to add-new-model-like failing on TOKENIZER_MAPPING_NAMES." + "reason": "Audio feature extraction and `add-new-model-like` tokenizer mapping logic are unrelated." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Input validation messaging and sequence-classification zero-loss behavior are separate issues." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "CLIP attentions assignment regression is not the same as RTDetrV2 output changes in v5." + "reason": "CLIP attention output regression and RTDetrV2 output drift are different model behaviors." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Void segmentation maps in Image Processor is unrelated to GenerationMixin import failure." + "reason": "Void segmentation-map processing and a `GenerationMixin` import error are unrelated." }, { "left": "issue:43653", "right": "issue:43720", "accept": false, - "reason": "BigBirdTokenizer special-token registration and BitNet accelerate loading are unrelated." - }, - { - "left": "issue:43335", - "right": "issue:43756", - "accept": false, - "reason": "SwitchTransformers sparse-layer creation bug is unrelated to Smollm3 RoPE layer dropping." - }, - { - "left": "issue:43716", - "right": "issue:44008", - "accept": false, - "reason": "Image preprocessor/model dtype mismatch is unrelated to Gemma 3n audio_mel_mask name collision." - }, - { - "left": "issue:43295", - "right": "issue:45834", - "accept": false, - "reason": "Processor/tokenizer regression in v4.57.5 is unrelated to Kosmos2.5 long OCR index errors." - }, - { - "left": "issue:43550", - "right": "issue:45072", - "accept": false, - "reason": "Different dtype/compile failures in different models; no shared concrete code-path problem." - }, - { - "left": "issue:43550", - "right": "issue:43819", - "accept": false, - "reason": "Bamba SDPA torch.compile failure is unrelated to DAC.from_latents missing-STE mismatch." + "reason": "BigBird special-token decode bug and BitNet packed-weight loading are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only clearly same-root-cause pair is issue:42886 and issue:44843 around the HF_HUB_OFFLINE / _patch_mistral_regex tokenizer regression, and the other soft-edge rejections do not overstate evidence." + "feedback": "The analysis is conservative and grounded in the packet. The single accepted overlap, 42886/44843, is directly supported by the titles: both concern `_patch_mistral_regex`/`model_info()` breaking offline tokenizer loading. The remaining soft-edge rejections are appropriately cautious and do not overstate evidence for duplicate bugs or mergeable PRs." }, "evaluator_used": true, "retried": false, @@ -4667,49 +4787,47 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:30064", "issue:36331", "issue:39692", "issue:41720", + "issue:43295", "issue:43322", + "issue:43335", "issue:43421", "issue:43531", "issue:43540", + "issue:43550", "issue:43577", - "issue:43582", - "issue:43606", "issue:43643", - "issue:43644", "issue:43653", - "issue:43749", + "issue:43716", + "issue:43756", "issue:43782", "issue:43818", "issue:43819", "issue:43825", - "issue:43827", + "issue:43950", "issue:43994", + "issue:44008", "issue:44062", "issue:44186", - "issue:44442", "issue:44448", - "issue:44479", "issue:44485", "issue:44488", "issue:44509", "issue:44561", "issue:44671", - "issue:44805", "issue:44811", "issue:44821", "issue:44843", "issue:44877", "issue:44898", - "issue:44936", "issue:44977", "issue:44991", "issue:45020", @@ -4719,227 +4837,221 @@ "issue:45381", "issue:45584", "issue:45685", - "issue:45834" + "issue:45834", + "issue:45987" ], "soft_pairs": [ - "issue:43322|issue:45685", + "issue:43335|issue:43756", + "issue:43716|issue:44008", + "issue:43295|issue:45834", + "issue:43550|issue:45072", + "issue:43550|issue:43819", "issue:44062|issue:44488", + "issue:43322|issue:45685", + "issue:43950|issue:45987", "issue:44186|issue:44898", "issue:44843|issue:45081", "issue:43531|issue:43643", "issue:43653|issue:43819", - "issue:43577|issue:43818", "issue:43643|issue:44877", - "issue:43540|issue:45381", + "issue:43577|issue:43818", "issue:43421|issue:44811", + "issue:43540|issue:45381", "issue:43782|issue:44977", "issue:44448|issue:44671", "issue:45584|issue:45834", - "issue:44561|issue:45020", "issue:43825|issue:43994", + "issue:44561|issue:45020", "issue:39692|issue:45834", "issue:44821|issue:45084", "issue:30064|issue:36331", - "issue:44485|issue:44509", "issue:41720|issue:44991", - "issue:43644|issue:43749", - "issue:44186|issue:44442", - "issue:44479|issue:45834", - "issue:43577|issue:43582", - "issue:43606|issue:45072", - "issue:43825|issue:43827", - "issue:44805|issue:44936" + "issue:44485|issue:44509" ], - "prepared_review_unit_hash": "1f206e81b172f9729dae36143839b80a8b3f230c8cdf697cd3dfe1b7941a3a16", + "prepared_review_unit_hash": "2c6a970724dfc40de87dc9b6a17b08caab0a1433266bd724db94ac812edf2fc3", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 35838, - "estimated_input_tokens": 8960, - "estimated_eval_tokens": 18176 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35169, + "estimated_input_tokens": 8793, + "estimated_eval_tokens": 17842 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated regression reports; I don\u2019t see a true duplicate cluster here. The only broad umbrella issue is the remote_code regression report, but it is still too general to absorb the other topics.", - "confidence": 0.87, - "canonical_issue_reason": "Issue 45020 is the broadest umbrella in the set (remote_code regressions) and is the closest thing to a central tracking issue, though the surrounding items are not true duplicates of it.", + "summary": "Mostly unrelated issue reports across model-specific regressions, tokenizer/config edge cases, and docs/errors. No soft pair looks like the same concrete bug, though several are loosely in the remote_code / model-loading regression family.", + "confidence": 0.94, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 45020 is the best single issue to serve as a general tracker because it is broad, open, and aligned with multiple remote_code-related reports; the other issues are narrower and largely unrelated.", + "best_issue_reason": "issue:45020 is the broadest representative of the recurring remote_code/model-loading regression family; it best anchors the cluster even though the overall set is heterogeneous.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43322", - "right": "issue:45685", + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different model bugs: sparse-layer construction vs RoPE-layer dropping." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different code paths and models: image preprocessor dtype mismatch vs Gemma3n variable-name collision." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Both are processor-related, but one is a regression in processor/tokenizer access while the other is a long-OCR index error in Kosmos2.5." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Different models and failures: Bamba torch.compile+SDPA vs SwitchTransformers/TimmWrapper bfloat16 mismatches." + }, + { + "left": "issue:43550", + "right": "issue:43819", "accept": false, - "reason": "Different models and failures: Llava Next loading segfault vs MPS histogram dtype error in MoE." + "reason": "Unrelated bugs in different subsystems: Bamba compilation failure vs DAC latent reconstruction mismatch." }, { "left": "issue:44062", "right": "issue:44488", "accept": false, - "reason": "Tokenizer AddedToken keyword error is unrelated to a model load failure for cjvt/sleng-bert." + "reason": "Both touch tokenizers, but one is an AddedToken argument error and the other is a tokenizer load failure for a specific model." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Different backend/runtime issues: Llava Next load segfault vs MPS histogram not implemented for int." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Both are API regressions, but one corrupts non-persistent buffers and the other returns the wrong type from StaticCache.get_seq_length()." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "Different subsystems: LayoutLMv2 tokenizer batching crash vs Perceiver image classification resize/interpolation failure." + "reason": "Different models and symptoms: LayoutLMv2 tokenizer crashes vs Perceiver image-classification failures." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Both involve _patch_mistral_regex, but the concrete failures differ: offline model_info call vs missing backend_tokenizer attribute." + "reason": "Same helper area (_patch_mistral_regex), but these are different failures: offline model_info access vs missing backend_tokenizer attribute." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Qwen3-MoE sliding_window bug is unrelated to AutoConfig/trust_remote_code missing fields." + "reason": "Unrelated: Qwen3-MoE sliding-window behavior vs trust_remote_code config field loss." }, { "left": "issue:43653", "right": "issue:43819", "accept": false, - "reason": "BigBirdTokenizer special-token decoding bug is unrelated to DAC latent/forward mismatch." - }, - { - "left": "issue:43577", - "right": "issue:43818", - "accept": false, - "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing are separate model bugs." + "reason": "Different bugs: BigBird special-token registration vs DAC forward/from_latents mismatch." }, { "left": "issue:43643", "right": "issue:44877", "accept": false, - "reason": "Both touch config loading, but one is missing fields with trust_remote_code while the other is strict config rejection for granite_speech." + "reason": "Both involve config loading, but one is missing fields under trust_remote_code and the other is strict config rejection for granite_speech." }, { - "left": "issue:43540", - "right": "issue:45381", + "left": "issue:43577", + "right": "issue:43818", "accept": false, - "reason": "Different video-input regressions on different Qwen variants with different symptoms." + "reason": "Different model-specific issues: BLIP2 dtype propagation vs Video-LLaVA temporal-attention/weight-sharing problem." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Runtime special-token/post-processor update bug is distinct from Whisper batch_decode skip_special_tokens handling." + "reason": "Both involve token handling, but one is runtime post-processor updates and the other is Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both are video-input bugs in Qwen models, but they appear to be distinct failures with different versions and code paths." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Qwen3VL weight_only load error is unrelated to Qwen3.5 flash-attention generation behavior." + "reason": "Different Qwen models and failures: weight_only loading error vs flash-attention generation issue." }, { "left": "issue:44448", "right": "issue:44671", "accept": false, - "reason": "Pegasus v4/v5 output drift is unrelated to CamemBERT masked-LM prediction regression." + "reason": "Both are output regressions, but they affect different models/tasks and do not share a concrete code path." }, { "left": "issue:45584", "right": "issue:45834", "accept": false, - "reason": "Whisper empty-transcription generation after align_special_tokens is unrelated to Kosmos2.5 long-OCR index errors." + "reason": "Unrelated: Whisper empty-transcription generation vs Kosmos2.5 long-input index error." }, { - "left": "issue:44561", - "right": "issue:45020", + "left": "issue:43825", + "right": "issue:43994", "accept": false, - "reason": "Related theme, but 44561 is a specific is_torch_fx_available removal breakage while 45020 is a broad remote_code regression report." + "reason": "Different issues in the pipeline stack: a bad error message vs incorrect/nonsensical model outputs." }, { - "left": "issue:43825", - "right": "issue:43827", + "left": "issue:44561", + "right": "issue:45020", "accept": false, - "reason": "One is a runtime error-message issue; the other is docs still referencing removed pipeline tasks." + "reason": "Related theme, but not the same concrete bug: one is a specific is_torch_fx_available regression, the other is a broader remote_code breakage report." }, { - "left": "issue:43994", - "right": "issue:43825", + "left": "issue:39692", + "right": "issue:45834", "accept": false, - "reason": "SigLIP2 nonsensical outputs with AutoModel/pipeline are not the same bug as the pipeline error-message wording." + "reason": "Different problems: SigLIP2 docs/example errors vs Kosmos2.5 OCR long-input failure." }, { "left": "issue:44821", "right": "issue:45084", "accept": false, - "reason": "AutoImageProcessor URL loading and template-node compilation errors are unrelated." + "reason": "Different failures: AutoImageProcessor URL loading vs template-node compilation error." }, { "left": "issue:30064", "right": "issue:36331", "accept": false, - "reason": "Image processor segmentation-map handling and CustomTrainer.compute_loss signature mismatch are unrelated." - }, - { - "left": "issue:44485", - "right": "issue:44509", - "accept": false, - "reason": "GLM-5 RoPE discussion is unrelated to v5 docs mentioning removed pipeline tasks." + "reason": "Completely unrelated: segmentation-map processing vs CustomTrainer compute_loss signature mismatch." }, { "left": "issue:41720", "right": "issue:44991", "accept": false, - "reason": "Qwen3 auto-device-map CUDA assert is unrelated to tokenizer loading for EMBEDDIA/est-roberta." - }, - { - "left": "issue:43644", - "right": "issue:43749", - "accept": false, - "reason": "Non-persistent buffer junk initialization and FSDP CPU RAM efficient loading are different issues." - }, - { - "left": "issue:44186", - "right": "issue:44442", - "accept": false, - "reason": "LayoutLMv2 NER/padding crash is unrelated to FastSpeech2ConformerTokenizer AutoTokenizer loading." - }, - { - "left": "issue:44479", - "right": "issue:45834", - "accept": false, - "reason": "Qwen video-input regression and Kosmos2.5 OCR index error are different code paths." - }, - { - "left": "issue:43577", - "right": "issue:43582", - "accept": false, - "reason": "BLIP2 dtype propagation and Apple Silicon caching_allocator_warmup TypeError are unrelated." + "reason": "Different models and subsystems: Qwen3 auto device mapping crash vs tokenizer loading regression for EMBEDDIA/est-roberta." }, { - "left": "issue:43606", - "right": "issue:45072", - "accept": false, - "reason": "CPU offload device mismatch for bark-small is not the same as dtype mismatches in SwitchTransformers/TimmWrapperModel." - }, - { - "left": "issue:43825", - "right": "issue:43827", - "accept": false, - "reason": "Same broad v5 pipeline-removal theme, but one is message text and the other is documentation references." - }, - { - "left": "issue:44805", - "right": "issue:44936", + "left": "issue:44485", + "right": "issue:44509", "accept": false, - "reason": "Mask/index shape mismatch at inference is unrelated to trainer.evaluate() failing after trainer.train()." + "reason": "GLM-5 RoPE discussion is unrelated to docs still mentioning removed pipeline tasks." } ] }, @@ -4958,49 +5070,48 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:34634", "issue:36010", "issue:36331", - "issue:38175", "issue:42175", "issue:43262", "issue:43329", - "issue:43452", "issue:43526", + "issue:43577", "issue:43582", + "issue:43606", "issue:43638", + "issue:43644", "issue:43650", "issue:43653", "issue:43697", "issue:43720", "issue:43742", - "issue:43746", "issue:43749", "issue:43782", "issue:43819", - "issue:43854", + "issue:43825", + "issue:43827", "issue:43906", - "issue:43927", "issue:44060", + "issue:44186", "issue:44291", "issue:44368", + "issue:44442", + "issue:44479", "issue:44554", - "issue:44589", "issue:44610", "issue:44671", - "issue:44811", + "issue:44805", "issue:44857", "issue:44912", "issue:44936", - "issue:44977", - "issue:44991", "issue:45020", - "issue:45042", "issue:45072", "issue:45081", "issue:45084", @@ -5010,227 +5121,235 @@ "issue:45538", "issue:45600", "issue:45701", - "issue:45803" + "issue:45803", + "issue:45834" ], "soft_pairs": [ + "issue:43644|issue:43749", + "issue:44186|issue:44442", + "issue:44479|issue:45834", + "issue:43577|issue:43582", + "issue:43606|issue:45072", + "issue:43825|issue:43827", + "issue:44805|issue:44936", "issue:44671|issue:45701", "issue:34634|issue:36010", - "issue:43782|issue:45325", "issue:44610|issue:45072", + "issue:43782|issue:45325", "issue:43720|issue:45072", "issue:42175|issue:45081", "issue:45081|issue:45406", "issue:43749|issue:44291", "issue:43650|issue:43906", - "issue:43582|issue:44857", "issue:44060|issue:44368", + "issue:43582|issue:44857", "issue:43262|issue:43819", "issue:43526|issue:43697", "issue:43526|issue:44554", "issue:45459|issue:45803", "issue:34634|issue:36331", "issue:45084|issue:45538", + "issue:43653|issue:44912", "issue:43742|issue:45020", "issue:43329|issue:45600", - "issue:43653|issue:44912", - "issue:43638|issue:44936", - "issue:43452|issue:44991", - "issue:43746|issue:44811", - "issue:38175|issue:44610", - "issue:44589|issue:45042", - "issue:43854|issue:44977", - "issue:43819|issue:43927" + "issue:43638|issue:44936" ], - "prepared_review_unit_hash": "8566e4c2a353cb77ff130ce2319a993bc7f95384979968ba27582323f20080b1", + "prepared_review_unit_hash": "6de2f9fdad2a73d5134527e1afc5b2ee8da69ab339b3b9caccfed4d27b8fc7c1", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 36108, - "estimated_input_tokens": 9027, - "estimated_eval_tokens": 18310 + "soft_pair_count": 28, + "serialized_chars": 36473, + "estimated_input_tokens": 9119, + "estimated_eval_tokens": 18494 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of unrelated Transformers issues that only weakly overlap by theme (loading, tokenization, processors, trainers). There are no strong duplicate issue/PR matches; the best representative is a broad open regression report.", - "confidence": 0.24, - "canonical_issue_reason": "issue:45020 is the broadest and most central active regression report in the set, covering breakages in recent Transformers versions with remote_code models; it is the best umbrella-style representative even though the rest are not true duplicates.", + "summary": "This cluster is mostly a loose collection of unrelated Transformers issues. The soft links mostly share broad themes like loading, tokenization, multimodal inputs, or dtype regressions, but not the same concrete bug or code path.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue stands out: the cluster spans many unrelated subsystems and failure modes, so any representative would be arbitrary.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the clearest high-signal issue: it is open, well-scoped to a version regression, and broad enough to represent the cluster\u2019s general upstream-breakage theme better than the narrower model-specific reports.", + "best_issue_reason": "No strong global best issue for deduping; the items are too heterogeneous to anchor a single duplicate cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both involve loading/memory behavior, but one is junk non-persistent buffers and the other is broken FSDP CPU RAM-efficient loading; different bugs." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Tokenizer-related failures, but different tokenizer classes and different crash conditions; not the same code path." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Both are multimodal input bugs, but they affect different model families and different preprocessing/indexing paths." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Completely different problems: BLIP2 dtype handling vs Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Both mention inference mismatches, but they are model-specific and caused by different mechanisms." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Related to v5 pipeline removals, but one is a runtime error message and the other is docs cleanup; not one bug." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Generic runtime errors in training/eval, but no shared concrete defect or code path." + }, { "left": "issue:44671", "right": "issue:45701", "accept": false, - "reason": "Both mention tokenization/version effects, but one is a model-specific masked-LM regression and the other is a broad tokenization-change report; not the same concrete bug." + "reason": "One is a CamemBERT masked-LM regression; the other is a broad tokenization change report." }, { "left": "issue:34634", "right": "issue:36010", "accept": false, - "reason": "Different failure modes and code paths: BarkProcessor voice_preset vs GenerationMixin import error." + "reason": "Unrelated: Bark voice_preset issue vs GenerationMixin import error." }, { - "left": "issue:43782", - "right": "issue:45325", + "left": "issue:44610", + "right": "issue:45072", "accept": false, - "reason": "Both are Qwen VL-related, but one is a from_pretrained weight_only loading error and the other is a rope-index positioning bug; distinct issues." + "reason": "Different models and different failures; input-size mismatch is unrelated to dtype mismatch." }, { - "left": "issue:44610", - "right": "issue:45072", + "left": "issue:43782", + "right": "issue:45325", "accept": false, - "reason": "Processor input-size mismatch and bfloat16 dtype mismatch are unrelated bug classes." + "reason": "Both are Qwen VL issues, but they concern different functions and distinct bugs." }, { "left": "issue:43720", "right": "issue:45072", "accept": false, - "reason": "Packed-weight loading in BitNet is a different concrete problem from dtype mismatches in inference." + "reason": "Packed-weight loading failure is unrelated to bfloat16 dtype mismatch." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "Packaging/backends issue vs tokenizer regex patch crash; no shared underlying bug." + "reason": "Backend packaging/install issue vs tokenizer regex patch crash; unrelated." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Both are tokenizer/processor load-time crashes, but they involve different models and different missing attributes/code paths." + "reason": "Both are attribute errors during loading, but they hit different objects and different fixes." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "Both concern loading, but one is FSDP CPU RAM-efficient loading and the other is init_empty_weights argument compatibility; not the same fix." + "reason": "Both are model-loading problems, but the root causes are different initialization/loading APIs." }, { "left": "issue:43650", "right": "issue:43906", "accept": false, - "reason": "Unrelated placeholder/data request vs isolated reproduction of another issue." + "reason": "The first is a nonspecific title; the second is a reproduction of another issue, not the same bug." }, { - "left": "issue:43582", - "right": "issue:44857", + "left": "issue:44060", + "right": "issue:44368", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and CUDA AMP image-loss crash are unrelated." + "reason": "Both mention tied-weights warnings, but the specific warning and root cause differ." }, { - "left": "issue:44060", - "right": "issue:44368", + "left": "issue:43582", + "right": "issue:44857", "accept": false, - "reason": "Both mention tie-weight warnings, but they are model-specific warning reports with different symptoms and likely different causes." + "reason": "Allocator warmup TypeError on Apple Silicon is unrelated to AMP/CUDA loss crash." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Audio processor sampling-rate defaulting and DAC from_latents STE mismatch are different subsystems and bugs." + "reason": "Both are audio-related, but one is chat-template sampling rate and the other is DAC latent reconstruction." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "Both involve vision processors/models, but one is a label-reduction bug and the other is an RTDetrV2 output change; not the same defect." + "reason": "Vision-model regressions, but different components and different symptoms." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "No meaningful overlap beyond general multimodal/model processing." + "reason": "No meaningful overlap beyond being correctness issues." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Both are error-handling smell issues, but they affect different functions and different failure scenarios." + "reason": "Both involve exception handling that hides errors, but they are different functions and different failure modes." }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "BarkProcessor voice preset and CustomTrainer.compute_loss signature mismatch are unrelated." + "reason": "Completely unrelated bug reports." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "Template compilation error and CLIPTokenizer max_length issue are unrelated." + "reason": "Template compilation error vs tokenizer model_max_length issue; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer special-token bug vs quantization fallback bug; no shared underlying defect." }, { "left": "issue:43742", "right": "issue:45020", "accept": false, - "reason": "Loading a specific model key error is not the same concrete issue as the broader remote_code regression report." + "reason": "Specific model loading key error vs broad remote_code regression claim; too different to be duplicates." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "Undefined multimodal-token helper bug and auto_mappings CI breakage are different code paths." - }, - { - "left": "issue:43653", - "right": "issue:44912", - "accept": false, - "reason": "Tokenizer special-token registration bug vs MXFP4 quantization loading/fallback issue; unrelated." + "reason": "Both are CI/regression flavored, but they affect different modules and unrelated code paths." }, { "left": "issue:43638", "right": "issue:44936", "accept": false, - "reason": "Training index error under ZeRO-3 and post-train evaluate failure are different trainer bugs." - }, - { - "left": "issue:43452", - "right": "issue:44991", - "accept": false, - "reason": "gguf_file support breakage and tokenizer loading failure are both load-related but not the same underlying bug." - }, - { - "left": "issue:43746", - "right": "issue:44811", - "accept": false, - "reason": "PEFT local checkpoint loading and Whisper batch_decode skip_special_tokens are unrelated." - }, - { - "left": "issue:38175", - "right": "issue:44610", - "accept": false, - "reason": "Both are vision-model regressions, but one is zero-probabilities output and the other is processor/model input-size mismatch." - }, - { - "left": "issue:44589", - "right": "issue:45042", - "accept": false, - "reason": "Float8 storage lookup failure and PIL backend torchvision dependency regression are unrelated." - }, - { - "left": "issue:43854", - "right": "issue:44977", - "accept": false, - "reason": "Different model-specific generation/loading failures with no shared concrete code path." - }, - { - "left": "issue:43819", - "right": "issue:43927", - "accept": false, - "reason": "DAC forward-vs-from_latents mismatch and DiaConfig token-ID persistence are unrelated bugs." + "reason": "Different training/evaluation failures with no shared root cause." } ] }, @@ -5249,19 +5368,18 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:34567", "issue:36010", "issue:36331", + "issue:38175", "issue:39692", "issue:40990", - "issue:41720", "issue:42490", - "issue:42915", "issue:43257", "issue:43262", "issue:43329", @@ -5269,51 +5387,58 @@ "issue:43452", "issue:43454", "issue:43531", - "issue:43540", "issue:43550", "issue:43577", - "issue:43582", "issue:43606", "issue:43643", "issue:43645", "issue:43696", "issue:43697", "issue:43720", - "issue:43742", + "issue:43746", "issue:43749", - "issue:43756", + "issue:43819", + "issue:43854", + "issue:43927", "issue:43931", "issue:44291", "issue:44479", "issue:44568", + "issue:44589", "issue:44610", "issue:44756", "issue:44811", "issue:44849", "issue:44912", + "issue:44977", "issue:44987", + "issue:44991", "issue:45042", "issue:45356", "issue:45357", - "issue:45381", "issue:45488", "issue:45538", "issue:45701", "issue:45759", - "issue:45859", - "issue:45907" + "issue:45859" ], "soft_pairs": [ + "issue:43452|issue:44991", + "issue:43746|issue:44811", + "issue:44589|issue:45042", + "issue:38175|issue:44610", + "issue:43854|issue:44977", + "issue:43819|issue:43927", "issue:39692|issue:44912", "issue:43257|issue:43329", "issue:36010|issue:43645", - "issue:43720|issue:44610", "issue:43550|issue:44912", - "issue:43454|issue:43577", + "issue:43720|issue:44610", "issue:43257|issue:43696", + "issue:43454|issue:43577", "issue:43329|issue:44479", - "issue:43262|issue:44811", "issue:43531|issue:45042", + "issue:43262|issue:44811", "issue:42490|issue:43257", "issue:36010|issue:36331", "issue:44568|issue:45356", @@ -5322,237 +5447,228 @@ "issue:44568|issue:45488", "issue:34567|issue:40990", "issue:43329|issue:43450", - "issue:44849|issue:45701", "issue:43257|issue:43931", "issue:43606|issue:45859", + "issue:44849|issue:45701", "issue:43697|issue:45357", - "issue:43257|issue:43756", "issue:44987|issue:45538", - "issue:43452|issue:43582", - "issue:44479|issue:45381", - "issue:44291|issue:45042", - "issue:41720|issue:43540", - "issue:42915|issue:43742", - "issue:44987|issue:45907" + "issue:44291|issue:45042" ], - "prepared_review_unit_hash": "295340dcde1e22be72f849b996889019366f0c78c3039bc3e28f90fa2662f7e2", + "prepared_review_unit_hash": "b0878c291f3d3af8a807a818a106e91faf5316d082284c0215ebf9d527d2ec82", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36927, - "estimated_input_tokens": 9232, - "estimated_eval_tokens": 18720 + "serialized_chars": 36973, + "estimated_input_tokens": 9244, + "estimated_eval_tokens": 18744 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated across different bugs and subsystems. The only plausible duplicate pair is the Qwen video-input regression around 44479/45381; everything else is too far apart to merge safely.", - "confidence": 0.78, - "canonical_issue_reason": "issue:44479 is the broadest umbrella for the Qwen video-input regression family and best represents the only near-duplicate cluster in this set.", + "summary": "No soft pair looks like the same underlying bug or change; most are only loosely related by subsystem (tokenization, video, loading, offload, etc.). If a single issue must anchor the cluster, the broad open tokenization regression report is the best representative.", + "confidence": 0.83, + "canonical_issue_reason": "issue:45701 is the broadest, most umbrella-like report in the set, with the most inbound references and a title that can absorb nearby tokenization regressions better than the more narrowly scoped bugs.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the most representative issue overall because it is broader than the other nearby Qwen video reports and can subsume the narrow duplicate-like follow-up.", + "best_issue_reason": "issue:45701 is the best overall representative because it is open, broad in scope, and appears most central to the tokenization-related slice of this cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Different failure modes: gguf_file handling for from_pretrained vs a tokenizer-loading regression for a specific model." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Unrelated bugs: PEFT/local checkpoint loading vs Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Different subsystems and symptoms: float8 storage lookup vs PIL image processors requiring torchvision." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision-related, but one is zero probabilities in SigLIP2 and the other is an OmDet processor/model image-size mismatch." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Different models and issues: GLM-4.7-Flash loading test failure vs Qwen3.5 flash-attention generation regression." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent reconstruction mismatch is unrelated to DiaConfig losing custom token IDs after save/load." + }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "Doc example errors in SigLIP2 are unrelated to the GPT-OSS quantization/load fallback bug." + "reason": "Both mention quantization, but one is a SigLIP2 docs example with model/processor mismatch and the other is a git-oss-20b MXFP4 loading fallback." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "Qwen3 MoE weight conversion during loading is a different code path from the undefined video token-count helper bug." + "reason": "Distinct code paths: Qwen3 MoE accelerate/deepspeed weight conversion vs multimodal token counting in a video branch." }, { "left": "issue:36010", "right": "issue:43645", "accept": false, - "reason": "GenerationMixin import breakage is unrelated to custom model initialization in notebooks." - }, - { - "left": "issue:43720", - "right": "issue:44610", - "accept": false, - "reason": "BitNet packed-weight loading and OmDet-Turbo image-size mismatch are different failures." + "reason": "ImportError for GenerationMixin is not the same as notebook-specific custom model initialization breakage." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "torch.compile SDPA on Bamba and MXFP4 quantization fallback are unrelated bugs." + "reason": "Different model/runtime problems: torch.compile with SDPA vs MXFP4 quantization fallback on a different model." }, { - "left": "issue:43454", - "right": "issue:43577", + "left": "issue:43720", + "right": "issue:44610", "accept": false, - "reason": "AyaVision weight-tying and Blip2 dtype propagation are separate model-loading issues." + "reason": "Packed-weight unpacking during accelerate loading is unrelated to an image processor output-size mismatch." }, { "left": "issue:43257", "right": "issue:43696", "accept": false, - "reason": "Qwen3 MoE accelerate/deepspeed loading is unrelated to GPT-OSS out-of-memory." + "reason": "MoE weight conversion/loading bug is not the same as a CUDA OOM report for GPT-oss-20b." }, { - "left": "issue:43329", - "right": "issue:44479", + "left": "issue:43454", + "right": "issue:43577", "accept": false, - "reason": "Both are video-related, but one is an undefined-helper bug in token counting while the other is a broader Qwen video-input regression; not clearly the same defect." + "reason": "AyaVision lm_head tying issue is unrelated to Blip2 dtype propagation for the main model and qformer." }, { - "left": "issue:43262", - "right": "issue:44811", + "left": "issue:43329", + "right": "issue:44479", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting is unrelated to Whisper batch_decode skip_special_tokens handling." + "reason": "Related video area, but not the same bug: undefined helpers in token counting vs a broader Qwen video-input regression." }, { "left": "issue:43531", "right": "issue:45042", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and PIL backend torchvision dependency are unrelated." + "reason": "Sliding-window behavior in Qwen3-MoE has no connection to PIL backend torchvision requirements." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting is unrelated to Whisper batch_decode token-skipping." }, { "left": "issue:42490", "right": "issue:43257", "accept": false, - "reason": "Path-trailing-slash import warning is unrelated to Qwen3 MoE weight conversion during accelerate+deepspeed loading." + "reason": "Local-path trailing-slash import warning is not the same as Qwen3 MoE accelerate/deepspeed weight conversion." }, { "left": "issue:36010", "right": "issue:36331", "accept": false, - "reason": "GenerationMixin import error and CustomTrainer.compute_loss signature mismatch are different trainer/import regressions." + "reason": "Importing GenerationMixin and compute_loss signature changes are separate trainer/library issues." }, { "left": "issue:44568", "right": "issue:45356", "accept": false, - "reason": "Tokenizer special-token insertion bug and Kimi-K2.5 codec/regex regression are separate tokenizer issues." + "reason": "Different tokenizer regressions affecting different models and behaviors: BOS/EOS insertion vs codec/warning handling." }, { "left": "issue:43749", "right": "issue:44756", "accept": false, - "reason": "FSDP CPU RAM efficient loading and Strix Halo mmap OOM are different memory-path problems." + "reason": "FSDP CPU RAM-efficient loading breakage is not the same as disabling mmap to avoid OOM on Strix Halo." }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "AutoConfig missing fields with trust_remote_code is unrelated to AutoModelForCausalLM.from_config text_config unwrapping." + "reason": "Missing fields from trust_remote_code config loading is distinct from unwrapping text_config for composite multimodal configs." }, { "left": "issue:44568", "right": "issue:45488", "accept": false, - "reason": "mDeBERTa BOS/EOS insertion and LlamaTokenizer pre-tokenizer override are different tokenizer regressions." + "reason": "Both are tokenization regressions, but they affect different tokenizer implementations and different concrete behaviors." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "Trainer token accounting and GPT-OSS perplexity are unrelated." + "reason": "TrainerState token counters and GPT-oss-20b perplexity are unrelated problems." }, { "left": "issue:43329", "right": "issue:43450", "accept": false, - "reason": "Undefined video token helper variables and batched video processor shape errors are not the same bug." - }, - { - "left": "issue:44849", - "right": "issue:45701", - "accept": false, - "reason": "Qwen3.5 hidden-state output behavior and version-dependent tokenization changes are unrelated." + "reason": "Undefined helpers in video token counting are different from batched video processor shape errors." }, { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Qwen3 MoE loading with accelerate/deepspeed is not the same as Qwen3-VL weight-shape mismatch." + "reason": "MoE weight conversion during accelerate/deepspeed loading is separate from Qwen3-VL weight-shape mismatch on load." }, { "left": "issue:43606", "right": "issue:45859", "accept": false, - "reason": "Both mention CPU offload, but the affected models and code paths differ too much to treat as duplicates." + "reason": "Both mention CPU offload, but they involve different models and different failure mechanisms." }, { - "left": "issue:43697", - "right": "issue:45357", + "left": "issue:44849", + "right": "issue:45701", "accept": false, - "reason": "RTDetrV2 output drift and Qwen3.5 save_pretrained visual-key regression are unrelated." + "reason": "Qwen3.5 hidden-state output bug is not the same as a broader tokenization change regression." }, { - "left": "issue:43257", - "right": "issue:43756", + "left": "issue:43697", + "right": "issue:45357", "accept": false, - "reason": "Qwen3 MoE loading and SmolLM3 RoPE-layer dropping are separate model/config bugs." + "reason": "RTDetrV2 output differences and Qwen3.5 save_pretrained visual-key regression are unrelated model bugs." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "Physical-Intelligence loading failure and CLIPTokenizer model_max_length issue are unrelated." - }, - { - "left": "issue:43452", - "right": "issue:43582", - "accept": false, - "reason": "gguf_file tokenizer/model loading breakage is unrelated to Apple Silicon warmup TypeError." - }, - { - "left": "issue:44479", - "right": "issue:45381", - "accept": true, - "reason": "Both describe the same Qwen video-input regression; 45381 is a narrower report of the broader v5.3.0 video-input bug in 44479." + "reason": "A model-loading failure for physical-intelligence/fast is not the same as CLIPTokenizer's model_max_length bug." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "init_empty_weights TypeError and PIL backend torchvision requirement are unrelated." - }, - { - "left": "issue:41720", - "right": "issue:43540", - "accept": false, - "reason": "Qwen3 auto device-mapping CUDA assert and Qwen3OmniMoe video ValueError are different failures." - }, - { - "left": "issue:42915", - "right": "issue:43742", - "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config and MobileLLM key errors are unrelated loading bugs." - }, - { - "left": "issue:44987", - "right": "issue:45907", - "accept": false, - "reason": "physical-intelligence loading and list_repo_files revision forwarding are unrelated CI/library bugs." + "reason": "init_empty_weights/_is_hf_initialized TypeError is unrelated to PIL backend processors depending on torchvision." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The assessment is grounded in the packet and stays conservative. All soft-edge verdicts match the packet\u2019s deterministic outcomes, and the only accepted pair (44479/45381) is well-supported as the same Qwen video-input regression family." - }, - "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 }, @@ -5564,27 +5680,28 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:28282", "issue:29127", "issue:33357", "issue:34567", "issue:34689", - "issue:36331", "issue:38175", + "issue:41720", "issue:42175", "issue:42915", + "issue:43257", "issue:43317", - "issue:43493", + "issue:43404", + "issue:43452", "issue:43526", "issue:43540", "issue:43577", "issue:43582", - "issue:43643", "issue:43742", "issue:43749", "issue:43756", @@ -5592,7 +5709,6 @@ "issue:43824", "issue:43906", "issue:43927", - "issue:43994", "issue:44062", "issue:44291", "issue:44479", @@ -5603,22 +5719,27 @@ "issue:44898", "issue:44912", "issue:44938", + "issue:44987", "issue:44991", "issue:45072", - "issue:45081", "issue:45137", "issue:45325", - "issue:45357", - "issue:45375", "issue:45381", "issue:45405", "issue:45479", "issue:45538", "issue:45588", "issue:45823", - "issue:45920" + "issue:45907", + "issue:45987" ], "soft_pairs": [ + "issue:43257|issue:43756", + "issue:44479|issue:45381", + "issue:42915|issue:43742", + "issue:41720|issue:43540", + "issue:43452|issue:43582", + "issue:44987|issue:45907", "issue:33357|issue:34567", "issue:42915|issue:44821", "issue:42915|issue:45538", @@ -5627,247 +5748,248 @@ "issue:42175|issue:43824", "issue:43540|issue:44479", "issue:43540|issue:44560", - "issue:43577|issue:45072", "issue:44062|issue:44991", + "issue:43577|issue:45072", "issue:42175|issue:44938", "issue:38175|issue:44898", + "issue:43404|issue:45987", "issue:42175|issue:44488", "issue:45137|issue:45405", "issue:43906|issue:45381", - "issue:44737|issue:45588", "issue:28282|issue:34689", "issue:43742|issue:44291", "issue:42915|issue:43749", - "issue:43582|issue:43782", + "issue:44737|issue:45588", "issue:43526|issue:45479", "issue:43540|issue:45823", "issue:43756|issue:45325", - "issue:28282|issue:29127", - "issue:43493|issue:43994", - "issue:34567|issue:36331", - "issue:44062|issue:45081", - "issue:44291|issue:44821", - "issue:45357|issue:45920", - "issue:43643|issue:45375" + "issue:43582|issue:43782", + "issue:28282|issue:29127" ], - "prepared_review_unit_hash": "34fd7776a457f7274538a63f6251d11b7126695d0cbe7f60fd4aec5455b2dadb", + "prepared_review_unit_hash": "314aaaeef15f08bed36cc02b76409f702aea634ba7c99538d92ca4ee87491c90", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 37017, - "estimated_input_tokens": 9255, - "estimated_eval_tokens": 18766 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36533, + "estimated_input_tokens": 9134, + "estimated_eval_tokens": 18524 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous. I see one clear duplicate pair around SigLIP2 behavior and one plausible tokenizer-loading duplicate pair; the rest look like distinct bugs in different models, error paths, or subsystems.", + "summary": "The cluster is still mostly a grab bag of distinct Transformer bugs. Most soft edges are appropriately rejected; the only correction is to treat 44479 \u2194 45381 as merely related Qwen VL video-input regressions, not confirmed duplicates.", "confidence": 0.69, - "canonical_issue_reason": "issue:43994 is the best anchor for the SigLIP2 correctness cluster: it is the clearest user-facing report, and it matches one of the strongest duplicate pairs in this set (with issue:43493).", + "canonical_issue_reason": "Issue 44479 remains the broadest representative of the Qwen video-input regression cluster, but the evidence is not strong enough to collapse 45381 into it as the same underlying bug.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43994 is the strongest overall issue anchor because it describes the observable failure directly and is a good representative target for the SigLIP2 duplicate pair.", + "best_issue_reason": "44479 is still the best cluster representative because it captures the broad v5.3.0 Qwen VL video regression framing more generally than 45381, even though the two should only be considered possibly related.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different bugs: MoE weight conversion during load vs Smollm3 RoPE layer selection." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": false, + "reason": "The titles point to related Qwen2.5-VL video-input regressions, but the packet does not show enough shared traceback, code path, or concrete overlap to call them the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Unrelated failures: Qwen3Moe FineGrainedFP8Config vs MobileLLM key error on load." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Both Qwen-related, but different code paths and failures: auto device mapping CUDA assert vs video-input ValueError." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Tokenizer/model gguf loading issue vs Apple Silicon allocator warmup TypeError; not the same bug." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Different concerns: model loading failure vs repo file listing not forwarding revision." + }, { "left": "issue:33357", "right": "issue:34567", "accept": false, - "reason": "MacOS CLIP model bus error vs TrainerState token-count bookkeeping: different bugs." + "reason": "Mac CLIP bus error and TrainerState token counting are unrelated." }, { "left": "issue:42915", "right": "issue:44821", "accept": false, - "reason": "Qwen3Moe FP8/config loading issue vs AutoImageProcessor URL loading: unrelated." + "reason": "Qwen3Moe FP8 load failure vs AutoImageProcessor URL loading problem." }, { "left": "issue:42915", "right": "issue:45538", "accept": false, - "reason": "FineGrainedFP8Config failure and CLIPTokenizer max-length behavior are different problems." + "reason": "FP8 config failure vs CLIPTokenizer max_length behavior; different artifacts and code paths." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "DiaConfig save/load token-ID bug vs MXFP4 quantization fallback: different code paths." + "reason": "Config save/load token ID loss is not the same as MXFP4 quantization fallback." }, { "left": "issue:43317", "right": "issue:45538", "accept": false, - "reason": "device_map/offload dequantization failure is not the same as CLIPTokenizer max_length behavior." + "reason": "device_map/offload loading failure vs tokenizer max_length constant; unrelated." }, { "left": "issue:42175", "right": "issue:43824", "accept": false, - "reason": "Packaging/backend availability issue vs model import/export name error: not the same bug." + "reason": "Packaging/backend availability issue vs missing Qwen2_5_VL class import." }, { "left": "issue:43540", "right": "issue:44479", "accept": false, - "reason": "Both involve video, but the model families and failures differ." + "reason": "Both video-related, but different models and errors; not enough to treat as the same concrete bug." }, { "left": "issue:43540", "right": "issue:44560", "accept": false, - "reason": "Qwen3OmniMoe ValueError and Qwen3-vl-embedding StopIteration look like different failures." + "reason": "Different video-input failures in different Qwen variants; no clear shared code-path bug from the titles alone." }, { - "left": "issue:43577", - "right": "issue:45072", + "left": "issue:44062", + "right": "issue:44991", "accept": false, - "reason": "Both mention dtype mismatches, but they affect different model families and code paths." + "reason": "AddedToken special-arg error vs tokenizer loading regression for a specific model." }, { - "left": "issue:44062", - "right": "issue:44991", - "accept": true, - "reason": "Likely the same tokenizer-loading regression: 44062 shows the concrete AddedToken TypeError, while 44991 reports the broader tokenizer load failure on the same upgrade path." + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "BLIP2 dtype persistence bug and CI dtype mismatches in other models are not the same issue." }, { "left": "issue:42175", "right": "issue:44938", "accept": false, - "reason": "TensorFlow backend packaging issue vs Python 3.14 load failure: different causes." + "reason": "Backend-install packaging problem vs Python 3.14 import failure." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "SigLIP2 zero-probabilities bug vs Perceiver resolution/interpolation failure: different model issues." + "reason": "Unexpected zero probabilities and Perceiver interpolation failure are distinct model behaviors." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "lm_head tying bug vs StaticCache seq-length return type mismatch." }, { "left": "issue:42175", "right": "issue:44488", "accept": false, - "reason": "Backend installation issue vs loading a specific model repo: unrelated." + "reason": "Package backend composition issue vs inability to load a specific model." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "DeepSpeed ZeRO3 deque error is unrelated to the PEFT version bump." + "reason": "DeepSpeed ZeRO3 deque error is unrelated to the PEFT version pinning problem." }, { "left": "issue:43906", "right": "issue:45381", "accept": false, - "reason": "Isolated reproduction of another issue vs Qwen2.5-VL video position-id regression." - }, - { - "left": "issue:44737", - "right": "issue:45588", - "accept": false, - "reason": "XLNet CPU placement bug and flash-attention sink handling are unrelated." + "reason": "One is a repro of an older issue; the other is a specific Qwen2.5-VL video regression." }, { "left": "issue:28282", "right": "issue:34689", "accept": false, - "reason": "Missing PyTorch import error vs Llama 3.2 Vision loading breakage: different failures." + "reason": "Missing PyTorch ImportError vs Llama 3.2 Vision loading regression are different causes." }, { "left": "issue:43742", "right": "issue:44291", "accept": false, - "reason": "MobileLLM key error vs init_empty_weights unexpected-argument error: different loading paths." + "reason": "MobileLLM key error and unexpected _is_hf_initialized argument are separate load-time bugs." }, { "left": "issue:42915", "right": "issue:43749", "accept": false, - "reason": "Qwen3Moe FP8 config issue vs FSDP_CPU_RAM_EFFICIENT_LOADING: unrelated." + "reason": "Qwen3Moe FP8 issue and FSDP CPU RAM efficient loading are unrelated." }, { - "left": "issue:43582", - "right": "issue:43782", + "left": "issue:44737", + "right": "issue:45588", "accept": false, - "reason": "Apple Silicon allocator TypeError vs Qwen3VL weight_only loading error: different problems." + "reason": "XLNet CPU arange issue vs flash_attention sink-less crash are distinct implementation bugs." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug vs sequence-classification zero-loss behavior: unrelated." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to the sequence-classification zero-loss issue." }, { "left": "issue:43540", "right": "issue:45823", "accept": false, - "reason": "Qwen3OmniMoe video-input ValueError and Gemma4 PLE device mismatch are different bugs." + "reason": "Qwen3OmniMoe video processing error and Gemma4 device mismatch are different failures." }, { "left": "issue:43756", "right": "issue:45325", "accept": false, - "reason": "Both involve positional/RoPE logic, but they affect different models and computations." + "reason": "Smollm3 RoPE-layer behavior and Qwen2.5-VL temporal position scaling are unrelated." }, { - "left": "issue:28282", - "right": "issue:29127", - "accept": false, - "reason": "Missing PyTorch import vs LayoutLMv3 error-message clarity: unrelated." - }, - { - "left": "issue:43493", - "right": "issue:43994", - "accept": true, - "reason": "Same SigLIP2 correctness issue: 43493 describes the implementation discrepancy, and 43994 reports the user-visible bad outputs on the same model." - }, - { - "left": "issue:34567", - "right": "issue:36331", - "accept": false, - "reason": "TrainerState token counting and CustomTrainer compute_loss signature mismatch are unrelated training issues." - }, - { - "left": "issue:44062", - "right": "issue:45081", - "accept": false, - "reason": "AddedToken constructor duplication and Mistral regex patch crash are different tokenizer bugs." - }, - { - "left": "issue:44291", - "right": "issue:44821", - "accept": false, - "reason": "init_empty_weights loading failure is unrelated to loading AutoImageProcessor from a URL." - }, - { - "left": "issue:45357", - "right": "issue:45920", + "left": "issue:43582", + "right": "issue:43782", "accept": false, - "reason": "Qwen3.5 save_pretrained key regression and AutoTokenizer wrong token IDs affect different components." + "reason": "Apple Silicon caching allocator TypeError vs Qwen3VL weight_only load error are different bugs." }, { - "left": "issue:43643", - "right": "issue:45375", + "left": "issue:28282", + "right": "issue:29127", "accept": false, - "reason": "General trust_remote_code AutoConfig field loss is not the same as the Qwen3_5MoeVisionConfig strict-field drop bug." + "reason": "AutoModel missing PyTorch and LayoutLMv3 box-information message clarity are unrelated." } ] }, "evaluator_result": { "accept": false, - "feedback": "The cluster summary is mostly grounded, but it overstates confidence in at least one place. In particular, the accepted 44062/44991 pair is described as the \u201csame tokenizer-loading regression\u201d and \u201cbroader manifestation,\u201d which is stronger than the packet\u2019s title-level evidence supports. Also, the canonical issue note saying 43994 matches the \u201conly strong duplicate pair in this set\u201d is inaccurate because the packet contains another accepted duplicate pair (44062/44991). Please soften those claims to plausible/likely duplicates rather than asserting the same underlying bug from titles alone." + "feedback": "The cluster-level summary is mostly grounded, but one soft-edge verdict is too strong for the evidence in the packet. The 44479 \u2194 45381 link is plausible from the titles, yet the packet does not provide enough direct overlap to assert they are the same underlying bug; this should be framed more conservatively (e.g. \"likely related\" / \"possible duplicate\") or left unaccepted. The rest of the verdicts look appropriately conservative." }, "evaluator_used": true, "retried": true, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -5879,40 +6001,38 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:24643", "issue:29127", - "issue:38175", + "issue:34567", + "issue:36331", "issue:41762", "issue:43295", "issue:43452", + "issue:43493", "issue:43531", "issue:43577", "issue:43643", - "issue:43653", "issue:43688", "issue:43697", "issue:43720", "issue:43742", "issue:43749", "issue:43819", - "issue:44361", - "issue:44442", - "issue:44464", + "issue:43994", + "issue:44062", + "issue:44291", "issue:44466", "issue:44484", "issue:44488", "issue:44514", - "issue:44561", - "issue:44568", "issue:44589", "issue:44625", "issue:44704", - "issue:44743", "issue:44792", "issue:44811", "issue:44821", @@ -5927,12 +6047,21 @@ "issue:45216", "issue:45290", "issue:45356", + "issue:45357", + "issue:45375", "issue:45381", "issue:45405", "issue:45600", - "issue:45823" + "issue:45823", + "issue:45920" ], "soft_pairs": [ + "issue:43493|issue:43994", + "issue:34567|issue:36331", + "issue:44062|issue:45081", + "issue:44291|issue:44821", + "issue:45357|issue:45920", + "issue:43643|issue:45375", "issue:43452|issue:44488", "issue:44792|issue:44964", "issue:45042|issue:45081", @@ -5942,222 +6071,219 @@ "issue:43697|issue:45216", "issue:43688|issue:43749", "issue:44514|issue:45381", - "issue:43720|issue:44898", "issue:44484|issue:44704", + "issue:43720|issue:44898", "issue:41762|issue:44936", "issue:24643|issue:29127", "issue:44625|issue:44877", - "issue:43452|issue:43577", "issue:44514|issue:45290", "issue:43452|issue:44843", + "issue:43452|issue:43577", "issue:44466|issue:45005", "issue:43295|issue:45356", "issue:43819|issue:44811", - "issue:44936|issue:45823", - "issue:43653|issue:44568", - "issue:44464|issue:44743", - "issue:38175|issue:43295", - "issue:43643|issue:44561", - "issue:43653|issue:44361", - "issue:44361|issue:44442" + "issue:44936|issue:45823" ], - "prepared_review_unit_hash": "52a6634dfff0056aef956b088f035c923f7536cfc9c0f6553aa1adde7675252d", + "prepared_review_unit_hash": "632b64d2460915bba5e36985386642433964426f1eb9a33b8aa2c70da634243d", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 35465, - "estimated_input_tokens": 8867, - "estimated_eval_tokens": 17990 + "serialized_chars": 36184, + "estimated_input_tokens": 9046, + "estimated_eval_tokens": 18348 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is not a duplicate set; it\u2019s a mix of unrelated loading, tokenizer, model-shape, generation, and trainer regressions. The closest thing to a representative issue is the broad loading regression in issue 43452, but the rest are mostly model- or path-specific.", - "confidence": 0.9, - "canonical_issue_reason": "Issue 43452 is the broadest shared-loader regression in the set and is the best heuristic representative for the cluster, even though the other issues are not true duplicates.", + "summary": "This cluster is mostly a loose collection of Transformers regressions around loading, tokenization, configs, and save_pretrained behavior. A few pairs look like true duplicates, but most are only broadly similar.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45920 is the broadest current regression report in the set: it spans multiple model families and the tokenizer/output corruption theme that recurs elsewhere in the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "43452 best captures the cluster\u2019s common theme of upstream loading regressions without being overly narrow to one model family.", + "best_issue_reason": "issue:45920 is the best representative issue for this cluster because it is the most general, user-facing tokenizer regression and could absorb related follow-ups.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 implementation bug: both report incorrect outputs from the HF SigLIP2 path, just from different entry points." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Trainer bookkeeping bug vs custom compute_loss signature mismatch; different code paths and symptoms." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "AddedToken constructor conflict vs Mistral regex patch crash; unrelated tokenizer failures." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized loading error vs AutoImageProcessor URL loading; different subsystems." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Qwen3.5 save_pretrained visual-encoder key serialization vs tokenizer ID regression across models; not the same bug." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Generic trust_remote_code AutoConfig field loss vs a specific Qwen3.5 vision config field omission; different defects." + }, { "left": "issue:43452", "right": "issue:44488", "accept": false, - "reason": "Both are loading-related, but 43452 is a gguf_file regression in tokenizer/model loading while 44488 is a specific sleng-bert load failure; different underlying bugs." + "reason": "GGUF loading regression vs a model-specific load failure; different mechanisms." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "Different model families and different failures: janus test instability vs Phi-4 multimodal load failure." + "reason": "Janus generate_images test failure vs Phi-4 multimodal model load failure; different models and code paths." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "Image-processor torchvision dependency bug vs Mistral regex tokenizer crash; unrelated code paths." + "reason": "Image processor torchvision dependency regression vs tokenizer regex crash; unrelated." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "MobileLLM loading key error and Float8 storage lookup error are distinct loader/runtime issues." + "reason": "MobileLLM key error vs Float8 storage deserialization issue; distinct loading bugs." }, { "left": "issue:43531", "right": "issue:44821", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and AutoImageProcessor URL loading are unrelated." + "reason": "Qwen3-MoE sliding_window bug vs image-processor URL loading; unrelated." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "PEFT version bump packaging issue vs removed config references in auto_mappings.py; different problems." + "reason": "PEFT version pin problem vs removed config references in auto_mappings; different maintenance issues." }, { "left": "issue:43697", "right": "issue:45216", "accept": false, - "reason": "RTDetrV2 output mismatch in v5 is not the same bug as Qwen3.5 save_pretrained checkpoint corruption." + "reason": "RTDetrV2 output drift vs Qwen3.5 save_pretrained regression; different models and code paths." }, { "left": "issue:43688", "right": "issue:43749", "accept": false, - "reason": "Auxiliary loss normalization and FSDP CPU RAM efficient loading are separate training/loading bugs." + "reason": "Aux-loss normalization bug vs FSDP CPU RAM efficient loading; different training/load problems." }, { "left": "issue:44514", "right": "issue:45381", "accept": false, - "reason": "Both involve Qwen2.5-VL, but one crashes in chat templating with batching/padding and the other has wrong video vision_position_ids; not the same defect." + "reason": "Both are Qwen2.5-VL, but one is a chat-template batching crash and the other is wrong vision_position_ids; not the same concrete defect." }, { - "left": "issue:43720", - "right": "issue:44898", + "left": "issue:44484", + "right": "issue:44704", "accept": false, - "reason": "BitNet packed-weight loading during accelerate vs Perceiver interpolation on non-default resolution are unrelated." + "reason": "save_pretrained shard-size question vs AutoProcessor kwarg forwarding bug; not duplicates." }, { - "left": "issue:44484", - "right": "issue:44704", + "left": "issue:43720", + "right": "issue:44898", "accept": false, - "reason": "Save-pretrained shard-size question and AutoProcessor kwarg forwarding are unrelated issues." + "reason": "BitNet packed-weight loading vs Perceiver interpolation/classification issue; unrelated." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "Gemma3 ZeRO-3 load failure and trainer.evaluate() after trainer.train() are different code paths and failures." + "reason": "DeepSpeed ZeRO-3 loading error vs trainer.evaluate() failing after train; different issues." }, { "left": "issue:24643", "right": "issue:29127", "accept": false, - "reason": "DeepSpeed weight dimensionality error and LayoutLMv3 box validation messaging are not the same underlying bug." + "reason": "DeepSpeed training runtime error vs LayoutLMv3 error-message clarity; unrelated." }, { "left": "issue:44625", "right": "issue:44877", "accept": false, - "reason": "Qwen3.5 num_labels propagation and strict granite_speech config loading are distinct config-handling regressions." - }, - { - "left": "issue:43452", - "right": "issue:43577", - "accept": false, - "reason": "gguf_file loading regression and Blip2 dtype propagation are unrelated." + "reason": "Qwen3.5 num_labels propagation bug vs strict config rejecting granite_speech; different config paths." }, { "left": "issue:44514", "right": "issue:45290", "accept": false, - "reason": "Both are chat-template issues, but one is batched padding behavior and the other is tool-call assistant messages with no content; different fixes." + "reason": "Both hit apply_chat_template, but the triggers differ: batched padding=False crash vs tool-call/no-content crash." }, { "left": "issue:43452", "right": "issue:44843", "accept": false, - "reason": "gguf_file loading breakage and mistral-regex offline model_info behavior are unrelated loading paths." + "reason": "GGUF loading regression vs offline model_info call in _patch_mistral_regex; different loading bugs." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "GGUF/model loading regression vs BLIP2 dtype propagation; unrelated." }, { "left": "issue:44466", "right": "issue:45005", - "accept": false, - "reason": "Both mention tied weights, but 44466 is device-dependent lm_head serialization while 45005 is a broader translation-model tied-weights issue; not enough evidence they\u2019re the same bug." + "accept": true, + "reason": "Both describe the same tied-weights/save_pretrained regression in v5, with device-dependent lm_head serialization and translation-model tied weights." }, { "left": "issue:43295", "right": "issue:45356", "accept": false, - "reason": "Custom processor.tokenizer regression and Kimi-K2.5 codec/fix_mistral_regex regression are different tokenizer issues." + "reason": "Processor.tokenizer regression vs Kimi-K2.5 codec/fix_mistral_regex warning issue; different bugs." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "DAC.from_latents mismatch and Whisper batch_decode skip_special_tokens handling are unrelated." + "reason": "DAC latent round-trip bug vs Whisper batch_decode skip_special_tokens handling; unrelated." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "trainer.evaluate() state issue and Gemma4 device_map='auto' mismatch are different failures." - }, - { - "left": "issue:43653", - "right": "issue:44568", - "accept": false, - "reason": "BigBirdTokenizer special-token registration and mdeberta-v3 BOS/EOS insertion are similar category-wise but clearly different tokenizers and bugs." - }, - { - "left": "issue:44464", - "right": "issue:44743", - "accept": false, - "reason": "Chunked generation with compiled forward and recurrent state reset with cache are distinct generation-path regressions." - }, - { - "left": "issue:38175", - "right": "issue:43295", - "accept": false, - "reason": "Siglip2 zero-probabilities and processor.tokenizer regression are unrelated." - }, - { - "left": "issue:43643", - "right": "issue:44561", - "accept": false, - "reason": "AutoConfig missing fields under trust_remote_code and removal of is_torch_fx_available are separate trust_remote_code compatibility issues." - }, - { - "left": "issue:43653", - "right": "issue:44361", - "accept": false, - "reason": "BigBirdTokenizer special-token behavior and MLukeTokenizer AttributeError are unrelated tokenizer bugs." - }, - { - "left": "issue:44361", - "right": "issue:44442", - "accept": false, - "reason": "Both are tokenizer loading failures, but for different tokenizer classes and different failure modes; not a duplicate." + "reason": "trainer.evaluate() after train vs Gemma4 PLE device mismatch; different runtime problems." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays appropriately cautious. The two accepted soft pairs are plausible duplicates, and the rejected pairs are consistently conservative rather than overstated. The canonical issue choice (45920) is well supported as the broadest tokenizer regression in the set." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -6169,10 +6295,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:28282", "issue:30064", @@ -6181,19 +6307,18 @@ "issue:33666", "issue:34567", "issue:35141", - "issue:36010", + "issue:38175", "issue:41720", "issue:43122", "issue:43278", + "issue:43295", "issue:43452", "issue:43493", "issue:43504", - "issue:43525", "issue:43531", "issue:43550", - "issue:43572", "issue:43577", - "issue:43606", + "issue:43643", "issue:43646", "issue:43653", "issue:43688", @@ -6205,291 +6330,307 @@ "issue:43906", "issue:43927", "issue:44361", + "issue:44442", "issue:44451", "issue:44464", "issue:44479", "issue:44554", + "issue:44561", + "issue:44568", "issue:44610", "issue:44625", + "issue:44743", "issue:44821", "issue:44843", - "issue:44849", "issue:44977", "issue:44991", - "issue:45357", "issue:45440", "issue:45588", "issue:45701", "issue:45704" ], "soft_pairs": [ + "issue:43653|issue:44568", + "issue:38175|issue:43295", + "issue:43653|issue:44361", + "issue:43643|issue:44561", + "issue:44361|issue:44442", "issue:30064|issue:33666", + "issue:44464|issue:44743", "issue:41720|issue:43906", "issue:43688|issue:45440", "issue:43688|issue:45704", - "issue:43577|issue:43697", "issue:28282|issue:32090", + "issue:43577|issue:43697", "issue:28282|issue:33357", + "issue:28282|issue:35141", "issue:44843|issue:44991", "issue:43646|issue:43749", - "issue:28282|issue:35141", "issue:43688|issue:45701", "issue:43653|issue:43927", "issue:43531|issue:43742", "issue:43550|issue:43927", "issue:44464|issue:44977", "issue:44479|issue:44625", - "issue:43577|issue:44554", "issue:43550|issue:44361", - "issue:43577|issue:45588", "issue:43122|issue:43906", - "issue:43504|issue:43550", + "issue:43577|issue:44554", + "issue:43577|issue:45588", "issue:43504|issue:43720", - "issue:41720|issue:44464", + "issue:43504|issue:43550", "issue:32090|issue:34567", + "issue:41720|issue:44464", "issue:43504|issue:44610", "issue:32090|issue:33666", "issue:43452|issue:44451", - "issue:44849|issue:45357", "issue:43742|issue:44821", "issue:43278|issue:43688", - "issue:33666|issue:36010", - "issue:43493|issue:43825", - "issue:43606|issue:43927", - "issue:43525|issue:43572" + "issue:43493|issue:43825" ], - "prepared_review_unit_hash": "c3e37aa0197d1ac495ee3f5ef25db9e97a79f75e047dd7d32d5a13f1af3958e9", + "prepared_review_unit_hash": "a47a6e14523fc9450088f5c09f8c07974418c6a1b1ddd5eda9880393c4a5b236", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 34, - "serialized_chars": 37206, - "estimated_input_tokens": 9302, - "estimated_eval_tokens": 18860 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38477, + "estimated_input_tokens": 9620, + "estimated_eval_tokens": 19496 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is not a duplicate set: the proposed soft edges span unrelated issues across loading, tokenization, training, generation, and model-specific regressions. No candidate pair looks like the same underlying bug/change.", - "confidence": 0.98, - "canonical_issue_reason": "No canonical issue: the items are heterogeneous and do not form a single duplicate cluster.", - "canonical_pr_reason": "No canonical PR: there are no pull requests in the input.", - "best_issue_reason": "No global best issue: the cluster is too mixed to nominate one representative duplicate target.", - "best_pr_reason": "No PRs to evaluate for global best PR suitability.", + "summary": "All soft edges look like false positives: they share broad subsystem themes, but not the same concrete bug or fix path. The set is heterogeneous across tokenizer loading, model init, training, generation, and device/runtime issues.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue is a clear canonical representative; the items are too heterogeneous to form one duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to pick an anchor, issue 45701 is the broadest tokenization-regression report and has the most inbound references, but it still does not represent the rest of the mixed set well.", + "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both concern tokenizers and special tokens, but they are different tokenizers with different failures and code paths." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Unrelated problems: SigLIP2 probability behavior vs processor/tokenizer API regression." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer classes and symptoms; special-token decode bug is not the same as an AttributeError on tasks." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both involve trust_remote_code, but one is missing config fields and the other is a removed helper breaking imports." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Separate tokenizer-loading failures for different models and failure modes." + }, { "left": "issue:30064", "right": "issue:33666", "accept": false, - "reason": "Image processor segmentation-map bug vs Qwen2-VL multi-GPU training; unrelated subsystems and failure modes." + "reason": "Image-processor segmentation-map bug vs multi-GPU training issue; no shared underlying bug." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both are generation/cache related, but one is compiled-forward inconsistency and the other is recurrent-state reset logic." }, { "left": "issue:41720", "right": "issue:43906", "accept": false, - "reason": "Qwen3 auto device-mapping CUDA assert vs isolated reproduction of another issue; not the same bug." + "reason": "An A800 cuda assert with auto device mapping is not the same as an isolated reproduction of a different issue." }, { "left": "issue:43688", "right": "issue:45440", "accept": false, - "reason": "Aux-loss normalization bug vs DeepSeekV3 implementation divergence; different code paths." + "reason": "Different MoE model bugs with different implementations and likely different fixes." }, { "left": "issue:43688", "right": "issue:45704", "accept": false, - "reason": "Aux-loss normalization vs T5 Apex RMSNorm memory leak; unrelated model/runtime issues." + "reason": "Aux-loss normalization bug is unrelated to a T5 apex RMSNorm memory leak." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "PyTorch-missing ImportError vs Trainer GPU broadcast NoneType TypeError; unrelated." }, { "left": "issue:43577", "right": "issue:43697", "accept": false, - "reason": "BLIP2 dtype propagation issue vs RTDetrV2 output mismatch; different models and symptoms." + "reason": "Dtype loading mismatch for BLIP2 is not the same as RT-DETR v5 output divergence." }, { "left": "issue:28282", - "right": "issue:32090", + "right": "issue:33357", "accept": false, - "reason": "Missing PyTorch ImportError vs Trainer NoneType broadcast error; unrelated causes." + "reason": "ImportError about missing PyTorch and a Mac bus error are unrelated." }, { "left": "issue:28282", - "right": "issue:33357", + "right": "issue:35141", "accept": false, - "reason": "Missing PyTorch library vs Mac bus error with CLIP; not the same problem." + "reason": "No common code path beyond generic loading/model usage." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Offline-model-info patch bug vs tokenizer load failure for a specific model; different failures." + "reason": "Both are tokenizer loading regressions, but they stem from different mechanisms and models." }, { "left": "issue:43646", "right": "issue:43749", "accept": false, - "reason": "Custom model init breakage in 5.0 vs FSDP RAM-efficient loading; separate features." + "reason": "Custom model init breakage and FSDP RAM-efficient loading are distinct failures." }, { - "left": "issue:28282", - "right": "issue:35141", + "left": "issue:43688", + "right": "issue:45701", "accept": false, - "reason": "ImportError for absent PyTorch vs embedding reinit during resize; unrelated regressions." - }, - { - "left": "issue:43688", - "right": "issue:45701", - "accept": false, - "reason": "Aux-loss normalization vs tokenization differences across versions; different layers of the stack." + "reason": "Aux-loss normalization in specific MoE models is not the same as a broad tokenization-version change." }, { "left": "issue:43653", "right": "issue:43927", "accept": false, - "reason": "BigBirdTokenizer special-token decode bug vs DiaConfig token-ID loss on save/load; different models and behavior." + "reason": "Tokenizer special-token decode bug and DiaConfig custom token ID persistence are different problems." }, { "left": "issue:43531", "right": "issue:43742", "accept": false, - "reason": "Qwen3-MoE sliding_window issue vs MobileLLM key error; unrelated model-specific bugs." + "reason": "Qwen3-MoE sliding-window logic and a MobileLLM key error are unrelated." }, { "left": "issue:43550", "right": "issue:43927", "accept": false, - "reason": "Bamba torch.compile/SDPA bug vs DiaConfig token-ID persistence bug; not the same code path." + "reason": "torch.compile SDPA failure and config token-ID persistence do not share the same fix path." }, { "left": "issue:44464", "right": "issue:44977", "accept": false, - "reason": "Compiled-forward chunked generation mismatch vs flash-attention generation bug; different generation paths." + "reason": "Both mention generation, but one is compiled-forward inconsistency and the other is flash-attention behavior in Qwen3.5." }, { "left": "issue:44479", "right": "issue:44625", "accept": false, - "reason": "Video-input regression vs num_labels propagation issue; different model components." - }, - { - "left": "issue:43577", - "right": "issue:44554", - "accept": false, - "reason": "BLIP2 dtype mismatch vs MPS attention correctness issue; unrelated bugs." + "reason": "Video input regression and num_labels propagation are separate issues." }, { "left": "issue:43550", "right": "issue:44361", "accept": false, - "reason": "Bamba compile/SDPA failure vs MLukeTokenizer task AttributeError; different subsystems." + "reason": "Different models and failure modes; no common underlying bug." }, { - "left": "issue:43577", - "right": "issue:45588", + "left": "issue:43122", + "right": "issue:43906", "accept": false, - "reason": "BLIP2 dtype issue vs flash_attention.py s_aux=None crash; unrelated failures." + "reason": "Generic tokenization change report vs an isolated reproduction of another issue." }, { - "left": "issue:43122", - "right": "issue:43906", + "left": "issue:43577", + "right": "issue:44554", "accept": false, - "reason": "Tokenization changes across versions vs isolated reproduction of another issue; not a duplicate." + "reason": "BLIP2 dtype loading bug and MPS attention correctness issue are unrelated." }, { - "left": "issue:43504", - "right": "issue:43550", + "left": "issue:43577", + "right": "issue:45588", "accept": false, - "reason": "BEiT legacy-field load bug vs Bamba torch.compile SDPA bug; different models and code paths." + "reason": "Different subsystems: dtype propagation vs flash_attention crash on sink-less models." }, { "left": "issue:43504", "right": "issue:43720", "accept": false, - "reason": "BEiT legacy-field load bug vs BitNet packed-weight unpacking bug; unrelated loading problems." + "reason": "Legacy-field model loading bug and packed-weight unpacking bug are different code paths." }, { - "left": "issue:41720", - "right": "issue:44464", + "left": "issue:43504", + "right": "issue:43550", "accept": false, - "reason": "Qwen3 device-mapping CUDA assert vs chunked generation inconsistency; different failure modes." + "reason": "Different model families and distinct loading/compile issues." }, { "left": "issue:32090", "right": "issue:34567", "accept": false, - "reason": "NoneType broadcast error in Trainer vs num_input_tokens_seen not updating; unrelated trainer issues." + "reason": "Trainer broadcast NoneType error vs token-count state not updating; not the same defect." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Auto device mapping cuda assert and chunked generation inconsistency are unrelated." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "BEiT pretrained-load legacy field vs OmDet-Turbo processor size mismatch; different model pipelines." + "reason": "Pretrained preset loading failure and processor size mismatch are separate bugs." }, { "left": "issue:32090", "right": "issue:33666", "accept": false, - "reason": "Trainer broadcast TypeError vs multi-GPU training request; not the same bug." + "reason": "Trainer GPU broadcast error and Qwen2-VL multi-GPU training question are not the same issue." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "gguf_file breaks AutoTokenizer/AutoModel loading vs specific model load failure; different root causes." - }, - { - "left": "issue:44849", - "right": "issue:45357", - "accept": false, - "reason": "Qwen3.5 hidden-states bug vs incorrect visual-encoder keys on save_pretrained; separate regressions." + "reason": "GGUF loading breakage and a model-specific tokenizer load failure are different root causes." }, { "left": "issue:43742", "right": "issue:44821", "accept": false, - "reason": "MobileLLM key error vs AutoImageProcessor URL-loading failure; unrelated loading paths." + "reason": "Model config loading key error vs AutoImageProcessor-from-URL failure." }, { "left": "issue:43278", "right": "issue:43688", "accept": false, - "reason": "Embedding dtype drift in evaluate vs auxiliary-loss normalization; different issues." - }, - { - "left": "issue:33666", - "right": "issue:36010", - "accept": false, - "reason": "Qwen2-VL multi-GPU training vs GenerationMixin import error; unrelated topics." + "reason": "Training/eval dtype mismatch is unrelated to MoE auxiliary-loss normalization." }, { "left": "issue:43493", "right": "issue:43825", "accept": false, - "reason": "SigLIP2 implementation discrepancy vs pipeline error-message wording; not the same bug." - }, - { - "left": "issue:43606", - "right": "issue:43927", - "accept": false, - "reason": "CPU offload device mismatch vs DiaConfig token-ID persistence; different models and code paths." - }, - { - "left": "issue:43525", - "right": "issue:43572", - "accept": false, - "reason": "Llama4Config missing pad_token_id vs StableLmConfig missing pad_token_idx; similar theme, but model-specific config regressions and not one concrete bug." + "reason": "SigLIP2 implementation discrepancy and an error-message wording bug are not the same bug." } ] }, @@ -6508,14 +6649,15 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:28218", "issue:33357", "issue:33666", + "issue:36010", "issue:36331", "issue:39692", "issue:43257", @@ -6526,45 +6668,48 @@ "issue:43334", "issue:43493", "issue:43504", + "issue:43525", "issue:43540", "issue:43572", "issue:43606", "issue:43646", - "issue:43653", "issue:43720", "issue:43756", "issue:43824", "issue:43844", "issue:43927", - "issue:43994", "issue:44291", "issue:44361", - "issue:44423", - "issue:44464", "issue:44466", "issue:44488", - "issue:44493", "issue:44568", "issue:44589", "issue:44625", - "issue:44734", "issue:44843", + "issue:44849", "issue:44913", "issue:44964", "issue:44977", "issue:45083", "issue:45200", "issue:45229", + "issue:45357", "issue:45405", "issue:45520", "issue:45584", "issue:45759", + "issue:45803", "issue:45812", - "issue:45823" + "issue:45823", + "issue:45987" ], "soft_pairs": [ + "issue:33666|issue:36010", + "issue:44849|issue:45357", + "issue:43606|issue:43927", "issue:44568|issue:45812", "issue:43720|issue:43927", + "issue:43525|issue:43572", "issue:43262|issue:43295", "issue:43756|issue:44913", "issue:43720|issue:44361", @@ -6574,248 +6719,251 @@ "issue:43540|issue:44977", "issue:43493|issue:43844", "issue:44964|issue:45405", + "issue:45803|issue:45987", "issue:43334|issue:43572", "issue:43278|issue:43844", "issue:44625|issue:45584", "issue:43257|issue:43299", "issue:43756|issue:45083", - "issue:43334|issue:45759", "issue:44488|issue:44843", "issue:45200|issue:45229", + "issue:43334|issue:45759", "issue:43824|issue:44589", - "issue:43646|issue:44466", "issue:39692|issue:43295", + "issue:43646|issue:44466", "issue:45229|issue:45823", "issue:43504|issue:43606", - "issue:44589|issue:45520", "issue:43572|issue:44291", + "issue:44589|issue:45520", "issue:33357|issue:33666", - "issue:44423|issue:44734", - "issue:43927|issue:44361", - "issue:43504|issue:43653", - "issue:44464|issue:45584", - "issue:43994|issue:44493" + "issue:43927|issue:44361" ], - "prepared_review_unit_hash": "cba50e2e792c8ae1e6fe36cf5636b5eef8a04156b1fd6f1717d0b12b862726b9", + "prepared_review_unit_hash": "996e68aed3375b661a22c6be681166785e69cdfe3ec414640df964eab05a2ce8", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37647, - "estimated_input_tokens": 9412, - "estimated_eval_tokens": 19080 + "soft_pair_count": 33, + "serialized_chars": 37873, + "estimated_input_tokens": 9469, + "estimated_eval_tokens": 19194 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is a loose collection of unrelated Transformers issues. The soft pairs mostly share subsystem keywords (tokenizers, multimodal configs, model loading, training) but describe different bugs and fixes, so none should be merged as duplicates.", - "confidence": 0.66, - "canonical_issue_reason": "issue:45812 is the strongest representative because it\u2019s a broad, user-facing tokenizer regression affecting many Granite models and has clear cross-model impact.", + "summary": "The soft pairs are broadly heterogeneous; none look like the same underlying bug or change, so no duplicates should be merged.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45812 is the best overall issue to anchor the cluster since it is specific, high-impact, and most likely to attract the right tokenizer-focused triage.", + "best_issue_reason": "issue:45812 is the best canonical-style issue: it is open, broad in impact, and clearly describes a specific regression with multiple references.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Different problems: Qwen2-VL training vs a GenerationMixin import failure." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is output_hidden_states behavior and the other is save_pretrained key serialization." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to DiaConfig token ID loss on save/load." + }, { "left": "issue:44568", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but one is about add_special_tokens/BOS-EOS behavior for mdeberta and the other is wrong token IDs for Granite models; different code paths and symptoms." + "reason": "Tokenizer regressions, but different models and different failure modes." }, { "left": "issue:43720", "right": "issue:43927", "accept": false, - "reason": "Packed-weight unpacking during accelerate loading and DiaConfig save/load token ID loss are unrelated bugs." + "reason": "BitNet accelerate loading bug is unrelated to DiaConfig token serialization." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both involve missing pad token fields, but they affect different configs and code paths." }, { "left": "issue:43262", "right": "issue:43295", "accept": false, - "reason": "Audio chat-template sampling rate defaults and processor.tokenizer/image-handling regression are different multimodal issues." + "reason": "Audio chat template sampling-rate default is unrelated to processor.tokenizer/image handling." }, { "left": "issue:43756", "right": "issue:44913", "accept": false, - "reason": "Smollm3 RoPE-layer omission and GPTNeoX rotary_pct reload fallback are separate configuration bugs." + "reason": "One is a RoPE layer-count bug, the other is config reload losing rotary_pct." }, { "left": "issue:43720", "right": "issue:44361", "accept": false, - "reason": "BitNet packed-weight loading and MLukeTokenizer task AttributeError do not share the same underlying failure." + "reason": "Packed-weight loading and tokenizer AttributeError are different bugs." }, { "left": "issue:28218", "right": "issue:33357", "accept": false, - "reason": "Tokenizer spacing after added tokens and a MacOS bus error in CLIP are clearly unrelated." + "reason": "Tokenizer spacing bug and MacOS bus error are unrelated." }, { "left": "issue:33666", "right": "issue:36331", "accept": false, - "reason": "Qwen2-VL multi-GPU training and a CustomTrainer signature mismatch are different training issues." + "reason": "Multi-GPU training support is unrelated to compute_loss signature mismatch." }, { "left": "issue:39692", "right": "issue:43493", "accept": false, - "reason": "SigLIP2 docs/example errors and SigLIP2 HF-vs-JAX implementation discrepancies are not the same bug." + "reason": "Same model family, but doc example mistakes are not the same as implementation discrepancies." }, { "left": "issue:43540", "right": "issue:44977", "accept": false, - "reason": "Qwen3OmniMoe video-input processing and Qwen3.5 flash-attention generation problems are distinct code paths." + "reason": "Video input processing in Qwen3OmniMoe is unrelated to flash-attention generation issues." }, { "left": "issue:43493", "right": "issue:43844", "accept": false, - "reason": "A model implementation discrepancy and a DeepSpeed gradient anomaly are different failures." + "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient growth are unrelated." }, { "left": "issue:44964", "right": "issue:45405", "accept": false, - "reason": "Phi-4 multimodal load failure and a bumped unreleased PEFT minimum version are unrelated." + "reason": "Model loading failure and an unreleased PEFT version bump are unrelated." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except in tensor conversion is unrelated to StaticCache return-type mismatch." }, { "left": "issue:43334", "right": "issue:43572", "accept": false, - "reason": "Both involve config fields, but Qwen3-VL pad_token_id and StableLmConfig pad_token_idx are separate model-specific regressions." + "reason": "Both mention missing token IDs, but they are different model/config regressions." }, { "left": "issue:43278", "right": "issue:43844", "accept": false, - "reason": "Embedding dtype drift in eval and gradient growth under ZeRO-3 are unrelated symptoms." + "reason": "Embedding dtype drift and gradient instability under ZeRO-3 are different issues." }, { "left": "issue:44625", "right": "issue:45584", "accept": false, - "reason": "Qwen3.5 num_labels propagation and Whisper empty transcription after align_special_tokens are different model families and bugs." + "reason": "Qwen3.5 num_labels propagation is unrelated to Whisper empty-transcription behavior." }, { "left": "issue:43257", "right": "issue:43299", "accept": false, - "reason": "Both are Qwen MOE loading issues, but one is about accelerate/deepspeed weight conversion and the other is a dev-version model-loading breakage for multimodal configs." + "reason": "Both involve Qwen MoE loading, but the concrete failure modes and model variants differ." }, { "left": "issue:43756", "right": "issue:45083", "accept": false, - "reason": "RoPE-layer dropping in Smollm3 and qwen3_omni_moe feature-length helper behavior are unrelated." - }, - { - "left": "issue:43334", - "right": "issue:45759", - "accept": false, - "reason": "Pad-token-id missing in Qwen3-VL and failing to unwrap text_config in composite Qwen configs are different multimodal config problems." + "reason": "RoPE-layer truncation and feature-length helper behavior are unrelated." }, { "left": "issue:44488", "right": "issue:44843", "accept": false, - "reason": "A model failing to load and an unconditional hub API call breaking offline mode are separate issues." + "reason": "Model load failure and offline model_info regression are different code paths." }, { "left": "issue:45200", "right": "issue:45229", "accept": false, - "reason": "Text-only mm_token_type_ids defaults and Gemma4 multi-GPU OOM are not the same defect." + "reason": "Text-only mm_token_type_ids defaulting and multi-GPU CUDA OOM are unrelated." }, { - "left": "issue:43824", - "right": "issue:44589", + "left": "issue:43334", + "right": "issue:45759", "accept": false, - "reason": "Importing Qwen2.5-VL class and missing Float8 storage support are unrelated runtime errors." + "reason": "Missing pad_token_id and text_config unwrapping are different multimodal config bugs." }, { - "left": "issue:43646", - "right": "issue:44466", + "left": "issue:43824", + "right": "issue:44589", "accept": false, - "reason": "Custom model initialization breakage and inconsistent lm_head.weight serialization are different v5 regressions." + "reason": "Import error for a model class is unrelated to Float8 storage lookup failure." }, { "left": "issue:39692", "right": "issue:43295", "accept": false, - "reason": "Doc/example mistakes and a processor.tokenizer regression are not the same underlying bug." + "reason": "Documentation example errors are unrelated to processor.tokenizer regression." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model init breakage and lm_head serialization inconsistency are different regressions." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "Gemma4 inference OOM and a device mismatch during forward are distinct multi-GPU/runtime failures." + "reason": "OOM during inference and a device mismatch bug are not the same failure." }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Legacy field loading in Beit semantic segmentation and Bark CPU-offload device mismatch are unrelated." - }, - { - "left": "issue:44589", - "right": "issue:45520", - "accept": false, - "reason": "Float8 storage lookup failure and a Python 3.13 flash_attn import-utils KeyError are different compatibility issues." + "reason": "Legacy-field load failure in BEiT is unrelated to bark-small CPU offload issues." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "StableLmConfig pad_token_idx regression and init_empty_weights unexpected _is_hf_initialized argument are separate API breakages." + "reason": "Missing pad_token_idx and unexpected _is_hf_initialized are separate loading regressions." }, { - "left": "issue:33357", - "right": "issue:33666", + "left": "issue:44589", + "right": "issue:45520", "accept": false, - "reason": "MacOS bus error in a CLIP community model and Qwen2-VL multi-GPU training are unrelated." + "reason": "Float8 storage lookup and flash_attn KeyError are unrelated." }, { - "left": "issue:44423", - "right": "issue:44734", + "left": "issue:33357", + "right": "issue:33666", "accept": false, - "reason": "Continuous-batching multimodal crash and KV-cache continuation indexing bug affect different serve paths." + "reason": "MacOS bus error on CLIP and Qwen2-VL multi-GPU training are unrelated." }, { "left": "issue:43927", "right": "issue:44361", "accept": false, - "reason": "DiaConfig custom-token-ID loss and MLukeTokenizer task AttributeError are unrelated model/tokenizer bugs." - }, - { - "left": "issue:43504", - "right": "issue:43653", - "accept": false, - "reason": "Beit legacy-field loading and BigBirdTokenizer special-token registration are different fixes." - }, - { - "left": "issue:44464", - "right": "issue:45584", - "accept": false, - "reason": "Compiled-forward chunked generation inconsistency and Whisper empty-transcription failure after align_special_tokens are different generation bugs." - }, - { - "left": "issue:43994", - "right": "issue:44493", - "accept": false, - "reason": "SigLIP2 bad results with AutoModel/pipeline and unexpected position-id keys across models are not the same issue." + "reason": "Config token persistence bug and MLukeTokenizer task AttributeError are different issues." } ] }, @@ -6834,10 +6982,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:15354", "issue:28218", @@ -6851,45 +6999,48 @@ "issue:43278", "issue:43295", "issue:43493", + "issue:43504", "issue:43540", - "issue:43572", "issue:43575", "issue:43582", "issue:43606", + "issue:43653", "issue:43696", "issue:43701", "issue:43844", - "issue:43873", "issue:43957", + "issue:43994", "issue:44112", "issue:44315", + "issue:44423", "issue:44464", - "issue:44466", + "issue:44493", "issue:44521", "issue:44554", "issue:44610", + "issue:44734", "issue:44792", "issue:44849", - "issue:44898", "issue:44964", "issue:44977", - "issue:44987", "issue:45072", "issue:45084", - "issue:45127", "issue:45198", "issue:45200", "issue:45290", "issue:45356", "issue:45405", - "issue:45412", "issue:45446", "issue:45520", - "issue:45563", + "issue:45584", "issue:45823" ], "soft_pairs": [ + "issue:44423|issue:44734", + "issue:43504|issue:43653", + "issue:44464|issue:45584", "issue:43606|issue:44112", + "issue:43994|issue:44493", "issue:43575|issue:45405", "issue:43278|issue:43701", "issue:44792|issue:45405", @@ -6908,205 +7059,194 @@ "issue:37428|issue:43957", "issue:45200|issue:45823", "issue:44315|issue:44849", - "issue:44554|issue:45356", - "issue:43295|issue:44610", "issue:43493|issue:43701", - "issue:43873|issue:44464", - "issue:44898|issue:45412", - "issue:44466|issue:45127", - "issue:44792|issue:45563", - "issue:43572|issue:44987" + "issue:43295|issue:44610", + "issue:44554|issue:45356" ], - "prepared_review_unit_hash": "6176ccff03352acb63903f83a924bd52aba9c06698ddee6dd706792a6a56f7ba", + "prepared_review_unit_hash": "e3f355efbedb0a8e6c7c661c0628ffec379763b934922cc42472b212446efbc7", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 35782, - "estimated_input_tokens": 8946, - "estimated_eval_tokens": 18148 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 34969, + "estimated_input_tokens": 8743, + "estimated_eval_tokens": 17742 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the issues span unrelated tokenizer, generation, loading, device, quantization, and CI problems. All soft pairs look like superficial text similarity rather than the same underlying bug/change, so there is no dedupe-worthy canonical artifact here.", - "confidence": 0.98, - "canonical_issue_reason": "No single canonical issue: the items cover many different models, subsystems, and failure modes, with only broad keyword overlap.", + "summary": "This set is mostly a grab-bag of unrelated Transformers bug reports across tokenization, generation, multimodal processing, device/dtype issues, and CI failures. None of the soft pairs look like true duplicates of the same underlying bug; a few are superficially similar but differ in concrete failure mode or code path.", + "confidence": 0.62, + "canonical_issue_reason": "issue:44521 is the most central active report in the only loosely related multimodal/chat-template subgroup and has inbound references, making it the best representative issue for this mixed cluster.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a good global representative because there is no shared defect to anchor a canonical duplicate cluster.", + "best_issue_reason": "issue:44521 is the strongest issue anchor here: open, referenced by others, and thematically closest to several multimodal/tokenization reports without being too specific.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve/runtime generation crashes, but one is a multimodal `.to()` attribute error and the other is KV-cache tensor indexing; different bugs." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "BEiT legacy-field loading and BigBirdTokenizer special-token decoding are unrelated subsystems and failure modes." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is not the same as empty-transcription failure after `align_special_tokens`." + }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "Both mention device-related failures, but one is CPU offload mismatch on a specific model and the other is a stale CI device-override test; different bugs and code paths." + "reason": "Both mention device mismatch, but one is a real CPU-offload bug and the other is a stale CI test for GraniteSpeech." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 output discrepancies and unexpected position-id keys are different model behaviors with no shared code-path evidence." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "OOM during tensor-parallel loading is unrelated to a packaging/version bump for MIN_PEFT_VERSION." + "reason": "Tensor-parallel OOM for a model load and an unmet PEFT version requirement are unrelated." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "BF16-to-FP32 dtype drift in evaluation is unrelated to a resume_from_checkpoint key mismatch." + "reason": "BF16/FP32 dtype drift in evaluation is not the same as resume-from-checkpoint key mismatch." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "A Janus image-generation test failure has no meaningful relation to the PEFT version requirement issue." + "reason": "Janus image-generation test failure and PEFT version pinning are unrelated." }, { "left": "issue:44521", "right": "issue:45290", "accept": false, - "reason": "Both involve chat template processing, but one is zeroed assistant masks for multimodal inputs while the other is a crash on tool-call assistant messages; not the same bug." + "reason": "Both touch `apply_chat_template`, but one is all-zero assistant masks for multimodal inputs while the other is a crash on tool-call assistant messages; different defects." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Flash Attention 2 test failures and MLflow reporting after training failure are unrelated." + "reason": "Flash Attention 2 test failures and MLflow job-status reporting are different CI/training issues." }, { "left": "issue:42490", "right": "issue:43696", "accept": false, - "reason": "Local-path import warning and CUDA OOM on GPT-oss are different loading/runtime issues." + "reason": "Import warning for trailing-slash local paths is unrelated to CUDA OOM on GPT-oss-20b." }, { "left": "issue:43844", "right": "issue:44964", "accept": false, - "reason": "DeepSpeed ZeRO-3 gradient growth and Phi-4 multimodal loading failure do not share a concrete code path." + "reason": "ZeRO-3 gradient explosion and Phi-4 multimodal load failure are different problems." }, { "left": "issue:28218", "right": "issue:34567", "accept": false, - "reason": "Tokenizer spacing after added tokens is unrelated to TrainerState token-count tracking." + "reason": "Tokenizer extra-space behavior and TrainerState token-count updates do not describe the same bug." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "An MPS attention correctness bug is unrelated to a PyTorch version check in flex_attention imports." + "reason": "MPS attention correctness and a PyTorch version check in flex_attention are unrelated." }, { "left": "issue:45084", "right": "issue:45520", "accept": false, - "reason": "Template compilation errors and a flash_attn import KeyError on Python 3.13 are different failures." + "reason": "Non-template-node compilation error and missing `flash_attn` import key on Python 3.13 are different import/runtime issues." }, { "left": "issue:43582", "right": "issue:44977", "accept": false, - "reason": "An Apple Silicon allocator TypeError and a flash-attention generation bug are not the same underlying issue." + "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention generation bug are separate platform/model issues." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Video-input processing in Qwen3OmniMoe and missing mm_token_type_ids in Gemma 4 are different multimodal bugs." + "reason": "Video-input processing error in Qwen3OmniMoe and Gemma4 token-type defaults are not the same underlying bug." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "TorchScript generator-expression support and zero probabilities in SigLIP2 are unrelated." + "reason": "TorchScript GeneratorExp export failure and SigLIP2 zero probabilities are different vision-model issues." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs update after sync_gpus is unrelated to the Qwen3.5 hidden-states bug." + "reason": "Generation kwargs update after `sync_gpus` and Qwen3.5 hidden-states output are distinct generation-path bugs." }, { "left": "issue:45072", "right": "issue:45198", "accept": false, - "reason": "Bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel are unrelated to Wav2Vec2 save_pretrained/tokenization failures." + "reason": "bfloat16 dtype mismatches in inference and Wav2Vec2 save/tokenization failures are unrelated." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "A missing flash attention import symbol and meta-device model loading breakage are different regression classes." + "reason": "Missing flash-attention helper import and meta-device loading breakage are different compatibility issues." }, { "left": "issue:45200", "right": "issue:45823", "accept": false, - "reason": "Gemma 4 text-only fine-tuning mask defaults and a device_map='auto' forward mismatch are separate issues." + "reason": "Gemma4 text-only token-type defaults and PLE device mismatch with `device_map=\"auto\"` are separate forward-pass problems." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger Kernel not applying with model_init is unrelated to the Qwen3.5 hidden-states bug." - }, - { - "left": "issue:44554", - "right": "issue:45356", - "accept": false, - "reason": "MPS attention correctness and Kimi-K2.5 tokenizer codec regression do not share the same bug surface." - }, - { - "left": "issue:43295", - "right": "issue:44610", - "accept": false, - "reason": "Processor/tokenizer regression with images is different from OmDet-Turbo's image-size mismatch." + "reason": "Liger Kernel not applied in `model_init` is unrelated to Qwen3.5 hidden-state output behavior." }, { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "SigLIP2 HF-vs-JAX discrepancy is unrelated to resume_from_checkpoint key mismatch." - }, - { - "left": "issue:43873", - "right": "issue:44464", - "accept": false, - "reason": "Quantization/offloading behavior and chunked generation with compiled forward are distinct problems." - }, - { - "left": "issue:44898", - "right": "issue:45412", - "accept": false, - "reason": "Perceiver non-default resolution failure is unrelated to RT-DETR memory release issues." - }, - { - "left": "issue:44466", - "right": "issue:45127", - "accept": false, - "reason": "Serialization of tied lm_head weights and LoRA merge collapse with extended vocab are not the same concrete defect." + "reason": "SigLIP2 HF-vs-JAX discrepancy and checkpoint resume key mismatch are not the same bug." }, { - "left": "issue:44792", - "right": "issue:45563", + "left": "issue:43295", + "right": "issue:44610", "accept": false, - "reason": "A Janus image-generation test failure is unrelated to a stale warning in paged generate()." + "reason": "Processor/tokenizer regression for multimodal custom code and OmDet-Turbo image-size mismatch are different processor bugs." }, { - "left": "issue:43572", - "right": "issue:44987", + "left": "issue:44554", + "right": "issue:45356", "accept": false, - "reason": "A missing StableLmConfig pad_token_idx after a 5.0 update is not the same as loading physical-intelligence/fast failing on transformers>=5.1.0." + "reason": "MPS attention correctness issue and Kimi tokenizer codec regression are unrelated." } ] }, @@ -7125,10 +7265,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:28218", "issue:35141", @@ -7141,14 +7281,12 @@ "issue:43295", "issue:43334", "issue:43388", - "issue:43425", "issue:43450", "issue:43493", "issue:43525", "issue:43526", "issue:43572", "issue:43575", - "issue:43606", "issue:43653", "issue:43819", "issue:43824", @@ -7162,29 +7300,36 @@ "issue:44112", "issue:44206", "issue:44442", + "issue:44466", "issue:44514", "issue:44521", "issue:44610", + "issue:44792", "issue:44857", + "issue:44898", "issue:44936", + "issue:44987", "issue:45083", "issue:45127", "issue:45198", "issue:45200", "issue:45245", - "issue:45290", "issue:45325", - "issue:45381", "issue:45412", + "issue:45563", "issue:45584" ], "soft_pairs": [ - "issue:37428|issue:43824", - "issue:45200|issue:45325", - "issue:43572|issue:43957", + "issue:44898|issue:45412", + "issue:44466|issue:45127", + "issue:44792|issue:45563", + "issue:43572|issue:44987", + "issue:45200|issue:45325", + "issue:43572|issue:43957", + "issue:37428|issue:43824", "issue:43844|issue:44936", - "issue:43334|issue:43525", "issue:43295|issue:43450", + "issue:43334|issue:43525", "issue:43824|issue:43975", "issue:43295|issue:43873", "issue:43388|issue:43526", @@ -7204,213 +7349,216 @@ "issue:43819|issue:45083", "issue:43819|issue:44112", "issue:43262|issue:43450", - "issue:44610|issue:44857", - "issue:37428|issue:43425", - "issue:45290|issue:45381", - "issue:43606|issue:45083" + "issue:44610|issue:44857" ], - "prepared_review_unit_hash": "17576ae4d099c4a9556ce8d1e0e7903c430f386680be48fbdb3bdb9347eec6bd", + "prepared_review_unit_hash": "03f6cf3f0514350557fb16e8e0ae9058a824da5400dc878b8a0d08eeb84e0790", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 36009, - "estimated_input_tokens": 9003, - "estimated_eval_tokens": 18262 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36949, + "estimated_input_tokens": 9238, + "estimated_eval_tokens": 18732 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is highly heterogeneous; most soft pairs are only loosely related by broad subsystem wording (imports, processors, tokenization, chat templates) and do not look like the same underlying bug. No PRs are present. If a single issue must serve as the anchor, issue 44521 is the most representative active user-facing bug in the list.", - "confidence": 0.72, - "canonical_issue_reason": "Issue 44521 is the most central and active item here, with multiple references and discussion around apply_chat_template/multimodal masking behavior.", + "summary": "These items do not form a true duplicate cluster; they span unrelated tokenizer, import, processor, training, and model-specific bugs. I reject all soft edges and pick the most concrete, well-documented issue as the best standalone representative.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43824 is the strongest standalone report here: it has the highest engagement, a precise import failure, and a clear reproduction path.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44521 is the best global representative because it is open, user-facing, and closest to a recurring processor/chat_template bug family in this set.", + "best_issue_reason": "issue:43824 is the best issue candidate because it is specific, broadly actionable, and better evidenced than the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:37428", - "right": "issue:43824", + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Different bugs: Perceiver resolution handling vs RT-DETR memory cleanup." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both involve weights/serialization, but one is device-dependent lm_head serialization and the other is LoRA merge collapse." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to a stale generate() warning." + }, + { + "left": "issue:43572", + "right": "issue:44987", "accept": false, - "reason": "Both are import errors, but they fail on different missing symbols in different code paths; not the same bug." + "reason": "StableLm pad_token_idx regression is unrelated to loading physical-intelligence/fast." }, { "left": "issue:45200", "right": "issue:45325", "accept": false, - "reason": "One is about mm_token_type_ids defaults, the other about rope/position-id scaling; unrelated." + "reason": "Gemma 4 token-type defaults and Qwen2.5-VL temporal rope scaling are different code paths." }, { "left": "issue:43572", "right": "issue:43957", "accept": false, - "reason": "A config attribute regression vs a broad meta-device loading breakage; different underlying failures." + "reason": "Missing pad_token_idx in StableLmConfig is not the same as meta-device model loading failures." }, { - "left": "issue:43844", - "right": "issue:44936", + "left": "issue:37428", + "right": "issue:43824", "accept": false, - "reason": "Different training/evaluation problems with no shared concrete code path." + "reason": "Different missing imports in different modules and model families." }, { - "left": "issue:43334", - "right": "issue:43525", + "left": "issue:43844", + "right": "issue:44936", "accept": false, - "reason": "Both mention missing pad_token_id, but they affect different configs/models and are separate bugs." + "reason": "DeepSpeed gradient growth and trainer.evaluate() failure are unrelated training issues." }, { "left": "issue:43295", "right": "issue:43450", "accept": false, - "reason": "Custom processor-tokenizer regression vs batched video processor shape bug; not the same change." + "reason": "Processor.tokenizer regression with images is not the same as batched video shape output." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Both mention pad_token_id, but they are separate model configs and not clearly one bug." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "Both are import/usage regressions, but for different classes and APIs; not the same issue." + "reason": "Import error for Qwen2.5-VL is unrelated to DeepSeek detokenization." }, { "left": "issue:43295", "right": "issue:43873", "accept": false, - "reason": "Processor API regression vs quantization/offloading behavior; unrelated." + "reason": "Processor API regression is not the same as quantization/offloading behavior." }, { "left": "issue:43388", "right": "issue:43526", "accept": false, - "reason": "Both involve labels, but one is distributed metric gathering and the other is image processor label reduction; different code paths." + "reason": "Both are label-handling bugs, but in different utilities with different failure modes." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "Both are memory/resource concerns, but one is model output probabilities and the other is deletion/GC memory release." + "reason": "SigLIP2 numerical issue and RT-DETR memory retention are unrelated." }, { "left": "issue:42915", "right": "issue:43824", "accept": false, - "reason": "Qwen3Moe FP8 failure is unrelated to an import error for a VL model symbol." + "reason": "Qwen3Moe FP8 config failure is unrelated to a Qwen2.5-VL import error." }, { "left": "issue:44514", "right": "issue:44521", "accept": false, - "reason": "Both touch apply_chat_template, but one is a batched-input crash and the other is incorrect assistant_mask generation; not clearly the same bug." + "reason": "Batched padding crash and zero assistant masks are different apply_chat_template failures." }, { "left": "issue:38175", "right": "issue:43493", "accept": false, - "reason": "Different SigLIP2 issues with different symptoms and likely different implementation defects." + "reason": "SigLIP2 implementation discrepancy is not the same as a separate vision-model processor bug." }, { "left": "issue:44442", "right": "issue:45198", "accept": false, - "reason": "Different tokenizer/model families with separate tokenization/save_pretrained failures." + "reason": "Different tokenizer failures for different model families and different operations." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing after added tokens is unrelated to embedding reinitialization during resize." + "reason": "Tokenizer spacing bug is unrelated to embedding reinitialization after resize." }, { "left": "issue:43278", "right": "issue:43856", "accept": false, - "reason": "Both mention training efficiency or dtype, but they are distinct issues in different contexts." + "reason": "Embedding dtype drift in eval is unrelated to Qwen3 MoE memory usage." }, { "left": "issue:42490", "right": "issue:43493", "accept": false, - "reason": "Import warning on local paths vs SigLIP2 implementation mismatch; different behavior." + "reason": "Local-path import warning is unrelated to SigLIP2 implementation discrepancy." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "Tokenizer special-token registration bug vs a CI device-override test failure; unrelated." + "reason": "BigBirdTokenizer special-token registration and GraniteSpeech CI failure are different issues." }, { "left": "issue:43827", "right": "issue:43901", "accept": false, - "reason": "Both are docs issues, but they target different API removals and different pipeline docs." + "reason": "Both are docs-related, but they concern different pipeline APIs and different behavior changes." }, { "left": "issue:43450", "right": "issue:43575", "accept": false, - "reason": "Video processor shape bug vs tensor-parallel OOM on model loading; not the same problem." + "reason": "Batched video output shape and Qwen2-57B TP OOM are unrelated." }, { "left": "issue:44206", "right": "issue:45584", "accept": false, - "reason": "Both are audio-related, but one is an unsupported argument in a feature extractor and the other is empty-transcription generation behavior." + "reason": "Feature-extractor center-arg regression and Whisper empty-transcription failure are different code paths." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA/extended-vocab collapse is unrelated to the categories limit runtime error." + "reason": "LoRA merge/tied-weights collapse is unrelated to category-count limits." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "DAC latent reconstruction mismatch vs a helper-length calculation issue in qwen3_omni_moe; different bugs." + "reason": "DAC latent/STE mismatch is unrelated to Qwen3 Omni MoE feature-length helper behavior." }, { "left": "issue:43819", "right": "issue:44112", "accept": false, - "reason": "No shared underlying code path; audio codec mismatch vs stale CI test." + "reason": "Different subsystems: DAC quantization logic vs GraniteSpeech device override test." }, { "left": "issue:43262", "right": "issue:43450", "accept": false, - "reason": "Audio chat-template sampling-rate default vs video batch shape regression; unrelated." + "reason": "Audio chat-template sampling-rate default and batched video processor shape are unrelated." }, { "left": "issue:44610", "right": "issue:44857", "accept": false, - "reason": "Different detection/image-processing failures with different symptoms and likely fixes." - }, - { - "left": "issue:37428", - "right": "issue:43425", - "accept": false, - "reason": "A missing symbol import error is not the same as generic Torch 2.10 incompatibility." - }, - { - "left": "issue:45290", - "right": "issue:45381", - "accept": false, - "reason": "One is a chat-template/tool-call crash, the other is a Qwen2.5-VL position-id bug; not the same issue." - }, - { - "left": "issue:43606", - "right": "issue:45083", - "accept": false, - "reason": "CPU offload device mismatch is unrelated to feature-extraction output length behavior." + "reason": "Processor image-size mismatch and AMP/CUDA loss crash are different bugs." } ] }, @@ -7429,23 +7577,21 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:29127", "issue:29942", "issue:32090", - "issue:34689", - "issue:35141", "issue:37428", "issue:38175", "issue:39692", - "issue:40444", "issue:42490", "issue:43278", "issue:43335", + "issue:43425", "issue:43504", "issue:43526", "issue:43550", @@ -7475,7 +7621,9 @@ "issue:45083", "issue:45200", "issue:45229", + "issue:45290", "issue:45310", + "issue:45381", "issue:45478", "issue:45520", "issue:45588", @@ -7484,286 +7632,279 @@ "issue:45859" ], "soft_pairs": [ + "issue:37428|issue:43425", + "issue:45290|issue:45381", "issue:43335|issue:43550", + "issue:43606|issue:45083", "issue:44448|issue:44743", "issue:44857|issue:45593", "issue:45200|issue:45588", "issue:44360|issue:44561", "issue:43278|issue:43825", - "issue:37428|issue:44351", "issue:29942|issue:32090", - "issue:44206|issue:45823", + "issue:37428|issue:44351", "issue:43611|issue:43931", + "issue:44206|issue:45823", "issue:39692|issue:43526", "issue:43335|issue:43653", "issue:43819|issue:44493", "issue:43550|issue:44112", - "issue:44855|issue:45083", "issue:43335|issue:43504", "issue:45310|issue:45478", + "issue:44855|issue:45083", "issue:43335|issue:45083", "issue:29127|issue:32090", "issue:45588|issue:45859", "issue:39692|issue:44493", "issue:44292|issue:45520", - "issue:38175|issue:44493", "issue:44448|issue:44779", + "issue:38175|issue:44493", "issue:43335|issue:45072", "issue:44462|issue:44561", "issue:44561|issue:44779", "issue:43720|issue:44112", "issue:43335|issue:45593", "issue:44977|issue:45229", - "issue:42490|issue:43854", - "issue:40444|issue:43526", - "issue:44448|issue:44977", - "issue:34689|issue:35141", - "issue:43606|issue:44857" + "issue:42490|issue:43854" ], - "prepared_review_unit_hash": "bd6f8d5671147a30a964f89015d1b612adb37f6e9acf80e8056efc6b37638406", + "prepared_review_unit_hash": "7653befb2093dfb26871099e882f47404bdf00e442b3a4a8eb1530bdb3c08198", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 38236, - "estimated_input_tokens": 9559, - "estimated_eval_tokens": 19374 + "soft_pair_count": 34, + "serialized_chars": 37851, + "estimated_input_tokens": 9463, + "estimated_eval_tokens": 19182 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a false-positive grouping of unrelated Transformer bug reports. The only clear duplicate pair is the two identical Qwen3.5 MoE `from_pretrained` regression issues; the rest differ by model, subsystem, or root cause.", - "confidence": 0.9, - "canonical_issue_reason": "issue:45310 is the best canonical issue because it appears to be the earlier and slightly more detailed report for the exact same Qwen3.5 MoE `from_pretrained` failure as issue:45478.", + "summary": "This cluster is mostly heterogeneous and does not look like a single duplicate set. The only clear duplicate soft edge is the Qwen3.5 MoE from_pretrained regression pair; the rest are distinct bugs/regressions across unrelated code paths.", + "confidence": 0.61, + "canonical_issue_reason": "issue:43611 is the broadest, clearest user-facing regression in this set: model loading breaks generically for models using `base_model_prefix`, which makes it a strong cluster anchor.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the strongest representative of the cluster\u2019s only true duplicate pair and has the clearest tie to the shared regression.", + "best_issue_reason": "issue:43611 is the most representative and broadly applicable issue here, with a concrete loading-path failure that could plausibly attract related duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "Flash-attention import failure vs a general Torch 2.10 compatibility issue; different root causes." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Chat template crash on tool-call messages vs Qwen2.5-VL video position-id bug; unrelated code paths." + }, { "left": "issue:43335", "right": "issue:43550", "accept": false, - "reason": "Different models and failures: SwitchTransformers sparse-layer config bug vs Bamba torch.compile/SDPA issue." + "reason": "SwitchTransformers sparse-layer config bug vs Bamba torch.compile/SDPA failure; not the same bug." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch in bark-small vs qwen3_omni_moe output-length helper behavior; different failures." }, { "left": "issue:44448", "right": "issue:44743", "accept": false, - "reason": "Pegasus v4/v5 output drift is unrelated to Qwen recurrent-state cache resetting." + "reason": "Pegasus v4/v5 output regression vs recurrent-state reset in modular_qwen3_5; separate model issues." }, { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "Different detection losses with distinct failure modes; not the same bug." + "reason": "AMP/CUDA loss crash vs missing auxiliary losses when denoising is off; unrelated functionality." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma4 text-only mm_token_type_ids defaulting issue is unrelated to flash_attention sink-less model attribute handling." + "reason": "Gemma4 token-type defaulting issue vs flash_attention s_aux=None crash; different affected components." }, { "left": "issue:44360", "right": "issue:44561", "accept": false, - "reason": "DSA ReLU discussion and removal of `is_torch_fx_available` breaking trust_remote_code are unrelated." + "reason": "DSA indexer ReLU comment vs removal of `is_torch_fx_available`; no shared underlying defect." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "BF16/FP32 dtype regression is unrelated to the pipeline translation-task error message." - }, - { - "left": "issue:37428", - "right": "issue:44351", - "accept": false, - "reason": "Both are import errors, but for different missing symbols and likely different fixes." + "reason": "BF16-to-FP32 eval dtype drift vs pipeline translation error messaging; not the same problem." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention 2 test failures are not the same as the Trainer `_gpu_broadcast_one` NoneType error." + "reason": "Flash Attention 2 test failures vs `_gpu_broadcast_one` NoneType error in Trainer; distinct issues." }, { - "left": "issue:44206", - "right": "issue:45823", + "left": "issue:37428", + "right": "issue:44351", "accept": false, - "reason": "Different models and different runtime problems; no shared code-path bug." + "reason": "Missing `_flash_supports_window_size` import vs missing `HybridCache` import; separate import regressions." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "General base_model_prefix loading breakage is not the same as Qwen3-VL weight-shape mismatch." + "reason": "Generic model-loading regression vs Qwen3-VL weight-shape mismatch; different failure modes." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "LaserFeatureExtractor `center` arg crash vs Gemma4 PLE device mismatch; unrelated." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "SigLIP2 docs errors and BEiT reduce_labels bug are unrelated." + "reason": "SigLIP2 docs example problems vs BeitImageProcessorFast `reduce_labels` bug; different artifacts." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "SwitchTransformers sparse-layer creation is unrelated to BigBird tokenizer special-token decode failure." + "reason": "SwitchTransformers sparse-layer creation bug vs BigBirdTokenizer special-token decode issue; not the same underlying bug." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "DAC latent/STE mismatch is unrelated to the position-id key warning." + "reason": "DAC `from_latents` mismatch vs unexpected position-id key behavior; unrelated model internals." }, { "left": "issue:43550", "right": "issue:44112", "accept": false, - "reason": "Bamba SDPA compile issue is unrelated to a GraniteSpeech stale device override test failure." - }, - { - "left": "issue:44855", - "right": "issue:45083", - "accept": false, - "reason": "Python 3.13 import indentation/script parsing bug is unrelated to qwen3_omni_moe feature-length helper behavior." + "reason": "Bamba SDPA/compile bug vs GraniteSpeech stale device-override CI failure; different scopes." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "Different models and different configuration/loading bugs." + "reason": "SwitchTransformers sparse-layer config issue vs Beit semantic-segmentation legacy-field loading issue; separate bugs." }, { "left": "issue:45310", "right": "issue:45478", "accept": true, - "reason": "Exact same title and same Qwen3.5 MoE `from_pretrained` error; these look like duplicate reports of the same bug." + "reason": "Same title and same Qwen3.5 MoE from_pretrained failure; these appear to be duplicates of the same regression." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 IndentationError in DebertaV2Model import vs qwen3_omni_moe feature-length helper bug; unrelated." }, { "left": "issue:43335", "right": "issue:45083", "accept": false, - "reason": "Unrelated model/config bug and feature-length helper behavior bug." + "reason": "SwitchTransformers sparse-layer bug vs qwen3_omni_moe helper behavior; different code paths." }, { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "LayoutLMV3 error-message clarity issue is unrelated to Trainer broadcast type failure." + "reason": "LayoutLMv3 error-message clarity issue vs Trainer `_gpu_broadcast_one` NoneType crash; unrelated." }, { "left": "issue:45588", "right": "issue:45859", "accept": false, - "reason": "Both involve MoE/flash-attention adjacent code, but they describe different failing paths and fixes." + "reason": "flash_attention sink-less `s_aux=None` crash vs Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility; separate failures." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "Doc-example/model mismatch is unrelated to unexpected key warnings with position ids." + "reason": "SigLIP2 docs example errors vs unexpected position-id key warnings; not the same bug." }, { "left": "issue:44292", "right": "issue:45520", "accept": false, - "reason": "Qwen-3-8B-NVFP4 runtime failure is unrelated to the Python 3.13 flash_attn import KeyError." + "reason": "Qwen-3-8B-NVFP4 runtime issue vs Python 3.13 `flash_attn` import KeyError; distinct causes." }, { - "left": "issue:38175", - "right": "issue:44493", + "left": "issue:44448", + "right": "issue:44779", "accept": false, - "reason": "SigLIP2 zero-probability behavior is unrelated to position-id key warnings." + "reason": "Pegasus output drift across versions vs Deepseek tokenizer regression in v5; different models and behaviors." }, { - "left": "issue:44448", - "right": "issue:44779", + "left": "issue:38175", + "right": "issue:44493", "accept": false, - "reason": "Different models and different regressions, despite both being v5-related output issues." + "reason": "SigLIP2 zero-probability output vs position-id key warning; unrelated symptoms." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "SwitchTransformers config bug is unrelated to dtype mismatches in bfloat16 inference." + "reason": "Sparse-layer creation bug vs bfloat16 dtype mismatch in inference; not the same code-path problem." }, { "left": "issue:44462", "right": "issue:44561", "accept": false, - "reason": "Tokenizer.json selection issue is unrelated to removed utility function breakage." + "reason": "AutoTokenizer ignoring `tokenizer.json` vs removal of `is_torch_fx_available`; unrelated loading regressions." }, { "left": "issue:44561", "right": "issue:44779", "accept": false, - "reason": "Trust-remote-code breakage is unrelated to Deepseek tokenizer output regression." + "reason": "`is_torch_fx_available` removal breakage vs Deepseek tokenizer regression; no shared root cause." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "BitNet packed-weight loading bug is unrelated to GraniteSpeech stale override CI failure." + "reason": "BitNet packed-weight unpacking bug vs GraniteSpeech stale device override CI failure; separate issues." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "Different models and different failure modes; not the same underlying bug." + "reason": "SwitchTransformers sparse-layer bug vs D-FINE auxiliary-loss behavior; unrelated model logic." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU OOM are unrelated." + "reason": "Qwen3.5 flash-attention generation bug vs Gemma4 multi-GPU CUDA OOM; different failure modes." }, { "left": "issue:42490", "right": "issue:43854", "accept": false, - "reason": "Local-path import warning is unrelated to GLM-4.7-Flash loading failure in tests." - }, - { - "left": "issue:40444", - "right": "issue:43526", - "accept": false, - "reason": "Qwen2.5-VL multi-image finetuning failure is unrelated to BEiT fast processor label reduction." - }, - { - "left": "issue:44448", - "right": "issue:44977", - "accept": false, - "reason": "Different models and distinct v5 behavior regressions; not mergeable as one bug." - }, - { - "left": "issue:34689", - "right": "issue:35141", - "accept": false, - "reason": "Llama 3.2 model loading regression and embedding resize reinit bug are different issues." - }, - { - "left": "issue:43606", - "right": "issue:44857", - "accept": false, - "reason": "CPU offload device mismatch and float16 AMP loss crash are unrelated." + "reason": "Trailing-slash local-path import warning vs GLM-4.7-Flash unit-test load failure; not the same bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded and conservative. The only accepted pair is the clearly identical Qwen3.5 MoE `from_pretrained` report, and the rejection reasons for the other soft pairs stay within what the titles/body metadata support. The canonical issue choice is also reasonable, with the earlier report selected appropriately." + "feedback": "The analysis is grounded in the packet and stays conservative on the soft edges. The single accepted duplicate pair (issue:45310 / issue:45478) is well-supported by the identical title and same Qwen3.5 MoE from_pretrained regression, and the remaining rejections do not overclaim shared root cause." }, "evaluator_used": true, "retried": false, @@ -7779,39 +7920,41 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:10000", "issue:15354", "issue:28218", - "issue:29127", "issue:29942", "issue:32090", "issue:33357", + "issue:34689", "issue:35141", "issue:37428", + "issue:40444", "issue:41720", "issue:42490", "issue:43065", "issue:43278", "issue:43329", "issue:43412", + "issue:43526", "issue:43550", "issue:43575", - "issue:43653", + "issue:43606", "issue:43701", "issue:43723", "issue:43873", "issue:43927", "issue:43976", "issue:43994", + "issue:44448", "issue:44493", "issue:44554", "issue:44568", - "issue:44743", "issue:44857", "issue:44977", "issue:44987", @@ -7822,7 +7965,6 @@ "issue:45245", "issue:45372", "issue:45406", - "issue:45412", "issue:45440", "issue:45459", "issue:45491", @@ -7833,245 +7975,238 @@ "issue:45803" ], "soft_pairs": [ + "issue:40444|issue:43526", + "issue:34689|issue:35141", + "issue:43606|issue:44857", + "issue:44448|issue:44977", "issue:43723|issue:44554", "issue:44857|issue:45072", "issue:44977|issue:45563", "issue:44568|issue:45491", - "issue:43927|issue:45698", "issue:28218|issue:32090", + "issue:43927|issue:45698", "issue:43701|issue:45083", "issue:43550|issue:45083", "issue:45198|issue:45803", - "issue:45372|issue:45588", "issue:37428|issue:44987", + "issue:45372|issue:45588", "issue:29942|issue:35141", "issue:45459|issue:45712", "issue:43873|issue:44493", - "issue:43412|issue:45588", "issue:32090|issue:33357", "issue:43873|issue:45229", "issue:45245|issue:45563", + "issue:43412|issue:45588", "issue:41720|issue:45229", "issue:43278|issue:43329", - "issue:10000|issue:15354", "issue:43976|issue:45440", + "issue:10000|issue:15354", "issue:45372|issue:45406", - "issue:43065|issue:43994", "issue:42490|issue:43575", - "issue:28218|issue:29127", - "issue:43065|issue:45412", - "issue:45372|issue:45459", - "issue:44857|issue:45588", - "issue:43653|issue:44743" + "issue:43065|issue:43994" ], - "prepared_review_unit_hash": "6081a1bac8a3467e4375579576655a23f36bc4bf5845b412539d92e80fefa77c", + "prepared_review_unit_hash": "05b3d6e92b6291034d8febae792ffb359f3897317620cba0cfa05fc5e85ffbe9", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 36332, - "estimated_input_tokens": 9083, - "estimated_eval_tokens": 18422 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36594, + "estimated_input_tokens": 9149, + "estimated_eval_tokens": 18554 }, "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 rather than a true duplicate set. None of the soft-edge pairs look like the same underlying issue or change, so I would not merge any of them.", - "confidence": 0.86, - "canonical_issue_reason": "No single issue is a clear canonical duplicate target because the cluster is heterogeneous. If a representative anchor is needed, issue 45372 is the most broadly useful open, well-described bug report with downstream references.", + "summary": "This cluster is highly heterogeneous: the soft pairs mostly share broad subsystem vocabulary, but they do not look like the same underlying bug or change. I found no strong duplicate PR/issue center, so the best representative is only a loose cluster hub rather than a true canonical duplicate.", + "confidence": 0.67, + "canonical_issue_reason": "issue:43873 is the broadest open infra bug in the set ('offloading not working as expected with quantization') and has the most inbound references, so it is the closest thing to a hub; the other items are mostly model-specific and not true duplicates.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45372 is the best global issue candidate here because it is open, concrete, and has inbound references, but it still does not meaningfully unify the cluster.", + "best_issue_reason": "issue:43873 is the safest global representative because it is broad, still active, and most likely to attract related reports, even though the cluster overall is too mixed to form a real duplicate group.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Different problems: multimodal finetuning with multiple images vs a BeitImageProcessorFast label-reduction bug." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "One is a model-loading regression for Llama 3.2 Vision, the other is embedding reinitialization during resize/eval." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch and float16 AMP loss crashes are unrelated failure modes." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different concrete bugs: Pegasus output drift across versions vs Qwen3.5 flash-attention generation failure." + }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "Different subsystems and failures: tokenizer loading vs MPS attention correctness." + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are not the same code-path." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Both involve numeric precision, but they are different model-specific bugs with different failure modes." + "reason": "These are different dtype-related issues in different paths: AMP loss crash vs inference dtype mismatch." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Flash-attention generation bug vs a stale warning about num_return_sequences." + "reason": "Generation correctness with flash-attention is not the same as a stale warning about num_return_sequences." }, { "left": "issue:44568", "right": "issue:45491", "accept": false, - "reason": "Tokenizer special-token behavior is unrelated to Gemma3 NaN embeddings on mixed-length batches." + "reason": "Tokenizer special-token omission and Gemma3 NaN embeddings are unrelated bugs." }, { - "left": "issue:43927", - "right": "issue:45698", + "left": "issue:28218", + "right": "issue:32090", "accept": false, - "reason": "Both touch save/load paths, but one is config token IDs and the other is custom module selection; not the same bug." + "reason": "Added-token spacing behavior and Trainer broadcast NoneType errors are unrelated." }, { - "left": "issue:28218", - "right": "issue:32090", + "left": "issue:43927", + "right": "issue:45698", "accept": false, - "reason": "Tokenizer spacing issue vs distributed trainer broadcast type error." + "reason": "Both touch save/load, but one loses custom token IDs in config while the other restores the wrong custom module; different serialization paths." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint key mismatch is unrelated to a helper-function behavior bug." + "reason": "Checkpoint resume key mismatch is unrelated to qwen3_omni_moe feature-length helper behavior." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "torch.compile/SDPA failure on Bamba is unrelated to qwen3_omni_moe feature-length logic." + "reason": "torch.compile/SDPA failure and feature-length calculation bugs are different issues." }, { "left": "issue:45198", "right": "issue:45803", "accept": false, - "reason": "save_pretrained/tokenization failure is not the same as a bare-except swallowing errors." + "reason": "Wav2Vec2 save/tokenization failure and a bare-except bug in Fuyu tensor conversion are not the same defect." }, { - "left": "issue:45372", - "right": "issue:45588", + "left": "issue:37428", + "right": "issue:44987", "accept": false, - "reason": "Gemma 4 processor import failure and flash_attention s_aux handling are different concrete bugs." + "reason": "The first is a missing flash-attn import symbol; the second is a generic model-loading failure with no clear same root cause." }, { - "left": "issue:37428", - "right": "issue:44987", + "left": "issue:45372", + "right": "issue:45588", "accept": false, - "reason": "Shared release area, but one is a missing import symbol and the other is a model loading failure." + "reason": "Gemma4 processor import dependency failure and flash_attention.py s_aux handling are distinct bugs." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Flash Attention test failures are unrelated to embedding reinitialization in post_init." + "reason": "Flash Attention 2 test failures and embedding reinitialization on resize are unrelated." }, { "left": "issue:45459", "right": "issue:45712", "accept": false, - "reason": "Tokenizer exception masking is unrelated to leftover dummy classes leaking into dir()." + "reason": "Tokenizer error masking from protobuf handling and dummy-class cleanup/dir leakage are different concerns." }, { "left": "issue:43873", "right": "issue:44493", "accept": false, - "reason": "Quantization offloading and unexpected position-id keys are different issues." - }, - { - "left": "issue:43412", - "right": "issue:45588", - "accept": false, - "reason": "ExecuTorch export problems are unrelated to flash_attention sink-less-model crashes." + "reason": "Quantization/offloading behavior and unexpected position-id key warnings do not share a concrete root cause." }, { "left": "issue:32090", "right": "issue:33357", "accept": false, - "reason": "Trainer NoneType broadcast error and MacOS bus error on CLIP are not the same bug." + "reason": "Trainer broadcast NoneType and a MacOS CLIP bus error are not the same failure." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "Offloading/quantization behavior is unrelated to multi-GPU OOM." + "reason": "Both involve large-model resource issues, but offloading/quantization misbehavior is not the same as multi-GPU OOM." }, { "left": "issue:45245", "right": "issue:45563", "accept": false, - "reason": "Category-cardinality runtime error is unrelated to a stale generate warning." + "reason": "A category-count runtime limit and a stale generation warning are unrelated." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export problems and a sink-less flash-attention AttributeError are different code paths." }, { "left": "issue:41720", "right": "issue:45229", "accept": false, - "reason": "cudaErrorAssert during auto device mapping is not the same as plain OOM." + "reason": "Auto device-mapping cudaErrorAssert and multi-GPU OOM are different resource failures." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Embedding dtype regression is unrelated to undefined video-token helper variables." - }, - { - "left": "issue:10000", - "right": "issue:15354", - "accept": false, - "reason": "Completely different models and failures: DistilBert model issue vs torch.jit.script GeneratorExp support." + "reason": "BF16-to-FP32 dtype drift and an undefined-variable multimodal token helper bug are unrelated." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "Python version compatibility is unrelated to DeepSeekV3MoE divergence from remote implementation." + "reason": "Python version incompatibility and DeepSeekV3MoE divergence are not the same bug." }, { - "left": "issue:45372", - "right": "issue:45406", + "left": "issue:10000", + "right": "issue:15354", "accept": false, - "reason": "Both mention Gemma 4, but one is processor import loading and the other is serve-time missing _tokenizer state." + "reason": "German DistilBertModel error and torch.jit GeneratorExp export support are unrelated." }, { - "left": "issue:43065", - "right": "issue:43994", + "left": "issue:45372", + "right": "issue:45406", "accept": false, - "reason": "Sam3PixelDecoder dummy layer and SigLIP2 nonsensical outputs are unrelated model bugs." + "reason": "Both mention Gemma4, but one is an import dependency issue and the other is a missing _tokenizer attribute in serve." }, { "left": "issue:42490", "right": "issue:43575", "accept": false, - "reason": "Import warning on trailing slash paths is unrelated to tensor-parallel OOM." - }, - { - "left": "issue:28218", - "right": "issue:29127", - "accept": false, - "reason": "Tokenizer adds extra space vs layoutlmv3 box-validation error messaging are not duplicates." + "reason": "A trailing-slash import warning and tensor-parallel OOM are unrelated." }, { "left": "issue:43065", - "right": "issue:45412", - "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to RT-DETR memory release behavior." - }, - { - "left": "issue:45372", - "right": "issue:45459", - "accept": false, - "reason": "Gemma 4 import dependency issue is not the same as protobuf-related tokenizer error masking." - }, - { - "left": "issue:44857", - "right": "issue:45588", - "accept": false, - "reason": "AMP/CUDA loss crash and flash_attention AttributeError are different code paths." - }, - { - "left": "issue:43653", - "right": "issue:44743", + "right": "issue:43994", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug is unrelated to Qwen3 recurrent state reset." + "reason": "Dummy Conv2d cleanup in Sam3PixelDecoder and SigLIP2 nonsensical outputs are different issues." } ] }, @@ -8090,12 +8225,13 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:25251", + "issue:28218", "issue:29127", "issue:29942", "issue:30064", @@ -8107,6 +8243,7 @@ "issue:42490", "issue:42915", "issue:42994", + "issue:43065", "issue:43066", "issue:43257", "issue:43278", @@ -8114,255 +8251,259 @@ "issue:43421", "issue:43653", "issue:43756", - "issue:43761", - "issue:43824", "issue:43873", "issue:43994", "issue:44186", "issue:44206", "issue:44265", - "issue:44279", "issue:44361", - "issue:44442", "issue:44448", "issue:44451", "issue:44462", "issue:44466", "issue:44479", "issue:44610", + "issue:44743", + "issue:44857", "issue:44871", "issue:44977", - "issue:45103", "issue:45198", "issue:45372", "issue:45412", "issue:45440", + "issue:45459", "issue:45491", "issue:45520", "issue:45588", "issue:45593", - "issue:45823", - "issue:45859" + "issue:45823" ], "soft_pairs": [ + "issue:28218|issue:29127", + "issue:43065|issue:45412", + "issue:45372|issue:45459", + "issue:44857|issue:45588", "issue:44448|issue:44466", + "issue:43653|issue:44743", "issue:45588|issue:45823", "issue:43278|issue:43381", - "issue:44206|issue:44479", "issue:43066|issue:44462", + "issue:44206|issue:44479", "issue:43994|issue:45412", - "issue:44186|issue:45198", "issue:25251|issue:32090", + "issue:44186|issue:45198", "issue:44451|issue:45520", "issue:44361|issue:45198", "issue:42915|issue:42994", - "issue:44265|issue:45198", "issue:44871|issue:44977", + "issue:44265|issue:45198", "issue:43756|issue:45440", - "issue:29942|issue:30064", "issue:43421|issue:45491", + "issue:29942|issue:30064", "issue:43257|issue:43278", "issue:33357|issue:39692", - "issue:44610|issue:45412", "issue:29127|issue:34567", - "issue:42490|issue:43873", + "issue:44610|issue:45412", "issue:32090|issue:33290", - "issue:45103|issue:45372", - "issue:45440|issue:45593", - "issue:43824|issue:44279", - "issue:43653|issue:44442", - "issue:43761|issue:45859" + "issue:42490|issue:43873", + "issue:45440|issue:45593" ], - "prepared_review_unit_hash": "6e4d5bc08dda6a7feb0ea134b973387278538d22db4174365a74ddb45cdda595", + "prepared_review_unit_hash": "3af4d7545024d9f5120b1043c2dce1be20a68aa6d9d4a7fed36bc6f661835c34", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 35829, - "estimated_input_tokens": 8958, - "estimated_eval_tokens": 18172 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35486, + "estimated_input_tokens": 8872, + "estimated_eval_tokens": 18000 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The items are a heterogeneous mix of unrelated bugs, regressions, tokenizer/model issues, and training/runtime problems. None of the soft-similarity pairs look like the same underlying bug or change, so all soft edges should be rejected.", - "confidence": 0.94, - "canonical_issue_reason": "No single canonical issue stands out: the set spans many unrelated subsystems and the soft pairs do not collapse into one duplicate family.", + "summary": "This cluster looks heterogeneous rather than like one duplicate family; all soft-pair candidates are distinct bugs/features and should be kept separate.", + "confidence": 0.86, + "canonical_issue_reason": "issue:44462 is the most representative standalone bug here: concrete, reproducible, user-facing, and with inbound references; the rest of the items are a mix of unrelated tokenizer, training, vision, quantization, and runtime issues.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a strong global representative for this cluster, because the similarities are only superficial and the underlying problems differ.", + "best_issue_reason": "issue:44462 is the best anchor for triage because it is narrowly scoped, clearly described, and has external references that suggest real impact.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Different subsystems and failure modes: tokenizer spacing vs. LayoutLMv3 error-message clarity." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "No shared code-path: Sam3PixelDecoder dummy layer is unrelated to RT-DETR memory cleanup." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma processor import breakage is unrelated to tokenizer error masking when protobuf is missing." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "Different bugs in different paths: LwDetr loss under AMP vs flash-attention crash on sink-less models." + }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Both mention v5 behavior changes, but one is a generation-output difference and the other is device-dependent weight serialization; different bugs and code paths." + "reason": "Both are version/regression complaints, but one is generation output drift and the other is serialization of tied weights." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "Tokenizer special-token registration bug is unrelated to Qwen3.5 recurrent-state reset logic." }, { "left": "issue:45588", "right": "issue:45823", "accept": false, - "reason": "One is a flash-attention crash on sink-less models, the other is a Gemma4 PLE device-mismatch during forward; not the same failure." + "reason": "One is a flash-attention attribute error; the other is a device-map forward mismatch in Gemma4 PLE." }, { "left": "issue:43278", "right": "issue:43381", "accept": false, - "reason": "BF16-to-FP32 dtype drift and gradient-checkpointing-in-eval are unrelated issues." + "reason": "Embedding dtype mismatch in eval is not the same issue as gradient checkpointing being disallowed in eval mode." }, { - "left": "issue:44206", - "right": "issue:44479", + "left": "issue:43066", + "right": "issue:44462", "accept": false, - "reason": "Unsupported processor argument in LasrFeatureExtractor vs a Qwen VL video-input regression; different components and symptoms." + "reason": "Tokenizer decoder-type regression is a different loading bug than ignoring tokenizer.json from a repo." }, { - "left": "issue:43066", - "right": "issue:44462", + "left": "issue:44206", + "right": "issue:44479", "accept": false, - "reason": "Both are tokenizer-loading related, but one is a wrong decoder type in v5 and the other is ignoring tokenizer.json; not the same bug." + "reason": "Feature extractor center-arg crash and Qwen video-input regression are unrelated code paths." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 doc example problems and RT-DETR memory leaks are unrelated." + "reason": "SigLIP2 model/pipeline output corruption is unrelated to RT-DETR memory release behavior." }, { - "left": "issue:44186", - "right": "issue:45198", + "left": "issue:25251", + "right": "issue:32090", "accept": false, - "reason": "LayoutLMv2 tokenizer crashes on NER/padding issues, while Wav2Vec2 has save_pretrained/tokenization failures; different code paths." + "reason": "Pipeline top_k nesting bug is unrelated to Trainer broadcast failing on NoneType." }, { - "left": "issue:25251", - "right": "issue:32090", + "left": "issue:44186", + "right": "issue:45198", "accept": false, - "reason": "Pipeline top_k nesting behavior and Trainer _gpu_broadcast_one TypeError are unrelated." + "reason": "LayoutLMv2 tokenizer NER/padding crash is unrelated to Wav2Vec2 save_pretrained/tokenization failures." }, { "left": "issue:44451", "right": "issue:45520", "accept": false, - "reason": "Model-load failure for ScandiBERT and Python 3.13 flash_attn import key error are unrelated." + "reason": "Model-loading failure for a specific checkpoint is unrelated to a flash_attn import KeyError on Python 3.13." }, { "left": "issue:44361", "right": "issue:45198", "accept": false, - "reason": "MLukeTokenizer AttributeError on tasks is not the same underlying problem as Wav2Vec2 save/tokenization failure." + "reason": "MLukeTokenizer task AttributeError and Wav2Vec2 save/tokenization failure are distinct tokenizer/model issues." }, { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "Both involve quantization, but one is a FineGrainedFP8Config failure and the other is a quantized-model save failure; different stages and causes." + "reason": "One concerns Qwen3 MoE loading with FP8 config; the other is quantized model saving." }, { - "left": "issue:44265", - "right": "issue:45198", + "left": "issue:44871", + "right": "issue:44977", "accept": false, - "reason": "torch.export failure with torch_compilable_check is unrelated to Wav2Vec2 save_pretrained/tokenization issues." + "reason": "EOS-token config inconsistency is unrelated to Qwen3.5 flash-attention generation problems." }, { - "left": "issue:44871", - "right": "issue:44977", + "left": "issue:44265", + "right": "issue:45198", "accept": false, - "reason": "Gemma-3 eos_token_id inconsistency and Qwen3.5 flash-attention generation regression are different bugs." + "reason": "torch.export failure from torch_compilable_check is a different export path than Wav2Vec2 save/tokenization." }, { "left": "issue:43756", "right": "issue:45440", "accept": false, - "reason": "Both compare model behavior to an expected/reference implementation, but they concern different models and different defects." + "reason": "Different models and different defects: Smollm3 RoPE-layer mismatch vs DeepseekV3MoE implementation divergence." }, { - "left": "issue:29942", - "right": "issue:30064", + "left": "issue:43421", + "right": "issue:45491", "accept": false, - "reason": "Flash Attention 2 test failures and void segmentation map processing failures are unrelated." + "reason": "Runtime special-token post-processor update bug is unrelated to Gemma3 NaN embeddings in mixed-length batches." }, { - "left": "issue:43421", - "right": "issue:45491", + "left": "issue:29942", + "right": "issue:30064", "accept": false, - "reason": "Runtime special-token/post-processor update logic is unrelated to Gemma3 NaN embeddings in mixed-length sliding-window batches." + "reason": "Flash Attention 2 CI failures and void segmentation-map processing are unrelated regressions." }, { "left": "issue:43257", "right": "issue:43278", "accept": false, - "reason": "Qwen3 MoE weight-conversion issues and embedding dtype changes are not the same underlying bug." + "reason": "Qwen3 MoE weight-conversion failure is unrelated to embedding dtype changing between train and eval." }, { "left": "issue:33357", "right": "issue:39692", "accept": false, - "reason": "Both involve vision models, but MacOS bus errors on CLIP and SigLIP2 doc/quantization problems are distinct." - }, - { - "left": "issue:44610", - "right": "issue:45412", - "accept": false, - "reason": "Processor input-size mismatch and RT-DETR memory not being released are unrelated." + "reason": "MacOS CLIP bus error and SigLIP2 docs-example errors are not the same bug or code path." }, { "left": "issue:29127", "right": "issue:34567", "accept": false, - "reason": "LayoutLMv3 error messaging for boxes and TrainerState token-count tracking are different issues." + "reason": "Clarity of a layoutlmv3 error message is unrelated to TrainerState token-count tracking not updating." }, { - "left": "issue:42490", - "right": "issue:43873", + "left": "issue:44610", + "right": "issue:45412", "accept": false, - "reason": "Local-path import warning and quantization offloading problems do not share the same code path." + "reason": "OmDet-Turbo processor resolution mismatch is unrelated to RT-DETR object lifetime/memory release." }, { "left": "issue:32090", "right": "issue:33290", "accept": false, - "reason": "Trainer NoneType broadcast error and DeepSpeed Adafactor OOM are both training-related but clearly separate bugs." + "reason": "Trainer NoneType broadcast error and DeepSpeed Adafactor OOM are different training failures." }, { - "left": "issue:45103", - "right": "issue:45372", + "left": "issue:42490", + "right": "issue:43873", "accept": false, - "reason": "Auto-docstring annotation parsing crash and Gemma4 processor import error are unrelated." + "reason": "Local-path import warning is unrelated to quantization offloading behavior." }, { "left": "issue:45440", "right": "issue:45593", "accept": false, - "reason": "DeepSeekV3 parity divergence and D-FINE auxiliary-loss behavior are different model-specific problems." - }, - { - "left": "issue:43824", - "right": "issue:44279", - "accept": false, - "reason": "Specific Qwen2.5-VL import error versus a vague dependency issue; too generic to be the same bug." - }, - { - "left": "issue:43653", - "right": "issue:44442", - "accept": false, - "reason": "BigBirdTokenizer special-token registration and AutoTokenizer loading FastSpeech2ConformerTokenizer are different tokenizer issues." - }, - { - "left": "issue:43761", - "right": "issue:45859", - "accept": false, - "reason": "CLIPVisionModel hidden_states regression and Qwen3_5Moe rotary embedding CPU-offload incompatibility are unrelated." + "reason": "DeepseekV3MoE implementation drift and D-FINE auxiliary-loss omission are different model-specific issues." } ] }, @@ -8381,10 +8522,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:29127", "issue:29942", @@ -8395,56 +8536,60 @@ "issue:42915", "issue:43232", "issue:43262", - "issue:43316", "issue:43334", "issue:43381", "issue:43388", "issue:43441", - "issue:43525", "issue:43526", "issue:43531", "issue:43575", "issue:43646", + "issue:43653", "issue:43701", "issue:43723", "issue:43761", + "issue:43824", "issue:43931", "issue:44062", "issue:44077", "issue:44079", "issue:44186", - "issue:44188", "issue:44206", + "issue:44279", "issue:44387", "issue:44442", "issue:44464", - "issue:44479", "issue:44743", "issue:44811", "issue:44857", "issue:44977", "issue:45003", "issue:45072", + "issue:45103", "issue:45245", - "issue:45290", + "issue:45372", "issue:45440", "issue:45479", "issue:45491", "issue:45588", - "issue:45803", "issue:45834", + "issue:45859", "issue:45907" ], "soft_pairs": [ + "issue:43824|issue:44279", + "issue:43653|issue:44442", + "issue:43761|issue:45859", "issue:43526|issue:45834", + "issue:45103|issue:45372", "issue:43381|issue:43701", "issue:43526|issue:44186", "issue:29942|issue:36010", "issue:29127|issue:33357", "issue:43334|issue:43531", "issue:44977|issue:45245", - "issue:44464|issue:45491", "issue:29127|issue:35141", + "issue:44464|issue:45491", "issue:42915|issue:43931", "issue:44442|issue:45072", "issue:43262|issue:44206", @@ -8455,212 +8600,208 @@ "issue:43232|issue:43388", "issue:44743|issue:44811", "issue:43646|issue:44077", - "issue:43761|issue:44079", "issue:43575|issue:43701", - "issue:45003|issue:45440", + "issue:43761|issue:44079", "issue:43575|issue:44387", - "issue:43723|issue:45479", - "issue:44442|issue:45803", - "issue:44479|issue:45290", - "issue:43761|issue:44188", - "issue:43316|issue:43525" + "issue:45003|issue:45440", + "issue:43723|issue:45479" ], - "prepared_review_unit_hash": "472d8644d3674aa9a72d3c4179dc858701aa133f81df81ed3f29c4dca3d26760", + "prepared_review_unit_hash": "72f91e550386cdbb74aee4678444bebbd63dcfe75dee13476ebd6039d6d6da79", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36170, - "estimated_input_tokens": 9043, - "estimated_eval_tokens": 18342 + "serialized_chars": 36208, + "estimated_input_tokens": 9052, + "estimated_eval_tokens": 18360 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is not a duplicate set; it mixes many unrelated Transformers bugs across tokenizers, vision, audio, generation, quantization, and config APIs. The soft pairs are mostly broad topical similarities only, not the same underlying defect.", - "confidence": 0.98, - "canonical_issue_reason": "No single canonical duplicate stands out because the items are heterogeneous. If forced to pick an anchor, issue 43646 is the broadest umbrella-style regression report.", + "summary": "This cluster is highly heterogeneous: the items span unrelated tokenizer, generation, model-loading, training, flash-attention, and processor bugs. None of the soft pairs look like the same underlying defect, so no duplicate merges are warranted.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43646 is the most general, high-level regression report in the set and is the best representative anchor, though it is not a true duplicate of the others.", + "best_issue_reason": "issue:45003 is the best representative issue because it is a concrete, self-contained core-library bug in modeling_utils with a clear code path and broad impact.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Different failure modes: Qwen2.5-VL import error vs a vague dependency issue; no shared code path." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "Both involve tokenizers, but one is a BigBird special-token decoding bug and the other is an AutoTokenizer load failure for a different model." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVision hidden_states regression and Qwen3_5Moe CPU offload incompatibility are unrelated model-specific bugs." + }, { "left": "issue:43526", "right": "issue:45834", "accept": false, - "reason": "Both are vision/processor-related, but one is a label reduction bug and the other is an OCR length/index error; different code paths and failures." + "reason": "Different processors and symptoms: Beit reduce_labels bug vs Kosmos2.5 OCR index error." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation parsing crash is unrelated to the Gemma 4 processor import failure." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Training-time gradient checkpointing in eval mode is unrelated to resume-from-checkpoint key mismatches." + "reason": "Training-loop issues in different places: gradient checkpointing eval-mode restriction vs checkpoint key mismatch." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "Different tokenizer/processor bugs: label reduction vs NER padding/truncation crashes." + "reason": "Both are vision/text preprocessing issues, but they hit different classes and code paths with different root causes." }, { "left": "issue:29942", "right": "issue:36010", "accept": false, - "reason": "Flash Attention test failures and a GenerationMixin import error are unrelated." + "reason": "Flash Attention test failures and a GenerationMixin import error are not the same bug." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 box-content messaging and a MacOS CLIP bus error are clearly different defects." + "reason": "A poor error message in LayoutLMv3 is unrelated to a MacOS bus error loading a CLIP model." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Missing pad_token_id on Qwen3-VL text config is a different bug from Qwen3-MoE sliding_window behavior." + "reason": "Both mention Qwen3, but one is missing pad_token_id and the other is a sliding_window regression in MoE models." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Flash-attention generation regression and a category-count limit error are unrelated." + "reason": "Qwen3.5 flash-attention generation bug and category-count limit error are completely different issues." }, { - "left": "issue:44464", - "right": "issue:45491", + "left": "issue:29127", + "right": "issue:35141", "accept": false, - "reason": "Both involve generation/attention, but chunked compiled generation inconsistency and Gemma3 NaN embeddings have different failure modes and likely different fixes." + "reason": "LayoutLMv3 box-validation messaging and token-embedding reinit after resize are unrelated." }, { - "left": "issue:29127", - "right": "issue:35141", + "left": "issue:44464", + "right": "issue:45491", "accept": false, - "reason": "Layout boxes validation/message clarity is unrelated to embedding reinitialization during post_init." + "reason": "Chunked generation inconsistency with compiled forward is not the same as Gemma3 NaN embeddings from sliding-window attention." }, { "left": "issue:42915", "right": "issue:43931", "accept": false, - "reason": "Qwen3Moe FP8 config failure and Qwen3-VL weight-shape mismatch are different loading issues." + "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen3-VL weight-shape mismatch are distinct loading/configuration problems." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "Tokenizer loading and bfloat16 inference dtype mismatches are unrelated." + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch in model wrappers do not share the same underlying defect." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Audio chat-template sample-rate defaults and an unsupported feature-extractor argument are different audio-processing bugs." + "reason": "Audio chat-template sampling-rate default bug and LasrFeatureExtractor center-arg crash are unrelated processor issues." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "Label reduction behavior and LwDetrImageLoss AMP/CUDA crashing are unrelated." + "reason": "Beit reduce_labels truncation and LwDetrImageLoss AMP/CUDA crash are different components and failure modes." }, { "left": "issue:42490", "right": "issue:43381", "accept": false, - "reason": "Trailing-slash import warnings and eval-mode gradient checkpointing are unrelated." + "reason": "Import warning on local-path loading is unrelated to gradient checkpointing in eval mode." }, { "left": "issue:44062", "right": "issue:45907", "accept": false, - "reason": "AddedToken argument duplication and list_repo_files revision forwarding are separate API issues." + "reason": "AddedToken keyword duplication and list_repo_files revision forwarding are different API bugs." }, { "left": "issue:43441", "right": "issue:45588", "accept": false, - "reason": "Both mention flash attention, but one is a model-specific failure and the other is an s_aux=None crash in a different code path." + "reason": "Different flash-attention problems: Ministral v5 RC failure vs s_aux=None crash in integrations/flash_attention.py." }, { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Generation kwargs sync logic and metrics gathering label truncation are unrelated." + "reason": "Generation kwargs sync after sync_gpus and metric-gathering label truncation are separate training/eval bugs." }, { "left": "issue:44743", "right": "issue:44811", "accept": false, - "reason": "Recurrent-state reset with cache and Whisper batch decoding skip_special_tokens are different subsystems." + "reason": "Qwen3_5 recurrent-state reset and Whisper batch_decode skip_special_tokens are unrelated behavioral bugs." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "General custom model initialization breakage is not the same concrete bug as patchtsmixer's post_init allowance change." - }, - { - "left": "issue:43761", - "right": "issue:44079", - "accept": false, - "reason": "Hidden_states disappearing in CLIPVisionModel.forward and ModelOutput key assignment when a previous key is None are different output-handling bugs." + "reason": "Custom model init breakage in Transformers 5.0.0 and patchtsmixer's post_init constraint are not the same issue." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "Tensor-parallel OOM on a large model is unrelated to checkpoint key mismatches." + "reason": "Tensor-parallel OOM on Qwen2-57B and resume_from_checkpoint key mismatch do not overlap." }, { - "left": "issue:45003", - "right": "issue:45440", + "left": "issue:43761", + "right": "issue:44079", "accept": false, - "reason": "Unsafe sys.modules access and DeepseekV3MoE remote/native divergence are unrelated." + "reason": "A CLIPVision forward regression is not the same as a generic ModelOutput key-assignment bug." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "Both are OOM reports, but one is tensor-parallel loading and the other is increased reserved memory under int4 quantization; different causes and fixes." - }, - { - "left": "issue:43723", - "right": "issue:45479", - "accept": false, - "reason": "AutoTokenizer loading and single-label classification zero-loss behavior are unrelated." - }, - { - "left": "issue:44442", - "right": "issue:45803", - "accept": false, - "reason": "Tokenizer-loading failure and bare-except masking errors in Fuyu tensor conversion are different bugs." + "reason": "Both mention OOM, but one is TP load OOM for a specific model and the other is increased reserved memory under int4 quantization." }, { - "left": "issue:44479", - "right": "issue:45290", - "accept": false, - "reason": "Both involve multimodal/chat flows, but the video-input regression and tool-call chat-template crash are distinct code paths." - }, - { - "left": "issue:43761", - "right": "issue:44188", + "left": "issue:45003", + "right": "issue:45440", "accept": false, - "reason": "A CLIPVisionModel output regression is unrelated to torch.compile attention-kernel branching." + "reason": "Unsafe sys.modules access in modeling_utils and DeepseekV3MoE divergence from remote implementation are different code paths." }, { - "left": "issue:43316", - "right": "issue:43525", + "left": "issue:43723", + "right": "issue:45479", "accept": false, - "reason": "Both are config/API discrepancies, but they affect different models and different missing-attribute behaviors; not the same bug." + "reason": "AutoTokenizer loading failure and zero-loss classification behavior are unrelated problems." } ] }, @@ -8679,10 +8820,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:33290", "issue:34567", @@ -8695,31 +8836,29 @@ "issue:42175", "issue:42490", "issue:42907", - "issue:43065", "issue:43316", "issue:43381", "issue:43404", "issue:43441", "issue:43493", + "issue:43525", "issue:43540", "issue:43611", "issue:43643", - "issue:43673", "issue:43720", "issue:43749", + "issue:43761", "issue:43827", "issue:43873", "issue:43931", "issue:44077", - "issue:44162", + "issue:44188", "issue:44190", "issue:44442", "issue:44479", "issue:44496", "issue:44514", - "issue:44617", "issue:44743", - "issue:44792", "issue:44855", "issue:44871", "issue:44877", @@ -8727,21 +8866,27 @@ "issue:44913", "issue:45137", "issue:45216", + "issue:45290", "issue:45372", "issue:45491", "issue:45698", - "issue:45759" + "issue:45759", + "issue:45803" ], "soft_pairs": [ + "issue:44442|issue:45803", + "issue:44479|issue:45290", + "issue:43761|issue:44188", + "issue:43316|issue:43525", "issue:42907|issue:45698", "issue:44442|issue:44898", "issue:42490|issue:44743", "issue:33290|issue:34567", "issue:34689|issue:43611", "issue:39692|issue:45491", - "issue:43931|issue:45216", "issue:33290|issue:35141", "issue:33290|issue:34689", + "issue:43931|issue:45216", "issue:43381|issue:43873", "issue:43493|issue:43827", "issue:44077|issue:44479", @@ -8750,215 +8895,224 @@ "issue:41628|issue:45372", "issue:43643|issue:44913", "issue:43749|issue:43931", - "issue:43873|issue:44871", "issue:34689|issue:36010", - "issue:44190|issue:44496", + "issue:43873|issue:44871", "issue:33290|issue:36331", + "issue:44190|issue:44496", "issue:44855|issue:45137", - "issue:43316|issue:44877", "issue:43540|issue:44514", + "issue:43316|issue:44877", "issue:42175|issue:43316", - "issue:43673|issue:44743", - "issue:43065|issue:44617", - "issue:43404|issue:43441", - "issue:44162|issue:44792" + "issue:43404|issue:43441" ], - "prepared_review_unit_hash": "90d10cac729bb1da9151671520641b165b5f4e0032bdf833071c2f49cb98d1e6", + "prepared_review_unit_hash": "03b9cab88a02228737fbda707b821ebb276a1152d6ba851ef14d84c2e35fec37", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35918, - "estimated_input_tokens": 8980, - "estimated_eval_tokens": 18216 + "soft_pair_count": 30, + "serialized_chars": 36437, + "estimated_input_tokens": 9110, + "estimated_eval_tokens": 18476 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is highly heterogeneous: most items are unrelated model-specific bugs, config/import regressions, or docs issues. I found no convincing duplicate pairs among the soft edges, so this should not be merged into a single canonical bug cluster.", - "confidence": 0.92, - "canonical_issue_reason": "If a representative issue is needed, issue 45698 is the broadest and most generic load/save regression in the set; however, the overall cluster does not look like a true duplicate group.", + "summary": "This cluster is mostly heterogeneous: the soft pairs cover unrelated bugs across tokenizers, vision, config reloads, multimodal chat, trainer APIs, and loading/saving regressions. None of the proposed soft edges look like true duplicates of the same underlying defect, so I reject them all.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical duplicate exists in this set. If one issue must serve as an anchor, issue #43749 has the strongest triage signal (discussion plus inbound references) and is a broad runtime/regression report.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45698 is the best global representative because it concerns core from_pretrained/save_pretrained behavior, which is broader than the mostly model-specific or niche issues here.", + "best_issue_reason": "Issue #43749 is the best single representative by external signal and breadth of impact, but it still does not match the rest closely enough to act as a true duplicate hub.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Different bugs: FastSpeech2Conformer tokenizer loading vs a Fuyu bare-except masking errors/KeyboardInterrupt." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Both are multimodal/chat regressions, but one is a video-input regression and the other is an assistant tool-call chat_template crash." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "Unrelated code paths: CLIPVision hidden_states handling vs attention-kernel divergence under torch.compile." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both concern config APIs, but they are different model-specific attribute mismatches with different symptoms and fixes." + }, { "left": "issue:42907", "right": "issue:45698", "accept": false, - "reason": "Different problems: saving dequantized models vs loading the wrong custom module after save/load." + "reason": "Save/load are both involved, but one is dequantized model saving and the other is loading the wrong custom module after save_pretrained." }, { "left": "issue:44442", "right": "issue:44898", "accept": false, - "reason": "Unrelated model paths and failures: tokenizer loading vs Perceiver image classification/interpolation." + "reason": "Different model families and failures: tokenizer import/loading vs Perceiver image-classification resize/interpolation behavior." }, { "left": "issue:42490", "right": "issue:44743", "accept": false, - "reason": "Different subsystems: local path warning vs recurrent state reset in a Qwen modular model." + "reason": "Completely different areas: local-path import warning vs recurrent state reset with cache in modular Qwen3.5 code." }, { "left": "issue:33290", "right": "issue:34567", "accept": false, - "reason": "Unrelated issues: DeepSpeed Adafactor OOM vs TrainerState token counter not updating." + "reason": "AdaFactor/DeepSpeed OOM is unrelated to TrainerState.num_input_tokens_seen not updating." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are loading regressions, but they affect different mechanisms and code paths." + "reason": "Both are loading regressions, but one is a Llama vision model breakage and the other is a base_model_prefix-related loading issue." }, { "left": "issue:39692", "right": "issue:45491", "accept": false, - "reason": "Different models and symptoms: SigLIP2 docs example errors vs Gemma3 NaN embeddings." - }, - { - "left": "issue:43931", - "right": "issue:45216", - "accept": false, - "reason": "Both involve Qwen models, but one is a shape-mismatch load error and the other is a save_pretrained regression." + "reason": "Docs-example errors are unrelated to Gemma3 NaN embeddings in mixed-length GPU batching." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "OOM in optimizer training is unrelated to embedding reinitialization during post_init." + "reason": "Different subsystems: optimizer memory blow-up vs embedding resize/post_init reinitialization." }, { "left": "issue:33290", "right": "issue:34689", "accept": false, - "reason": "Different bug classes: optimizer memory blowup vs model loading failure." + "reason": "No shared bug: DeepSpeed optimizer OOM is unrelated to model-loading failure." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Both mention Qwen models, but one is a shape-mismatch load failure and the other is an incorrect save_pretrained regression." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Eval-mode gradient checkpointing is unrelated to quantization offloading behavior." + "reason": "Gradient checkpointing in eval mode is unrelated to quantization/offloading behavior." }, { "left": "issue:43493", "right": "issue:43827", "accept": false, - "reason": "SigLIP2 implementation discrepancy is unrelated to docs still referencing pipeline()." + "reason": "A model-implementation discrepancy is not the same as stale docs still referencing removed pipeline() APIs." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "Different model families and different failures; no shared concrete code path." + "reason": "PatchTSTMixer post_init policy and Qwen video-input regression are different bugs." }, { "left": "issue:43316", "right": "issue:45759", "accept": false, - "reason": "Both mention config/API shape, but they do not clearly describe the same underlying bug." + "reason": "Both involve config shape, but Gemma3TextConfig API inconsistency is not the same as Qwen multimodal config unwrapping in from_config." }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "BitNet packed-weight loading failure is unrelated to tokenizer loading for FastSpeech2Conformer." + "reason": "BitNet packed-weight loading and tokenizer import failure are unrelated." }, { "left": "issue:41628", "right": "issue:45372", "accept": false, - "reason": "Both are import errors, but for different symbols, packages, and loaders." + "reason": "Both are import errors, but they come from different symbols, dependencies, and processor-loading paths." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "Both involve config values after reload, but the affected configs and failure modes differ." + "reason": "Different config persistence bugs: trust_remote_code missing fields vs GPTNeoX rotary_pct resetting on reload." }, { "left": "issue:43749", "right": "issue:43931", "accept": false, - "reason": "FSDP CPU RAM efficient loading is a distributed-loading issue, not the same as a Qwen weight-shape mismatch." + "reason": "FSDP CPU RAM-efficient loading and Qwen3-VL weight-shape mismatch are different loading failures." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Model-loading breakage and GenerationMixin import failure are not the same underlying issue." }, { "left": "issue:43873", "right": "issue:44871", "accept": false, - "reason": "Quantization/offloading behavior is unrelated to eos_token_id configuration inconsistency." + "reason": "Quantization/offloading behavior is unrelated to Gemma-3 eos_token_id config inconsistency." }, { - "left": "issue:34689", - "right": "issue:36010", + "left": "issue:33290", + "right": "issue:36331", "accept": false, - "reason": "Different breakages: one is a model loading regression, the other is an import path failure for GenerationMixin." + "reason": "DeepSpeed OOM is unrelated to CustomTrainer.compute_loss receiving an unexpected keyword argument." }, { "left": "issue:44190", "right": "issue:44496", "accept": false, - "reason": "Dataset loading in a training script is unrelated to an unrecognized model/config error." + "reason": "Local dataset loading in an image-classification script is unrelated to an unrecognized model/config_type error." }, { "left": "issue:44855", "right": "issue:45137", "accept": false, - "reason": "Python 3.13 import parsing error is unrelated to DeepSpeed ZeRO3 deque failure." - }, - { - "left": "issue:43316", - "right": "issue:44877", - "accept": false, - "reason": "Different config-loading problems; no evidence they are the same bug." + "reason": "Python 3.13 torch.jit parsing/IndentationError is unrelated to DeepSpeed ZeRO3 deque underflow." }, { "left": "issue:43540", "right": "issue:44514", "accept": false, - "reason": "Both are Qwen multimodal input bugs, but the failing inputs and code paths differ." - }, - { - "left": "issue:42175", - "right": "issue:43316", - "accept": false, - "reason": "Backend dependency packaging issue is unrelated to a Gemma3TextConfig API discrepancy." + "reason": "Both are Qwen multimodal issues, but one is video-input processing and the other is chat-template handling for tool calls." }, { - "left": "issue:43673", - "right": "issue:44743", + "left": "issue:43316", + "right": "issue:44877", "accept": false, - "reason": "Cache-missing in chunked prefill and recurrent-state reset are different cache bugs." + "reason": "Different config issues for different models; not the same API discrepancy." }, { - "left": "issue:43065", - "right": "issue:44617", + "left": "issue:42175", + "right": "issue:43316", "accept": false, - "reason": "A dummy Conv2d in Sam3PixelDecoder is not the same as a Sam3Video CUDA OOM." + "reason": "TensorFlow backend packaging is unrelated to Gemma3TextConfig behavior." }, { "left": "issue:43404", "right": "issue:43441", "accept": false, - "reason": "Both are Mistral-family issues, but one is tied weights and the other is FlashAttention compatibility." - }, - { - "left": "issue:44162", - "right": "issue:44792", - "accept": false, - "reason": "ESM2 regression and janus image-generation test failure are unrelated." + "reason": "Mistral3 lm_head tying and Ministral FlashAttention failure are different bugs with different code paths." } ] }, @@ -8977,10 +9131,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:16998", "issue:22355", @@ -9000,277 +9154,276 @@ "issue:43575", "issue:43606", "issue:43646", + "issue:43673", "issue:43688", "issue:43701", "issue:43742", "issue:43761", "issue:43825", - "issue:43906", "issue:43931", "issue:44060", "issue:44077", + "issue:44162", "issue:44242", "issue:44464", "issue:44479", "issue:44496", - "issue:44521", "issue:44534", "issue:44610", "issue:44617", "issue:44734", + "issue:44743", "issue:44792", "issue:44871", "issue:44913", "issue:44977", "issue:45127", "issue:45200", - "issue:45290", - "issue:45381", "issue:45406", "issue:45563", "issue:45584", "issue:45698" ], "soft_pairs": [ - "issue:25251|issue:28282", + "issue:43065|issue:44617", + "issue:43673|issue:44743", "issue:43295|issue:43825", + "issue:25251|issue:28282", + "issue:44162|issue:44792", "issue:43388|issue:43688", "issue:41950|issue:43475", "issue:44077|issue:44534", "issue:16998|issue:22355", "issue:43550|issue:43701", "issue:44871|issue:45584", - "issue:43761|issue:44479", "issue:43606|issue:43701", + "issue:43761|issue:44479", "issue:45127|issue:45200", "issue:43295|issue:44871", - "issue:43452|issue:44496", "issue:42617|issue:43575", + "issue:43452|issue:44496", "issue:43575|issue:43742", "issue:44734|issue:45406", "issue:43646|issue:44913", "issue:43504|issue:45698", "issue:44617|issue:45584", - "issue:43761|issue:44242", "issue:43931|issue:44060", + "issue:43761|issue:44242", "issue:45563|issue:45584", "issue:32090|issue:35141", "issue:44464|issue:44871", "issue:43065|issue:44610", - "issue:44479|issue:44734", "issue:44792|issue:44977", - "issue:44521|issue:45381", - "issue:43906|issue:45290", - "issue:44464|issue:45563" + "issue:44479|issue:44734" ], - "prepared_review_unit_hash": "63b4d9320b40dc30ba22228bb113fe4d23859ff1af3bfab868eec4d9b2bd5046", + "prepared_review_unit_hash": "5aaf6fc09974e85d2fda2229f6e2f9723f80cc45baa7f826133142af95d25183", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36698, - "estimated_input_tokens": 9175, - "estimated_eval_tokens": 18606 + "serialized_chars": 36084, + "estimated_input_tokens": 9021, + "estimated_eval_tokens": 18298 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster does not contain any convincing duplicate pairs; the soft matches mostly share only broad subsystem vocabulary (pipelines, loading, generation, training) but describe different failures. I picked a highly active issue as the representative issue since there are no PRs and no true canonical duplicate emerges.", - "confidence": 0.23, - "canonical_issue_reason": "issue:44521 is the most active/open, with the strongest inbound reference signal and broad current relevance, so it is the best available representative despite the cluster not being a real duplicate set.", + "summary": "This set is heterogeneous: the issues span unrelated Transformers bugs across loading, generation, processors, training, and model-specific regressions. None of the soft-similarity pairs look like the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:45698 is the broadest and most active report in the set, but the overall collection is too heterogeneous to treat as a true duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the best global issue representative here because it has the most discussion/inbound reference activity among the listed issues and is still open.", + "best_issue_reason": "issue:45698 has the strongest discussion/inbound-reference signal and is the best single anchor if one must be chosen, though it does not represent the unrelated reports well.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:25251", - "right": "issue:28282", + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Both are SAM3/video-related, but one is a dummy layer issue and the other is an OOM report; different code paths and failure modes." + }, + { + "left": "issue:43673", + "right": "issue:44743", "accept": false, - "reason": "Different symptoms and code paths: pipeline top_k return-shape behavior vs AutoModel/PyTorch import failure." + "reason": "Both involve cache behavior, but one is missing GenerationMixin cache in chunked prefill and the other resets recurrent states in modular_qwen3_5; not the same bug." }, { "left": "issue:43295", "right": "issue:43825", "accept": false, - "reason": "Both involve v5 regressions around processors/pipeline messaging, but one is a processor API break and the other is an incorrect task-support error message." + "reason": "Both are v5 regressions, but one is a processor/tokenizer API break and the other is a pipeline error-message problem; unrelated fixes." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Top-k output nesting and a missing PyTorch import are unrelated issues." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 breakage and a Janus image-generation test failure are model-specific and unrelated." }, { "left": "issue:43388", "right": "issue:43688", "accept": false, - "reason": "Training metric gathering bug vs auxiliary-loss normalization bug; unrelated mechanisms and model families." + "reason": "One is a last-batch label-dropping bug in gather_for_metrics; the other is auxiliary-loss normalization in MoE models." }, { "left": "issue:41950", "right": "issue:43475", "accept": false, - "reason": "Video-classification processor lookup issue is unrelated to a SAM3 vision encoder missing attribute." + "reason": "A pipeline processor-selection bug and a missing Sam3VisionEncoderOutput attribute are different failures." }, { "left": "issue:44077", "right": "issue:44534", "accept": false, - "reason": "Optional post_init deprecation/allowance issue is different from non-persistent buffers being filled with junk." + "reason": "Optional post_init handling and non-persistent buffer junk are separate initialization/state bugs." }, { "left": "issue:16998", "right": "issue:22355", "accept": false, - "reason": "Model_max_length question for DeBERTa-v3 is unrelated to missing transformers.onnx module import." + "reason": "Model_max_length on DeBERTa-V3 and a missing transformers.onnx module are unrelated." }, { "left": "issue:43550", "right": "issue:43701", "accept": false, - "reason": "torch.compile SDPA failure in Bamba is unrelated to resume_from_checkpoint key mismatches." + "reason": "A torch.compile/SDPA OOM in Bamba and a resume_from_checkpoint key mismatch are different problems." }, { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "Gemma eos_token_id mismatch is unrelated to Whisper empty-transcription failure after align_special_tokens." + "reason": "Both concern generation/token IDs, but Gemma eos_token_id inconsistency and Whisper empty-transcription failure are distinct bugs." }, { - "left": "issue:43761", - "right": "issue:44479", + "left": "issue:43606", + "right": "issue:43701", "accept": false, - "reason": "CLIP hidden_states regression and Qwen video-input regression are both v5 issues but different models, inputs, and failure points." + "reason": "CPU offload device mismatch and checkpoint key mismatch are unrelated." }, { - "left": "issue:43606", - "right": "issue:43701", + "left": "issue:43761", + "right": "issue:44479", "accept": false, - "reason": "CPU offload device mismatch in bark-small is unrelated to checkpoint key mismatch." + "reason": "CLIPVisionModel hidden_states regression and a Qwen video-input regression affect different models/code paths." }, { "left": "issue:45127", "right": "issue:45200", "accept": false, - "reason": "LoRA merge/tie_word_embeddings collapse is not the same bug as missing default mm_token_type_ids in Gemma 4 fine-tuning." + "reason": "LoRA merge collapse with tied embeddings and Gemma 4 mm_token_type_ids defaults are different bugs." }, { "left": "issue:43295", "right": "issue:44871", "accept": false, - "reason": "Processor/tokenizer regression and eos_token_id configuration mismatch are distinct API/config problems." + "reason": "Processor/tokenizer regression and eos_token_id configuration mismatch are not the same underlying issue." }, { - "left": "issue:43452", - "right": "issue:44496", + "left": "issue:42617", + "right": "issue:43575", "accept": false, - "reason": "gguf_file handling for tokenizer/model loading is not the same as unrecognized model loading due to missing model_type." + "reason": "Running 3d_parallel.py and loading Qwen2-57B with tensor parallelism are different distributed/runtime failures." }, { - "left": "issue:42617", - "right": "issue:43575", + "left": "issue:43452", + "right": "issue:44496", "accept": false, - "reason": "3d_parallel runtime failure and Qwen2-57B-A14B-Instruct OOM during tensor-parallel load are different issues." + "reason": "gguf_file loading breaks specific from_pretrained paths, while the other is an unrecognized model_type config issue." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "OOM with tensor parallel loading is not the same as a key error while loading MobileLLM." + "reason": "Qwen2-57B TP OOM and MobileLLM key-error loading are unrelated model-loading failures." }, { "left": "issue:44734", "right": "issue:45406", "accept": false, - "reason": "serve KV-cache continuation indexing crash is unrelated to Gemma4Processor missing _tokenizer." + "reason": "KV-cache continuation indexing in serve and a missing _tokenizer attribute on Gemma4Processor are different code paths." }, { "left": "issue:43646", "right": "issue:44913", "accept": false, - "reason": "Custom model initialization breakage in Transformers 5.0 is unrelated to GPTNeoX rotary_pct not persisting on reload." + "reason": "Custom model initialization breakage in v5 and GPTNeoXConfig rotary_pct reload drift are unrelated." }, { "left": "issue:43504", "right": "issue:45698", "accept": false, - "reason": "BEiT preset legacy-field loading bug is unrelated to wrong custom module resolution after save/load." + "reason": "Legacy preset loading for BEiT segmentation and wrong custom-module loading after save/load are both loading-related but not the same bug." }, { "left": "issue:44617", "right": "issue:45584", "accept": false, - "reason": "Sam3Video OOM and Whisper empty-transcription failure are different resource vs logic failures." + "reason": "Sam3Video OOM and Whisper empty-transcription handling are unrelated." }, { - "left": "issue:43761", - "right": "issue:44242", + "left": "issue:43931", + "right": "issue:44060", "accept": false, - "reason": "Both are model/training regressions, but hidden_states propagation and load-balancing loss inclusion are unrelated code paths." + "reason": "Qwen3-VL weight-shape mismatch and Qwen3-Next tied-weights warning are different model/config issues." }, { - "left": "issue:43931", - "right": "issue:44060", + "left": "issue:43761", + "right": "issue:44242", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and Qwen3-Next tied-weights warning bug are different loading/config issues." + "reason": "A CLIP vision hidden-states regression and a missing load-balancing loss are unrelated." }, { "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "Paged generate stale warning is unrelated to Whisper empty transcription crash." + "reason": "A stale num_return_sequences warning and Whisper align_special_tokens failure are different generation bugs." }, { "left": "issue:32090", "right": "issue:35141", "accept": false, - "reason": "Trainer gpu_broadcast NoneType error and resize-token-embeddings reinit bug affect different subsystems and behaviors." + "reason": "GPU broadcast NoneType handling and token-embedding resize reinitialization are unrelated." }, { "left": "issue:44464", "right": "issue:44871", "accept": false, - "reason": "Chunked generation inconsistency under compiled forward is unrelated to Gemma eos_token_id config mismatch." + "reason": "Chunked-generation inconsistency with compiled forward and Gemma eos_token_id mismatch are not the same bug." }, { "left": "issue:43065", "right": "issue:44610", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d implementation issue is not the same as OmDet-Turbo processor output-size mismatch." - }, - { - "left": "issue:44479", - "right": "issue:44734", - "accept": false, - "reason": "Qwen2.5-VL/Qwen3 video-input regression and serve KV-cache continuation indexing bug are different failures." + "reason": "SAM3 dummy Conv2d and OmDet-Turbo processor/model size mismatch are different vision-model issues." }, { "left": "issue:44792", "right": "issue:44977", "accept": false, - "reason": "Janus image-generation test failure is unrelated to Qwen3.5 flash-attention generation malfunction." - }, - { - "left": "issue:44521", - "right": "issue:45381", - "accept": false, - "reason": "Assistant mask generation for multimodal chat templates is distinct from Qwen2.5-VL video vision_position_ids being wrong." + "reason": "A Janus image-generation test failure and a Qwen3.5 flash-attention generation bug are unrelated." }, { - "left": "issue:43906", - "right": "issue:45290", - "accept": false, - "reason": "Isolated reproduction of an external issue is unrelated to chat template crashes on tool-call assistant messages." - }, - { - "left": "issue:44464", - "right": "issue:45563", + "left": "issue:44479", + "right": "issue:44734", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency is unrelated to paged generate warning text." + "reason": "Qwen video-input regression and serve KV-cache continuation crash are distinct regressions." } ] }, @@ -9289,38 +9442,35 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:35141", - "issue:36246", "issue:39692", - "issue:41628", "issue:41720", - "issue:41950", "issue:42490", - "issue:43295", "issue:43335", "issue:43388", - "issue:43479", "issue:43540", "issue:43550", "issue:43582", "issue:43644", "issue:43650", "issue:43827", + "issue:43906", "issue:43976", "issue:43994", - "issue:44016", "issue:44077", "issue:44079", "issue:44112", "issue:44190", "issue:44220", "issue:44462", + "issue:44464", "issue:44496", + "issue:44521", "issue:44534", "issue:44734", "issue:44737", @@ -9333,10 +9483,12 @@ "issue:45127", "issue:45245", "issue:45276", + "issue:45290", "issue:45357", "issue:45362", - "issue:45375", + "issue:45381", "issue:45542", + "issue:45563", "issue:45584", "issue:45588", "issue:45600", @@ -9344,7 +9496,10 @@ "issue:45907" ], "soft_pairs": [ + "issue:44521|issue:45381", + "issue:43906|issue:45290", "issue:43827|issue:43994", + "issue:44464|issue:45563", "issue:44534|issue:44913", "issue:44190|issue:44964", "issue:44933|issue:45362", @@ -9356,233 +9511,211 @@ "issue:43388|issue:43582", "issue:35141|issue:42490", "issue:44462|issue:45907", - "issue:43335|issue:44855", "issue:44077|issue:44079", "issue:44938|issue:45542", - "issue:43976|issue:44855", + "issue:43335|issue:44855", "issue:43550|issue:44190", + "issue:43976|issue:44855", "issue:43644|issue:44913", "issue:43540|issue:44734", "issue:44112|issue:45600", - "issue:44496|issue:45803", "issue:43650|issue:44220", + "issue:44496|issue:45803", "issue:43335|issue:44190", "issue:45276|issue:45584", "issue:39692|issue:44190", - "issue:45245|issue:45584", - "issue:43479|issue:45375", - "issue:41950|issue:44016", - "issue:43295|issue:45276", - "issue:36246|issue:41628" + "issue:45245|issue:45584" ], - "prepared_review_unit_hash": "696194d6cbab93cf7987e73883c3be319c417be8dc4831a484a4de086619c68c", + "prepared_review_unit_hash": "7638ebc92705cea9ef77496ffc819edcd8892c59cfc3d743e30af37b43eaa4b4", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36921, - "estimated_input_tokens": 9231, - "estimated_eval_tokens": 18718 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35918, + "estimated_input_tokens": 8980, + "estimated_eval_tokens": 18216 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: one small token-embedding resize/output-embedding theme, plus many unrelated import, config, pipeline, and runtime bugs. No PRs are present, so the best canonical issue is the clearest representative issue in the token-embedding area.", - "confidence": 0.74, - "canonical_issue_reason": "Issue 35141 is the clearest, most general description of the resize-token-embeddings/output-embedding regression and is the best anchor among the issues here.", + "summary": "These items are mostly unrelated bug reports; none of the suggested soft pairs are true duplicates. The only loosely related subgroup is around token-embedding resize/output-embedding behavior, but even there the evidence is not strong enough to merge the other pairs.", + "confidence": 0.94, + "canonical_issue_reason": "issue:35141 is the best anchor for the only coherent subgroup here: it states the underlying resize_token_embeddings/post_init bug in general terms, while the other embedding-related report is a model-specific variant.", "canonical_pr_reason": null, - "best_issue_reason": "35141 is the least-specific, most precise statement of the core bug, while the rest of the cluster is largely unrelated noise.", + "best_issue_reason": "issue:35141 is the strongest issue to keep as the representative bug report because it describes a concrete code-path regression with a clear root cause and broader applicability than the more model-specific variants.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal-related, but one is about all-zero assistant masks in apply_chat_template while the other is about wrong vision_position_ids for Qwen2.5-VL video input; different failures and likely different fixes." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "The first is an isolated reproduction of an older issue, while the second is a crash with tool-call assistant messages; they do not describe the same bug." + }, { "left": "issue:43827", "right": "issue:43994", "accept": false, - "reason": "Both mention pipeline usage, but one is about removed v5 pipelines in docs and the other is a SigLIP2 model/processor correctness issue." + "reason": "Docs still referencing pipeline() and SigLIP2 producing bad outputs are unrelated problems." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Chunked generation inconsistencies with compiled forward and a stale paged-generate warning are different generation issues." }, { "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "One is about non-persistent buffers being junk in v5, the other is a GPTNeoX config field not persisting on reload." + "reason": "Non-persistent buffer junk and GPTNeoX rotary_pct reload behavior affect different code paths." }, { "left": "issue:44190", "right": "issue:44964", "accept": false, - "reason": "Different failure modes: local dataset loading in an example script versus loading a specific multimodal model." + "reason": "Dataset-loading failure in an example script and a model config/load failure for Phi-4 multimodal instruct are not the same bug." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "Both are import/runtime problems, but they involve different symbols and code paths with no clear shared bug." + "reason": "A missing import from image_utils is unrelated to Qwen3.5 chat crashes." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "A device-mapping CUDA assert and a category-count overflow are unrelated failures." + "reason": "Auto device mapping on Qwen3 and a categories-limit RuntimeError are different failures." }, { "left": "issue:44792", "right": "issue:45600", "accept": false, - "reason": "Both affect CI/tests, but they are about different models and different root causes." + "reason": "A Janus generation test failure and stale auto_mappings references to removed configs do not share the same underlying defect." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Python 3.13 import parsing versus a flash-attention crash on missing sink parameters are unrelated." + "reason": "Python 3.13 import parsing failure in DebertaV2 and a flash_attention crash on s_aux=None are unrelated." }, { "left": "issue:44737", "right": "issue:45803", "accept": false, - "reason": "One is a performance/device placement bug in XLNet, the other is a broad exception-handling bug in Fuyu preprocessing." + "reason": "CPU placement in XLNet relative positional encoding and a bare except swallowing errors in FuyuBatchFeature are different bugs." }, { "left": "issue:45127", "right": "issue:45357", "accept": false, - "reason": "Both are model-specific regressions, but one is about LoRA/extended vocab collapse and the other about incorrect visual encoder keys in save_pretrained." + "reason": "LoRA merge collapse with extended vocabulary and incorrect visual encoder keys in save_pretrained are not the same code-path issue." }, { "left": "issue:43388", "right": "issue:43582", "accept": false, - "reason": "A metrics-gathering label truncation bug and an Apple Silicon allocator TypeError are not the same issue." + "reason": "A last-batch label handling bug and an Apple Silicon TypeError in caching_allocator_warmup are unrelated." }, { "left": "issue:35141", "right": "issue:42490", "accept": false, - "reason": "Token-embedding reinitialization and a trailing-slash local path import warning are unrelated." + "reason": "resize_token_embeddings/post_init behavior and a trailing-slash import warning are unrelated." }, { "left": "issue:44462", "right": "issue:45907", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json and list_repo_files not forwarding revision are separate repository-loading bugs." - }, - { - "left": "issue:43335", - "right": "issue:44855", - "accept": false, - "reason": "SwitchTransformers layer construction and a DebertaV2 Python 3.13 import error are unrelated." + "reason": "AutoTokenizer ignoring tokenizer.json and list_repo_files not forwarding revision target different repository/file-resolution paths." }, { "left": "issue:44077", "right": "issue:44079", "accept": false, - "reason": "Optional post_init enforcement in patchtsmixer and ModelOutput key assignment are different code paths." + "reason": "patchtsmixer post_init policy and ModelOutput key assignment with None are different issues." }, { "left": "issue:44938", "right": "issue:45542", "accept": false, - "reason": "Python 3.14 import failure and undefined tf backend from tensorboard-only install are unrelated environment issues." + "reason": "Python 3.14 load failure and a tf-backend warning when only tensorboard is installed are separate compatibility problems." }, { - "left": "issue:43976", + "left": "issue:43335", "right": "issue:44855", "accept": false, - "reason": "Both are Python-version compatibility reports, but they concern different versions and distinct import failures." + "reason": "SwitchTransformers sparse-layer construction and DebertaV2 import parsing are unrelated." }, { "left": "issue:43550", "right": "issue:44190", "accept": false, - "reason": "A torch.compile/SDPA model bug and a dataset loading example bug are unrelated." + "reason": "torch.compile/SDPA failure in Bamba and a local dataset-loading example failure are not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python version support mismatch and DebertaV2 import parsing under Python 3.13 are different compatibility failures." }, { "left": "issue:43644", "right": "issue:44913", "accept": false, - "reason": "Non-persistent buffer corruption and a config reload default-reset bug are not the same underlying defect." + "reason": "Non-persistent buffer initialization junk and GPTNeoX rotary_pct reload are separate state-loading issues." }, { "left": "issue:43540", "right": "issue:44734", "accept": false, - "reason": "Video input validation in Qwen3OmniMoe and KV-cache continuation indexing in serve are different failures." + "reason": "Qwen3OmniMoe video processing ValueError and KV-cache continuation tensor indexing are different runtime failures." }, { "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "These are separate CI breakages with different affected components and causes." - }, - { - "left": "issue:44496", - "right": "issue:45803", - "accept": false, - "reason": "Model config recognition failure and bare-except swallowing errors are unrelated." + "reason": "A stale CI test in GraniteSpeech and broken auto_mappings entries for removed configs are unrelated maintenance issues." }, { "left": "issue:43650", "right": "issue:44220", "accept": false, - "reason": "The first is a nonspecific placeholder title; the second is a concrete feature-extraction bug." + "reason": "The placeholder issue and the _torch_extract_fbank_features bug are not duplicates." }, { - "left": "issue:43335", - "right": "issue:44190", - "accept": false, - "reason": "Single-layer SwitchTransformers config logic and local dataset loading are unrelated." - }, - { - "left": "issue:45276", - "right": "issue:45584", + "left": "issue:44496", + "right": "issue:45803", "accept": false, - "reason": "Resize-token-embeddings/output-embedding behavior and Whisper empty-transcription generation are unrelated." + "reason": "Unrecognized model loading via missing model_type and a bare-except bug in FuyuBatchFeature are unrelated." }, { - "left": "issue:39692", + "left": "issue:43335", "right": "issue:44190", "accept": false, - "reason": "SigLIP2 doc example issues and a local dataset loading failure are different problems." + "reason": "SwitchTransformers sparse-layer behavior and local dataset loading in an example script are unrelated." }, { - "left": "issue:45245", + "left": "issue:45276", "right": "issue:45584", "accept": false, - "reason": "Category-count overflow and Whisper empty-transcription generation are unrelated." - }, - { - "left": "issue:43479", - "right": "issue:45375", - "accept": false, - "reason": "Both involve multimodal config fields, but they describe different models and different serialization/defaulting bugs." - }, - { - "left": "issue:41950", - "right": "issue:44016", - "accept": false, - "reason": "A pipeline processor lookup bug and a notebook syntax error are clearly unrelated." - }, - { - "left": "issue:43295", - "right": "issue:45276", - "accept": false, - "reason": "Processor.tokenizer regression and resize_token_embeddings not updating embeddings are different bugs." - }, - { - "left": "issue:36246", - "right": "issue:41628", - "accept": false, - "reason": "Both are import errors, but one is a missing model-specific processor export and the other is a top-level AutoImageProcessor import issue." + "reason": "Gemma4 resize_token_embeddings/output_embeddings behavior and Whisper empty-transcription generation after align_special_tokens are different bugs." } ] }, @@ -9601,23 +9734,25 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36246", "issue:38175", "issue:38617", + "issue:41628", + "issue:41950", "issue:42175", "issue:42490", "issue:42907", "issue:43065", "issue:43295", "issue:43299", - "issue:43381", "issue:43404", "issue:43441", + "issue:43479", "issue:43526", "issue:43531", "issue:43643", @@ -9628,14 +9763,12 @@ "issue:43976", "issue:44016", "issue:44062", - "issue:44075", "issue:44112", "issue:44186", "issue:44220", "issue:44246", "issue:44279", "issue:44336", - "issue:44368", "issue:44466", "issue:44496", "issue:44561", @@ -9648,24 +9781,28 @@ "issue:45003", "issue:45042", "issue:45216", + "issue:45276", "issue:45335", + "issue:45375", "issue:45446", - "issue:45584", - "issue:45593", "issue:45600", "issue:45632" ], "soft_pairs": [ + "issue:41950|issue:44016", + "issue:43479|issue:45375", + "issue:43295|issue:45276", + "issue:36246|issue:41628", "issue:36246|issue:38617", "issue:44186|issue:44734", "issue:38175|issue:43065", - "issue:42175|issue:44279", "issue:44683|issue:45446", + "issue:42175|issue:44279", "issue:44016|issue:44220", "issue:44466|issue:44913", "issue:43404|issue:45216", - "issue:44734|issue:45632", "issue:44561|issue:45632", + "issue:44734|issue:45632", "issue:44246|issue:45003", "issue:42490|issue:45632", "issue:43643|issue:44496", @@ -9681,220 +9818,216 @@ "issue:43824|issue:44933", "issue:44496|issue:45042", "issue:43526|issue:43901", - "issue:43299|issue:45216", - "issue:44075|issue:44368", - "issue:45335|issue:45584", - "issue:43976|issue:44279", - "issue:43381|issue:45593" + "issue:43299|issue:45216" ], - "prepared_review_unit_hash": "9347925bcd14e02f3fc2002dc678a532b3a33d2a3db900099977a75e12095b8d", + "prepared_review_unit_hash": "06324f74e335087e67daa6dc63a556e7384fc527dde3e2c5b1b69571dff62c4e", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36718, - "estimated_input_tokens": 9180, - "estimated_eval_tokens": 18616 + "serialized_chars": 36738, + "estimated_input_tokens": 9185, + "estimated_eval_tokens": 18626 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated Transformers issues. The soft pairs share broad keywords or subsystems, but they do not describe the same concrete bug/change, so none should be merged as duplicates. There is no meaningful canonical issue/PR for this set.", - "confidence": 0.95, - "canonical_issue_reason": null, + "summary": "These issues are largely heterogeneous; none of the soft pairs look like the same underlying bug or change, so I would not collapse any of them as duplicates. If a representative issue must be chosen, issue 43824 is the strongest anchor because it is a concrete import regression with the most external signal.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43824 is the best canonical anchor: it has the clearest, concrete failure mode (missing top-level import) and the strongest signal (multiple inbound refs and active discussion), making it more representative than the others.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Issue 43824 is the most actionable and well-evidenced issue in the set; the rest are scattered across unrelated models, config fields, pipelines, and regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Video-classification pipeline lookup bug vs notebook syntax error; unrelated symptoms and code paths." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Both involve multimodal config handling, but they target different models and different bugs (default config init vs strict field dropping)." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Different regressions: processor/tokenizer image handling vs resize_token_embeddings not updating Gemma4 embeddings." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different exported symbols and different breakages." + }, { "left": "issue:36246", "right": "issue:38617", "accept": false, - "reason": "Both are import errors, but for different missing symbols in different modules; not the same bug." + "reason": "Unrelated import failures: Qwen2.5 VL image processor vs layer_type_validation." }, { "left": "issue:44186", "right": "issue:44734", "accept": false, - "reason": "Different code paths: tokenizer batching/NER crash vs serve KV-cache continuation indexing." + "reason": "Different failures in different subsystems: tokenizer padding/NER vs serving KV-cache continuation indexing." }, { "left": "issue:38175", "right": "issue:43065", "accept": false, - "reason": "Unrelated models and failures; one is zero probabilities, the other is a dummy Conv2d in a decoder." + "reason": "Siglip2 zero-probabilities issue and Sam3PixelDecoder dummy Conv2d are unrelated model bugs." }, { - "left": "issue:42175", - "right": "issue:44279", + "left": "issue:44683", + "right": "issue:45446", "accept": false, - "reason": "General dependency/install complaints, but no shared concrete failure mode." + "reason": "Both touch flex_attention/PyTorch gating, but one is a compile/runtime failure on torch>=2.9 and the other is an incorrect version check for an import path." }, { - "left": "issue:44683", - "right": "issue:45446", + "left": "issue:42175", + "right": "issue:44279", "accept": false, - "reason": "Both mention flex_attention/versioning, but they point to different import/runtime issues and fixes." + "reason": "Dependency installation issue vs vague dependency issue; no shared concrete code-path or fix." }, { "left": "issue:44016", "right": "issue:44220", "accept": false, - "reason": "A notebook syntax error and an audio feature extraction issue are unrelated." + "reason": "Notebook syntax error vs _torch_extract_fbank_features failure; unrelated." }, { "left": "issue:44466", "right": "issue:44913", "accept": false, - "reason": "Both concern serialization/reload behavior, but different fields and different model classes." + "reason": "Both concern serialization/reload, but one is tied lm_head weights and the other is a GPTNeoXConfig field reset." }, { "left": "issue:43404", "right": "issue:45216", "accept": false, - "reason": "Both involve tied weights/save_pretrained, but they are different regressions on different models." + "reason": "Different model families and different bugs: Mistral3 weight tying vs Qwen3.5 checkpoint save regression." }, { - "left": "issue:44734", + "left": "issue:44561", "right": "issue:45632", "accept": false, - "reason": "Serve KV-cache indexing and local trust_remote_code cache collisions are unrelated." + "reason": "Both involve trust_remote_code, but one is a removed API breakage and the other is a local-model cache-path collision." }, { - "left": "issue:44561", + "left": "issue:44734", "right": "issue:45632", "accept": false, - "reason": "Removal of an API vs cache-path collision are different trust_remote_code failures." + "reason": "Serving KV-cache continuation crash vs trust_remote_code cache collision; different mechanisms and fixes." }, { "left": "issue:44246", "right": "issue:45003", "accept": false, - "reason": "Import slowness and unsafe sys.modules access are related at most indirectly, not the same bug." + "reason": "Import performance issue vs unsafe sys.modules access; not the same bug." }, { "left": "issue:42490", "right": "issue:45632", "accept": false, - "reason": "Both are path-related, but one is a trailing-slash warning and the other is a cache collision." + "reason": "Both are local path handling problems, but one is a trailing-slash warning and the other is a cache collision between leaf-name matches." }, { "left": "issue:43643", "right": "issue:44496", "accept": false, - "reason": "Different config-loading failures: missing fields with trust_remote_code vs unrecognized model_type." + "reason": "Both are config/loading failures, but one is trust_remote_code missing fields and the other is an unrecognized model/type key problem." }, { "left": "issue:44964", "right": "issue:45600", "accept": false, - "reason": "Model loading failure vs stale auto_mappings CI breakage; different causes." + "reason": "Different model-loading/CI failures with no shared code-path." }, { "left": "issue:44112", "right": "issue:44964", "accept": false, - "reason": "CI test flake in GraniteSpeech is unrelated to Phi-4 multimodal loading." + "reason": "CI test flake in GraniteSpeech vs Phi-4 multimodal loading regression; unrelated." }, { "left": "issue:42907", "right": "issue:43441", "accept": false, - "reason": "Same family name, but save-dequantized behavior and FlashAttention loading are distinct bugs." + "reason": "Both mention Ministral/Devstral, but save-dequantized failure and FlashAttention failure are distinct bugs." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "Different multimodal model loading problems with different failure modes." + "reason": "Different model load failures affecting different model families and failure points." }, { "left": "issue:44016", "right": "issue:44062", "accept": false, - "reason": "Notebook syntax error vs tokenizer AddedToken argument collision; unrelated." + "reason": "Notebook syntax error vs AddedToken keyword-argument TypeError; unrelated." }, { "left": "issue:43976", "right": "issue:44987", "accept": false, - "reason": "A Python version support issue is not the same as a specific model-loading regression." + "reason": "Python-version compatibility issue vs a specific model-loading failure; not the same underlying defect." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "Processor/tokenizer regression and resize_token_embeddings mismatch are different code paths." + "reason": "Different embedding-update regressions in different models; not mergeable as one fix." }, { "left": "issue:43673", "right": "issue:44336", "accept": false, - "reason": "Generation cache bug and ANSI-code logging issue are unrelated." + "reason": "Generation cache bug vs ANSI formatting in loading_report; unrelated." }, { "left": "issue:43531", "right": "issue:45600", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and stale config mappings are unrelated." + "reason": "Qwen3-MoE sliding_window behavior vs stale auto_mappings references; different areas and fixes." }, { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "Both are import-related, but they involve different missing exports from different modules." + "reason": "Both are import-related, but one is a missing model class export and the other is a missing image_utils export; different symbols and root causes." }, { "left": "issue:44496", "right": "issue:45042", "accept": false, - "reason": "Model config discovery and image processor torchvision dependency are unrelated." + "reason": "Unrecognized model/config issue vs PIL image processors incorrectly requiring torchvision; unrelated." }, { "left": "issue:43526", "right": "issue:43901", "accept": false, - "reason": "A BEiT processor bug and a docs/behavior mismatch for text classification are not duplicates." + "reason": "BeitImageProcessorFast label reduction bug vs documentation drift for return_all_scores; not the same issue." }, { "left": "issue:43299", "right": "issue:45216", "accept": false, - "reason": "Different regressions affecting different Qwen model families and different save/load behavior." - }, - { - "left": "issue:44075", - "right": "issue:44368", - "accept": false, - "reason": "Optimizer argument handling and tie_word_embeddings warnings are unrelated." - }, - { - "left": "issue:45335", - "right": "issue:45584", - "accept": false, - "reason": "Embedding resize behavior and Whisper empty-transcription generation are different bugs." - }, - { - "left": "issue:43976", - "right": "issue:44279", - "accept": false, - "reason": "Python/package compatibility and a generic dependency issue do not match the same failure." - }, - { - "left": "issue:43381", - "right": "issue:45593", - "accept": false, - "reason": "Gradient checkpointing eval-mode limitation and D-FINE auxiliary-loss behavior are unrelated." + "reason": "Both are version regressions for model loading/saving, but they affect different Qwen variants and different code paths." } ] }, @@ -9913,22 +10046,19 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:33290", "issue:38175", "issue:39692", "issue:41950", - "issue:42994", - "issue:43065", "issue:43295", "issue:43299", - "issue:43317", + "issue:43381", "issue:43441", - "issue:43450", "issue:43479", "issue:43525", "issue:43577", @@ -9937,30 +10067,32 @@ "issue:43901", "issue:43976", "issue:44016", + "issue:44075", "issue:44242", "issue:44279", "issue:44291", "issue:44297", "issue:44351", + "issue:44368", "issue:44462", "issue:44496", "issue:44521", "issue:44617", "issue:44683", "issue:44779", - "issue:44898", "issue:45020", "issue:45081", "issue:45200", "issue:45216", "issue:45278", "issue:45325", + "issue:45335", "issue:45357", "issue:45405", "issue:45542", - "issue:45600", + "issue:45584", + "issue:45593", "issue:45656", - "issue:45712", "issue:45759", "issue:45812", "issue:45823", @@ -9968,22 +10100,26 @@ "issue:45907" ], "soft_pairs": [ + "issue:44075|issue:44368", + "issue:45335|issue:45584", + "issue:43976|issue:44279", + "issue:43381|issue:45593", "issue:43299|issue:45357", "issue:43901|issue:44496", "issue:44496|issue:45759", - "issue:44351|issue:45278", "issue:44521|issue:45325", "issue:41950|issue:45020", + "issue:44351|issue:45278", "issue:43976|issue:45405", "issue:44242|issue:45200", "issue:43479|issue:43525", "issue:44779|issue:45812", "issue:41950|issue:45823", - "issue:38175|issue:44617", "issue:43577|issue:45216", "issue:44683|issue:45542", - "issue:43299|issue:43854", + "issue:38175|issue:44617", "issue:39692|issue:43901", + "issue:43299|issue:43854", "issue:44279|issue:45405", "issue:41950|issue:43650", "issue:43295|issue:44779", @@ -9992,214 +10128,210 @@ "issue:45081|issue:45907", "issue:44016|issue:44291", "issue:43441|issue:45834", - "issue:45600|issue:45712", - "issue:43450|issue:44279", - "issue:33290|issue:45656", - "issue:43065|issue:44898", - "issue:42994|issue:43317" + "issue:33290|issue:45656" ], - "prepared_review_unit_hash": "4a97838951d538e5edc969679a45c3532e518ec50a824bf92e66e69cf743fcff", + "prepared_review_unit_hash": "0a634433dd61ed2343f10287f8d37e82bee7123eafe43d635d84b633ab24be8f", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 36352, - "estimated_input_tokens": 9088, - "estimated_eval_tokens": 18432 + "serialized_chars": 35828, + "estimated_input_tokens": 8957, + "estimated_eval_tokens": 18170 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of distinct Transformers regressions and docs issues, with only superficial similarity around loading/tokenizer/model-compatibility failures. I do not see any pair that is clearly the same underlying bug or change.", - "confidence": 0.82, - "canonical_issue_reason": "issue:45020 is the broadest open regression report in the set and the best umbrella-style representative for the overall 'recent Transformers versions break model loading' theme.", + "summary": "This cluster is heterogeneous rather than duplicate-heavy: it mixes unrelated Transformers issues spanning tokenizers, multimodal configs, pipelines, docs, DeepSpeed/optimizer behavior, and model-loading regressions. None of the soft edges looks like the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue: the cluster spans unrelated bugs/regressions across tokenizers, multimodal configs, pipelines, docs, and DeepSpeed/optimizer behavior.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the strongest global representative: open, detailed, and broad enough to anchor the cluster even though the other items are not true duplicates.", + "best_issue_reason": "No issue cleanly serves as an umbrella; the broadest report (#45020) is still too general to represent the rest of the items.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Optimizer-arg handling is unrelated to the tie_word_embeddings warning; different symptoms and code paths." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "resize_token_embeddings on t5gemma decoder is unrelated to Whisper empty-transcription failure after align_special_tokens." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python-version compatibility and a generic dependency issue are not the same defect." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to D-FINE auxiliary-loss behavior when denoising is off." + }, { "left": "issue:43299", "right": "issue:45357", "accept": false, - "reason": "Different Qwen3VL loading failure vs Qwen3.5 save_pretrained checkpoint-key bug; separate code paths." + "reason": "Model loading regression and save_pretrained key regression affect different code paths." }, { "left": "issue:43901", "right": "issue:44496", "accept": false, - "reason": "Docs mismatch for text classification pipeline vs unrecognized-model/config loading failure." + "reason": "Docs mismatch for return_all_scores is unrelated to an unrecognized-model/config loading error." }, { "left": "issue:44496", "right": "issue:45759", "accept": false, - "reason": "Both involve config/model resolution, but one is unrecognized model loading and the other is AutoModelForCausalLM not unwrapping text_config; not the same bug." - }, - { - "left": "issue:44351", - "right": "issue:45278", - "accept": false, - "reason": "Importing HybridCache missing vs broad post-upgrade import errors; too different and not a single code-path issue." + "reason": "One is config/model recognition failure; the other is from_config failing to unwrap text_config in multimodal configs." }, { "left": "issue:44521", "right": "issue:45325", "accept": false, - "reason": "assistant_masks generation vs temporal position-id scaling in Qwen2.5-VL; unrelated multimodal bugs." + "reason": "All-zero assistant masks and rope-index scaling are distinct multimodal internals." }, { "left": "issue:41950", "right": "issue:45020", "accept": false, - "reason": "Video pipeline processor lookup vs remote_code model breakage; different subsystem and failure mode." + "reason": "A pipeline processor lookup bug is not the same as a broad remote_code compatibility regression." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "Missing HybridCache import and broad import errors after upgrade are not a single concrete bug." }, { "left": "issue:43976", "right": "issue:45405", "accept": false, - "reason": "Python-version compatibility regression vs PEFT minimum-version bump; no shared bug." + "reason": "Python support breakage is unrelated to the PEFT minimum-version bump." }, { "left": "issue:44242", "right": "issue:45200", "accept": false, - "reason": "MoE load-balancing loss gating vs Gemma4 mm_token_type_ids defaulting; separate training semantics." + "reason": "Missing load-balancing loss and default mm_token_type_ids are separate modeling issues." }, { "left": "issue:43479", "right": "issue:43525", "accept": false, - "reason": "Phi4 multimodal config defaults vs Llama4Config missing pad_token_id; different model families and errors." + "reason": "Default multimodal config initialization is unrelated to Llama4Config missing pad_token_id." }, { "left": "issue:44779", "right": "issue:45812", "accept": false, - "reason": "Deepseek tokenizer regression vs Granite tokenizer regression; same broad area, but not the same concrete tokenizer bug." + "reason": "Both are tokenizer regressions, but for different model families and failure modes; no evidence of one shared bug." }, { "left": "issue:41950", "right": "issue:45823", "accept": false, - "reason": "Video-classification pipeline processor lookup vs Gemma4 PLE device mismatch; unrelated." - }, - { - "left": "issue:38175", - "right": "issue:44617", - "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 vs Sam3Video CUDA OOM; entirely different failures." + "reason": "Video pipeline processor lookup and Gemma4 PLE device mismatch are unrelated." }, { "left": "issue:43577", "right": "issue:45216", "accept": false, - "reason": "BLIP2 dtype propagation bug vs Qwen3.5 save_pretrained regression; different code paths." + "reason": "Blip2 dtype propagation and Qwen3.5 save_pretrained corruption are different bugs." }, { "left": "issue:44683", "right": "issue:45542", "accept": false, - "reason": "torch >= 2.9 flex_attention failure vs tensorboard/TensorFlow backend import issue; unrelated." + "reason": "torch>=2.9 flex_attention failure is unrelated to the tensorboard/TensorFlow backend error." }, { - "left": "issue:43299", - "right": "issue:43854", + "left": "issue:38175", + "right": "issue:44617", "accept": false, - "reason": "Qwen3VL MoE loading regression vs GLM-4.7-Flash unit-test loading issue; different models and causes." + "reason": "SigLIP2 zero-probability outputs and Sam3Video OOM are clearly different model-specific problems." }, { "left": "issue:39692", "right": "issue:43901", "accept": false, - "reason": "SigLIP2 documentation example errors vs text-classification docs mismatch; separate documentation bugs." + "reason": "Both involve docs, but they concern different APIs and unrelated fixes." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3VL loading breakage and GLM-4.7-Flash unit-test loading failures are different models and code paths." }, { "left": "issue:44279", "right": "issue:45405", "accept": false, - "reason": "Generic dependency issue vs PEFT version pin bump; not the same underlying problem." + "reason": "A dependency issue and a PEFT version requirement bump are not the same defect." }, { "left": "issue:41950", "right": "issue:43650", "accept": false, - "reason": "Video processor lookup bug vs unrelated 'ADD THE DATA' report." + "reason": "The video-classification processor bug is unrelated to the placeholder 'ADD THE DATA' issue." }, { "left": "issue:43295", "right": "issue:44779", "accept": false, - "reason": "processor.tokenizer/images-to-tokenizer regression vs Deepseek tokenizer wrong results; both tokenizer-related but not the same concrete defect." + "reason": "Processor/tokenizer regression in v4.57.5 is unrelated to DeepSeek tokenizer output changes in v5." }, { "left": "issue:44462", "right": "issue:45081", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json vs Mistral regex patch crash; different failure modes." + "reason": "AutoTokenizer ignoring tokenizer.json and Mistral regex patch crashes are different tokenizer bugs." }, { "left": "issue:44297", "right": "issue:44462", "accept": false, - "reason": "tokenizer_class mismatch on save vs AutoTokenizer ignoring tokenizer.json on load; related area but distinct bug." + "reason": "Tokenizer save_pretrained metadata mismatch is separate from AutoTokenizer ignoring tokenizer.json." }, { "left": "issue:45081", "right": "issue:45907", "accept": false, - "reason": "Mistral regex crash vs list_repo_files revision forwarding; unrelated." + "reason": "A tokenizer regex crash and list_repo_files not forwarding revision are unrelated." }, { "left": "issue:44016", "right": "issue:44291", "accept": false, - "reason": "Notebook syntax error vs init_empty_weights unexpected argument TypeError; separate issues." + "reason": "Notebook syntax error and init_empty_weights argument handling are unrelated." }, { "left": "issue:43441", "right": "issue:45834", "accept": false, - "reason": "Ministral FlashAttention failure vs Kosmos2.5 OCR index error; different models and code paths." - }, - { - "left": "issue:45600", - "right": "issue:45712", - "accept": false, - "reason": "auto_mappings stale references vs leftover dummy classes leaking into dir(transformers); both cleanup-related but not the same bug." - }, - { - "left": "issue:43450", - "right": "issue:44279", - "accept": false, - "reason": "Batched video processor shape bug vs generic dependency issue; no overlap." + "reason": "FlashAttention failure in Ministral-3 and long-input OCR index errors in Kosmos2.5 are distinct issues." }, { "left": "issue:33290", "right": "issue:45656", "accept": false, - "reason": "DeepSpeed adafactor OOM vs optimizer.step being called twice under DeepSpeed; not the same underlying problem." - }, - { - "left": "issue:43065", - "right": "issue:44898", - "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder vs Perceiver non-default-resolution failure; different components and symptoms." - }, - { - "left": "issue:42994", - "right": "issue:43317", - "accept": false, - "reason": "Quantized model saving failure vs dequantized model offload loading failure; separate lifecycle stages and bugs." + "reason": "DeepSpeed-related optimizer OOM and optimizer step being called twice are different failure modes." } ] }, @@ -10218,17 +10350,17 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ - "issue:41628", "issue:42175", - "issue:42491", + "issue:42994", + "issue:43065", "issue:43122", "issue:43262", - "issue:43299", + "issue:43317", "issue:43441", "issue:43450", "issue:43525", @@ -10249,30 +10381,34 @@ "issue:44188", "issue:44261", "issue:44263", + "issue:44279", "issue:44297", "issue:44336", "issue:44361", "issue:44466", "issue:44521", - "issue:44589", "issue:44617", "issue:44623", "issue:44671", "issue:44683", "issue:44749", "issue:44779", + "issue:44898", "issue:44987", "issue:45276", "issue:45290", - "issue:45362", "issue:45397", "issue:45542", - "issue:45561", - "issue:45563", "issue:45593", + "issue:45600", + "issue:45712", "issue:45823" ], "soft_pairs": [ + "issue:45600|issue:45712", + "issue:43450|issue:44279", + "issue:43065|issue:44898", + "issue:42994|issue:43317", "issue:44466|issue:45276", "issue:44261|issue:44263", "issue:43650|issue:45290", @@ -10296,208 +10432,204 @@ "issue:43525|issue:43881", "issue:44188|issue:44336", "issue:43525|issue:43643", - "issue:43450|issue:44617", - "issue:44589|issue:45362", - "issue:41628|issue:43976", - "issue:45561|issue:45563", - "issue:42491|issue:43299" + "issue:43450|issue:44617" ], - "prepared_review_unit_hash": "e0bcd1c29a12ccea85da4a2944b392759e46589ba59e0ea6c2134bc0e46768e7", + "prepared_review_unit_hash": "e9a4a570caf81a6c125f97c9b8073c3f1c4adb608c09311853339cc809d9a709", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 35947, - "estimated_input_tokens": 8987, - "estimated_eval_tokens": 18230 + "serialized_chars": 35940, + "estimated_input_tokens": 8985, + "estimated_eval_tokens": 18226 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The items are mostly separate regressions across tokenizer, chat-template, model-loading, and backend/version compatibility areas. I found no soft pair that clearly represents the same concrete bug, so I kept all soft edges rejected. For the canonical issue, I picked the most broadly representative, high-activity regression report in the set.", - "confidence": 0.34, - "canonical_issue_reason": "issue:44521 has the strongest evidence of being a central user-facing regression in this cluster: it is active, has multiple inbound references, and describes a concrete multimodal chat-template failure rather than a narrow model-specific edge case.", + "summary": "This cluster is heterogeneous: the issues share broad Transformers/v5 regression language, but the paired items point to different code paths and failure modes, so I would not deduplicate any soft-edge pair. The strongest representative issue is the open multimodal `apply_chat_template` regression.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44521 is the clearest ongoing, well-documented regression in the set: open, actively discussed, with a concrete repro and multiple references.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the best representative issue because it is concrete, broadly relevant, and has the highest apparent external impact/activity among the listed issues.", + "best_issue_reason": "issue:44521 is the most actionable representative issue in this mixed cluster because it is open and has the richest current discussion/repro context.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both are repo-hygiene/dummy-object problems, but one is stale auto-mapping references and the other is leftover dummy classes; different fixes." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batch shape bug vs a dependency issue; unrelated failure modes." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Both touch vision models, but one is a dummy Conv2d in Sam3PixelDecoder and the other is Perceiver resizing behavior; not the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Both involve quantization/dequantization, but one is save failure and the other is device_map offload load failure; distinct code paths." + }, { "left": "issue:44466", "right": "issue:45276", "accept": false, - "reason": "Both involve v5 model weight handling, but one is serialization of tied lm_head weights and the other is resize_token_embeddings not updating Gemma4 embedding/output layers; different bugs and code paths." + "reason": "lm_head serialization/tied-weights issue vs Gemma4 embedding resize propagation; different underlying problems." }, { "left": "issue:44261", "right": "issue:44263", "accept": false, - "reason": "These are unrelated GLM/MoE issues: one is a missing rms_norm_eps in MLA q_a_layernorm, the other is torch.split return handling in GlmMoeDsaIndexer." + "reason": "MLA layernorm epsilon precision issue vs torch.split return handling in GlmMoeDsaIndexer; unrelated." }, { "left": "issue:43650", "right": "issue:45290", "accept": false, - "reason": "'ADD THE DATA' is not a technical duplicate, and the assistant-message/tool-call crash is a specific chat-template parsing bug." + "reason": "Generic placeholder issue vs a specific tool-call assistant message crash in apply_chat_template; no same bug." }, { "left": "issue:44623", "right": "issue:45397", "accept": false, - "reason": "One is processor.save_pretrained missing files; the other is gemma-4 zero3 from_pretrained. Different failure points and symptoms." + "reason": "Missing processor save files vs Gemma-4 ZeRO-3 from_pretrained loading; different symptoms and paths." }, { "left": "issue:43441", "right": "issue:44683", "accept": false, - "reason": "Both mention attention kernels, but one is Ministral-3 with FlashAttention and the other is compiled flex_attention on torch>=2.9; not the same concrete bug." + "reason": "Model-specific FlashAttention failure vs compiled flex_attention failure on torch>=2.9; not the same fix target." }, { "left": "issue:44623", "right": "issue:44749", "accept": false, - "reason": "Missing processor files and slow filtering after upgrade are unrelated issues." + "reason": "Processor save_pretrained missing files vs a severe data filtering slowdown; unrelated." }, { "left": "issue:43653", "right": "issue:45593", "accept": false, - "reason": "BigBirdTokenizer special-token registration and a stale generate warning are unrelated." + "reason": "BigBirdTokenizer special-token registration bug vs D-FINE auxiliary-loss behavior; different subsystems." }, { "left": "issue:43262", "right": "issue:44521", "accept": false, - "reason": "Both touch apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant mask generation; different code paths." + "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant masks; distinct bugs." }, { "left": "issue:43723", "right": "issue:44162", "accept": false, - "reason": "Tokenizer loading in v5 and ESM2 model breakage are different regressions." + "reason": "Tokenizer loading regression vs ESM2 model breakage; no shared concrete code path." }, { "left": "issue:44016", "right": "issue:45823", "accept": false, - "reason": "Notebook syntax error and Gemma4 device-mismatch forward failure are unrelated." + "reason": "Notebook syntax error vs Gemma4 device-mismatch runtime bug; unrelated." }, { "left": "issue:43673", "right": "issue:43761", "accept": false, - "reason": "Generation cache missing during chunked_prefill and CLIPVisionModel hidden_states handling are different model/runtime bugs." + "reason": "Generation cache/chunked_prefill issue vs CLIPVision hidden_states regression; different components." }, { "left": "issue:42175", "right": "issue:43976", "accept": false, - "reason": "Backend install packaging and Python-version compatibility are distinct environment issues." + "reason": "Packaging/backend dependency problem vs Python version compatibility issue; separate causes." }, { "left": "issue:44361", "right": "issue:45593", "accept": false, - "reason": "MLukeTokenizer AttributeError is unrelated to the stale num_return_sequences warning." + "reason": "MLukeTokenizer task AttributeError vs D-FINE auxiliary-loss logic; unrelated." }, { "left": "issue:44671", "right": "issue:44779", "accept": false, - "reason": "CamemBERT masked-LM prediction regression and Deepseek tokenizer incorrect results are separate model/tokenizer bugs." + "reason": "Both are v5 regressions affecting outputs, but one is masked LM predictions and the other is tokenizer correctness; not the same underlying bug." }, { "left": "issue:43784", "right": "issue:45542", "accept": false, - "reason": "Importing sentence-transformers fails with undefined nn, while the other issue is about TensorFlow being absent when only tensorboard is installed." + "reason": "sentence-transformers import NameError vs missing TensorFlow backend due to only tensorboard installed; different root causes." }, { "left": "issue:43901", "right": "issue:43994", "accept": false, - "reason": "Docs mismatch for return_all_scores is not the same as SigLIP2 producing nonsensical outputs." + "reason": "Docs mismatch for return_all_scores vs a bad model/pipeline output regression; not duplicates." }, { "left": "issue:44987", "right": "issue:45542", "accept": false, - "reason": "Loading physical-intelligence/fast on v5.1.0 and undefined tf backend error are different failures." + "reason": "Specific model loading failure vs TensorFlow backend installation problem; unrelated." }, { "left": "issue:43122", "right": "issue:43650", "accept": false, - "reason": "Tokenizer output changes across versions are unrelated to the placeholder 'ADD THE DATA' issue." + "reason": "Tokenizer version regression vs a placeholder/data request issue; no overlap in bug." }, { "left": "issue:43824", "right": "issue:43976", "accept": false, - "reason": "A missing Qwen2.5-VL export and a Python version support problem are not duplicates." + "reason": "Missing exported class import vs Python 3.9+ compatibility problem; different issues." }, { "left": "issue:44297", "right": "issue:45397", "accept": false, - "reason": "Tokenizer class serialization mismatch and gemma-4 zero3 loading are different serialization/loading bugs." + "reason": "Tokenizer save metadata mismatch vs Gemma-4 zero3 loading failure; distinct behavior." }, { "left": "issue:43525", "right": "issue:43881", "accept": false, - "reason": "Missing pad_token_id on Llama4Config and glm-4v-9b loading failure are model-specific but not the same bug." + "reason": "Missing pad_token_id on Llama4Config vs glm-4v-9b loading failure; not the same concrete defect." }, { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "torch.compile attention-kernel divergence and ANSI codes in loading_report are unrelated." + "reason": "torch.compile attention-branch divergence vs ANSI code emission in loading_report; unrelated." }, { "left": "issue:43525", "right": "issue:43643", "accept": false, - "reason": "Llama4Config missing pad_token_id and trust_remote_code returning missing fields are separate config-loading issues." + "reason": "The latter is a general missing-fields issue with trust_remote_code, but the former is a specific Llama4Config attribute absence; too weak to merge as one bug." }, { "left": "issue:43450", "right": "issue:44617", "accept": false, - "reason": "Video batched-shape handling and Sam3Video CUDA OOM are different problems." - }, - { - "left": "issue:44589", - "right": "issue:45362", - "accept": false, - "reason": "Float8 storage lookup failure and Qwen3.5-35B chat crash are unrelated runtime issues." - }, - { - "left": "issue:41628", - "right": "issue:43976", - "accept": false, - "reason": "AutoImageProcessor import failure and Python-version compatibility are unrelated." - }, - { - "left": "issue:45561", - "right": "issue:45563", - "accept": false, - "reason": "pytest-xdist race on captured_info.txt and a stale generation warning are unrelated." - }, - { - "left": "issue:42491", - "right": "issue:43299", - "accept": false, - "reason": "Both involve Qwen3/MoE on v5, but one is a LoRA model incompatibility and the other is a Qwen3VL MoE loading breakage; not clearly the same concrete bug." + "reason": "Batched video shape bug vs CUDA OOM in Sam3Video; different failure modes." } ] }, @@ -10516,19 +10648,19 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36246", + "issue:41628", "issue:41950", + "issue:42491", "issue:42757", - "issue:42886", "issue:43065", "issue:43232", - "issue:43257", - "issue:43262", + "issue:43299", "issue:43352", "issue:43408", "issue:43526", @@ -10536,6 +10668,7 @@ "issue:43596", "issue:43673", "issue:43901", + "issue:43976", "issue:44162", "issue:44220", "issue:44242", @@ -10547,17 +10680,15 @@ "issue:44485", "issue:44496", "issue:44561", + "issue:44589", "issue:44749", "issue:44779", "issue:44857", "issue:44871", "issue:44877", "issue:44987", - "issue:44995", "issue:45003", - "issue:45137", "issue:45200", - "issue:45229", "issue:45250", "issue:45292", "issue:45362", @@ -10565,23 +10696,28 @@ "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:45561|issue:45563", + "issue:42491|issue:43299", "issue:44336|issue:44373", "issue:44242|issue:45593", "issue:44295|issue:45397", "issue:41950|issue:44220", "issue:44246|issue:44496", "issue:43531|issue:45362", - "issue:36246|issue:42757", - "issue:36246|issue:44351", "issue:43352|issue:45250", + "issue:36246|issue:42757", "issue:43526|issue:45003", + "issue:36246|issue:44351", "issue:44336|issue:44485", "issue:45003|issue:45561", "issue:43673|issue:44561", @@ -10597,240 +10733,236 @@ "issue:45292|issue:45701", "issue:43232|issue:44336", "issue:44987|issue:45459", - "issue:42886|issue:45229", "issue:43065|issue:43408", "issue:44496|issue:45003", - "issue:45375|issue:45759", - "issue:43262|issue:44246", - "issue:43257|issue:45137", - "issue:44995|issue:45200" + "issue:45375|issue:45759" ], - "prepared_review_unit_hash": "9f497729fa03af61a97d57eeda2a6d32c2c4b5b196b6960869e0ca77e6af43a7", + "prepared_review_unit_hash": "1ed288d19888d5534e09e7dc41e84d48d4a0d1010a630bdd555692f00a1a02ef", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37300, - "estimated_input_tokens": 9325, - "estimated_eval_tokens": 18906 + "serialized_chars": 37278, + "estimated_input_tokens": 9320, + "estimated_eval_tokens": 18896 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is very heterogeneous: most pairs are only loosely related by broad themes like import failures, config loading, generation, or loss computation, but they do not look like the same underlying bug. I would not merge any of the soft edges as duplicates.", - "confidence": 0.82, - "canonical_issue_reason": "issue:44246 is the most central node in the cluster by soft-link connectivity, so it is the best single anchor if one issue must represent the cluster, even though the cluster itself is not a true duplicate set.", + "summary": "These are mostly loosely related Transformers issues, but the suggested soft pairs are not true duplicates: they mix different models, different code paths, or unrelated docs/perf/config problems.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43299 is the most concrete version-regression model-loading report in the set, so it works best as a representative anchor; the rest are mostly separate bugs rather than one duplicate thread.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44246 has the strongest cross-links and substantial discussion activity, making it the best representative issue for triage.", + "best_issue_reason": "issue:43299 has a clear reproduction scope and a specific failing path (Qwen3VL MoE loading on v5.0.0.dev0), making it the strongest single issue to triage from this mixed cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Different failures: float8 storage lookup vs a Qwen3.5 chat crash." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Import error for AutoImageProcessor vs a Python-version compatibility problem." + }, { "left": "issue:43901", "right": "issue:44246", "accept": false, - "reason": "Docs wording about return_all_scores and an intermittent import slowdown are unrelated problems." + "reason": "Docs mismatch in a pipeline vs slow package import; unrelated code paths." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "pytest-xdist file race vs a stale generation warning; no shared bug." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen/MoE, but they are different model families and different load failures." }, { "left": "issue:44336", "right": "issue:44373", "accept": false, - "reason": "ANSI output in loading_report and a wrong docstring for position_ids are not the same bug." + "reason": "ANSI output in loading_report vs a wrong docstring; not the same issue." }, { "left": "issue:44242", "right": "issue:45593", "accept": false, - "reason": "Both concern loss terms, but they affect different models and different code paths." + "reason": "Different loss-missing bugs in different models and settings." }, { "left": "issue:44295", "right": "issue:45397", "accept": false, - "reason": "A position_ids buffer access error is distinct from a Gemma-4 ZeRO3 from_pretrained loading failure." + "reason": "Position_ids buffer access vs Gemma-4 Zero3 loading; unrelated." }, { "left": "issue:41950", "right": "issue:44220", "accept": false, - "reason": "Video-classification processor lookup and _torch_extract_fbank_features() are unrelated audio/video issues." + "reason": "Video pipeline image-processor lookup vs audio fbank feature extraction; different subsystems." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import performance and unrecognized model config loading are different failure modes." + "reason": "Import latency vs unrecognized model/config loading; not duplicates." }, { "left": "issue:43531", "right": "issue:45362", "accept": false, - "reason": "Both mention Qwen, but one is a sliding_window bug and the other is a chat/runtime crash; not the same issue." + "reason": "Different Qwen bugs: sliding window behavior vs a chat crash." }, { - "left": "issue:36246", - "right": "issue:42757", + "left": "issue:43352", + "right": "issue:45250", "accept": false, - "reason": "These are different missing-import errors for different symbols." + "reason": "Specific Nemotron Flash Attention support bug vs a generic Flash Attention issue." }, { "left": "issue:36246", - "right": "issue:44351", + "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they concern different missing exports and different root causes." + "reason": "Different missing-symbol imports from different packages." }, { - "left": "issue:43352", - "right": "issue:45250", + "left": "issue:43526", + "right": "issue:45003", "accept": false, - "reason": "A specific model not supporting Flash Attention 2.0 is not the same as a generic FA2 issue title." + "reason": "BeitImageProcessorFast label reduction vs sys.modules access in modeling_utils." }, { - "left": "issue:43526", - "right": "issue:45003", + "left": "issue:36246", + "right": "issue:44351", "accept": false, - "reason": "A BeitImageProcessorFast label reduction bug is unrelated to unsafe sys.modules access." + "reason": "Both are import errors, but for different exported symbols and different failure modes." }, { "left": "issue:44336", "right": "issue:44485", "accept": false, - "reason": "ANSI logging artifacts and GLM-5 RoPE implementation are unrelated." + "reason": "Terminal ANSI leakage vs GLM-5 RoPE implementation; unrelated." }, { "left": "issue:45003", "right": "issue:45561", "accept": false, - "reason": "sys.modules access and a pytest-xdist file race are separate concurrency/import problems." + "reason": "Unsafe sys.modules access vs a test-file race condition; different bugs." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Chunked-prefill cache handling and removal of is_torch_fx_available affect different code paths." + "reason": "Generation cache handling vs removal of an import helper for trust_remote_code models." }, { "left": "issue:44246", "right": "issue:44871", "accept": false, - "reason": "Import slowdown and Gemma eos_token_id inconsistency are unrelated." + "reason": "Slow import vs inconsistent eos_token_id config; unrelated." }, { "left": "issue:44242", "right": "issue:44857", "accept": false, - "reason": "Missing load-balancing loss and an AMP crash in LwDetrImageLoss are different bugs." + "reason": "Missing load-balancing loss vs a float16 CUDA loss crash; not the same code path." }, { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "ESM2 breakage and Gemma 4 token-type defaults are unrelated model-specific issues." + "reason": "ESM2 breakage vs Gemma-4 token-type defaults; different models and fixes." }, { "left": "issue:44295", "right": "issue:44749", "accept": false, - "reason": "A buffer read error and a tokenizer slowdown after upgrade are not the same underlying bug." + "reason": "Buffer registration error vs a tokenizer/filtering slowdown after upgrade." }, { "left": "issue:36246", "right": "issue:43596", "accept": false, - "reason": "An import-name failure and a DeepSpeed zero3 IndexError are unrelated." + "reason": "ImportError on Qwen image processor vs a zero3/BertModel IndexError." }, { "left": "issue:44877", "right": "issue:45375", "accept": false, - "reason": "Both involve config strictness, but they are different models and likely different missing fields." + "reason": "Strict config loading granite_speech vs missing deepstack_visual_indexes in Qwen vision config." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "Tokenizer correctness regression and resize_token_embeddings not syncing output embeddings are different issues." + "reason": "Tokenizer output regression vs resize_token_embeddings not updating output embeddings." }, { "left": "issue:45292", "right": "issue:45584", "accept": false, - "reason": "Embedding resize behavior and Whisper empty-transcription generation are unrelated." + "reason": "Embedding resize bug vs Whisper empty-transcription generation failure." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "A docs mismatch and unsafe sys.modules access do not share the same bug." + "reason": "Pipeline docs mismatch vs unsafe sys.modules access; no overlap." }, { "left": "issue:45292", "right": "issue:45701", "accept": false, - "reason": "Tokenization changes across versions and embedding resize/output mismatch are not the same defect." + "reason": "Embedding resize/output mismatch vs version-dependent tokenization changes." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs handling and ANSI codes in loading_report are unrelated." + "reason": "Generation kwarg update bug vs terminal ANSI output in loading_report." }, { "left": "issue:44987", "right": "issue:45459", "accept": false, - "reason": "A model-loading regression and tokenizer exception masking are different tokenizer/loading problems." - }, - { - "left": "issue:42886", - "right": "issue:45229", - "accept": false, - "reason": "Offline cache loading and multi-GPU CUDA OOM are unrelated." + "reason": "Model loading failure on v5.1.0 vs tokenizer error masking when protobuf is missing." }, { "left": "issue:43065", "right": "issue:43408", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and sam3_video vs sam3_tracker config mismatch are not the same bug." + "reason": "Dummy conv in Sam3PixelDecoder vs a model-type mismatch warning for sam3_video/sam3_tracker." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Unrecognized model config and unsafe sys.modules access are different loading failures." + "reason": "Config/model-type resolution failure vs unsafe sys.modules access; distinct problems." }, { "left": "issue:45375", "right": "issue:45759", "accept": false, - "reason": "Missing a strict config field and failing to unwrap text_config are different composite-model config bugs." - }, - { - "left": "issue:43262", - "right": "issue:44246", - "accept": false, - "reason": "Audio chat-template sampling-rate defaults and import slowdown are unrelated." - }, - { - "left": "issue:43257", - "right": "issue:45137", - "accept": false, - "reason": "Qwen3 MoE weight conversion and DeepSpeed deque underflow are different distributed-training failures." - }, - { - "left": "issue:44995", - "right": "issue:45200", - "accept": false, - "reason": "A stale indexer cache crash and a missing mm_token_type_ids default are unrelated." + "reason": "Missing strict field in a Qwen vision config vs AutoModelForCausalLM not unwrapping text_config; related domain but different concrete bugs." } ] }, @@ -10849,20 +10981,21 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:28282", "issue:30990", - "issue:41628", "issue:42371", + "issue:42886", "issue:42994", "issue:43232", + "issue:43257", + "issue:43262", "issue:43475", "issue:43482", - "issue:43525", "issue:43540", "issue:43643", "issue:43646", @@ -10873,22 +11006,22 @@ "issue:44060", "issue:44077", "issue:44162", + "issue:44246", "issue:44297", "issue:44361", "issue:44368", "issue:44466", "issue:44623", - "issue:44661", "issue:44734", "issue:44749", "issue:44869", "issue:44933", "issue:44977", "issue:44995", - "issue:45081", "issue:45092", - "issue:45103", "issue:45137", + "issue:45200", + "issue:45229", "issue:45230", "issue:45278", "issue:45310", @@ -10903,24 +11036,28 @@ "issue:45656" ], "soft_pairs": [ - "issue:44060|issue:44077", + "issue:42886|issue:45229", + "issue:43257|issue:45137", + "issue:43262|issue:44246", + "issue:44995|issue:45200", "issue:43475|issue:43540", - "issue:43653|issue:44162", + "issue:44060|issue:44077", "issue:44466|issue:45335", + "issue:43653|issue:44162", "issue:45397|issue:45656", - "issue:44368|issue:45563", "issue:44995|issue:45588", + "issue:44368|issue:45563", "issue:44368|issue:44977", "issue:43673|issue:44734", "issue:45137|issue:45600", "issue:43931|issue:44368", "issue:44933|issue:45459", "issue:44869|issue:45356", - "issue:43232|issue:43673", "issue:44297|issue:44623", - "issue:43673|issue:45278", - "issue:43646|issue:44162", + "issue:43232|issue:43673", "issue:44361|issue:44749", + "issue:43646|issue:44162", + "issue:43673|issue:45278", "issue:44623|issue:45656", "issue:44749|issue:45656", "issue:44749|issue:45310", @@ -10930,238 +11067,228 @@ "issue:42371|issue:45092", "issue:43475|issue:43643", "issue:44038|issue:44623", - "issue:43475|issue:45381", - "issue:41628|issue:44933", - "issue:45081|issue:45103", - "issue:43475|issue:44661", - "issue:42994|issue:43525" + "issue:43475|issue:45381" ], - "prepared_review_unit_hash": "91ced0ba32dab54dee0754efe7f9f22fbdf26360ed0c5cf94c178b48cb2352ad", + "prepared_review_unit_hash": "b99a8b016c653fb8a6af484cfad62016b4495c0fb83f4d55adb645fc70a44571", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 36715, - "estimated_input_tokens": 9179, - "estimated_eval_tokens": 18614 + "serialized_chars": 37146, + "estimated_input_tokens": 9287, + "estimated_eval_tokens": 18830 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated issue reports, with a loose common thread of Transformers v5 regressions and import/model-loading breakages. None of the soft-edge pairs look like the exact same underlying bug or change, so I would not merge any of them.", - "confidence": 0.38, - "canonical_issue_reason": "issue:45278 is the broadest and most cluster-representative report: it covers widespread import breakages after upgrading from 4.57.0 to 5.5.0, which matches the main theme better than the model-specific or symptom-specific issues.", + "summary": "This cluster is highly heterogeneous: loading/import errors, generation-cache bugs, tokenizer/processor save issues, multimodal model-specific failures, and unrelated deepspeed/CI regressions. I don\u2019t see a single duplicate family here, so all soft-edge pairs should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best global issue candidate because it is broad, current, and describes a user-facing regression class that can subsume several of the other v5-related reports.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44060", - "right": "issue:44077", + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache loading and Gemma 4 multi-GPU OOM are unrelated failure modes." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed is not the same bug as the ZeRO3 deque IndexError." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio processor sample-rate defaulting and slow import are different subsystems and symptoms." + }, + { + "left": "issue:44995", + "right": "issue:45200", "accept": false, - "reason": "Both mention warnings, but they concern different models and different code paths; no evidence of the same bug." + "reason": "GlmMoeDsa stale indexer cache is unrelated to Gemma 4 mm_token_type_ids defaults." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "Both are video/model issues, but they affect different architectures with distinct failures and are not plausibly the same fix." + "reason": "Both are multimodal, but SAM3 encoder attribute failure and Qwen3OmniMoe video-processing ValueError are different code paths." }, { - "left": "issue:43653", - "right": "issue:44162", + "left": "issue:44060", + "right": "issue:44077", "accept": false, - "reason": "Different models and different failure modes; too broad a similarity to treat as one underlying bug." + "reason": "Incorrect tied-weights warning and patchtsmixer post_init policy are unrelated model/config issues." }, { "left": "issue:44466", "right": "issue:45335", "accept": false, - "reason": "Both involve embeddings/tied weights, but one is serialization and the other is resize propagation; not the same concrete defect." + "reason": "Both mention tied embeddings, but one is serialization inconsistency and the other is resize_token_embeddings not updating decoder embeddings." }, { - "left": "issue:45397", - "right": "issue:45656", + "left": "issue:43653", + "right": "issue:44162", "accept": false, - "reason": "These are unrelated: one is a from_pretrained/ZeRO3 loading problem, the other is a deepspeed optimizer-step issue." + "reason": "BigBirdTokenizer special-token registration and ESM2 breakage are unrelated." }, { - "left": "issue:44368", - "right": "issue:45563", + "left": "issue:45397", + "right": "issue:45656", "accept": false, - "reason": "Only the presence of a warning is shared; the model, API, and bug mechanism are different." + "reason": "Gemma-4 Zero3 from_pretrained failure is not the same as deepspeed calling optimizer.step twice." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "Different subsystems and symptoms: stale cache in one model versus flash-attention crash in another." + "reason": "Stale indexer cache in GlmMoeDsa and flash_attention.py crashing on s_aux=None are separate bugs." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "A tied-word-embeddings warning in ms-swift fine-tuning is unrelated to paged generate() warning behavior." }, { "left": "issue:44368", "right": "issue:44977", "accept": false, - "reason": "Both involve Qwen3.5 and generation/fine-tuning, but the reported failures are different and not the same code-path problem." + "reason": "Qwen3.5 tied-embedding warning and flash-attention generation failure do not share the same underlying defect." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Both are cache-related generation issues, but one is missing cache in chunked prefill and the other is wrong indexing in serve responses; not one bug." + "reason": "Both involve generation/cache, but chunked_prefill cache handling and /v1/responses continuation indexing are different code paths." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "Completely different topics: DeepSpeed ZeRO3 deque error versus removed auto-mapping config references." + "reason": "ZeRO3 deque underflow and auto_mappings references to removed Sam3LiteText configs are unrelated." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "Different models and unrelated behaviors; no shared underlying defect is evident." + "reason": "Qwen3-VL weight-shape mismatch and Qwen3.5 tied-embeddings warning are different model initialization problems." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "Both touch imports, but one is a missing public import and the other is tokenizer error handling; not the same issue." + "reason": "Missing image_utils import and protobuf-decode-error handling are different import/error-reporting bugs." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Tokenizer/decoding regressions, but for different models and different failure conditions." + "reason": "Whisper word-timestamp crash and Kimi-K2.5 tokenizer codec regression are both tokenizer-related but not the same bug." }, { - "left": "issue:43232", - "right": "issue:43673", + "left": "issue:44297", + "right": "issue:44623", "accept": false, - "reason": "Both relate to generation internals, but one is sync_gpus kwarg handling and the other is cache availability; too different to merge." + "reason": "Tokenizer save_pretrained writes the wrong tokenizer_class, while processor.save_pretrained is missing files; these are distinct save-path issues." }, { - "left": "issue:44297", - "right": "issue:44623", + "left": "issue:43232", + "right": "issue:43673", "accept": false, - "reason": "Both are save_pretrained bugs, but one is tokenizer metadata and the other is processor file output; not the same concrete defect." + "reason": "sync_gpus generation-kwargs update and missing GenerationMixin cache in chunked_prefill are separate generation bugs." }, { - "left": "issue:43673", - "right": "issue:45278", + "left": "issue:44361", + "right": "issue:44749", "accept": false, - "reason": "One is a generation cache bug, the other is a broad import-regression report; they do not describe the same problem." + "reason": "MLukeTokenizer task AttributeError and a data-filtering slowdown after upgrade are unrelated." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Custom model initialization breakage versus a model-family workflow regression; too generic to be the same bug." + "reason": "Transformers 5 custom model init breakage and ESM2 breakage are different model-loading failures." }, { - "left": "issue:44361", - "right": "issue:44749", + "left": "issue:43673", + "right": "issue:45278", "accept": false, - "reason": "An AttributeError in a tokenizer versus a slowdown after upgrade; no common underlying code-path." + "reason": "A generation cache bug and broad import errors after upgrade are not the same underlying issue." }, { "left": "issue:44623", "right": "issue:45656", "accept": false, - "reason": "Save-pretrained file emission and optimizer stepping are unrelated." - }, - { - "left": "issue:44749", - "right": "issue:45310", - "accept": false, - "reason": "Performance regression versus Qwen3.5-Moe from_pretrained error; different failures." + "reason": "Processor save_pretrained missing files is unrelated to deepspeed double optimizer stepping." }, { "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "Slow filtering after upgrade and duplicate optimizer stepping are unrelated." + "reason": "Performance regression in filtering does not match a deepspeed optimizer-step duplication bug." }, { "left": "issue:44749", "right": "issue:45310", "accept": false, - "reason": "No shared underlying bug: one is a runtime slowdown, the other is a model-loading failure." + "reason": "The filtering slowdown and Qwen3.5 MoE from_pretrained error are separate issues." }, { "left": "issue:42994", "right": "issue:43482", "accept": false, - "reason": "Both involve model formats and loading/saving, but quantized model saving and GGUF loading under v5 are distinct issues." + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are opposite directions and different formats." }, { "left": "issue:28282", "right": "issue:30990", "accept": false, - "reason": "A missing PyTorch dependency error and a sentence-transformers loading hang are different environment/load problems." + "reason": "PyTorch-missing AutoModel ImportError and Sentence Transformers loading hang are not the same bug." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "One is an unspecified bug report and the other is a specific ZeRO3/from_pretrained failure; not enough to connect them." + "reason": "A generic bug report cannot be merged with a specific Gemma-4 Zero3 from_pretrained failure." }, { "left": "issue:42371", "right": "issue:45092", "accept": false, - "reason": "TF32 API guidance and remote-code/meta-init incompatibility are unrelated." + "reason": "TF32 configuration guidance and InternVL2 meta-initialization incompatibility are unrelated." }, { "left": "issue:43475", "right": "issue:43643", "accept": false, - "reason": "SAM3 video output fields and AutoConfig missing fields with trust_remote_code=True are different bug classes." + "reason": "SAM3 video encoder missing attribute and trust_remote_code AutoConfig field loss are different failures." }, { "left": "issue:44038", "right": "issue:44623", "accept": false, - "reason": "Qwen3-VL-Moe v5 breakage and processor.save_pretrained missing files are not the same problem." + "reason": "Qwen3-VL-Moe transformers v5 bug and processor.save_pretrained missing files are unrelated." }, { "left": "issue:43475", "right": "issue:45381", "accept": false, - "reason": "Both concern vision/video models, but they affect different models and different internal fields/logic." - }, - { - "left": "issue:41628", - "right": "issue:44933", - "accept": false, - "reason": "Both are import-related, but they refer to different missing symbols and likely different export paths." - }, - { - "left": "issue:45081", - "right": "issue:45103", - "accept": false, - "reason": "Tokenizer regex patching and auto-docstring annotation handling are unrelated." - }, - { - "left": "issue:43475", - "right": "issue:44661", - "accept": false, - "reason": "A SAM3 vision encoder attribute error and add-new-model-like tokenizer mapping failure are not the same defect." - }, - { - "left": "issue:44038", - "right": "issue:44623", - "accept": false, - "reason": "No shared underlying code-path; one is a model-specific v5 bug and the other is serialization output missing files." + "reason": "SAM3 Video missing fpn_position_embeddings and Qwen2.5-VL wrong vision_position_ids are separate video-model bugs." } ] }, @@ -11180,10 +11307,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:30990", "issue:35141", @@ -11196,15 +11323,14 @@ "issue:42898", "issue:42994", "issue:43232", - "issue:43278", "issue:43377", + "issue:43475", "issue:43479", "issue:43504", + "issue:43525", "issue:43526", "issue:43673", "issue:43704", - "issue:43784", - "issue:43824", "issue:43873", "issue:43976", "issue:44038", @@ -11214,15 +11340,17 @@ "issue:44222", "issue:44242", "issue:44351", - "issue:44373", "issue:44496", "issue:44568", "issue:44623", + "issue:44661", "issue:44792", "issue:44869", "issue:44933", "issue:44945", "issue:44964", + "issue:45081", + "issue:45103", "issue:45137", "issue:45200", "issue:45310", @@ -11230,10 +11358,13 @@ "issue:45478", "issue:45561", "issue:45712", - "issue:45753", - "issue:45812" + "issue:45753" ], "soft_pairs": [ + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:43475|issue:44661", + "issue:42994|issue:43525", "issue:45375|issue:45478", "issue:43232|issue:44188", "issue:42673|issue:43704", @@ -11243,260 +11374,253 @@ "issue:42831|issue:44222", "issue:44945|issue:45753", "issue:44222|issue:45310", - "issue:42994|issue:44164", - "issue:36010|issue:41628", "issue:43673|issue:44188", - "issue:42175|issue:45712", + "issue:36010|issue:41628", + "issue:42994|issue:44164", "issue:42222|issue:45200", + "issue:42175|issue:45712", "issue:43232|issue:44792", "issue:44038|issue:45310", - "issue:43377|issue:44242", "issue:43526|issue:45561", "issue:43504|issue:45561", "issue:44496|issue:45561", + "issue:43377|issue:44242", "issue:44964|issue:45137", "issue:42175|issue:44933", "issue:42898|issue:44568", "issue:30990|issue:35141", - "issue:43479|issue:44869", "issue:43976|issue:44933", + "issue:43479|issue:44869", "issue:43479|issue:44079", - "issue:44188|issue:44373", - "issue:43784|issue:43824", - "issue:44623|issue:45310", - "issue:42898|issue:45812", - "issue:43278|issue:45137" + "issue:44623|issue:45310" ], - "prepared_review_unit_hash": "5588d8a3cea2150ffa6ae5878845ffefc83403c50e8e48eb316d0e182466d40e", + "prepared_review_unit_hash": "7957d1c363d0912b679721c9d5578077f12198ad39f70297c1fdc3ac73dbfcec", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 36428, - "estimated_input_tokens": 9107, - "estimated_eval_tokens": 18470 + "serialized_chars": 36576, + "estimated_input_tokens": 9144, + "estimated_eval_tokens": 18544 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a set of unrelated transformer bug reports, with one clear duplicate pair around the Qwen3ForCausalLM VRAM leak. I would canonicalize that pair; the rest should stay separate.", - "confidence": 0.91, - "canonical_issue_reason": "issue:42673 is the stronger canonical: it is the earlier report, has much more discussion/references, and matches issue:43704 exactly on the same Qwen3ForCausalLM multi-dataloader-thread VRAM leak.", + "summary": "This cluster is heterogeneous and does not contain any true duplicate pairs. The strongest apparent overlaps are superficial topical similarities around import regressions, Qwen/MoE loading, and save/load behavior, but each points to a different code path.", + "confidence": 0.74, + "canonical_issue_reason": "issue:41628 is the clearest representative of the import/export regression mini-theme and the most broadly phrased among the similar-looking issues, even though the cluster overall is not a single duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42673 is the best representative issue because it is the clearest true duplicate target and the most complete/active report among the accepted pair.", + "best_issue_reason": "issue:41628 is the best single anchor for triage because it is concrete, library-wide, and sits closest to the other import-related reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import failures, but they target different missing exports/modules (`AutoImageProcessor` vs `image_utils`) and likely different fixes." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Different failure modes: Mistral regex patching vs auto-docstring annotation handling." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "SAM3 vision output attribute breakage vs tokenizer-mapping/model-registration logic; not the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving failure and `Llama4Config.pad_token_id` are separate config/persistence problems." + }, { "left": "issue:45375", "right": "issue:45478", "accept": false, - "reason": "Same model family, but these describe different failures: missing config field being dropped vs a from_pretrained error. Not the same underlying bug." + "reason": "Same model family, but one is a missing config field and the other is a `from_pretrained` loading regression; different underlying issues." }, { "left": "issue:43232", "right": "issue:44188", "accept": false, - "reason": "Both are generation-related, but one is about cache updates after sync_gpus and the other is about attention-kernel divergence under torch.compile. Different code paths." + "reason": "One is generation kwargs handling after `sync_gpus`; the other is attention-kernel branching under `torch.compile`." }, { "left": "issue:42673", "right": "issue:43704", - "accept": true, - "reason": "Exact same title and symptom: Qwen3ForCausalLM VRAM leak when used in multiple dataloader threads. Clear duplicate." + "accept": false, + "reason": "Same title, but the reports are separate instances and there is no evidence they are the same concrete leak." }, { "left": "issue:45310", "right": "issue:45375", "accept": false, - "reason": "Both involve Qwen3.5/Moe configs, but one is a from_pretrained error while the other is a specific missing field silently dropped by strict config handling. Not the same bug." + "reason": "`from_pretrained` error for Qwen3.5 MoE vs missing `deepstack_visual_indexes` config field; not one fix." }, { "left": "issue:43873", "right": "issue:44945", "accept": false, - "reason": "Offloading/quantization behavior and pipeline-parallel output correctness are different problems." + "reason": "Quantization/offloading behavior and pipeline-parallelism output correctness are unrelated code paths." }, { "left": "issue:41628", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but for different symbols and likely different missing exports. Too broad to treat as one bug." + "reason": "Both are import errors, but for different symbols (`AutoImageProcessor` vs `HybridCache`) and likely different export points." }, { "left": "issue:42831", "right": "issue:44222", "accept": false, - "reason": "FineGrainedFP8 accuracy issues and FP8 save_pretrained failures are distinct symptoms and code paths." + "reason": "FP8 accuracy regression vs FP8 save/pretrained failure; one is numerical correctness, the other serialization." }, { "left": "issue:44945", "right": "issue:45753", "accept": false, - "reason": "Pipeline-parallel output corruption and a Qwen3_5 infinite-loop-on-specific-image report do not look like the same defect." + "reason": "Pipeline parallelism output mismatch vs Qwen3_5 image infinite loop; unrelated behaviors." }, { "left": "issue:44222", "right": "issue:45310", "accept": false, - "reason": "One is about saving FP8 MoE checkpoints; the other is a from_pretrained load error. Related area, different bug." + "reason": "Both mention Qwen3.5/MoE, but one is FP8 saving and the other is loading via `from_pretrained`; different bugs." }, { - "left": "issue:42994", - "right": "issue:44164", + "left": "issue:43673", + "right": "issue:44188", "accept": false, - "reason": "Both involve saving/loading, but quantized model saving and extra_state handling are not the same concrete failure." + "reason": "Chunked-prefill cache handling vs compile-time attention-kernel branching are distinct generation internals." }, { "left": "issue:36010", "right": "issue:41628", "accept": false, - "reason": "Different missing imports (GenerationMixin vs AutoImageProcessor) and different breakages." + "reason": "Both are import-related, but the missing symbol and module path differ (`GenerationMixin` vs `AutoImageProcessor`)." }, { - "left": "issue:43673", - "right": "issue:44188", + "left": "issue:42994", + "right": "issue:44164", "accept": false, - "reason": "Chunked-prefill cache behavior and torch.compile branching in attention kernels are separate generation issues." + "reason": "Quantized saving failure and `extra_state` handling in save/from_pretrained are separate persistence bugs." }, { - "left": "issue:42175", - "right": "issue:45712", + "left": "issue:42222", + "right": "issue:45200", "accept": false, - "reason": "Packaging backend inclusion and leftover dummy class cleanup are unrelated." + "reason": "Different model families and different fixes: ViTPose breakage vs Gemma 4 multimodal token-type defaults." }, { - "left": "issue:42222", - "right": "issue:45200", + "left": "issue:42175", + "right": "issue:45712", "accept": false, - "reason": "VitPose model breakage and Gemma 4 mm_token_type_ids behavior are unrelated model-specific bugs." + "reason": "Packaging/backend dependency issue vs dummy class cleanup in repo checks; unrelated." }, { "left": "issue:43232", "right": "issue:44792", "accept": false, - "reason": "Generation kwargs handling after sync_gpus is unrelated to the janus test failure." + "reason": "Generation kwargs update bug vs Janus image-generation test failure; different models and paths." }, { "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Both touch Qwen3.5/Qwen3-VL-Moe, but they appear to be different version/model load failures rather than the same concrete bug." - }, - { - "left": "issue:43377", - "right": "issue:44242", - "accept": false, - "reason": "Padding-mask batching bug in MIMI encoder and missing load-balancing loss when output_router_logits=False are different issues." + "reason": "Related Qwen/MoE family, but one is Qwen3-VL-Moe loading and the other is Qwen3.5 MoE `from_pretrained`; not the same concrete bug." }, { "left": "issue:43526", "right": "issue:45561", "accept": false, - "reason": "BeitImageProcessorFast label reduction and xdist race on captured_info.txt are unrelated." + "reason": "Beit image processor label reduction vs pytest-xdist file race; unrelated subsystems." }, { "left": "issue:43504", "right": "issue:45561", "accept": false, - "reason": "Beit legacy-field loading failure and the pytest-xdist race are unrelated." + "reason": "Legacy-field pretrained loading vs pytest-xdist race; no shared code path." }, { "left": "issue:44496", "right": "issue:45561", "accept": false, - "reason": "Model auto-loading failure and a test-utility race condition are unrelated." + "reason": "Unrecognized-model/config loading failure vs testing-utils race condition; unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "MIMI padding-mask discrepancy vs MoE load-balancing loss omission; different model components." }, { "left": "issue:44964", "right": "issue:45137", "accept": false, - "reason": "Phi-4 multimodal loading and DeepSpeed ZeRO3 deque underflow are unrelated." + "reason": "Phi-4 multimodal loading issue vs DeepSpeed ZeRO3 deque error; unrelated." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "Package-install backend composition and missing image_utils import are unrelated." + "reason": "Tensorflow extra/backend packaging issue vs nonexistent import from `image_utils`; unrelated." }, { "left": "issue:42898", "right": "issue:44568", "accept": false, - "reason": "Both are v5 tokenizer behavior regressions, but one is cleanup spacing and the other is add_special_tokens/BOS-EOS behavior. Different bugs." + "reason": "Tokenizer cleanup behavior change vs BOS/EOS special-token insertion bug; distinct tokenization behaviors." }, { "left": "issue:30990", "right": "issue:35141", "accept": false, - "reason": "Sentence Transformers loading hang and embedding reinitialization after resize are unrelated." - }, - { - "left": "issue:43479", - "right": "issue:44869", - "accept": false, - "reason": "Phi4Multimodal config defaults and Whisper timestamp decode crash are unrelated." + "reason": "Sentence Transformers loading hang vs embedding resize/reinit bug; unrelated." }, { "left": "issue:43976", "right": "issue:44933", "accept": false, - "reason": "Python version compatibility and a missing image_utils import are unrelated." + "reason": "Python-version compatibility problem vs image_utils import failure; unrelated." }, { "left": "issue:43479", - "right": "issue:44079", - "accept": false, - "reason": "Both mention None-handling, but one is multimodal config initialization and the other is ModelOutput key assignment. Not the same defect." - }, - { - "left": "issue:44188", - "right": "issue:44373", + "right": "issue:44869", "accept": false, - "reason": "Attention-kernel divergence and a wrong docstring are unrelated." + "reason": "Phi4 multimodal default-config initialization vs Whisper timestamp decode crash; different subsystems." }, { - "left": "issue:43784", - "right": "issue:43824", + "left": "issue:43479", + "right": "issue:44079", "accept": false, - "reason": "Both are import failures with latest transformers, but for different packages/symbols and different root causes." + "reason": "Default multimodal config init vs `ModelOutput` key assignment semantics; unrelated." }, { "left": "issue:44623", "right": "issue:45310", "accept": false, - "reason": "Processor save_pretrained missing files and Qwen3.5 from_pretrained error are different save/load problems." - }, - { - "left": "issue:42898", - "right": "issue:45812", - "accept": false, - "reason": "Tokenizer cleanup behavior and Granite token ID regression are different tokenizer bugs." - }, - { - "left": "issue:43278", - "right": "issue:45137", - "accept": false, - "reason": "Embedding dtype drift between train/eval and ZeRO3 deque underflow are unrelated." + "reason": "Processor save_pretrained missing files vs Qwen3.5 MoE loading error; persistence vs loading bug." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: 42673 and 43704 have identical titles, and 42673 is the earlier/more active report. The soft-edge verdicts are conservative and do not overclaim duplicate status for clearly different issues." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -11508,10 +11632,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:22355", "issue:28282", @@ -11526,25 +11650,24 @@ "issue:42898", "issue:43116", "issue:43232", + "issue:43278", "issue:43479", "issue:43644", "issue:43723", + "issue:43784", + "issue:43824", "issue:43874", "issue:44060", + "issue:44188", "issue:44190", "issue:44206", "issue:44222", - "issue:44261", "issue:44263", "issue:44295", "issue:44297", - "issue:44360", "issue:44373", "issue:44448", - "issue:44483", "issue:44484", - "issue:44485", - "issue:44514", "issue:44568", "issue:44623", "issue:44734", @@ -11554,20 +11677,25 @@ "issue:45092", "issue:45103", "issue:45125", + "issue:45137", "issue:45310", "issue:45356", "issue:45405", - "issue:45406", "issue:45656", "issue:45712", + "issue:45812", "issue:45834" ], "soft_pairs": [ + "issue:43784|issue:43824", + "issue:44188|issue:44373", + "issue:42898|issue:45812", + "issue:43278|issue:45137", "issue:44734|issue:45103", "issue:30333|issue:33290", "issue:43723|issue:44568", - "issue:42898|issue:45356", "issue:43874|issue:45092", + "issue:42898|issue:45356", "issue:44060|issue:45125", "issue:42898|issue:44779", "issue:45405|issue:45712", @@ -11579,8 +11707,8 @@ "issue:43116|issue:44190", "issue:43479|issue:43644", "issue:44222|issue:44623", - "issue:44206|issue:45103", "issue:42831|issue:44623", + "issue:44206|issue:45103", "issue:41628|issue:42757", "issue:22355|issue:28282", "issue:30333|issue:36331", @@ -11591,252 +11719,234 @@ "issue:43723|issue:44977", "issue:28282|issue:30333", "issue:44263|issue:45092", - "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:44261|issue:45092" + "issue:30333|issue:35141" ], - "prepared_review_unit_hash": "69471f0b9929c6b273ae978d4f365705981e2922d2501e19c3c4aa266b04b124", + "prepared_review_unit_hash": "337840a5810e4c271382568acc62e5505032ce82763fc387c9fd450a30dd46c3", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 38112, - "estimated_input_tokens": 9528, - "estimated_eval_tokens": 19312 + "soft_pair_count": 33, + "serialized_chars": 37572, + "estimated_input_tokens": 9393, + "estimated_eval_tokens": 19042 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous cluster of Transformer issues with only loose topical similarity. None of the soft pairs look like the same underlying bug/change strongly enough to merge, so all soft edges should be rejected.", - "confidence": 0.84, - "canonical_issue_reason": "Issue 42898 is the clearest high-level regression report in the set: it describes a broad v5 tokenizer behavior change with a well-scoped symptom and likely captures the most representative regression theme among the mostly unrelated items.", + "summary": "This cluster is mostly a grab-bag of Transformers issues with superficial overlap around tokenizer/regression reports; none of the soft pairs look like the same underlying bug or change, so no duplicate merges are warranted.", + "confidence": 0.43, + "canonical_issue_reason": "issue:42898 is the closest representative of the recurring v5 tokenizer-regression theme and has the broadest, most explicit behavioral description among the set, though it is not a duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": "42898 is the best representative issue because it is explicit, general, and regression-focused, whereas most other issues are narrow model- or component-specific failures.", + "best_issue_reason": "issue:42898 is the strongest standalone issue to anchor the cluster because it describes a concrete, versioned tokenizer behavior change and is central to the small tokenizer-related subtheme here.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import failures in unrelated packages/models: sentence-transformers import vs missing Qwen2_5_VL class." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "One is a torch.compile attention-kernel divergence; the other is a docstring mismatch for position_ids." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenization regressions, but one is about clean_up_tokenization_spaces behavior and the other about Granite token IDs; different bugs/code paths." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift in evaluation vs a DeepSpeed ZeRO3 deque error are unrelated failures." + }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "Unrelated crashes: serving KV-cache indexing vs. auto-docstring annotation handling." + "reason": "KV-cache indexing crash in serving is unrelated to auto_docstring annotation handling." }, { "left": "issue:30333", "right": "issue:33290", "accept": false, - "reason": "Different problems: MLflow status reporting vs. deepspeed/Adafactor OOM." + "reason": "MLflow reporting on training failure and adafactor OOM in deepspeed are different training problems." }, { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "Both are tokenizer regressions, but one is a generic AutoTokenizer load failure and the other is a specific BOS/EOS behavior bug." + "reason": "Both are tokenizer regressions in v5, but one is a generic from_pretrained loading issue and the other is add_special_tokens/BOS-EOS behavior." }, { - "left": "issue:42898", - "right": "issue:45356", + "left": "issue:43874", + "right": "issue:45092", "accept": false, - "reason": "Different tokenizer regressions with different models and different root causes." + "reason": "Missing image patch count in a fast image processor is not the same bug as remote-code checkpoint/meta-init incompatibility." }, { - "left": "issue:43874", - "right": "issue:45092", + "left": "issue:42898", + "right": "issue:45356", "accept": false, - "reason": "Image patch counting API bug vs. remote-code checkpoint/meta-init incompatibility." + "reason": "Both are tokenizer regressions, but the specific failures differ: whitespace cleanup behavior vs codec/fix_mistral_regex handling." }, { "left": "issue:44060", "right": "issue:45125", "accept": false, - "reason": "Different Qwen3 issues: incorrect tie warning vs. missing tensor-parallel plan." + "reason": "Incorrect tied-weights warning for Qwen3-Next is unrelated to Qwen3_5Moe missing _tp_plan." }, { "left": "issue:42898", "right": "issue:44779", "accept": false, - "reason": "Both involve tokenizers in v5, but the model-specific symptoms and likely code paths differ." + "reason": "Both mention tokenizer regressions, but Deepseek tokenization output mismatch is a different concrete issue than clean_up_tokenization_spaces." }, { "left": "issue:45405", "right": "issue:45712", "accept": false, - "reason": "Unrelated: dependency version pinning vs. dummy class cleanup in import surfaces." + "reason": "A dependency-version bump and leftover dummy classes failing repo checks are unrelated." }, { "left": "issue:42898", "right": "issue:44448", "accept": false, - "reason": "Shared v4/v5 regression theme, but the reported behavior and affected model differ." + "reason": "Pegasus output drift across v4/v5 is a generation/model-output regression, not the same as clean_up_tokenization_spaces." }, { "left": "issue:44295", "right": "issue:45656", "accept": false, - "reason": "Buffer access after registration is unrelated to a double optimizer-step bug." + "reason": "A position_ids buffer-reading error and a double optimizer-step issue with DeepSpeed are different failure modes." }, { "left": "issue:44933", "right": "issue:45712", "accept": false, - "reason": "Import-from-image_utils failure is not the same as leftover dummy classes leaking into dir()." + "reason": "Missing import from image_utils is unrelated to dummy classes leaking into dir(transformers)." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "FP8 save_pretrained behavior and tokenizer_config metadata mismatch are different bugs." + "reason": "Both involve save_pretrained, but one is FP8 MoE serialization and the other is tokenizer config metadata; not the same bug." }, { "left": "issue:44297", - "right": "issue:45310", + "right": "issue:45656", "accept": false, - "reason": "Tokenizer save/load metadata bug vs. Qwen3.5 MoE from_pretrained failure." + "reason": "Tokenizer config mismatch has no relation to DeepSpeed calling optimizer.step twice." }, { "left": "issue:43116", "right": "issue:44190", "accept": false, - "reason": "Different example-script failures with different input pipelines and error modes." + "reason": "Example-script multi-label classification output bug and local dataset loading failure are different script-level issues." }, { "left": "issue:43479", "right": "issue:43644", "accept": false, - "reason": "Config default initialization bug is unrelated to non-persistent buffer corruption." + "reason": "Bad default multimodal config initialization is not the same as non-persistent buffers being filled with junk." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "Both mention save_pretrained, but one is FP8/MoE and the other is processor file serialization." + "reason": "Both are save_pretrained-related, but they affect different objects and different serialization outputs." }, { - "left": "issue:44206", - "right": "issue:45103", + "left": "issue:42831", + "right": "issue:44623", "accept": false, - "reason": "Feature-extractor argument regression is unrelated to auto-docstring annotation crashes." + "reason": "FineGrainedFP8 accuracy degradation is unrelated to processor save_pretrained missing files." }, { - "left": "issue:42831", - "right": "issue:44623", + "left": "issue:44206", + "right": "issue:45103", "accept": false, - "reason": "FP8 accuracy issue is not the same as missing processor save_pretrained files." + "reason": "Feature extractor center-arg regression and auto_docstring annotation crash do not share a code path." }, { "left": "issue:41628", "right": "issue:42757", "accept": false, - "reason": "Two separate import errors from different packages and causes." + "reason": "Different missing imports from different packages: transformers vs huggingface_hub." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "Missing transformers.onnx module is unrelated to the absent PyTorch dependency error." + "reason": "Missing transformers.onnx module and missing PyTorch dependency are separate environment/import problems." }, { "left": "issue:30333", "right": "issue:36331", "accept": false, - "reason": "MLflow reporting vs. trainer compute_loss signature mismatch are different regressions." + "reason": "MLflow reporting on failure and Trainer.compute_loss signature breakage are unrelated trainer issues." }, { "left": "issue:44297", "right": "issue:45310", "accept": false, - "reason": "Tokenizer config mismatch is not the same as the Qwen3.5 MoE from_pretrained regression." + "reason": "Tokenizer save metadata mismatch is not the same as Qwen3.5 MoE from_pretrained load failure." }, { "left": "issue:30333", "right": "issue:34689", "accept": false, - "reason": "Training-job reporting bug and Llama model-loading regression are unrelated." + "reason": "Failed MLflow reporting and Llama 3.2 Vision model loading regression are unrelated." }, { "left": "issue:44222", "right": "issue:44484", "accept": false, - "reason": "Save_pretrained shard-size question is unrelated to the FP8 MoE save bug." + "reason": "FP8 MoE save_pretrained bug and max_shard_size default question are different save_pretrained concerns." }, { "left": "issue:43232", "right": "issue:45834", "accept": false, - "reason": "Generation kwargs handling and OCR long-input indexing are different code paths." + "reason": "Generation kwargs update after sync_gpus is unrelated to long-ocr-input index errors in Kosmos2.5." }, { "left": "issue:43723", "right": "issue:44977", "accept": false, - "reason": "Both are tokenizer regressions, but the affected models and symptoms are different." + "reason": "Generic tokenizer loading issues and Qwen3.5 flash-attention generation failures are different problems." }, { "left": "issue:28282", "right": "issue:30333", "accept": false, - "reason": "ImportError about PyTorch is unrelated to MLflow reporting after failed training jobs." + "reason": "AutoModel missing PyTorch and MLflow-not-reported-on-failure are unrelated." }, { "left": "issue:44263", "right": "issue:45092", "accept": false, - "reason": "DSA indexer split semantics are unrelated to multimodal checkpoint/meta-init compatibility." + "reason": "torch.split return handling in a MoE indexer is unrelated to meta-initialization incompatibility." }, { "left": "issue:30333", "right": "issue:35141", "accept": false, - "reason": "Training-job reporting bug is unrelated to embedding resize reinitialization." - }, - { - "left": "issue:44483", - "right": "issue:45406", - "accept": false, - "reason": "Chat-completions rejection and missing Gemma4Processor attribute are different serve failures." - }, - { - "left": "issue:44263", - "right": "issue:44360", - "accept": false, - "reason": "Same subsystem, but different bugs: split return handling vs. missing ReLU." - }, - { - "left": "issue:44373", - "right": "issue:44485", - "accept": false, - "reason": "Wrong docstring for position_ids is not the same as the GLM-5 RoPE implementation issue." - }, - { - "left": "issue:44295", - "right": "issue:44623", - "accept": false, - "reason": "Reading a registered buffer and processor serialization are unrelated." - }, - { - "left": "issue:44514", - "right": "issue:45103", - "accept": false, - "reason": "Batched chat-template crash and auto-docstring annotation crash have no shared code path." - }, - { - "left": "issue:44261", - "right": "issue:44360", - "accept": false, - "reason": "MLA config epsilon precision bug is unrelated to the DSA indexer ReLU issue." + "reason": "MLflow reporting on failed training and embedding reinitialization during resize are distinct bugs." } ] }, @@ -11855,10 +11965,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:22355", "issue:28218", @@ -11871,7 +11981,6 @@ "issue:42757", "issue:42831", "issue:42886", - "issue:42907", "issue:42994", "issue:43066", "issue:43122", @@ -11882,38 +11991,45 @@ "issue:43756", "issue:43784", "issue:43824", - "issue:43976", "issue:44038", "issue:44060", "issue:44117", + "issue:44261", "issue:44263", "issue:44295", - "issue:44297", + "issue:44360", "issue:44373", "issue:44442", - "issue:44488", + "issue:44483", + "issue:44485", "issue:44514", "issue:44521", "issue:44568", + "issue:44623", "issue:44704", - "issue:44743", "issue:44871", "issue:44913", - "issue:44945", "issue:44991", "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:44373|issue:44485", + "issue:44295|issue:44623", + "issue:44514|issue:45103", + "issue:44261|issue:45092", "issue:45092|issue:45357", "issue:43723|issue:44871", - "issue:30990|issue:38175", "issue:43723|issue:44991", + "issue:30990|issue:38175", "issue:43723|issue:44442", "issue:41628|issue:43824", "issue:43479|issue:44913", @@ -11932,122 +12048,150 @@ "issue:42371|issue:44263", "issue:22355|issue:28218", "issue:44117|issue:44704", - "issue:30990|issue:33357", - "issue:43232|issue:44743", - "issue:44295|issue:44297", - "issue:44704|issue:45290", - "issue:42907|issue:44945", - "issue:43122|issue:44514", - "issue:41628|issue:45278", - "issue:43976|issue:44945", - "issue:39401|issue:44488" + "issue:30990|issue:33357" ], - "prepared_review_unit_hash": "6f701ecddad96af777ba9487b398f64bd2cb5f021cecfbafd88f7ff35bf50652", + "prepared_review_unit_hash": "26b759fa9f72b604900b7dbc09793524144ce3820d4e67ca39562d3753991247", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36563, - "estimated_input_tokens": 9141, - "estimated_eval_tokens": 18538 + "soft_pair_count": 29, + "serialized_chars": 35994, + "estimated_input_tokens": 8999, + "estimated_eval_tokens": 18254 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are largely heterogeneous regressions across tokenizer loading, model-specific multimodal behavior, config reloads, and unrelated import/runtime errors. I do not see any soft pair that clearly describes the same concrete bug, so all candidate duplicate edges should be rejected.", - "confidence": 0.78, - "canonical_issue_reason": "Issue 43723 is the broadest representative of the tokenizer-loading regression family in this set (AutoTokenizer.from_pretrained in v5). It is the best single issue to anchor the cluster, though the surrounding items still look mostly unrelated rather than true duplicates.", + "summary": "The cluster is mostly a grab-bag of unrelated Transformers regression reports; the only strong common thread is tokenizer/loading-related breakage, but the pairs are still too specific to merge together confidently.", + "confidence": 0.68, + "canonical_issue_reason": "issue:43723 is the broadest and most representative user-facing regression here, centered on tokenizer loading via AutoTokenizer.from_pretrained in v5.", "canonical_pr_reason": null, - "best_issue_reason": "43723 is the most general and user-facing issue here, with the clearest umbrella scope over tokenizer-loading failures. It is the best representative issue, even if the cluster does not collapse into a single duplicate group.", + "best_issue_reason": "issue:43723 is the best anchor for this cluster because it is generic, high-signal, and closest to several tokenizer-related reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Different failures and code paths: chat/completions request validation vs Gemma4Processor missing _tokenizer in transformers serve." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA, but one is about torch.split return values and the other about a missing ReLU in the indexer; not the same bug." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Docstring/position_ids documentation issue vs GLM-5 RoPE implementation bug; unrelated symptoms." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Registering position_ids as a buffer causing read errors is unrelated to processor.save_pretrained missing files." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "apply_chat_template batching crash is unrelated to auto_docstring failing under future annotations." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "Layer norm epsilon precision mismatch is not the same as old InternVL2 remote-code checkpoints failing meta initialization." + }, { "left": "issue:45092", "right": "issue:45357", "accept": false, - "reason": "Different model-specific bugs: meta-initialization incompatibility vs incorrect visual encoder keys on save_pretrained." + "reason": "Different multimodal Qwen/InternVL save/load problems; one is meta-init incompatibility, the other is wrong visual encoder keys on save." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "One is a tokenizer loading failure in v5; the other is an eos_token_id config mismatch for Gemma-3." + "reason": "Both are tokenizer-related, but one is generic loading failure and the other is eos_token_id config inconsistency for a specific model." }, { - "left": "issue:30990", - "right": "issue:38175", + "left": "issue:43723", + "right": "issue:44991", "accept": false, - "reason": "Different symptoms and models: Sentence Transformers loading stall vs SigLIP2 zero-probability outputs." + "reason": "Both involve AutoTokenizer loading, but the affected models and failure mode are not shown to be the same bug." }, { - "left": "issue:43723", - "right": "issue:44991", + "left": "issue:30990", + "right": "issue:38175", "accept": false, - "reason": "Both involve tokenizer loading, but the concrete failures and affected models differ; not clearly the same bug." + "reason": "Sentence Transformers loading hang and SigLIP2 zero probabilities are different model/runtime issues." }, { "left": "issue:43723", "right": "issue:44442", "accept": false, - "reason": "Broad AutoTokenizer loading regression vs a FastSpeech2ConformerTokenizer-specific load failure." + "reason": "FastSpeech2ConformerTokenizer load failure is a separate model-specific tokenizer issue, not clearly the same as the v5 AutoTokenizer regression." }, { "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different missing symbols/classes and different code paths." + "reason": "Import errors for different symbols do not indicate the same underlying export bug." }, { "left": "issue:43479", "right": "issue:44913", "accept": false, - "reason": "Unrelated config bugs: default multimodal sub-config initialization vs GPTNeoX rotary_pct reload behavior." + "reason": "Different config bugs: multimodal default config initialization vs GPTNeoX rotary_pct not persisting on reload." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "Different problems: FineGrainedFP8 accuracy degradation vs Qwen3.5-Moe from_pretrained error." + "reason": "FineGrainedFP8 accuracy issues are unrelated to Qwen3.5 MoE from_pretrained errors." }, { "left": "issue:44263", "right": "issue:44373", "accept": false, - "reason": "A runtime/indexer issue is not the same as a docstring correction." + "reason": "Different DSA/position_ids problems with no shared concrete code-path." }, { "left": "issue:39401", "right": "issue:44568", "accept": false, - "reason": "Different tokenizer bugs: wrong offset_mapping vs missing BOS/EOS insertion with add_special_tokens." + "reason": "Tokenizer offset_mapping regression and missing BOS/EOS insertion are different tokenizer behaviors." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "Different model families and failure modes; one is FP8 accuracy, the other is a Qwen3-VL-Moe loading bug." + "reason": "Different problems: FP8 accuracy vs Qwen3-VL-Moe bug in v5." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "One is a specific is_offline_mode import failure; the other is a broader collection of import errors after upgrade." + "reason": "A single huggingface_hub import symbol issue is not the same as a broad report of many import errors after upgrade." }, { "left": "issue:42886", "right": "issue:42994", "accept": false, - "reason": "Offline tokenizer cache loading and quantized model saving are unrelated subsystems." + "reason": "Offline tokenizer cache loading and quantized model saving are unrelated." }, { "left": "issue:43232", @@ -12059,103 +12203,55 @@ "left": "issue:43756", "right": "issue:44060", "accept": false, - "reason": "Different model internals: RoPE-layer dropping vs a tied-weights warning in Qwen3-Next." + "reason": "Smollm3 RoPE-layer mismatch and Qwen3-Next tied-weights warning are different model/config issues." }, { "left": "issue:43576", "right": "issue:43784", "accept": false, - "reason": "transformers env CLI breakage is not the same bug as sentence-transformers failing with nn undefined." + "reason": "CLI env command breakage and sentence-transformers import NameError are unrelated." }, { "left": "issue:42831", "right": "issue:45753", "accept": false, - "reason": "Accuracy regression in FineGrainedFP8 is unrelated to a Qwen3_5 image-specific infinite loop." + "reason": "FP8 accuracy issues are unrelated to Qwen3_5 infinite-loop behavior on a specific image." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Offline cache loading and wrong tokenizer decoder type in v5 are different issues." + "reason": "Offline cache loading and wrong tokenizer decoder type are different tokenizer failures." }, { "left": "issue:43122", "right": "issue:44521", "accept": false, - "reason": "Both touch tokenization/chat templating, but one is a version-to-version tokenization change and the other is a multimodal assistant_mask bug." + "reason": "Different multimodal/tokenization regressions: changed tokenization across versions vs all-zero assistant masks." }, { "left": "issue:42371", "right": "issue:44263", "accept": false, - "reason": "TF32 settings guidance is unrelated to a torch.split return-value bug." + "reason": "TF32 API guidance and a DSA torch.split issue are unrelated." }, { "left": "issue:22355", "right": "issue:28218", "accept": false, - "reason": "Missing transformers.onnx module and an extra-space tokenizer behavior are different bugs." + "reason": "onnx import failure and extra space after added token are unrelated issues." }, { "left": "issue:44117", "right": "issue:44704", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES returning None is a different loader issue than AutoProcessor forwarding kwargs to cached_file." + "reason": "Tokenizer mapping returning None and AutoProcessor not forwarding kwargs to cached_file are separate loader bugs." }, { "left": "issue:30990", "right": "issue:33357", "accept": false, - "reason": "A loading hang in Sentence Transformers is not the same as a Mac bus error with a CLIP model." - }, - { - "left": "issue:43232", - "right": "issue:44743", - "accept": false, - "reason": "Generation sync_gpus state handling and Qwen3_5 recurrent-state reset are different code paths." - }, - { - "left": "issue:44295", - "right": "issue:44297", - "accept": false, - "reason": "Reading a buffer after registration and saving the wrong tokenizer_class are unrelated." - }, - { - "left": "issue:44704", - "right": "issue:45290", - "accept": false, - "reason": "AutoProcessor cached_file kwarg forwarding is unrelated to chat-template crashes on tool-call assistant messages." - }, - { - "left": "issue:42907", - "right": "issue:44945", - "accept": false, - "reason": "Quantized-model saving failure and pipeline-parallelism output corruption are different bugs." - }, - { - "left": "issue:43122", - "right": "issue:44514", - "accept": false, - "reason": "Tokenization differences across versions are not the same as a batched apply_chat_template crash with padding=False." - }, - { - "left": "issue:41628", - "right": "issue:45278", - "accept": false, - "reason": "A specific AutoImageProcessor import failure is not the same as a broad multi-import regression report." - }, - { - "left": "issue:43976", - "right": "issue:44945", - "accept": false, - "reason": "Python version compatibility is unrelated to pipeline-parallelism output errors." - }, - { - "left": "issue:39401", - "right": "issue:44488", - "accept": false, - "reason": "Wrong offset_mapping in Qwen3 tokenizer is unrelated to loading a specific model/tokenizer checkpoint." + "reason": "Sentence Transformers loading hang and MacOS bus error with CLIP are different failures." } ] }, @@ -12174,24 +12270,21 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ - "issue:22355", "issue:29127", "issue:30990", "issue:36296", - "issue:38617", "issue:39401", - "issue:42371", - "issue:42673", + "issue:41628", "issue:42757", "issue:42907", - "issue:43066", "issue:43116", "issue:43122", + "issue:43232", "issue:43278", "issue:43408", "issue:43452", @@ -12199,8 +12292,8 @@ "issue:43493", "issue:43784", "issue:43824", - "issue:43874", "issue:43937", + "issue:43976", "issue:43992", "issue:44038", "issue:44222", @@ -12211,34 +12304,45 @@ "issue:44360", "issue:44373", "issue:44485", + "issue:44488", + "issue:44514", "issue:44521", "issue:44625", "issue:44704", + "issue:44743", "issue:44779", "issue:44829", "issue:44945", "issue:44964", "issue:44977", - "issue:45072", "issue:45200", "issue:45216", "issue:45278", + "issue:45290", "issue:45446", "issue:45478", "issue:45600", "issue:45753" ], "soft_pairs": [ + "issue:44295|issue:44297", + "issue:43232|issue:44743", + "issue:44704|issue:45290", + "issue:42907|issue:44945", + "issue:43122|issue:44514", + "issue:43976|issue:44945", + "issue:41628|issue:45278", + "issue:39401|issue:44488", "issue:43784|issue:45600", + "issue:44261|issue:44373", "issue:43408|issue:43475", "issue:42907|issue:43937", - "issue:44261|issue:44373", "issue:44360|issue:44485", "issue:44625|issue:44829", "issue:39401|issue:44521", "issue:43116|issue:45200", - "issue:29127|issue:30990", "issue:44038|issue:44297", + "issue:29127|issue:30990", "issue:42907|issue:44964", "issue:43122|issue:44779", "issue:44038|issue:44295", @@ -12253,228 +12357,234 @@ "issue:42907|issue:44222", "issue:43122|issue:44977", "issue:43992|issue:44704", - "issue:43784|issue:45446", - "issue:43066|issue:44779", - "issue:38617|issue:45278", - "issue:42673|issue:45072", - "issue:43937|issue:44485", - "issue:22355|issue:29127", - "issue:42371|issue:43874" + "issue:43784|issue:45446" ], - "prepared_review_unit_hash": "bc29e2105b6271bb31659554d6fcbdded8ac98a1a459c05409eae5b6c0f82235", + "prepared_review_unit_hash": "8b1a2a1e18838fa8da6d21b0b8896a7972f98c962a1ae00a2c50ae875afa4ffe", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36602, - "estimated_input_tokens": 9151, - "estimated_eval_tokens": 18558 + "soft_pair_count": 33, + "serialized_chars": 37225, + "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 topical rather than duplicate-heavy: many items share broad themes like import regressions, tokenizer issues, or model-specific bugs, but they do not look like the same underlying defect. No soft edge is strong enough to accept.", - "confidence": 0.46, - "canonical_issue_reason": "issue:45278 is the best umbrella representative because it captures the broad import-regression theme after the 4.57.x -> 5.5.0 upgrade, which is the closest thing to a shared cluster topic here.", + "summary": "No soft pairs look like true duplicates; the set is mostly unrelated issue reports across different models, import paths, tokenizer behavior, and generation bugs. The most central issue is the open multimodal apply_chat_template report with the highest activity and references.", + "confidence": 0.91, + "canonical_issue_reason": "issue:44521 is the most active and referenced report, and it has a concrete, reproducible bug description in a currently open area.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most globally suitable issue because it is broad, central, and representative of the recurring import-failure reports in this set.", + "best_issue_reason": "issue:44521 is the best cluster anchor because it has the strongest discussion/inbound-reference signal and a clearly scoped user-facing failure mode.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43784", - "right": "issue:45600", + "left": "issue:44295", + "right": "issue:44297", "accept": false, - "reason": "Both are import-related, but one is a NameError in sentence-transformers and the other is a stale auto_mappings reference in transformers CI; different code paths and bugs." + "reason": "Both are tokenizer/model serialization issues, but one is about reading registered buffer position_ids and the other is about tokenizer_class metadata in tokenizer_config.json; different failure modes and code paths." }, { - "left": "issue:43408", - "right": "issue:43475", + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/cache state, but one is about _update_model_kwargs_for_generation after sync_gpus and the other about recurrent state reset in modular_qwen3_5.py; not the same bug." + }, + { + "left": "issue:44704", + "right": "issue:45290", "accept": false, - "reason": "Same SAM 3 area, but one is a model-type warning and the other is a missing attribute on vision output; not the same defect." + "reason": "AutoProcessor kwargs forwarding and apply_chat_template crashes with tool-call assistant messages are distinct processor/template bugs." }, { "left": "issue:42907", - "right": "issue:43937", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals and incorrect pipeline-parallel LLM output are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer behavior changes across versions and a batched apply_chat_template padding crash are different issues." + }, + { + "left": "issue:43976", + "right": "issue:44945", "accept": false, - "reason": "Dequantized save failure for Ministrals/Devstrals vs invalid GenerationConfig for GLM-5; unrelated model paths." + "reason": "Python version compatibility is unrelated to pipeline parallelism output corruption." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "A missing AutoImageProcessor import and a broad wave of import errors after upgrade may be thematically similar, but they are not the same concrete broken symbol or code path." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping correctness and failure to load a specific model are different problems." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "sentence-transformers import NameError and stale auto_mappings references to removed configs are separate import-time regressions." }, { "left": "issue:44261", "right": "issue:44373", "accept": false, - "reason": "One is a numerical/config precision issue in MLA q_a_layernorm, the other is a docstring mismatch for position_ids; not duplicates." + "reason": "One is a numerical precision/config issue in MLA q_a_layernorm; the other is a wrong docstring for position_ids." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "A model-type mismatch warning and a missing fpn_position_embeddings attribute in SAM 3 video are not the same defect." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Dequantized save failures and invalid GenerationConfig for GLM-5 are unrelated." }, { "left": "issue:44360", "right": "issue:44485", "accept": false, - "reason": "DSA indexer ReLU complaint and GLM-5 RoPE implementation are unrelated subsystems and symptoms." + "reason": "DSA indexer activation logic and GLM-5 RoPE implementation are entirely different areas." }, { "left": "issue:44625", "right": "issue:44829", "accept": false, - "reason": "Qwen3.5 num_labels propagation and flash_attention_3 degenerate training are different bugs with different code paths." + "reason": "num_labels propagation in Qwen3.5 config and flash_attention_3 degenerate training are different behaviors." }, { "left": "issue:39401", "right": "issue:44521", "accept": false, - "reason": "Both concern tokenization/multimodal behavior, but one is wrong offset_mapping for Qwen3 and the other is all-zero assistant masks in apply_chat_template; not the same issue." + "reason": "Tokenizer offset_mapping correctness and multimodal assistant_masks being all-zero are different apply_chat_template/tokenizer bugs." }, { "left": "issue:43116", "right": "issue:45200", "accept": false, - "reason": "Example script multi-label output bug vs Gemma 4 mm_token_type_ids defaulting; different components and failure modes." + "reason": "Empty multi-label classification outputs in an example script and Gemma 4 mm_token_type_ids defaults are unrelated." }, { - "left": "issue:29127", - "right": "issue:30990", + "left": "issue:44038", + "right": "issue:44297", "accept": false, - "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang are unrelated." + "reason": "A Qwen3-VL-Moe load bug and tokenizer_class mismatch on save are different code paths." }, { - "left": "issue:44038", - "right": "issue:44297", + "left": "issue:29127", + "right": "issue:30990", "accept": false, - "reason": "Qwen3-VL-Moe compatibility bug vs tokenizer.save_pretrained class-name mismatch; not the same concrete problem." + "reason": "LayoutLMv3 error messaging and Sentence Transformers loading hang are unrelated." }, { "left": "issue:42907", "right": "issue:44964", "accept": false, - "reason": "Dequantized save failure and Phi-4-multimodal load failure are distinct model-management bugs." + "reason": "Saving dequantized Ministrals/Devstrals and loading Phi-4 multimodal instruct are different model-specific failures." }, { "left": "issue:43122", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions in v5, but one is a generic version-to-version tokenization change and the other is Deepseek-specific incorrect output; not clearly the same bug." + "reason": "Both concern tokenization regressions, but for different model families and different observable failures." }, { "left": "issue:44038", "right": "issue:44295", "accept": false, - "reason": "Qwen3-VL-Moe error and position_ids buffer-read error are unrelated." + "reason": "Qwen3-VL-Moe loading and position_ids buffer access are unrelated." }, { "left": "issue:36296", "right": "issue:43116", "accept": false, - "reason": "Tensor parallel training bug and multi-label classification example bug are different training/example paths." + "reason": "Tensor-parallel training bugs and multi-label classification empty outputs are different domains." }, { "left": "issue:42907", "right": "issue:43452", "accept": false, - "reason": "Saving dequantized Ministrals/Devstrals and gguf_file breaking AutoTokenizer/AutoModel loading are separate loading/saving issues." + "reason": "Dequantized save issues and gguf_file failures in from_pretrained are separate loading/saving problems." }, { "left": "issue:43824", "right": "issue:44351", "accept": false, - "reason": "Cannot import Qwen2_5_VLForConditionalGeneration and cannot import HybridCache are both import errors, but they stem from different symbols and fixes." + "reason": "Both are missing imports, but they are different symbols from different subsystems and not one shared underlying bug." }, { "left": "issue:44038", "right": "issue:44222", "accept": false, - "reason": "Qwen3-VL-Moe compatibility and FP8 save_pretrained moe are different model serialization/runtime bugs." + "reason": "Qwen3-VL-Moe load failure and FP8 save_pretrained for moe are different change points." }, { "left": "issue:45216", "right": "issue:45478", "accept": false, - "reason": "Both involve Qwen3.5 and Transformers 5.4+, but one is save_pretrained checkpoint correctness and the other is from_pretrained loading failure; different code paths." + "reason": "Both mention Qwen3.5 and newer versions, but one is about save_pretrained checkpoints and the other about from_pretrained loading errors; not the same concrete failure." }, { "left": "issue:42757", "right": "issue:44351", "accept": false, - "reason": "Missing is_offline_mode import from huggingface_hub versus missing HybridCache export from transformers; both imports fail, but not the same missing symbol or fix." + "reason": "Missing is_offline_mode from huggingface_hub and missing HybridCache from transformers are unrelated import errors." }, { "left": "issue:43278", "right": "issue:44945", "accept": false, - "reason": "Embedding dtype drift between train/eval and incorrect LLM output under pipeline parallelism are unrelated issues." + "reason": "Embedding dtype drift between train/eval and incorrect pipeline-parallel output are different bugs." }, { "left": "issue:43493", "right": "issue:45753", "accept": false, - "reason": "SigLIP2 implementation discrepancy and Qwen3_5 infinite loop on a specific image are different model behaviors." + "reason": "SigLIP2 implementation mismatch and Qwen3_5 infinite loop on a specific image are unrelated multimodal problems." }, { "left": "issue:42907", "right": "issue:44222", "accept": false, - "reason": "Dequantized save failure and FP8 moe save_pretrained bug are separate serialization problems." + "reason": "Both touch MoE/saving, but one is dequantized model save failure and the other is FP8 save_pretrained behavior; not the same issue." }, { "left": "issue:43122", "right": "issue:44977", "accept": false, - "reason": "Generic tokenizer regression across versions vs Qwen3.5 flash-attention generation bug; not the same underlying defect." + "reason": "Tokenizer differences across versions and Qwen3.5 flash-attention generation failure are separate regressions." }, { "left": "issue:43992", "right": "issue:44704", "accept": false, - "reason": "UMT5Encoder missing embed_tokens.weight and AutoProcessor not passing kwargs to cached_file are unrelated loader issues." + "reason": "Missing embed_tokens.weight in UMT5Encoder and cached_file kwargs forwarding are unrelated model-loading issues." }, { "left": "issue:43784", "right": "issue:45446", "accept": false, - "reason": "Sentence-transformers import NameError and flex_attention PyTorch version check are entirely different failures." - }, - { - "left": "issue:43066", - "right": "issue:44779", - "accept": false, - "reason": "Tokenizer decoder type migration issue in Transformers v5 and Deepseek tokenization regression are different tokenizer bugs." - }, - { - "left": "issue:38617", - "right": "issue:45278", - "accept": false, - "reason": "A specific missing import in configuration_utils is not the same as the broad multi-import regression report, even if both are import-related." - }, - { - "left": "issue:42673", - "right": "issue:45072", - "accept": false, - "reason": "Qwen3ForCausalLM VRAM leak in dataloader threads and dtype mismatches in bfloat16 inference are different runtime bugs." - }, - { - "left": "issue:43937", - "right": "issue:44485", - "accept": false, - "reason": "Invalid GenerationConfig for GLM-5 and GLM-5 RoPE implementation are separate model configuration vs positional encoding issues." - }, - { - "left": "issue:22355", - "right": "issue:29127", - "accept": false, - "reason": "Transformers.onnx import failure and LayoutLMv3 error-message clarity do not describe the same bug." - }, - { - "left": "issue:42371", - "right": "issue:43874", - "accept": false, - "reason": "TF32 behavior API guidance and GLM46V image patch-count AttributeError are unrelated." + "reason": "sentence-transformers import NameError and a PyTorch version check bug in flex_attention are different import-time problems." } ] }, @@ -12493,31 +12603,31 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ + "issue:22355", + "issue:29127", "issue:33453", "issue:38617", "issue:39401", "issue:41628", "issue:42222", "issue:42371", - "issue:42617", "issue:42673", "issue:43064", + "issue:43066", "issue:43116", - "issue:43408", "issue:43421", "issue:43441", "issue:43450", "issue:43493", - "issue:43582", "issue:43673", - "issue:43742", "issue:43825", "issue:43827", + "issue:43874", "issue:43906", "issue:43937", "issue:43976", @@ -12525,18 +12635,18 @@ "issue:44038", "issue:44075", "issue:44117", - "issue:44261", "issue:44291", "issue:44410", "issue:44484", + "issue:44485", "issue:44779", - "issue:44829", "issue:44936", "issue:44977", "issue:45071", + "issue:45072", "issue:45081", "issue:45083", - "issue:45216", + "issue:45278", "issue:45310", "issue:45341", "issue:45357", @@ -12548,16 +12658,22 @@ "issue:45588" ], "soft_pairs": [ - "issue:43064|issue:43673", + "issue:43066|issue:44779", + "issue:38617|issue:45278", + "issue:42673|issue:45072", + "issue:43937|issue:44485", + "issue:22355|issue:29127", + "issue:42371|issue:43874", "issue:43976|issue:45446", + "issue:43064|issue:43673", "issue:43116|issue:43493", "issue:42222|issue:43441", "issue:44075|issue:44936", "issue:43116|issue:43825", "issue:45357|issue:45478", "issue:44038|issue:45478", - "issue:45083|issue:45446", "issue:43937|issue:45563", + "issue:45083|issue:45446", "issue:44117|issue:45588", "issue:33453|issue:39401", "issue:39401|issue:44779", @@ -12572,56 +12688,228 @@ "issue:38617|issue:41628", "issue:39401|issue:43421", "issue:44410|issue:45310", - "issue:44484|issue:45310", - "issue:44829|issue:45216", - "issue:42371|issue:44261", - "issue:42673|issue:43582", - "issue:43408|issue:43742", - "issue:42617|issue:45341" + "issue:44484|issue:45310" ], - "prepared_review_unit_hash": "deb290f9e8456531e99e9add2da481f0d1505dd510f9d09959d1ceb9e1d9454a", + "prepared_review_unit_hash": "3b8a61bb52959381db3effb138e257402a71e8dc3ab1e052e1fc8711992f6000", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36560, - "estimated_input_tokens": 9140, - "estimated_eval_tokens": 18536 + "soft_pair_count": 31, + "serialized_chars": 36739, + "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 centered on Qwen3.5 loading/saving regressions, but it is not a single duplicate pair. The only strong overlap is the exact-title pair issue:45310 and issue:45478; issue:45357 is a separate save_pretrained visual-encoder-key regression and should not be merged with the from_pretrained failure.", - "confidence": 0.79, - "canonical_issue_reason": "issue:45478 is a good canonical representative because it is the latest report with the exact Qwen3.5 MoE from_pretrained failure title; however, issue:45310 is an equally important duplicate-like report with the same title, so 45478 should be treated as representative rather than uniquely authoritative.", + "summary": "This cluster is not a true duplicate set: the issues span many unrelated bugs (tokenizers, training, vision, imports, docs, version checks). I would not merge any of the proposed soft pairs.", + "confidence": 0.95, + "canonical_issue_reason": "If a single representative is required, issue:45561 is the most concrete and actively discussed report, but the cluster is too heterogeneous for a real canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45478 best anchors the cluster because it most directly names the concrete failing code path and is the clearest representative of the repeated Qwen3.5 MoE from_pretrained reports.", + "best_issue_reason": "issue:45561 is the clearest actionable bug report with the strongest current activity, though it should not be treated as a global duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:45357", - "right": "issue:45478", + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they describe different models and different failure modes; no evidence of the same code-path bug." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "45278 is a broad collection of import errors, while 38617 is one specific missing symbol; too general to be the same issue." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in threaded inference and dtype mismatch in bfloat16 inference are unrelated bugs." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "A GenerationConfig validation error and a RoPE implementation discussion are different problems." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "ONNX import failure and LayoutLMv3 box-validation messaging are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API guidance and a missing image-patch helper are different subsystems and different bugs." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility and a PyTorch version check bug are not the same underlying issue." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Wrong optimizer state handling in FSDP/PEFT and missing GenerationMixin cache in chunked prefill are distinct training/generation bugs." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example-script multi-label output handling and SigLIP2 HF/JAX mismatch are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "VitPose model breakage and Ministral flash-attention failure affect different models and code paths." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "SGD args being ignored and train/evaluate failing after train are different trainer bugs." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "A classification example bug and a pipeline error-message issue are unrelated." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5, but one is save_pretrained key serialization and the other is from_pretrained loading; not the same defect." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen variants and different failure symptoms; too broad to merge as one bug." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig invalidity and a stale warning about num_return_sequences are separate issues." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Feature-extraction length behavior and a version-check import guard are unrelated." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer mapping fallback behavior and a flash-attention crash on s_aux=None are different problems." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Both are tokenizer regressions, but one is loading regression and the other is wrong offset mapping; not the same bug." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Different tokenizer models and different symptoms; similar theme is not enough to treat as duplicates." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Documentation lag around pipeline removal and a PyTorch version check bug are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig validation and flash-attention generation failure are distinct code paths." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "No concrete shared bug is visible; 43906 is only an isolated reproduction of another issue, while 42673 is a VRAM leak report." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument handling and PreTrainedConfig type-checking are separate compatibility regressions." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video processor shape handling and missing torchvision crash are different video-processing issues." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "PEFT minimum-version bump and an AuxRequest PyTorch version check are unrelated." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Both mention testing_utils, but one is a general bug and the other is a specific xdist race; not the same fix." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping assumptions and a Mistral regex patch crash are unrelated tokenizer bugs." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and likely different causes." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Wrong offset mapping and runtime post-processor updates for special tokens are different tokenizer behaviors." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "qwen3next missing projections and Qwen3.5 MoE from_pretrained errors are different model-specific bugs." + }, + { + "left": "issue:44484", + "right": "issue:45310", "accept": false, - "reason": "Different regressions: 45357 is about incorrect save_pretrained visual encoder keys, while 45478 is a from_pretrained loading error. Same model family, but not the same bug." + "reason": "A max_shard_size question and a from_pretrained regression are not the same underlying issue." } ] }, - "evaluator_result": { - "accept": false, - "feedback": "The writeup overstates the evidence in the packet. The strongest counterexample is issue:45310, which has the exact same title as issue:45478, so 45478 is not the sole or clearly latest duplicate-like report. Also, the accepted pair issue:45357 \u2194 issue:45478 is not well grounded: 45357 is about incorrect `save_pretrained` visual encoder keys, not the same `from_pretrained` failure described in 45478. Overall the cluster may still center on Qwen3.5 loading/saving regressions, but the summary is too strong in calling it a single duplicate pair and in treating the non-matching Qwen3.5 issue as the same bug." - }, - "evaluator_used": true, - "retried": true, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -12634,10 +12922,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:38617", "issue:41628", @@ -12645,6 +12933,7 @@ "issue:42222", "issue:42371", "issue:42490", + "issue:42617", "issue:42673", "issue:42831", "issue:43012", @@ -12656,19 +12945,18 @@ "issue:43441", "issue:43452", "issue:43577", + "issue:43582", "issue:43673", + "issue:43742", "issue:43874", "issue:43931", "issue:43937", - "issue:43976", "issue:43986", "issue:44038", "issue:44075", - "issue:44117", "issue:44220", "issue:44261", "issue:44263", - "issue:44368", "issue:44410", "issue:44483", "issue:44484", @@ -12677,9 +12965,9 @@ "issue:44496", "issue:44829", "issue:44933", - "issue:44987", "issue:45003", "issue:45071", + "issue:45216", "issue:45278", "issue:45341", "issue:45459", @@ -12689,6 +12977,11 @@ "issue:45656" ], "soft_pairs": [ + "issue:44829|issue:45216", + "issue:42371|issue:44261", + "issue:42673|issue:43582", + "issue:43408|issue:43742", + "issue:42617|issue:45341", "issue:44933|issue:45278", "issue:42222|issue:45542", "issue:42490|issue:42673", @@ -12701,8 +12994,8 @@ "issue:44075|issue:45656", "issue:43673|issue:45341", "issue:43012|issue:43577", - "issue:44484|issue:45478", "issue:43874|issue:44261", + "issue:44484|issue:45478", "issue:44410|issue:45478", "issue:43097|issue:44493", "issue:44263|issue:44485", @@ -12716,239 +13009,234 @@ "issue:43931|issue:44038", "issue:45003|issue:45341", "issue:43097|issue:43452", - "issue:43986|issue:45341", - "issue:44117|issue:44987", - "issue:43986|issue:44484", - "issue:43408|issue:44368", - "issue:43874|issue:44263", - "issue:43976|issue:45071" + "issue:43986|issue:45341" ], - "prepared_review_unit_hash": "14226c2a3e5a77ef3753d358bd9c1559f12c6bc6c7cd0a53dbfc8ee2956e842f", + "prepared_review_unit_hash": "5d5b20b2dd186fe1ac3bebc18bd70b3355b8002ca634968dcaad4a0ff423c170", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37337, - "estimated_input_tokens": 9335, - "estimated_eval_tokens": 18926 + "serialized_chars": 37204, + "estimated_input_tokens": 9301, + "estimated_eval_tokens": 18858 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose mix of unrelated Transformers regressions. I would keep the broad import-regression report as the canonical issue, but I do not see any soft pair that is strong enough to merge as the same underlying bug/change.", - "confidence": 0.39, - "canonical_issue_reason": "issue:45278 is the broadest umbrella report here (many import errors after upgrading) and is the best place to anchor related import-regression duplicates.", + "summary": "This cluster is mostly noisy and heterogeneous: the issues cover unrelated Transformers v5 regressions, model-loading failures, tokenizer changes, backend packaging, and optimizer/runtime bugs. I don\u2019t see any soft pair that looks like the same underlying bug or change.", + "confidence": 0.95, + "canonical_issue_reason": "issue:45278 is the broadest representative item, summarizing a general v5 import-regression theme that overlaps with several other reports more than any single narrow bug does.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45464 is the most detailed and actionable standalone report in the set, with a large reproduction write-up and active discussion.", + "best_issue_reason": "issue:45278 is the best cluster representative because it is the most umbrella-like report and closest to the shared import/regression flavor among otherwise distinct issues.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "FlashAttention-3 training degeneration and a Qwen3.5 save_pretrained checkpoint regression are different bugs with different failure modes." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API guidance and an MLA rms_norm_eps precision issue are unrelated." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "VRAM leakage across dataloader threads is not the same as an Apple Silicon TypeError in caching_allocator_warmup." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "A sam3 model-type warning and a MobileLLM key error are distinct loading problems." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel.py runtime failure and a testing_utils bug do not share the same underlying issue." + }, { "left": "issue:44933", "right": "issue:45278", "accept": false, - "reason": "One is a specific missing import from image_utils; the other is a broad post-upgrade import-error report. Same symptom class, not the same concrete bug." + "reason": "The first is a specific missing import from image_utils; the second is a broad v5 import-regression report." }, { "left": "issue:42222", "right": "issue:45542", "accept": false, - "reason": "VitPose model breakage and TensorFlow backend installation behavior are unrelated failures." + "reason": "A broken vitpose model and a missing-TensorFlow backend packaging issue are unrelated." }, { "left": "issue:42490", "right": "issue:42673", "accept": false, - "reason": "Local-path import warning and Qwen3ForCausalLM VRAM leakage are different code paths and symptoms." + "reason": "Local-path import warning behavior and a VRAM leak in dataloader threads are different code paths." }, { "left": "issue:43937", "right": "issue:44496", "accept": false, - "reason": "GLM-5 generation config validation and an unrelated model-type loading error are not the same bug." + "reason": "Invalid GenerationConfig and unrecognized model/config.json errors are different model-loading failures." }, { "left": "issue:42175", "right": "issue:42222", "accept": false, - "reason": "Package backend installation coverage and broken VitPose models are unrelated." + "reason": "TensorFlow not being included in a torch extra install is unrelated to vitpose model breakage." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "Both concern chat/completions, but one is a generic API rejection and the other is a streaming-specific Qwen3.5-0.8B failure; not clearly the same code-path problem." + "reason": "Both mention chat/completions, but one is a general request rejection and the other is a streaming-specific Qwen3.5 failure." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "ImportError for layer_type_validation is unrelated to the audio feature-extraction issue." + "reason": "An import error from configuration_utils and an audio feature-extraction issue are unrelated." }, { "left": "issue:42371", "right": "issue:42831", "accept": false, - "reason": "TF32 behavior warnings and FineGrainedFP8 accuracy problems are different precision-related issues." + "reason": "TF32 API behavior and FineGrainedFP8 accuracy are different precision-related problems." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Tokenizer decoder-type regression and changed tokenization output are related to v5 tokenizer behavior, but not clearly the same concrete defect." + "reason": "A wrong tokenizer decoder type and changed tokenization output are related broadly to tokenization, but not the same concrete bug." }, { "left": "issue:44075", "right": "issue:45656", "accept": false, - "reason": "SGD argument handling and double optimizer-step behavior under deepspeed are different optimizer bugs." + "reason": "Unused SGD arguments and double optimizer stepping under deepspeed are different optimizer bugs." }, { "left": "issue:43673", "right": "issue:45341", "accept": false, - "reason": "Generation cache missing in chunked_prefill and a testing_utils bug are unrelated." + "reason": "Generation cache missing during chunked_prefill and a testing_utils bug are unrelated." }, { "left": "issue:43012", "right": "issue:43577", "accept": false, - "reason": "A PyTorch warning on compiling bf16 models is not the same as Blip2 dtype fields staying float32 on load." + "reason": "A PyTorch warning during bfloat16 compilation and BLIP2 dtype fields staying float32 are different dtype issues." }, { - "left": "issue:44484", - "right": "issue:45478", + "left": "issue:43874", + "right": "issue:44261", "accept": false, - "reason": "max_shard_size behavior and Qwen3.5-MoE from_pretrained errors are unrelated." + "reason": "A missing image-patch count method and an rms_norm_eps precision mismatch are unrelated multimodal/model bugs." }, { - "left": "issue:43874", - "right": "issue:44261", + "left": "issue:44484", + "right": "issue:45478", "accept": false, - "reason": "Missing get_number_of_image_patches in GLM46V and MLA rms_norm_eps precision issues are different multimodal bugs." + "reason": "A save_pretrained shard-size question and a Qwen3.5 MoE from_pretrained error do not describe the same bug." }, { "left": "issue:44410", "right": "issue:45478", "accept": false, - "reason": "Missing projections in qwen3next layer 0 and Qwen3.5-MoE loading failures are different model implementations." + "reason": "Missing layer projections in qwen3next and a Qwen3.5 MoE loading error are different model-specific failures." }, { "left": "issue:43097", "right": "issue:44493", "accept": false, - "reason": "Removed tie_embeddings_and_encoder_decoder and unexpected position-id keys are not the same regression." + "reason": "Removed tie_embeddings_and_encoder_decoder and unexpected position-id keys are different regressions." }, { "left": "issue:44263", "right": "issue:44485", "accept": false, - "reason": "torch.split return-value handling in GlmMoeDsaIndexer is unrelated to GLM-5 RoPE implementation." + "reason": "A torch.split return-value issue in GlmMoeDsaIndexer is not the same as a GLM-5 RoPE implementation problem." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "bf16 compile warnings and sam3_tracker/sam3_video model-type mismatch are unrelated." + "reason": "These concern unrelated dtype-warning behavior and sam3 model-type warnings." }, { "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Cannot import AutoImageProcessor and PretrainedConfig type-checking regressions are different API breakages." + "reason": "An AutoImageProcessor import failure and a PretrainedConfig type-checking regression are separate API breakages." }, { "left": "issue:42222", "right": "issue:45459", "accept": false, - "reason": "VitPose model breakage and protobuf-tokenizer error masking are unrelated." + "reason": "A broken vitpose model and tokenizer error handling when protobuf is absent are unrelated." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "Both mention flash_attention_3, but one is an inference/load failure and the other is a training degradation issue; not the same code-path." + "reason": "Ministral FlashAttention failure and FlashAttention-3 training degeneration are not the same concrete bug." }, { "left": "issue:45071", "right": "issue:45542", "accept": false, - "reason": "PretrainedConfig type checking and missing TensorFlow backend errors are unrelated." + "reason": "PretrainedConfig type checking and a missing-TensorFlow backend error are unrelated." }, { "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Weight-shape mismatch for Qwen3-VL and missing projections in qwen3next are different model-loading failures." + "reason": "Qwen3-VL weight-shape mismatch and qwen3next missing projections are distinct model-loading issues." }, { "left": "issue:43335", "right": "issue:45071", "accept": false, - "reason": "SwitchTransformers sparse-layer construction and PretrainedConfig type checking are different regressions." + "reason": "A SwitchTransformersConfig sparse-layer bug and a PretrainedConfig type-check regression are different failures." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Qwen3-VL weight mismatch and Qwen3.5/Qwen3 transformers v5 bug reports are unrelated." + "reason": "Qwen3-VL shape mismatch and Qwen3-VL-Moe bug reports are different model-specific problems." }, { "left": "issue:45003", "right": "issue:45341", "accept": false, - "reason": "sys.modules access in modeling_utils and a testing_utils bug are unrelated." + "reason": "Unsafe sys.modules access in modeling_utils and a testing_utils bug are unrelated." }, { "left": "issue:43097", "right": "issue:43452", "accept": false, - "reason": "Removed tie_embeddings_and_encoder_decoder and gguf_file/from_pretrained loading failures are different issues." + "reason": "A removed config field and gguf_file breaking from_pretrained are different regressions." }, { "left": "issue:43986", "right": "issue:45341", "accept": false, - "reason": "Video-model loading without torchvision and a testing_utils bug are unrelated." - }, - { - "left": "issue:44117", - "right": "issue:44987", - "accept": false, - "reason": "Tokenizer mapping None handling and a specific physical-intelligence/fast loading failure may be related in theme, but not enough evidence they are the same underlying bug." - }, - { - "left": "issue:43986", - "right": "issue:44484", - "accept": false, - "reason": "Video processor import failure and max_shard_size behavior are unrelated." - }, - { - "left": "issue:43408", - "right": "issue:44368", - "accept": false, - "reason": "sam3 model-type warning and tie_word_embeddings warning are different model-configuration problems." - }, - { - "left": "issue:43874", - "right": "issue:44263", - "accept": false, - "reason": "GLM46V image patch counting and GlmMoeDsaIndexer torch.split behavior are unrelated." - }, - { - "left": "issue:43976", - "right": "issue:45071", - "accept": false, - "reason": "Python version compatibility in 5.1.0 and PretrainedConfig type checking in 5.4.0 are different release issues." + "reason": "A missing-torchvision crash in AutoProcessor and a testing_utils bug are unrelated." } ] }, @@ -12967,10 +13255,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:38617", "issue:42757", @@ -12983,13 +13271,14 @@ "issue:43208", "issue:43352", "issue:43381", + "issue:43408", "issue:43502", - "issue:43526", "issue:43531", "issue:43550", "issue:43824", "issue:43825", "issue:43873", + "issue:43874", "issue:43901", "issue:43906", "issue:43976", @@ -12999,36 +13288,41 @@ "issue:44062", "issue:44117", "issue:44261", + "issue:44263", "issue:44315", "issue:44351", "issue:44368", "issue:44380", "issue:44410", - "issue:44483", "issue:44484", "issue:44485", - "issue:44514", "issue:44655", "issue:44704", "issue:44829", + "issue:44987", + "issue:45071", "issue:45103", "issue:45245", "issue:45341", "issue:45372", "issue:45375", - "issue:45479", "issue:45588", "issue:45753" ], "soft_pairs": [ + "issue:44117|issue:44987", + "issue:43986|issue:44484", + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:43976|issue:45071", "issue:43986|issue:45372", - "issue:43531|issue:45341", "issue:44829|issue:45245", + "issue:43531|issue:45341", "issue:38617|issue:42757", "issue:44261|issue:44485", "issue:43064|issue:44315", - "issue:38617|issue:44351", "issue:44410|issue:45375", + "issue:38617|issue:44351", "issue:44062|issue:44117", "issue:43097|issue:45588", "issue:44038|issue:44410", @@ -13042,214 +13336,233 @@ "issue:43825|issue:44655", "issue:43992|issue:44484", "issue:43208|issue:43550", - "issue:43012|issue:43550", "issue:43012|issue:44368", + "issue:43012|issue:43550", "issue:42886|issue:43381", "issue:43352|issue:44380", "issue:42907|issue:45753", - "issue:42907|issue:44655", - "issue:44380|issue:45479", - "issue:43352|issue:43976", - "issue:43064|issue:44380", - "issue:43208|issue:43526", - "issue:44483|issue:44514" + "issue:42907|issue:44655" ], - "prepared_review_unit_hash": "5e65e64cbc5263addea6f2ff54360451a4872be60ca8fcd49eaf5bf2ce488885", + "prepared_review_unit_hash": "ff9adebd2232d78a24639231f15017a3a66bf272c20ce0d0cd022bb43ea08a10", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 36713, - "estimated_input_tokens": 9179, - "estimated_eval_tokens": 18614 + "serialized_chars": 37187, + "estimated_input_tokens": 9297, + "estimated_eval_tokens": 18850 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is very heterogeneous: most items are distinct Transformers bugs, regressions, or API/deprecation reports. None of the soft pairs look like true duplicates of the same underlying issue or change.", - "confidence": 0.26, - "canonical_issue_reason": "issue:43097 is the strongest cluster anchor: it is a concrete v5-breaking behavior change, has inbound references, and is broad enough to sit near several other v5 compatibility reports even though they are not duplicates.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers issues. The soft-similarity pairs generally share a subsystem or symptom class, but not the same concrete bug, so I would not collapse any of them as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": "No single true canonical issue stands out because the set is heterogeneous. If one representative is needed, issue 43873 is the strongest anchor: it is open, has substantial discussion, and describes a concrete runtime problem with quantization/offloading.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43097 is the best representative issue in this set because it is well-scoped, release-relevant, and likely the most central of the v5 compatibility regressions here.", + "best_issue_reason": "Issue 43873 is the most suitable representative because it is active, detailed, and has the clearest broad user impact among this mostly unrelated set.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Both involve loading/tokenizer resolution, but 44117 is a generic mapping bug while 44987 is a model-specific load failure; not the same underlying code path." + }, { "left": "issue:43986", - "right": "issue:45372", + "right": "issue:44484", "accept": false, - "reason": "Both are import/crash reports during processor loading, but they involve different missing symbols, different optional dependencies, and different code paths." + "reason": "One is an AutoProcessor/video-model crash without torchvision; the other is about save_pretrained shard sizing. Different features and failure modes." }, { - "left": "issue:43531", - "right": "issue:45341", + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "These concern unrelated model/config warnings in different architectures; they do not describe the same bug." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Both are GLM-related, but one is an image-processor multimodal token AttributeError and the other is a torch.split indexing issue in a different component." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "A Python-version compatibility regression is not the same as a PreTrainedConfig type-checking breakage." + }, + { + "left": "issue:43986", + "right": "issue:45372", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and a small testing_utils bug are unrelated." + "reason": "Both are processor-loading failures, but caused by different missing dependencies/symbols and different model families." }, { "left": "issue:44829", "right": "issue:45245", "accept": false, - "reason": "torch.compile/FlashAttention training degeneration is unrelated to the category-cardinality RuntimeError." + "reason": "These are unrelated training/runtime problems: flash_attention_3 degeneracy versus a categorical-cardinality RuntimeError." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and a testing_utils bug are unrelated." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Different import errors from different modules and symbols; not the same bug." + "reason": "Both are import errors, but for different symbols from different modules; not the same concrete breakage." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "Missing rms_norm_eps precision issue and GLM-5 RoPE implementation are different model-specific problems." + "reason": "One is an eps/config precision mismatch in MLA layernorm; the other is a RoPE implementation question. Different code paths." }, { "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "FSDP2/PEFT optimizer-state corruption and Liger-kernel model_init behavior are different training paths." + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to Liger Kernel application with model_init." }, { - "left": "issue:38617", - "right": "issue:44351", + "left": "issue:44410", + "right": "issue:45375", "accept": false, - "reason": "Cannot import layer_type_validation and cannot import HybridCache are separate API surface regressions." + "reason": "Both are Qwen-family model/config issues, but one is missing attention projections and the other is a dropped vision config field." }, { - "left": "issue:44410", - "right": "issue:45375", + "left": "issue:38617", + "right": "issue:44351", "accept": false, - "reason": "Both mention Qwen-family vision models, but they concern different configs and different missing fields." + "reason": "Both are import failures, but they involve different missing exports and different modules." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "AddedToken keyword collision and TOKENIZER_MAPPING_NAMES returning None are unrelated tokenizer bugs." + "reason": "An AddedToken constructor argument conflict is not the same issue as TOKENIZER_MAPPING_NAMES returning None." }, { "left": "issue:43097", "right": "issue:45588", "accept": false, - "reason": "Config removal warning and flash_attention s_aux=None crash are different code paths and symptoms." + "reason": "A removed config API and a flash_attention runtime AttributeError are unrelated." }, { "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Qwen3-VL-Moe model compatibility and qwen3next missing projections are distinct model implementation issues." + "reason": "These are different Qwen-related bugs; one is a broader v5 compatibility issue, the other is a specific missing-layer-projection defect." }, { "left": "issue:44704", "right": "issue:45103", "accept": false, - "reason": "AutoProcessor kwargs passthrough and auto_docstring annotation parsing are unrelated." + "reason": "Passing kwargs to cached_file and an auto_docstring annotations crash are separate utility-layer bugs." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "local_files_only still making API requests is unrelated to missing embed_tokens.weight on UMT5Encoder load." + "reason": "local_files_only network leakage and a missing embed_tokens.weight load path are distinct from each other." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Missing torchvision on video model load and tokenizer mapping None are different failures." + "reason": "A video-model processor crash without torchvision and a tokenizer mapping None bug are different subsystems and failures." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "Removed tie_embeddings_and_encoder_decoder and offloading with quantization are separate release/feature problems." + "reason": "Removal of a config attribute and quantization/offloading failure are not the same underlying bug." }, { "left": "issue:43824", "right": "issue:43986", "accept": false, - "reason": "Different missing-import failures for different model families and dependencies." + "reason": "One is a missing class export/import error; the other is a processor crash due to missing torchvision. Different root causes." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Wrong tokenizer decoder type in v5 and a reproduction of another issue are not the same concrete bug." + "reason": "Wrong tokenizer decoder type in v5 and a reproduction of another issue are not the same defect." }, { "left": "issue:43097", "right": "issue:43901", "accept": false, - "reason": "Missing configuration API and pipeline docs mentioning return_all_scores are unrelated." + "reason": "A config API removal and a docs/behavior mismatch for return_all_scores are unrelated." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Incorrect translation-task messaging and inability to save Pipeline objects are different pipeline issues." + "reason": "These both touch pipeline behavior, but one is an error-message issue and the other is save_pretrained support; not mergeable as one fix." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Missing pretrained weight handling and max_shard_size default behavior are unrelated save/load topics." + "reason": "Missing encoder weights on load and save_pretrained shard sizing are separate save/load concerns." }, { "left": "issue:43208", "right": "issue:43550", "accept": false, - "reason": "xLSTM training bugs and Bamba SDPA compile failure are unrelated model-specific regressions." + "reason": "xLSTM training blockers and Bamba SDPA/torch.compile failures are different model-specific problems." }, { "left": "issue:43012", - "right": "issue:43550", + "right": "issue:44368", "accept": false, - "reason": "A PyTorch bfloat16 warning and a compile/SDPA failure are not the same underlying issue." + "reason": "A float32 warning on bfloat16 compilation and a tie_word_embeddings warning are unrelated warnings with different triggers." }, { "left": "issue:43012", - "right": "issue:44368", + "right": "issue:43550", "accept": false, - "reason": "bfloat16 precision warning and tie_word_embeddings warning are different warnings with different causes." + "reason": "These are different failure modes: a precision warning versus a torch.compile backend bug." }, { "left": "issue:42886", "right": "issue:43381", "accept": false, - "reason": "Offline cache loading failure and gradient checkpointing in eval mode are unrelated behaviors." + "reason": "Offline cache loading and gradient checkpointing in eval mode are unrelated." }, { "left": "issue:43352", "right": "issue:44380", "accept": false, - "reason": "Nemotron FA2 support error and GPT2 attention scaling ignored under SDPA/FlashAttention are different attention/backends bugs." - }, - { - "left": "issue:43064", - "right": "issue:44380", - "accept": false, - "reason": "Trainer/FSDP optimizer-state corruption and GPT2 attention scaling are separate subsystems." + "reason": "Both mention attention backends, but one is explicit FA2 support gating and the other is GPT-2 attention scaling behavior; not the same bug." }, { - "left": "issue:43208", - "right": "issue:43526", + "left": "issue:42907", + "right": "issue:45753", "accept": false, - "reason": "xLSTM training bugs and BeitImageProcessorFast reduce_labels behavior are unrelated." + "reason": "Dequantized model saving and a Qwen3.5 image infinite loop are unrelated." }, { - "left": "issue:44483", - "right": "issue:44514", + "left": "issue:42907", + "right": "issue:44655", "accept": false, - "reason": "Chat/completions request handling and batched apply_chat_template padding behavior are different APIs and failures." + "reason": "Saving dequantized models and saving Pipeline objects are different save_pretrained problems." } ] }, @@ -13268,10 +13581,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:36010", "issue:36683", @@ -13279,15 +13592,16 @@ "issue:42490", "issue:42757", "issue:42994", - "issue:43010", "issue:43012", "issue:43064", "issue:43066", + "issue:43208", "issue:43299", "issue:43352", "issue:43475", "issue:43502", "issue:43525", + "issue:43526", "issue:43582", "issue:43611", "issue:43618", @@ -13296,7 +13610,6 @@ "issue:43824", "issue:43867", "issue:43901", - "issue:43931", "issue:43937", "issue:43976", "issue:44038", @@ -13309,25 +13622,30 @@ "issue:44380", "issue:44483", "issue:44485", - "issue:44492", + "issue:44514", "issue:44655", "issue:44683", "issue:44938", "issue:45216", - "issue:45278", "issue:45290", "issue:45381", "issue:45440", "issue:45478", + "issue:45479", "issue:45593", "issue:45753" ], "soft_pairs": [ + "issue:44380|issue:45479", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:44483|issue:44514", "issue:36683|issue:43582", + "issue:43208|issue:43526", "issue:44222|issue:45478", "issue:42490|issue:43012", - "issue:43012|issue:44683", "issue:43618|issue:43761", + "issue:43012|issue:44683", "issue:42757|issue:43824", "issue:43618|issue:44380", "issue:38617|issue:43502", @@ -13337,15 +13655,15 @@ "issue:44483|issue:45381", "issue:43756|issue:44485", "issue:43901|issue:44655", - "issue:36683|issue:43475", "issue:43299|issue:45753", + "issue:36683|issue:43475", "issue:42994|issue:44655", "issue:43352|issue:43937", - "issue:44077|issue:44380", "issue:43867|issue:45216", + "issue:44077|issue:44380", "issue:36010|issue:42757", - "issue:43066|issue:45381", "issue:36683|issue:44077", + "issue:43066|issue:45381", "issue:43611|issue:44655", "issue:43976|issue:44938", "issue:36683|issue:43525", @@ -13353,201 +13671,252 @@ "issue:44263|issue:45440", "issue:43618|issue:45216", "issue:36683|issue:44242", - "issue:44188|issue:44380", - "issue:43064|issue:44492", - "issue:43352|issue:43931", - "issue:43010|issue:45278" + "issue:44188|issue:44380" ], - "prepared_review_unit_hash": "b54861e2774782127a222d5bf6cc3926024c7e7208094f047ac7aa69429a7938", + "prepared_review_unit_hash": "b13199a9087816e3b325d254134c5600ef1f368e73461cecb6258910e21ccea5", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 34, - "serialized_chars": 37412, - "estimated_input_tokens": 9353, - "estimated_eval_tokens": 18962 + "soft_pair_count": 36, + "serialized_chars": 38176, + "estimated_input_tokens": 9544, + "estimated_eval_tokens": 19344 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a set of unrelated Transformers regression reports; the soft pairs are mostly superficial similarity matches (imports, loading, MoE, CLIP, or save_pretrained) rather than the same underlying bug. One broad import-regression issue stands out as the best representative.", - "confidence": 0.42, - "canonical_issue_reason": "issue:45278 is the broadest umbrella report in the set: multiple import errors after upgrading from 4.57.0 to 5.5.0. It best represents the shared import/regression theme without being overly specific.", + "summary": "Mostly a heterogeneous set of Transformers regression reports, import errors, and model-specific bugs. The items are not strong duplicates overall; they share broad v5-regression language but usually hit different code paths or models.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 43611 is the broadest and most representative regression report in the set: a general Transformers 5.0 model-loading break tied to base_model_prefix handling.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most representative issue for the cluster because it describes a broad, user-visible regression class rather than a single model-specific edge case.", + "best_issue_reason": "Issue 43611 is the clearest, most actionable cluster representative because it describes a concrete, user-facing regression with a broad impact across models.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Different subsystems: attention scaling backend behavior vs sequence-classification loss computation." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Unrelated problems: FlashAttention support for a model vs Python-version compatibility." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Distributed training optimizer-state bug is unrelated to GPT-2 attention scaling." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Both involve chat/template paths, but one is request acceptance and the other is batched chat-template crashing." + }, { "left": "issue:36683", "right": "issue:43582", "accept": false, - "reason": "Different failures: Gemma3Config missing vocab_size vs AppleSilicon TypeError in caching_allocator_warmup. Same broad severity, not the same bug." + "reason": "Different model/config attribute error vs Apple Silicon allocator TypeError." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs are unrelated to BeitImageProcessorFast label reduction." }, { "left": "issue:44222", "right": "issue:45478", "accept": false, - "reason": "Both involve MoE/save/load workflows, but one is FP8 save_pretrained failure and the other is a from_pretrained loading error for Qwen3.5 MoE. Different code paths." + "reason": "Save-pretrained FP8 MoE bug and from-pretrained Qwen3.5 MoE load error are not the same concrete failure." }, { "left": "issue:42490", "right": "issue:43012", "accept": false, - "reason": "One is a local model path trailing-slash warning; the other is a bfloat16 compile precision warning. No shared underlying defect." + "reason": "Trailing-slash import warning and bf16 compiler warning are unrelated issues." }, { - "left": "issue:43012", - "right": "issue:44683", + "left": "issue:43618", + "right": "issue:43761", "accept": false, - "reason": "Both mention compile-related issues, but one is a warning and the other is a hard failure in compiled flex_attention on newer torch. Not the same bug." + "reason": "Both are CLIP regressions, but the titles point to different missing outputs and no shared concrete failure is shown." }, { - "left": "issue:43618", - "right": "issue:43761", + "left": "issue:43012", + "right": "issue:44683", "accept": false, - "reason": "Both are CLIP v5 regressions, but they affect different outputs: attentions missing vs hidden_states=None. Separate return-value bugs." + "reason": "PyTorch precision warning is unrelated to compiled flex_attention failure on newer torch." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different missing symbols from different modules. This looks like separate packaging/API breakages." + "reason": "Different missing imports from different packages and different symbols." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "CLIP attentions regression and GPT2 attention scaling behavior are unrelated model/backend issues." + "reason": "CLIP output-field regression is unrelated to GPT-2 attention scaling config being ignored." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "ImportError for layer_type_validation is unrelated to local_files_only still making API requests." + "reason": "Import error in configuration_utils is unrelated to local_files_only network requests." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "One is chat/completions request validation, the other is apply_chat_template crashing on tool-call assistant messages. Different layers of the stack." + "reason": "Chat-completions request rejection and tool-call template crashing are different code paths." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Both mention Qwen3 VL MoE/fp8, but one is a loading regression and the other is fp8 inference support. Not the same concrete bug." + "reason": "Generic Qwen3-VL-Moe breakage and FP8 inference support are not the same bug." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Both are model-loading problems, but one is a Qwen3VL MoE load breakage and the other is a sorted state_dict loading error. Different triggers and fixes." + "reason": "Model-loading failure for Qwen3VL MoE differs from a sorted-state_dict load error." }, { "left": "issue:44483", "right": "issue:45381", "accept": false, - "reason": "Chat completions request acceptance and qwen2.5-vl video vision_position_ids are unrelated issues." + "reason": "API request validation and Qwen2.5-VL video position-id issues are unrelated." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "Both mention RoPE, but one is Smollm3 dropping layers and the other is GLM-5 RoPE implementation discussion. Different model implementations." + "reason": "Smollm3 RoPE-layer mismatch is unrelated to GLM-5 RoPE implementation discussion." }, { "left": "issue:43901", "right": "issue:44655", "accept": false, - "reason": "Docs mismatch for return_all_scores is unrelated to save_pretrained failing on Pipeline objects." + "reason": "Docs mismatch for return_all_scores is unrelated to Pipeline save_pretrained failure." }, { - "left": "issue:36683", - "right": "issue:43475", + "left": "issue:43299", + "right": "issue:45753", "accept": false, - "reason": "Different missing-attribute bugs in different models/configs: vocab_size vs fpn_position_embeddings." + "reason": "Qwen3VL MoE loading failure and a specific-image infinite loop are different defects." }, { - "left": "issue:43299", - "right": "issue:45753", + "left": "issue:36683", + "right": "issue:43475", "accept": false, - "reason": "Qwen3VL MoE loading breakage and Qwen3_5 infinite loop on a specific image are distinct failures." + "reason": "Gemma3Config missing vocab_size and SAM3 missing fpn_position_embeddings are distinct model attribute bugs." }, { "left": "issue:42994", "right": "issue:44655", "accept": false, - "reason": "Both involve saving, but one is quantized model saving and the other is Pipeline.save_pretrained. Not the same issue." + "reason": "Quantized model saving failure is not the same as Pipeline save_pretrained failure." }, { "left": "issue:43352", "right": "issue:43937", "accept": false, - "reason": "Flash Attention support error for NemotronHForCausalLM is unrelated to GLM-5 GenerationConfig validation." + "reason": "FlashAttention unsupported-model issue is unrelated to GLM-5 generation config validation." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "State-dict ordering load error and Qwen3.5 checkpoint save regression are different save/load paths." }, { "left": "issue:44077", "right": "issue:44380", "accept": false, - "reason": "Patchtsmixer post_init validation and GPT2 attention scaling under SDPA/FlashAttention are unrelated model/config bugs." + "reason": "post_init contract issue in patchtsmixer is unrelated to GPT-2 attention scaling." }, { - "left": "issue:43867", - "right": "issue:45216", + "left": "issue:36010", + "right": "issue:42757", "accept": false, - "reason": "One is a load failure with sorted state_dict keys; the other is incorrect checkpoint saving for Qwen3.5. Different directions of the save/load path." + "reason": "Different missing imports from different modules and symbols." }, { - "left": "issue:36010", - "right": "issue:42757", + "left": "issue:36683", + "right": "issue:44077", "accept": false, - "reason": "Both are import errors from Transformers-related APIs, but they concern different missing symbols and likely separate dependency/version regressions." + "reason": "Gemma3 config attribute missing is unrelated to patchtsmixer post_init policy." }, { "left": "issue:43066", "right": "issue:45381", "accept": false, - "reason": "Wrong tokenizer decoder type and wrong vision_position_ids are different v5 regressions in different components." + "reason": "Tokenizer decoder type bug is unrelated to Qwen2.5-VL vision_position_ids." }, { - "left": "issue:36683", - "right": "issue:44242", + "left": "issue:43611", + "right": "issue:44655", "accept": false, - "reason": "Gemma3Config missing vocab_size and load balancing loss omission in MoE training are unrelated bugs." + "reason": "Base-model-prefix loading regression is unrelated to Pipeline serialization." }, { - "left": "issue:44188", - "right": "issue:44380", + "left": "issue:43976", + "right": "issue:44938", "accept": false, - "reason": "torch.compile attention-kernel divergence and GPT2 attention scaling ignorement are separate attention/backend issues." + "reason": "Different Python compatibility failures affecting different versions and environments." }, { - "left": "issue:43064", - "right": "issue:44492", + "left": "issue:36683", + "right": "issue:43525", "accept": false, - "reason": "FSDP2 optimizer state corruption and a typo in cache strategies are unrelated." + "reason": "Different missing config attributes on different model families." }, { "left": "issue:43352", - "right": "issue:43931", + "right": "issue:45593", "accept": false, - "reason": "Nemotron Flash Attention 2 support and Qwen3-VL weight-shape mismatch are not the same model-loading problem." + "reason": "FlashAttention support issue is unrelated to D-FINE auxiliary-loss behavior." }, { - "left": "issue:43010", - "right": "issue:45278", + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "torch.split indexing behavior is unrelated to DeepSeekV3 implementation divergence." + }, + { + "left": "issue:43618", + "right": "issue:45216", "accept": false, - "reason": "Cache update no_grad decoration and broad import errors after upgrade are unrelated." + "reason": "CLIP output regression is unrelated to Qwen3.5 save_pretrained checkpoint corruption." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3 config attribute error is unrelated to MoE load-balancing loss omission." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "torch.compile branching divergence is unrelated to GPT-2 attention scaling config handling." } ] }, @@ -13566,10 +13935,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:28282", "issue:33453", @@ -13577,16 +13946,16 @@ "issue:36683", "issue:41669", "issue:42490", - "issue:42548", "issue:42890", "issue:43010", "issue:43064", - "issue:43065", + "issue:43352", "issue:43502", "issue:43575", "issue:43618", "issue:43723", "issue:43867", + "issue:43931", "issue:43976", "issue:43992", "issue:44062", @@ -13595,12 +13964,11 @@ "issue:44112", "issue:44222", "issue:44246", - "issue:44351", "issue:44355", "issue:44360", "issue:44387", "issue:44484", - "issue:44485", + "issue:44492", "issue:44556", "issue:44855", "issue:44857", @@ -13609,6 +13977,7 @@ "issue:44977", "issue:45071", "issue:45125", + "issue:45278", "issue:45310", "issue:45341", "issue:45357", @@ -13621,7 +13990,10 @@ "issue:45850" ], "soft_pairs": [ + "issue:43064|issue:44492", + "issue:43352|issue:43931", "issue:43992|issue:45310", + "issue:43010|issue:45278", "issue:43867|issue:45375", "issue:44355|issue:44855", "issue:41669|issue:44246", @@ -13648,225 +14020,198 @@ "issue:43723|issue:44556", "issue:42890|issue:45341", "issue:44222|issue:45125", - "issue:44387|issue:44556", - "issue:42548|issue:44351", - "issue:43010|issue:43065", - "issue:43502|issue:44485" + "issue:44387|issue:44556" ], - "prepared_review_unit_hash": "fb171a1b41d9c3c3eb88869d9dce9469e1dd09359effb1873a12f95f1499fce5", + "prepared_review_unit_hash": "7a999fb156dbf30a17af3bfa72a43e0fc6598f1906ad207ce0301f2c3282bf69", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36423, - "estimated_input_tokens": 9106, - "estimated_eval_tokens": 18468 + "serialized_chars": 36452, + "estimated_input_tokens": 9113, + "estimated_eval_tokens": 18482 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are mostly unrelated issues that only share broad themes like loading, imports, tensor-parallelism, or test flakiness. I found no soft pair that looks like the same concrete bug/change, so all soft edges are rejected. The most representative issue for the overall set is the v5 tokenizer/loading regression.", - "confidence": 0.88, - "canonical_issue_reason": "issue:43723 is the broadest, most representative loading-regression report here: it targets AutoTokenizer.from_pretrained behavior in v5 and overlaps conceptually with several other load-failure reports.", + "summary": "This cluster is mostly a grab bag of Transformer v5 regression reports, especially model-loading/import/tokenizer failures, with several unrelated training, quantization, and test issues mixed in. The soft similarity links are largely false positives.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the best umbrella representative: it explicitly captures the broad post-upgrade import/regression theme that most of the cluster superficially resembles, while still being a concrete user report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43723 is the best umbrella issue for this set because it is a clear, user-facing regression around model/tokenizer loading in v5 rather than a narrow model-specific or test-only failure.", + "best_issue_reason": "issue:45278 is the most representative issue for this cluster because it is broad, recent, and aligned with the dominant failure mode seen across the grouped issues (v5 upgrade regressions and import/load breakage).", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Different problems: distributed training optimizer-state corruption vs a cache-strategy typo." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Different models and failure modes: Flash Attention support error vs Qwen3-VL weight-shape mismatch." + }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "Different failures and model families: missing embed_tokens.weight in UMT5Encoder vs a Qwen3.5 MoE from_pretrained error." + "reason": "Both are loading errors, but they affect different models and concrete code paths; too broad to be the same bug." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "One is about adding @torch.no_grad to cache update methods; the other is a broad import-regression report. Not the same change/bug." }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "One is a sorted-state_dict loading error; the other is a missing config field in Qwen3_5MoeVisionConfig. Same broad area, not the same bug." + "reason": "State-dict loading order issue vs missing config field in Qwen3.5 Vision config; distinct root causes." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "Both are import-related, but one is about compiled Python files and the other is a Python 3.13 torch.jit.script parsing/IndentationError issue." + "reason": "Both mention import-time failures, but one is compiled Python files and the other is a Python 3.13 torch.jit parsing/IndentationError issue." }, { "left": "issue:41669", "right": "issue:44246", "accept": false, - "reason": "Both mention import slowness, but one is caused by import * fanout and the other is a general intermittent import-time slowdown; too broad to merge." + "reason": "Both concern import performance, but one is a specific import-* cleanup change and the other is a generic slow-import report; not the same concrete bug." }, { "left": "issue:36683", "right": "issue:43064", "accept": false, - "reason": "Unrelated problems: missing Gemma3Config.vocab_size vs wrong optimizer state/params under v5 + FSDP2 + PEFT + cpu_ram_efficient_loading." + "reason": "Gemma3Config missing vocab_size is unrelated to the FSDP2+PEFT optimizer-state bug." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Both are test/CI issues, but one is missing set_seed coverage and the other is an xdist race on captured_info.txt." + "reason": "Test flakiness from missing set_seed() is different from an xdist race on captured_info.txt." }, { "left": "issue:44938", "right": "issue:45071", "accept": false, - "reason": "Different regressions: Python 3.14 import/load failure vs PretrainedConfig type-checking breakage in v5.4.0." + "reason": "Python 3.14 import failure and PretrainedConfig type-checking breakage are different regressions." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Loading a sorted state_dict and saving wrong visual encoder keys are different code paths and failure modes." - }, - { - "left": "issue:43010", - "right": "issue:45850", - "accept": false, - "reason": "One is a specific no_grad decoration request for cache/layer updates; the other is a vague complaint about many models breaking." - }, - { - "left": "issue:43992", - "right": "issue:45478", - "accept": false, - "reason": "Both involve Qwen3.5/Qwen-style loading, but they are different model variants and different from_pretrained failures." - }, - { - "left": "issue:43010", - "right": "issue:43976", - "accept": false, - "reason": "No_grad on cache updates is unrelated to a Python-version compatibility problem in Transformers 5.1.0." - }, - { - "left": "issue:44938", - "right": "issue:45381", - "accept": false, - "reason": "Python 3.14 loading failure and Qwen2.5-VL video position_id corruption are unrelated bugs." + "reason": "Different Qwen3.5 issues: generic state_dict loading error vs incorrect visual encoder keys saved by save_pretrained." }, { "left": "issue:43618", "right": "issue:44077", "accept": false, - "reason": "CLIPOutput attentions regression and patchtsmixer post_init policy are unrelated model-specific changes." + "reason": "CLIPOutput attentions regression and patchtsmixer post_init validation are unrelated." }, { "left": "issue:42490", "right": "issue:44075", "accept": false, - "reason": "Local-path trailing-slash import warning is unrelated to SGD optimizer arguments not being used." + "reason": "Local-files-only path warning and unused SGD args are unrelated." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Both mention tensor parallelism, but one is a training bug and the other is OOM when loading a specific large model with tp." + "reason": "Generic tensor-parallel training bug and OOM when loading a specific Qwen2 model are not the same underlying issue." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "DSA indexer ReLU discussion and DeepseekV3MoE remote-divergence are unrelated." + "reason": "DSA indexer/ReLU discussion is unrelated to DeepseekV3MoE implementation divergence." }, { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "PyTorch-not-found ImportError and tokenizer-loading regression are different root causes." + "reason": "PyTorch missing dependency error and tokenizer-loading regression are unrelated." }, { "left": "issue:43867", "right": "issue:44484", "accept": false, - "reason": "State_dict sorting load error has nothing to do with the 50GB default max_shard_size question." + "reason": "Model-loading failure vs save_pretrained shard-size question; not the same bug." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIPOutput attentions regression and LwDetrImageLoss AMP/CUDA crash are unrelated." + "reason": "CLIPOutput attentions regression is unrelated to LwDetrImageLoss AMP/CUDA crash." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "CLIPOutput attentions assignment and Qwen3.5 flash-attention generation failure are different bugs." + "reason": "Different failures: CLIPOutput attentions assignment vs Qwen3.5 flash-attention generation bug." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "Test seeding flakiness is unrelated to a Phi-4 multimodal model loading failure." + "reason": "Test seeding flake is unrelated to Phi-4-multimodal model loading failure." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Both are CI/test-related, but one is set_seed coverage and the other is a stale device override failure in GraniteSpeech." + "reason": "A stale GraniteSpeech CI test and a missing set_seed() issue are different test problems." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "Different test-suite problems: xdist seed/captured_info race vs auto_mappings referencing removed configs." + "reason": "Patched testing-utils xdist race and auto_mappings CI breakage are unrelated." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "local_files_only still making API requests is unrelated to AddedToken receiving duplicate special kwargs." + "reason": "local_files_only network leakage and AddedToken keyword-argument conflict are different tokenizer/download bugs." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Both concern loading regressions after v5, but one is tokenizer loading and the other is checkpoint reload after upgrade; not the same concrete bug." + "reason": "Tokenizer loading regression in v5 and checkpoint reload incompatibility after version upgrade are related only at a very broad level, but not the same concrete bug." }, { "left": "issue:42890", "right": "issue:45341", "accept": false, - "reason": "A generic testing_utils bug does not match the specific set_seed-related SAM HQ integration failure." + "reason": "Missing set_seed() test flakiness is unrelated to the testing_utils typo bug." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "FP8 save_pretrained for MoE and missing _tp_plan for tensor parallelism are different functionality paths." + "reason": "FP8 save_pretrained issue and missing _tp_plan for tensor parallelism are different Qwen-related bugs." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 quantization memory regression and checkpoint reload failure after upgrading are both v5-related, but not the same issue." - }, - { - "left": "issue:42548", - "right": "issue:44351", - "accept": false, - "reason": "Both are top-level import errors, but they involve different symbols and likely different export paths." - }, - { - "left": "issue:43010", - "right": "issue:43065", - "accept": false, - "reason": "Cache update no_grad decoration and Sam3PixelDecoder dummy Conv2d are unrelated." - }, - { - "left": "issue:43502", - "right": "issue:44485", - "accept": false, - "reason": "local_files_only network access bug and GLM-5 RoPE implementation discussion are unrelated." + "reason": "Int4 quantization memory regression and checkpoint reload failures are unrelated." } ] }, @@ -13885,10 +14230,10 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:30333", "issue:30990", @@ -13902,6 +14247,7 @@ "issue:42757", "issue:42831", "issue:43010", + "issue:43065", "issue:43232", "issue:43299", "issue:43502", @@ -13915,8 +14261,8 @@ "issue:44222", "issue:44230", "issue:44261", - "issue:44273", "issue:44315", + "issue:44351", "issue:44355", "issue:44360", "issue:44485", @@ -13928,7 +14274,6 @@ "issue:44908", "issue:44938", "issue:44961", - "issue:45003", "issue:45071", "issue:45125", "issue:45230", @@ -13936,20 +14281,22 @@ "issue:45375", "issue:45468", "issue:45478", - "issue:45542", "issue:45850" ], "soft_pairs": [ + "issue:42548|issue:44351", + "issue:43010|issue:43065", + "issue:43502|issue:44485", "issue:44355|issue:44749", "issue:45125|issue:45478", - "issue:43010|issue:43232", "issue:30990|issue:31795", + "issue:43010|issue:43232", "issue:45125|issue:45375", "issue:30333|issue:33453", "issue:43299|issue:44556", + "issue:42831|issue:43874", "issue:43502|issue:44222", "issue:44315|issue:44360", - "issue:42831|issue:43874", "issue:43502|issue:44961", "issue:44355|issue:45071", "issue:30333|issue:36296", @@ -13959,11 +14306,11 @@ "issue:33453|issue:34689", "issue:42757|issue:43576", "issue:33453|issue:36296", - "issue:43576|issue:45071", "issue:43576|issue:43824", + "issue:43576|issue:45071", "issue:31795|issue:38617", - "issue:41628|issue:42548", "issue:44961|issue:45468", + "issue:41628|issue:42548", "issue:38617|issue:43576", "issue:43576|issue:44938", "issue:43673|issue:44492", @@ -13974,260 +14321,264 @@ "issue:36296|issue:43526", "issue:45362|issue:45850", "issue:44261|issue:44360", - "issue:44623|issue:45230", - "issue:44273|issue:45542", - "issue:44273|issue:45003" + "issue:44623|issue:45230" ], - "prepared_review_unit_hash": "843c4fe4b6249675e3a5d333c47fbfbf024bef61affc44bca82cb98fbc104f22", + "prepared_review_unit_hash": "c5e31dea24d7b009784b14d779c4b9571f31b849064f06e35b8ce17b2048351f", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 37, - "serialized_chars": 38005, - "estimated_input_tokens": 9502, - "estimated_eval_tokens": 19260 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 38, + "serialized_chars": 37735, + "estimated_input_tokens": 9434, + "estimated_eval_tokens": 19124 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a mix of distinct Transformers regressions, import/load failures, and docs-only issues rather than true duplicates. No soft edge is strong enough to merge with confidence from titles alone.", - "confidence": 0.36, - "canonical_issue_reason": "Issue 45850 is the broadest umbrella-style report in the set, covering many v5 breakages; if one issue must represent the cluster, it is the most general fit, though it is not very specific.", + "summary": "Mostly false positives: the set mixes unrelated Transformers bugs, import failures, docs issues, and version-regression reports. No soft pair looks like the same concrete underlying bug or fix.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45850 is the broadest umbrella ('Since 5.0 version it breaks too many models') and best matches the cluster\u2019s repeated v5 regression theme, though it is very generic.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43299 is the strongest concrete example of a v5 loading regression and is more actionable than the generic umbrella reports, so it is the best representative issue overall.", + "best_issue_reason": "issue:45850 is the most suitable cluster representative because it can absorb many of the v5-breakage complaints; it is still too vague to be an ideal canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different breakages." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Different problems: cache update no_grad behavior vs a dummy Conv2d in Sam3PixelDecoder." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Unrelated code paths: local_files_only network requests vs GLM-5 RoPE implementation." + }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Different symptom classes: compiled-file execution errors vs a performance regression while filtering data." + "reason": "One is compiled Python file errors; the other is a data filtering slowdown after upgrade." }, { "left": "issue:45125", "right": "issue:45478", "accept": false, - "reason": "Same model family, but one is tensor-parallel metadata and the other is a from_pretrained load failure; related, not clearly the same bug." + "reason": "Both mention Qwen3.5 MoE, but one is tensor-parallel planning and the other is from_pretrained loading." }, { - "left": "issue:43010", - "right": "issue:43232", + "left": "issue:30990", + "right": "issue:31795", "accept": false, - "reason": "Both involve generation/cache internals, but the reported failures are on different code paths and look separately fixable." + "reason": "Sentence Transformers loading hang is unrelated to documentation confusion about forward arguments." }, { - "left": "issue:30990", - "right": "issue:31795", + "left": "issue:43010", + "right": "issue:43232", "accept": false, - "reason": "A stuck-loading runtime bug and a documentation clarity issue are not duplicates." + "reason": "Cache no_grad decoration and generation kwargs after sync_gpus are different generation bugs." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Different missing fields/metadata in the same model family; too little evidence that they are one underlying defect." + "reason": "Both are Qwen3.5 MoE-related, but one is tensor parallelism and the other is a missing config field." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "Training-job reporting in MLflow is unrelated to tokenizer-loading regressions." + "reason": "MLFlow job status reporting and tokenizer loading regression are different failures." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Both are version-regression loading failures, but they concern different model/checkpoint situations and are not the same concrete bug." + "reason": "Different version regressions affecting different model-loading paths." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy and missing image-patch counting are unrelated bugs." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "Offline-download behavior and FP8 save_pretrained are unrelated." + "reason": "Both involve saving/loading behavior, but one is offline API requests and the other is FP8 moe save_pretrained." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Liger-kernel application and a DSA indexer activation-function issue are unrelated." - }, - { - "left": "issue:42831", - "right": "issue:43874", - "accept": false, - "reason": "An FP8 accuracy problem and a multimodal-token count AttributeError are different bugs." + "reason": "Liger kernel application in model_init is unrelated to a missing ReLU in the DSA indexer." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "No meaningful overlap between local_files_only network requests and an unrelated placeholder title." + "reason": "local_files_only networking bug and a standalone 'racoon' issue are not the same problem." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled-file execution errors are unrelated to PretrainedConfig type checking." + "reason": "Compiled Python file errors are unrelated to PretrainedConfig type checking in v5.4.0." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "MLflow failure reporting and tensor-parallel training are different subsystems and failure modes." + "reason": "MLFlow reporting on training failure and tensor parallel training are different subsystems." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Running compiled Python files and saving Pipeline objects are distinct problems." + "reason": "Compiled file execution errors are unrelated to Pipeline save_pretrained support." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Docs referencing pipeline() and a meaningless single-word issue title are not duplicates." + "reason": "Docs still mentioning pipeline() and an unrelated 'racoon' issue share no underlying bug." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "FP8 save_pretrained and FP8 inference support are related only at a broad feature level, not the same bug." + "reason": "Both are FP8/moe themed, but one is save_pretrained and the other is inference support." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Different loading regressions affecting different model classes and code paths." + "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading are not the same failure." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "An import error from huggingface_hub and a broken env command are not the same defect." + "reason": "Importing is_offline_mode and the transformers env command are different breakages." }, { "left": "issue:33453", "right": "issue:36296", "accept": false, - "reason": "Tokenizer loading and tensor-parallel training are unrelated." + "reason": "Tokenizer loading and tensor parallel training bugs do not share a concrete code path." }, { "left": "issue:43576", - "right": "issue:45071", + "right": "issue:43824", "accept": false, - "reason": "CLI breakage and config type-checking are different issues." + "reason": "Broken env command and missing Qwen2.5-VL import are unrelated v5 issues." }, { "left": "issue:43576", - "right": "issue:43824", + "right": "issue:45071", "accept": false, - "reason": "A broken CLI command is not the same as a missing Qwen2.5-VL export." + "reason": "CLI env command failure and PretrainedConfig type checking are different features." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation confusion and an import error are not duplicates." + "reason": "Docs confusion about forward arguments is unrelated to a missing layer_type_validation import." }, { - "left": "issue:41628", - "right": "issue:42548", + "left": "issue:44961", + "right": "issue:45468", "accept": false, - "reason": "Both are import errors, but for different symbols and likely different missing exports." + "reason": "A placeholder 'racoon' issue is unrelated to Gemma-4 audio positional encoding." }, { - "left": "issue:44961", - "right": "issue:45468", + "left": "issue:41628", + "right": "issue:42548", "accept": false, - "reason": "No clear shared underlying bug; one title is non-informative." + "reason": "AutoImageProcessor import failure and PreTrainedModel import failure are different missing-export issues." }, { "left": "issue:38617", "right": "issue:43576", "accept": false, - "reason": "ImportError for a specific symbol and a broken env command are not the same code-path problem." + "reason": "Missing layer_type_validation import and broken env command are different regressions." }, { "left": "issue:43576", "right": "issue:44938", "accept": false, - "reason": "CLI breakage and Python 3.14 load failure are too broad to treat as one duplicate." + "reason": "CLI env command breakage and Python 3.14 load failure are not the same bug." }, { "left": "issue:43673", "right": "issue:44492", "accept": false, - "reason": "Generation cache missing and a cache-strategy typo are not the same bug." + "reason": "Missing GenerationMixin cache in chunked_prefill is unrelated to a typo in cache strategies." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Scheduler kwargs handling is unrelated to the other title." + "reason": "Scheduler kwargs handling and an unrelated placeholder issue are different problems." }, { "left": "issue:44485", "right": "issue:44961", "accept": false, - "reason": "RoPE implementation discussion and the other title are unrelated." + "reason": "GLM-5 RoPE implementation and an unrelated placeholder issue are not duplicates." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor-parallel training and docs mentioning return_all_scores are unrelated." + "reason": "Tensor parallel training and TextClassificationPipeline docs are unrelated." }, { "left": "issue:41628", "right": "issue:44355", "accept": false, - "reason": "An import-name regression and compiled-file execution errors do not match." + "reason": "Missing AutoImageProcessor export and compiled Python file errors are different issues." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are different bugs." + "reason": "Tensor parallel training and BeitImageProcessorFast label reduction are unrelated bugs." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "A specific Qwen3.5 chat crash is not the same concrete issue as a generic complaint about many broken models." + "reason": "Qwen3.5 chat crash and the broad 'many models break' report are related only by general version complaints, not the same concrete bug." }, { "left": "issue:44261", "right": "issue:44360", "accept": false, - "reason": "Missing rms_norm_eps precision handling and a missing ReLU in DSA indexer are unrelated." + "reason": "RMS norm epsilon precision discussion and DSA indexer missing ReLU are different code paths." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "Missing processor.save_pretrained files is too specific to merge with a generic bug report." - }, - { - "left": "issue:44273", - "right": "issue:45542", - "accept": false, - "reason": "Lazy loading behavior and a TensorFlow backend error from tensorboard-only installs are unrelated." - }, - { - "left": "issue:44273", - "right": "issue:45003", - "accept": false, - "reason": "Lazy loading failure and unsafe sys.modules access are different mechanisms." + "reason": "Missing processor save_pretrained files and a generic bug report are not the same underlying issue." } ] }, @@ -14246,15 +14597,13 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:31795", "issue:33453", - "issue:34689", - "issue:37428", "issue:41669", "issue:42371", "issue:42890", @@ -14288,6 +14637,7 @@ "issue:44861", "issue:44908", "issue:44945", + "issue:45003", "issue:45071", "issue:45092", "issue:45125", @@ -14297,10 +14647,13 @@ "issue:45341", "issue:45468", "issue:45478", + "issue:45542", "issue:45753", "issue:45850" ], "soft_pairs": [ + "issue:44273|issue:45542", + "issue:44273|issue:45003", "issue:44393|issue:45753", "issue:44393|issue:45071", "issue:44038|issue:45125", @@ -14330,8 +14683,8 @@ "issue:44077|issue:44861", "issue:43827|issue:44908", "issue:31795|issue:33453", - "issue:44315|issue:44829", "issue:41669|issue:44908", + "issue:44315|issue:44829", "issue:43576|issue:44273", "issue:44655|issue:44861", "issue:44360|issue:45468", @@ -14339,312 +14692,282 @@ "issue:44273|issue:44908", "issue:43519|issue:44485", "issue:43519|issue:44908", - "issue:31795|issue:34689", - "issue:41669|issue:43704", - "issue:31795|issue:37428", - "issue:44315|issue:45092", - "issue:44485|issue:45468", - "issue:43704|issue:44485", - "issue:42371|issue:43704" + "issue:41669|issue:43704" ], - "prepared_review_unit_hash": "98ff1b978ef90c3908b75cededd85ba4571d25410243827f679875f62290f311", + "prepared_review_unit_hash": "dedf8843e9a9926d998c7c17091d0ffd9ca24dd19469a177b3829b70a447d4e3", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 45, - "serialized_chars": 40585, - "estimated_input_tokens": 10147, - "estimated_eval_tokens": 20550 + "soft_pair_count": 41, + "serialized_chars": 39338, + "estimated_input_tokens": 9835, + "estimated_eval_tokens": 19926 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a grab-bag of mostly unrelated Transformers v5 regressions, model-specific loading/runtime bugs, docs issues, and performance complaints. None of the soft-edge pairs look like the same underlying fix; most only share a broad subsystem or upgrade context.", - "confidence": 0.76, - "canonical_issue_reason": "issue:45278 is the best umbrella-style issue: it\u2019s open, broad, and explicitly captures the post-4.57/5.x import-breakage pattern affecting many models, which fits the cluster better than the narrower model-specific reports.", + "summary": "This cluster is a loose grab-bag of unrelated Transformers v5 regressions, model-specific bugs, and a few docs/perf complaints. The titles are superficially similar, but the concrete failure modes do not line up closely enough for duplicate merging.", + "confidence": 0.9, + "canonical_issue_reason": "No single issue is a reliable canonical for this cluster; it spans many distinct bugs and regressions rather than one underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the strongest global issue candidate because it summarizes the broadest recurring failure mode in this set (upgrade-related import/loading regressions) without being tied to one model or one code path.", + "best_issue_reason": "If forced to pick the closest umbrella, issue:44273 is the broadest open item, but it is still too vague to serve as a true duplicate anchor for the rest.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Generic lazy-loading complaint vs TensorBoard-without-TF backend error; different subsystems and root causes." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading failure vs unsafe sys.modules access in modeling_utils; not the same bug." + }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Same model family, but different symptoms and likely different bugs: 2D bbox hallucination/error vs infinite loop on a specific image." + "reason": "Qwen3-VL 2D box hallucination/error vs infinite loop on one image; distinct symptoms and likely causes." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Qwen3-VL output bug and PretrainedConfig type-checking regression are unrelated." + "reason": "Model output bug vs PretrainedConfig type-checking regression; unrelated code paths." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Both mention Qwen3.5/MoE, but one is a from_pretrained error and the other is missing _tp_plan for tensor parallelism; not the same concrete fix." + "reason": "Qwen3-VL-Moe bug vs missing _tp_plan for Qwen3_5Moe tensor parallelism; separate model features." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Different failures: broken `transformers env` command vs checkpoint reload incompatibility after upgrade." + "reason": "Broken `transformers env` command vs checkpoint reload failure after upgrade; not the same issue." }, { "left": "issue:43525", "right": "issue:45850", "accept": false, - "reason": "A specific `Llama4Config.pad_token_id` attribute error is not the same as a generic \u201cmany models break\u201d report." + "reason": "Llama4 pad_token_id AttributeError vs broad complaint that many models break in v5." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-star performance problem and missing GenerationMixin cache during chunked prefill are separate issues." + "reason": "Import-* slowdown/explosion vs GenerationMixin cache missing during chunked_prefill; different failure modes." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both are upgrade/loading-related, but one is a general reload failure and the other is a specific remote-code/meta-init incompatibility." + "reason": "Both upgrade-related, but one is checkpoint reload regression and the other is meta-init incompatibility for old remote-code checkpoints." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "A typo in cache strategy text is not the same underlying bug as a broad v5 regression report." + "reason": "Cache-strategy typo vs generic v5 breakage report; not the same concrete problem." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "Missing `pad_token_idx` in StableLmConfig is model-specific and distinct from the generic breakage umbrella." + "reason": "Missing pad_token_idx in StableLmConfig vs vague 'many models break' complaint." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "TF32 API/settings guidance and a cache-strategy typo are unrelated." + "reason": "TF32 API-setting warning vs cache-strategy typo; unrelated topics." }, { "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "AutoProcessor kwargs forwarding and inverse_sqrt scheduler kwargs are different code paths and different bugs." + "reason": "AutoProcessor kwargs not forwarded to cached_file vs inverse_sqrt scheduler kwargs ignored; different components." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Test flakiness from missing `set_seed()` is unrelated to scheduler kwarg handling." + "reason": "Missing set_seed in SamHQ tests vs scheduler kwargs bug; no shared underlying defect." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "Both are broad v5 complaint-style issues, but they don\u2019t point to the same concrete defect or fix; one is about import errors, the other about many models breaking generally." + "reason": "Many import errors after upgrade vs generic v5 breakage complaint; too broad to be duplicates." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Import-time slowness and lazy-loading malfunction are related only at a high level, not the same bug." + "reason": "Importing transformers is slow sometimes vs lazy loading not working properly; related theme, but not the same bug." }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "Model-type warning and Liger Kernel application with `model_init` are unrelated." + "reason": "sam3_video/sam3_tracker model-type warning vs Liger Kernel not applied with model_init; different code paths." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python version compatibility and Qwen3-VL bbox output are unrelated." + "reason": "Python version compatibility issue vs Qwen3-VL 2D bbox output bug; unrelated." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash Attention 2.0 support error for Nemotron and Qwen3-VL output bug are unrelated." + "reason": "Flash Attention 2 unsupported for Nemotron vs Qwen3-VL hallucination/error; different models and failures." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer save metadata mismatch and a generic bug report are not the same underlying issue." + "reason": "Tokenizer_class mismatch on save_pretrained vs a vague generic bug report; no shared concrete issue." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "Broken `transformers env` command and scheduler kwarg handling are unrelated." + "reason": "`transformers env` command broken vs scheduler kwargs ignored; unrelated functionality." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "`position_ids` buffer access error is a concrete model/runtime bug, not the same as a placeholder bug report." + "reason": "position_ids buffer AttributeError vs generic bug report; not the same problem." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs handling and PretrainedConfig type-checking are unrelated." + "reason": "Scheduler kwarg omission vs PretrainedConfig type checking regression; separate bugs." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Import-star performance and missing `HybridCache` import are different problems." + "reason": "Import-* slowdown vs cannot import HybridCache; both import-related but clearly different causes." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Import-star performance and a small testing_utils bug do not share the same fix." + "reason": "Import-* slowdown vs a small testing_utils bug; unrelated." }, { "left": "issue:44492", "right": "issue:44945", "accept": false, - "reason": "Cache-strategy typo and incorrect pipeline-parallel LLM output are unrelated." + "reason": "Cache-strategy typo vs incorrect LLM output under pipeline parallelism; different areas." }, { "left": "issue:43874", "right": "issue:45850", "accept": false, - "reason": "GLM46V missing method is a model-specific implementation gap, not the same as a broad breakage report." + "reason": "GLM46V processor missing method vs generic v5 breakage complaint; not duplicates." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Different Qwen3.5/VL failures with different symptoms and likely different code paths." + "reason": "Qwen3-VL bbox issue vs Qwen3.5 Moe from_pretrained error; separate models and failures." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Optional `post_init` policy and `_get_tied_weight_keys` list crash are unrelated." + "reason": "patchtsmixer post_init policy vs _tied_weight_keys list AttributeError; unrelated model utilities." }, { "left": "issue:43827", "right": "issue:44908", "accept": false, - "reason": "Docs still referencing `pipeline()` and scheduler kwarg handling are unrelated." + "reason": "Docs still reference pipeline() vs scheduler kwargs ignored; docs issue vs runtime bug." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Documentation confusion about `input_ids`/`past_key_values` is not the same as a tokenizer loading regression." + "reason": "Documentation confusion in model.forward vs tokenizer loading regression; unrelated issue types." }, { - "left": "issue:44315", - "right": "issue:44829", + "left": "issue:41669", + "right": "issue:44908", "accept": false, - "reason": "Liger Kernel not applied with `model_init` and degenerate training under flash_attention_3 are separate issues." + "reason": "Import-* slowdown vs scheduler kwargs bug; no shared underlying code path." }, { - "left": "issue:41669", - "right": "issue:44908", + "left": "issue:44315", + "right": "issue:44829", "accept": false, - "reason": "Import-star performance and inverse_sqrt scheduler kwargs are unrelated." + "reason": "Liger Kernel application with model_init vs degenerate training under flash_attention_3; different behaviors." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Broken env command and lazy-loading malfunction are different bugs." + "reason": "Broken `transformers env` command vs lazy loading malfunction; different features." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Pipeline save/load failure and tied-weights key crash are unrelated." + "reason": "Saving Pipeline objects vs tied weight keys AttributeError; unrelated internals." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "DSA indexer missing ReLU and Gemma-4 audio positional encoding are unrelated." - }, - { - "left": "issue:45230", - "right": "issue:45310", - "accept": false, - "reason": "Generic bug report and Qwen3.5 MoE from_pretrained error are not the same issue." - }, - { - "left": "issue:44273", - "right": "issue:44908", - "accept": false, - "reason": "Lazy loading bug and scheduler kwarg handling are unrelated." - }, - { - "left": "issue:43519", - "right": "issue:44485", - "accept": false, - "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are unrelated model-specific bugs." - }, - { - "left": "issue:43519", - "right": "issue:44908", - "accept": false, - "reason": "Timestamp calculation bug and scheduler kwargs bug are unrelated." - }, - { - "left": "issue:31795", - "right": "issue:34689", - "accept": false, - "reason": "Docs confusion around forward args and Llama 3.2 Vision model loading failure are unrelated." - }, - { - "left": "issue:41669", - "right": "issue:43704", - "accept": false, - "reason": "Import-star performance and VRAM leak in dataloader threads are different problems." + "reason": "DSA indexer/ReLU discussion vs Gemma-4 audio positional encoding bug; not the same bug." }, { - "left": "issue:31795", - "right": "issue:37428", + "left": "issue:45230", + "right": "issue:45310", "accept": false, - "reason": "Forward-doc wording and flash-attention import error are unrelated." + "reason": "Generic bug report vs specific Qwen3.5 Moe from_pretrained error; no matching concrete failure." }, { - "left": "issue:44315", - "right": "issue:45092", + "left": "issue:44273", + "right": "issue:44908", "accept": false, - "reason": "Liger Kernel/model_init behavior and remote-code meta-init incompatibility are different fixes." + "reason": "Lazy loading problem vs inverse_sqrt scheduler kwargs bug; separate concerns." }, { - "left": "issue:44485", - "right": "issue:45468", + "left": "issue:43519", + "right": "issue:44485", "accept": false, - "reason": "GLM-5 RoPE implementation and Gemma-4 audio positional encoding are unrelated." + "reason": "Qwen3VL timestamp calculation bug vs GLM-5 RoPE implementation discussion; distinct models/issues." }, { - "left": "issue:43704", - "right": "issue:44485", + "left": "issue:43519", + "right": "issue:44908", "accept": false, - "reason": "VRAM leak across threads and RoPE implementation are unrelated." + "reason": "Qwen3VL timestamp bug vs scheduler kwargs bug; unrelated." }, { - "left": "issue:42371", + "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "TF32 API guidance and VRAM leak in dataloader threads are unrelated." + "reason": "Import-* slowdown vs VRAM leak across dataloader threads; different symptom and subsystem." } ] }, @@ -14663,17 +14986,20 @@ "review_unit_count": 47, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-400", + "cluster_id": "cluster-10000-402", "nodes": [ "issue:30333", "issue:31515", "issue:31795", "issue:33453", + "issue:34689", "issue:36296", + "issue:37428", "issue:38617", + "issue:42371", "issue:42913", "issue:43066", "issue:43298", @@ -14687,11 +15013,14 @@ "issue:44230", "issue:44261", "issue:44263", + "issue:44315", + "issue:44485", "issue:44492", "issue:44623", "issue:44861", "issue:44908", "issue:44998", + "issue:45092", "issue:45290", "issue:45310", "issue:45341", @@ -14699,6 +15028,12 @@ "issue:45850" ], "soft_pairs": [ + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:42371|issue:43704", "issue:43502|issue:43519", "issue:43519|issue:44623", "issue:43519|issue:43704", @@ -14723,172 +15058,208 @@ "issue:31515|issue:33453", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "424dc500e96f887e45fe2a581e971db5217a8398fcf0083cb93d1ec134ed6ba9", + "prepared_review_unit_hash": "98f6e14948d3aa984537c0b0a85be964cf212a28dada1f1bf72c0d6904e73731", "component_budget": { - "node_count": 400, - "item_count": 400, - "soft_pair_count": 1499, - "serialized_chars": 772949, - "estimated_input_tokens": 193238, - "estimated_eval_tokens": 386732 + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 }, "budget": { - "node_count": 29, - "item_count": 29, - "soft_pair_count": 23, - "serialized_chars": 23090, - "estimated_input_tokens": 5773, - "estimated_eval_tokens": 11802 + "node_count": 35, + "item_count": 35, + "soft_pair_count": 29, + "serialized_chars": 28342, + "estimated_input_tokens": 7086, + "estimated_eval_tokens": 14428 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This looks like a mostly noisy, title-similarity cluster: the paired issues share broad Transformer/modeling vocabulary, but the underlying bugs are different enough that none should be merged as duplicates.", - "confidence": 0.41, - "canonical_issue_reason": "issue:43502 is the clearest concrete bug report in the set and a reasonable representative of the loading/runtime-failure group; the others are either narrower model-specific defects, documentation, or unrelated noise.", + "summary": "The cluster is highly heterogeneous; the soft-similarity links are mostly superficial and none look like true duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45092 is the clearest representative of the v5/model-loading regression subset, but the overall cluster is too mixed to be treated as one duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43502 is the strongest standalone issue for triage because it states a reproducible user-facing failure plainly and is less ambiguous than the more model-specific or off-topic candidates.", + "best_issue_reason": "issue:45092 is the most concrete, user-facing regression among the mixed reports, so it is the best single issue to anchor the cluster if one must be chosen.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion about forward args vs a specific model-loading regression; different problems." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Docs wording issue vs flash-attention import failure; unrelated code paths." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel not applied with model_init vs remote-code/meta-init incompatibility; not the same bug." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE implementation vs Gemma4 audio positional encoding; different model families and failures." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM threading vs GLM-5 RoPE math; unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 API migration notice vs a memory leak bug; no shared code-path." + }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "One is network access despite local_files_only=True; the other is a Qwen3VL timestamp-calculation bug. Different code paths and symptoms." + "reason": "local_files_only still triggers requests vs timestamp calculation in a processor; distinct behaviors." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Timestamp math in a processor is unrelated to missing files from processor.save_pretrained()." + "reason": "Processor timestamp bug vs missing save_pretrained files; different processor issues." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Processor timestamp logic and VRAM leakage in multi-threaded dataloader use are distinct bugs." + "reason": "Processor timestamp calculation vs VRAM leak in causal LM usage; unrelated." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "torch.split return handling in GLM MoE is unrelated to Gemma-4 audio positional encoding." + "reason": "torch.split return handling in an indexer vs audio positional encoding; different components." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device-mismatch in suno/bark-small is a different failure than Gemma-4 audio rel-positional encoding." + "reason": "CPU offload device mismatch vs audio positional encoding; unrelated failure modes." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "Missing rms_norm_eps in MLA q_a_layernorm is a different model-specific precision issue, not the Gemma-4 audio bug." + "reason": "Layernorm epsilon precision issue vs audio positional encoding; not the same underlying bug." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both mention tokenizer v5 behavior, but one is a broad behavior change and the other is a decoder-type mismatch; not enough evidence of the same bug." + "reason": "Both concern tokenizer changes in v5, but one is general behavioral drift and the other is a decoder-type bug; too broad to merge." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler kwargs handling is unrelated to the off-topic 'Unemployment' issue." + "reason": "Scheduler kwargs bug vs an off-topic/invalid issue; no duplicate relationship." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "_get_tied_weight_keys AttributeError and chat-template crashes with tool calls are different APIs and failure modes." + "reason": "Tied-weights key crash vs chat template crash with tool calls; different code paths." }, { "left": "issue:44492", "right": "issue:44998", "accept": false, - "reason": "A cache-strategy typo is unrelated to the off-topic unemployment issue." + "reason": "Cache-strategy typo vs an unrelated issue; not duplicates." }, { "left": "issue:44998", "right": "issue:45850", "accept": false, - "reason": "The off-topic unemployment report is not the same as the broad 'many models break after 5.0' complaint." + "reason": "Unrelated issue text vs broad v5 regression complaint; no shared concrete bug." }, { "left": "issue:43618", "right": "issue:44998", "accept": false, - "reason": "CLIPOutput attentions assignment is a concrete model-output bug, not related to the off-topic unemployment report." + "reason": "CLIPOutput attentions regression vs unrelated issue; no overlap." }, { "left": "issue:44998", "right": "issue:45341", "accept": false, - "reason": "An off-topic issue and a testing_utils bug are unrelated." + "reason": "Unrelated issue text vs testing_utils bug; different artifacts." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_id in Llama4Config and an AttributeError in tied-weight key extraction are different config/runtime paths." + "reason": "Missing pad_token_id in Llama4Config vs tied-weights key crash; different subsystems." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "StableLmConfig missing pad_token_idx is unrelated to _get_tied_weight_keys crashing." + "reason": "Missing pad_token_idx in StableLmConfig vs tied-weights key crash; unrelated." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Slow checkpoint loading from from_pretrained and an ImportError for layer_type_validation are unrelated." + "reason": "Slow checkpoint loading vs import error for layer_type_validation; different symptoms and code paths." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 support for Qwen3-VL/Qwen3.5 MoE and missing processor.save_pretrained files are different problems." + "reason": "fp8 inference support request vs processor save_pretrained file omission; unrelated." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow failure-reporting on training-job failure is unrelated to slow checkpoint loading." + "reason": "MLflow status reporting on failed training vs slow from_pretrained loading; different areas." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Checkpoint loading slowness and tensor-parallel training behavior are different issues." + "reason": "Slow checkpoint loading vs tensor-parallel training bug; not the same bug." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Loading performance and confusing forward() documentation are not the same bug." + "reason": "Loading performance regression vs documentation confusion; unrelated." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "FP8 inference support and a from_pretrained error for Qwen3.5 MoE are related by model family but not the same concrete failure." + "reason": "fp8 support for qwen3-vl/qwen3.5 moe vs from_pretrained error in transformers>=5.4.0; different problems." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "from_pretrained checkpoint slowness and tokenizer-loading regression are different code paths." + "reason": "Slow checkpoint loading vs tokenizer loading regression; related topic but not the same concrete failure." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching not supporting audio models is unrelated to Qwen3-VL/Qwen3.5 FP8 inference support." + "reason": "Continuous batching support for audio models vs fp8 inference support; different feature gaps." } ] }, @@ -14907,8 +15278,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-13244-3", "nodes": [ @@ -14920,7 +15291,7 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "858dc1e43cba70bec3314b07910c2e3be01217118fdec36f4b4aa5b6c473e2cf", + "prepared_review_unit_hash": "e88daaae9626e68719478e7d4036d6089bc3864f97b3c13bdf192f369e1f34ee", "component_budget": { "node_count": 3, "item_count": 3, @@ -14942,24 +15313,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These three issues are not true duplicates: one is about Tapas tokenization mismatch, one is an auth/error-message problem when downloading a private model, and one is a general model-loading failure for bert-base-uncased. The cluster is loosely related by NLP/model loading, but the underlying problems differ.", - "confidence": 0.89, - "canonical_issue_reason": "Issue #16618 is the best representative only because it is the broadest and most active of the three, but the cluster is heterogeneous rather than a real duplicate set.", + "summary": "These three issues are not true duplicates. Two are about model-loading/tokenization behavior in unrelated contexts, but the concrete problems differ: one is Tapas tokenization mismatch, one is a private-model auth/error-message problem, and one is a generic failure to load bert-base-uncased.", + "confidence": 0.85, + "canonical_issue_reason": "Issue #16618 is the broadest and most central model-loading complaint in the cluster, so it is the best single issue to represent the cluster if one must be chosen.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 has the most general model-loading framing and the most discussion, so it is the least misleading single anchor for this noisy cluster.", + "best_issue_reason": "#16618 is the most generally framed and likely to attract related model-loading reports, unlike the more specific Tapas tokenization and private-model login issues.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tokenization parity for Tapas is a different bug from a model-loading failure for bert-base-uncased." + "reason": "Tapas tokenization mismatch is a specific preprocessing/implementation issue, while #16618 is a generic model-loading failure for bert-base-uncased; they do not describe the same bug." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "Private-model download auth/error-message behavior is not the same underlying problem as a generic inability to load bert-base-uncased." + "reason": "#15980 is specifically about the error message when downloading a private model while logged out, whereas #16618 concerns failure to load bert-base-uncased; the underlying failures are different." } ] }, @@ -14978,8 +15349,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-26350-2", "nodes": [ @@ -14989,12 +15360,12 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "ee5967d31c785b6051de8857ffb7e15fe7c90333094ab8cc8b77869e3601789c", + "prepared_review_unit_hash": "368ce75a4fa55bb21be0d293db4a24e26bc300daf8b31ce38440df972765776e", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -15002,7 +15373,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -15011,18 +15382,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related in that both are community contribution requests about expanding architecture support, but they target different features: Flash Attention 2 vs GGUF. They should not be deduplicated.", - "confidence": 0.95, + "summary": "These are not duplicates: one asks for Flash Attention 2 support across more architectures, the other asks for GGUF support across more architectures. They share a generic framing but target different features/code paths.", + "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue #26350 is the more established discussion thread by age and activity, but it is not a duplicate of #33260 because the requested support is for a different mechanism and code path.", + "best_issue_reason": "issue:26350 is the older, more actively discussed request, so it is the better representative issue if one must be chosen, but it is not a duplicate of issue:33260.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Both are feature requests for broader architecture support, but they concern different underlying changes: Flash Attention 2 support versus GGUF support. They are not the same bug or mergeable PR-equivalent change." + "reason": "Different requested capabilities (Flash Attention 2 vs GGUF) with no indication of the same underlying bug or change." } ] }, @@ -15041,8 +15412,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-27088-5", "nodes": [ @@ -15064,7 +15435,7 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "9aaf826beffaac7266a69254b9b26d749f875a7150656a3edae3d9516bef46aa", + "prepared_review_unit_hash": "d4d14e48950bf859b7e0938466fbc5370276ac7ca0b4183957eb0711a5a7feff", "component_budget": { "node_count": 5, "item_count": 5, @@ -15086,79 +15457,82 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly parallel docs-translation requests, not true duplicates: Turkish and Spanish are distinct, and the three generic placeholder issues are nearly identical but still lack evidence they refer to the same concrete translation task. I would keep them separate, with the oldest generic placeholder issue as the best representative only for that narrow subgroup.", - "confidence": 0.91, - "canonical_issue_reason": "Issue 43834 is the oldest and most generic of the near-identical placeholder-template issues, so it is the cleanest representative if one must pick a canonical anchor; however, it does not subsume the language-specific Turkish/Spanish requests.", + "summary": "The cluster splits into one near-duplicate trio of generic i18n translation issues and two standalone language-specific requests (Turkish, Spanish). Only the three placeholder-titled issues look like the same underlying issue; the language-specific ones are separate requests.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43834 is the earliest of the near-identical generic translation issues and serves as the cleanest representative of that duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "43834 is the best single representative of the generic placeholder subgroup because it is the earliest and most broadly worded, but it should not be treated as a duplicate of the actual Turkish or Spanish translation requests.", + "best_issue_reason": "issue:43834 is the best overall issue representative because it is the oldest member of the duplicate trio and matches the shared generic translation request most cleanly.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Different concrete translation requests: Turkish vs a generic placeholder issue; same i18n theme is not enough to merge." + "reason": "Different language targets: Turkish vs generic placeholder translation request. Same broad i18n theme, but not the same concrete issue." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Different concrete translation requests: Turkish vs a generic placeholder issue; no evidence they are the same task." + "reason": "Turkish docs translation request is distinct from the generic placeholder issue; no evidence they track the same language or task." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "Turkish translation request and a generic placeholder issue are not the same underlying change." + "reason": "Different language-specific request versus generic placeholder issue; too broad to call duplicates." }, { "left": "issue:27088", "right": "issue:28936", "accept": false, - "reason": "They target different languages, Turkish and Spanish, so they are distinct requests." + "reason": "Turkish and Spanish translations are separate language requests, not the same underlying issue." }, { "left": "issue:28936", "right": "issue:43834", "accept": false, - "reason": "Spanish translation request vs generic placeholder issue; not the same concrete work item." + "reason": "Spanish request is distinct from the generic placeholder translation issue; same subsystem, different concrete target." }, { "left": "issue:28936", "right": "issue:44365", "accept": false, - "reason": "Spanish translation request and a generic placeholder issue are distinct tasks." + "reason": "Spanish docs translation request does not match the generic placeholder issue at the concrete level." }, { "left": "issue:28936", "right": "issue:44370", "accept": false, - "reason": "Spanish translation request and a generic placeholder issue are distinct tasks." + "reason": "Spanish versus generic placeholder translation request; not the same underlying issue." }, { "left": "issue:43834", "right": "issue:44370", - "accept": false, - "reason": "The titles are nearly identical, but they still look like separate placeholder issues rather than a clearly identical concrete translation task." + "accept": true, + "reason": "Near-identical titles and extremely high body similarity indicate the same generic translation issue." }, { "left": "issue:43834", "right": "issue:44365", - "accept": false, - "reason": "Near-identical placeholder issues, but no explicit target or other evidence that they are the same underlying change." + "accept": true, + "reason": "These look like duplicate copies of the same placeholder translation issue with only minor wording/metadata differences." }, { "left": "issue:44365", "right": "issue:44370", - "accept": false, - "reason": "Almost identical template issues, but the available data does not prove they are the same concrete request." + "accept": true, + "reason": "The two issues are effectively identical generic translation requests and plausibly one duplicate set." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The clustering is well grounded in the packet: the three placeholder-titled issues have near-identical titles and very high similarity, while the Turkish and Spanish issues are meaningfully different, language-specific requests. The soft-edge verdicts are conservative and consistent with the evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -15170,8 +15544,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-36817-15", "nodes": [ @@ -15228,12 +15602,12 @@ "issue:37015|issue:45027", "issue:43837|issue:45177" ], - "prepared_review_unit_hash": "3c31d82c4886f731a4fbe5feb7861bca4b95cbc96436a636f7c4a3372ef77812", + "prepared_review_unit_hash": "6aab5a3bbc399cb4ee5ba9918efd769ea68ea55641896e4a3ca26192ce33d491", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20711, + "serialized_chars": 20710, "estimated_input_tokens": 5178, "estimated_eval_tokens": 10612 }, @@ -15241,7 +15615,7 @@ "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20711, + "serialized_chars": 20710, "estimated_input_tokens": 5178, "estimated_eval_tokens": 10612 }, @@ -15250,222 +15624,222 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This is a loose similarity cluster of unrelated model-request issues; the overlap is mostly generic \u201cadd/support model\u201d wording, not the same underlying bug or change.", + "summary": "These are separate model-support requests for different architectures and modalities (e.g., EuroBert, RF-DETR, NeoBERT, MiniCPM3, Qwen3-ASR/TTS, Voxtral, EUPE). The soft links reflect topical similarity only; none look like the same underlying bug or change.", "confidence": 0.97, - "canonical_issue_reason": null, + "canonical_issue_reason": "No canonical issue: the items are distinct model requests, not duplicates of one underlying report or implementation.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "No single issue is a good global representative because the cluster spans unrelated model additions with different code paths and model families.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different model requests (EuroBert vs DEIMv2); only the generic add-model template overlaps." + "reason": "Different model requests: EuroBert config support vs DEIMv2. Same broad task type, not the same change." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert and Qwen3-TTS are unrelated model requests, not one underlying change." + "reason": "EuroBert config support and Qwen3-TTS support are unrelated model families and code paths." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "Different requested models (EuroBert vs RF-DETR); same broad \u201cadd model\u201d phrasing only." + "reason": "EuroBert and RF-DETR are distinct models; not the same implementation request." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are different models with no shared concrete fix." + "reason": "RF-DETR and DEIMv2 are different vision models, so this is only category-level similarity." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "RF-DETR and LFM2.5 Audio are distinct model additions in different domains." + "reason": "RF-DETR and LFM2.5 Audio 1.5B are unrelated modalities and changes." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "RF-DETR vs weight-sparse transformer request; no same code-path problem." + "reason": "RF-DETR and a weight-sparse transformer request are different model additions." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR and Qwen3-ASR are unrelated model requests." + "reason": "RF-DETR vs Qwen3-ASR support: different model families and tasks." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR and Qwen3-TTS are different models; similarity is only superficial." + "reason": "RF-DETR vs Qwen3-TTS support are distinct requests, not one bug." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT and Qwen3-ASR are unrelated requests." + "reason": "NeoBERT and Qwen3-ASR are unrelated architectures and code paths." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT and circuit-sparsity/circuitgpt are different model additions." + "reason": "NeoBERT support and a sparse-transformer request do not describe the same change." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT and LFM2.5 Audio target different model families and modalities." + "reason": "NeoBERT and LFM2.5 Audio 1.5B are different model support requests." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are different requested models; not the same change." + "reason": "RF-DETR and NeoBERT are different model families; no duplicate evidence beyond similarity." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are separate model requests, not duplicates." + "reason": "NeoBERT and ModernVBERT are separate model additions, not one underlying fix." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture request vs Qwen3-ASR request; different models and tasks." + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are different tasks." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 and circuit-sparsity/circuitgpt are unrelated additions." + "reason": "MiniCPM3 and the sparse-transformer request target different model architectures." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 and ModernVBERT are distinct model requests." + "reason": "MiniCPM3 and ModernVBERT are distinct model support requests." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral TTS are different model families and modalities." + "reason": "MiniCPM3 vs Voxtral TTS support are unrelated model families and modalities." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 and Qwen3-TTS are unrelated model requests." + "reason": "DEIMv2 and Qwen3-TTS are different model requests, not the same code change." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT and Qwen3-ASR are different models, not the same bug/change." + "reason": "ModernVBERT and Qwen3-ASR are separate model additions." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT and Qwen3-TTS are distinct requests." + "reason": "ModernVBERT and Qwen3-TTS are unrelated model requests." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT vs BERT-like models with RoPE is not the same concrete request." + "reason": "ModernVBERT models and BERT-like models with RoPE are only loosely related by BERT naming." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "BERT-like RoPE models and Voxtral TTS are unrelated additions." + "reason": "BERT-like RoPE support and Voxtral TTS support are different model behaviors." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are same family but different tasks; not one mergeable PR." + "reason": "Qwen3-TTS and Qwen3-ASR are sister models, but they are separate support requests and code paths." }, { "left": "issue:43671", "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS and Voxtral-4B-TTS-2603 are different TTS model requests." + "reason": "Qwen3-TTS and Voxtral TTS are different TTS models with different implementations." }, { "left": "issue:43671", "right": "issue:45177", "accept": false, - "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated model requests." + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated modalities and model families." }, { "left": "issue:43671", "right": "issue:44121", "accept": false, - "reason": "Qwen3-TTS and circuit-sparsity/circuitgpt are different model changes." + "reason": "Qwen3-TTS support and sparse-transformer support are unrelated requests." }, { "left": "issue:43671", "right": "issue:43909", "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio are separate audio-model requests, not duplicates." + "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are different audio-model additions." }, { "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio are different models and implementation paths." + "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are separate audio model requests." }, { "left": "issue:43837", "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and EUPE are unrelated model requests." + "reason": "Qwen3-ASR and EUPE are different model families and tasks." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "Qwen3-ASR and circuit-sparsity/circuitgpt are different changes." + "reason": "Qwen3-ASR support and sparse-transformer support are not the same underlying change." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "LFM2.5 Audio and SAM3-LiteText are unrelated audio vs vision/text requests." + "reason": "LFM2.5 Audio 1.5B and SAM3-LiteText are unrelated models/modalities." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Weight-sparse transformer request and EUPE are different model additions." + "reason": "Sparse-transformer support and EUPE support are different model implementations." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different speech-model requests." + "reason": "Qwen3-ASR and Voxtral-4B-TTS are different speech models and fixes." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated model requests." + "reason": "NeoBERT and Voxtral-4B-TTS target completely different code paths." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are different domains and code paths." + "reason": "Qwen3-ASR support and DeepSeek-OCR2 support are separate model additions." } ] }, @@ -15484,8 +15858,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-37934-6", "nodes": [ @@ -15506,12 +15880,12 @@ "issue:43668|issue:44031", "issue:43668|issue:43813" ], - "prepared_review_unit_hash": "69eaeebe2f75ca112a039daa8b0fda47db97aa12346879a97bf5280f607039b0", + "prepared_review_unit_hash": "6ef6af7df13263c80867dbcaae899bd61e99222a39b689e9a93adce905da9fd6", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6293, + "serialized_chars": 6294, "estimated_input_tokens": 1574, "estimated_eval_tokens": 3404 }, @@ -15519,7 +15893,7 @@ "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6293, + "serialized_chars": 6294, "estimated_input_tokens": 1574, "estimated_eval_tokens": 3404 }, @@ -15528,60 +15902,60 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues are not duplicates of one another; they span unrelated models, configs, tokenizer warnings, and typo/propagation bugs. The cluster is mostly soft-similarity noise rather than one underlying defect.", + "summary": "The cluster is highly heterogeneous: normalization implementation, Mask2Former loss plumbing, generic kwargs propagation, a config type-hint typo, a quantization typo, and a tokenizer warning regression. The only commonality is loose text similarity, not the same underlying bug.", "confidence": 0.97, - "canonical_issue_reason": null, + "canonical_issue_reason": "No clear canonical issue: the items describe distinct bugs across unrelated modules and change types, so there is no single duplicate target.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "If forced to name a representative issue, #43240 is the broadest concrete bug report, but it still does not unify the rest of the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Different components and bug types: a model normalization design question vs. a config type-hint issue." + "reason": "Different problems: a model norm implementation question vs. an incorrect type hint in a config class." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Mask2former ignore_value handling is unrelated to missing kwargs in a loss-call path." + "reason": "Both involve losses, but one is Mask2Former ignore_value handling and the other is generic kwargs plumbing; not the same bug." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Unrelated subsystems: segmentation loss config vs. tokenizer regex warning regression." + "reason": "Unrelated: Mask2Former loss config vs. tokenizer regex warning regression." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "No shared code path; this is a mask2former parameter usage bug, not a typo in quantization naming." + "reason": "Mask2Former loss behavior and a quantization typo are different code paths and fix types." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "Different models and different failure modes; not the same underlying bug." + "reason": "Different components and bug classes: model loss handling vs. config annotation typo." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Loss-function kwargs forwarding and a config annotation mistake are not the same issue." + "reason": "Generic loss kwargs bug does not overlap with a ModernBERT config type-hint issue." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "A type-hint bug in ModernBERTConfig is unrelated to tokenizer regex warnings." + "reason": "Config typing issue and tokenizer warning regression are unrelated." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "These concern unrelated areas: config typing vs. a typo in a quantization attribute name." + "reason": "A type-hint correction and a typo in a different symbol are not the same underlying change." } ] }, @@ -15600,8 +15974,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-41084-2", "nodes": [ @@ -15611,12 +15985,12 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "3fee830e0daf28fa54ee2f361c024149a0bad964c3953740a03d18b45f63089b", + "prepared_review_unit_hash": "b40c999af3fb40266822aff110e744baba9b5d23b3e5e7ef2ac378b888296405", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1479, + "serialized_chars": 1480, "estimated_input_tokens": 370, "estimated_eval_tokens": 996 }, @@ -15624,7 +15998,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1479, + "serialized_chars": 1480, "estimated_input_tokens": 370, "estimated_eval_tokens": 996 }, @@ -15633,18 +16007,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are not duplicates: one is a generic request for \"Set Block Decoding,\" while the other asks for \"DeepSeek v3.2 support.\" They describe different kinds of work and different likely code paths.", - "confidence": 0.93, - "canonical_issue_reason": null, + "summary": "These two issues are not duplicates: one is a vague request about block decoding, the other is a model-specific feature request for DeepSeek v3.2 support.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate issue can be chosen because the titles and likely scope are unrelated.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #43037 is the more concrete and actionable request; it names a specific model support gap, whereas #41084 is a broader/less-defined decoding feature request.", + "best_issue_reason": "Issue 43037 is the more concrete and actionable request; 41084 is too broad/vague to serve as a clear representative.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different underlying requests: block decoding support vs. DeepSeek v3.2 model support. They do not appear to be the same bug or change." + "reason": "Different underlying concerns: block decoding implementation vs support for a specific model version. They do not appear to describe the same bug or change." } ] }, @@ -15663,8 +16037,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43598-2", "nodes": [ @@ -15674,7 +16048,7 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "cb0d8d3692a4529927193bdad6982cc11ca006d45d84fa2eedd173fc5b9d63de", + "prepared_review_unit_hash": "b1eb4e98536b0066491fd13618064228aa8c4526283c94443a20555ff5795d91", "component_budget": { "node_count": 2, "item_count": 2, @@ -15696,18 +16070,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are both about Trainer customization, but they describe different problems and likely different fixes: one is about `remove_unused_column` behavior, the other about FLOPs estimation for custom trainers.", - "confidence": 0.91, - "canonical_issue_reason": "Issue #43598 is the broader and more representative Trainer customizability request; #43600 is a separate FLOPs-estimation edge case.", + "summary": "These two issues are related only at a very high level (custom Trainer behavior) but they describe different problems and different code paths, so they should not be treated as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 43598 is the more concrete Trainer customization request; issue 43600 is a separate FLOPS-estimation concern.", "canonical_pr_reason": null, - "best_issue_reason": "#43598 is the better cluster anchor because it frames a general Trainer customization limitation, while #43600 is narrower and unrelated in concrete fix path.", + "best_issue_reason": "43598 is the better representative issue because it is specific and directly about a single Trainer behavior change, while 43600 is a distinct performance/accounting topic.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "Both mention custom trainers, but one concerns unused-column handling and the other concerns FLOPs estimation; they are not the same underlying bug or change." + "reason": "Reject: the titles and likely fixes target different behaviors in Trainer\u2014unused-column handling vs FLOPS estimation for custom trainers\u2014so they are not the same underlying bug." } ] }, @@ -15726,8 +16100,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43684-2", "nodes": [ @@ -15737,7 +16111,7 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "8679537367b512bdfd81e55c2afc525f8cc7d177e4e6c9f60f697629777df31a", + "prepared_review_unit_hash": "f799de03a450a9b17304c04cb1762353586a62cfa6b66ed255fddf6a58fb3778", "component_budget": { "node_count": 2, "item_count": 2, @@ -15759,18 +16133,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related at a very high level (both ask for new AutoModel support for Qwen variants), but they are not the same underlying request: one is for Qwen3-Omni registration in base/conditional-generation auto classes, the other is for Qwen3.5 sequence-classification support.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 43684 is the broader and more generic registration request, so it is the better representative issue for this cluster topic.", + "summary": "These are related only at a very broad AutoModel-support level, but they request different capabilities for different model/config combinations. They should not be treated as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43684 is the broader AutoModel registration request and is the better representative of the cluster\u2019s auto-class support theme.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43684 best represents the cluster because it targets core AutoModel registration, whereas 44405 is a narrower, task-specific classifier-head request for a different Qwen family.", + "best_issue_reason": "Issue 43684 is the more general feature request; 44405 is a separate AutoModelForSequenceClassification request for a different config.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different model families and different auto-task surfaces (conditional generation vs sequence classification); they are not the same concrete bug or change." + "reason": "Different underlying changes: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs Qwen3.5 sequence-classification support. They touch different model families and different auto heads." } ] }, @@ -15789,8 +16163,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43835-4", "nodes": [ @@ -15807,12 +16181,12 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "bcf2c67d1c1393c59985e3bb355de6de4eb39ac97584a5bdf1a29a54de5512c7", + "prepared_review_unit_hash": "4528debffbb114be8ae3eb249f5137032d095023a38c451210b571731d45a982", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4264, + "serialized_chars": 4263, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -15820,7 +16194,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4264, + "serialized_chars": 4263, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -15829,55 +16203,58 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All four are extremely low-signal closed issues with generic or likely spammy titles and no body detail. If one issue must stand in as canonical, the earliest repeated-title issue is the best anchor, but there is not enough evidence to confidently merge any pair.", - "confidence": 0.63, - "canonical_issue_reason": "Issue #43845 is the earliest of the three identical 'huggingface ' reports, so it is the most reasonable canonical anchor for that repeated cluster.", + "summary": "Three issues appear to be near-identical duplicates of the vague \"huggingface \" report; the \"Fett\" issue looks unrelated. No PRs are present.", + "confidence": 0.76, + "canonical_issue_reason": "Issue 43845 is the earliest of the three identical \"huggingface \" issues and is the safest representative for the duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "#43845 is the best overall issue representative because it is the first repeated-title entry and has the strongest superficial similarity to #43846 and #43859.", + "best_issue_reason": "Issue 43845 is the best single issue to keep because it matches the repeated title, is earliest, and has no sign of being distinct from the other two huggingface reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles ('Fett' vs 'huggingface') and no body or target evidence linking them to the same underlying issue." + "reason": "Different titles and no evidence they describe the same problem; \"Fett\" does not align with the huggingface reports." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "Different titles and no descriptive evidence; cannot treat as the same bug or change." + "reason": "Different titles and no shared concrete bug details; likely unrelated." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "Different titles and no supporting context, so the shared cluster signal is too weak to accept." + "reason": "Different titles and no shared concrete bug details; likely unrelated." }, { "left": "issue:43845", "right": "issue:43846", - "accept": false, - "reason": "Exact same title, but there is no issue description or concrete bug detail to prove they report the same underlying problem." + "accept": true, + "reason": "Same title and no distinguishing details; they look like duplicate reports of the same underlying issue." }, { "left": "issue:43845", "right": "issue:43859", - "accept": false, - "reason": "Same generic title, but the available evidence is insufficient to confirm identical underlying content." + "accept": true, + "reason": "Same title and no distinguishing details; they look like duplicate reports of the same underlying issue." }, { "left": "issue:43846", "right": "issue:43859", - "accept": false, - "reason": "Same generic title, but no body, targets, or references provide enough proof that these are true duplicates." + "accept": true, + "reason": "Same title and no distinguishing details; they look like duplicate reports of the same underlying issue." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: three issues share the same title, 43845 is the earliest of that group, and 43835 has a clearly different title. The soft-edge calls are conservative enough overall given the limited evidence; no PR-related claim is made." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -15889,8 +16266,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-44371-5", "nodes": [ @@ -15911,7 +16288,7 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "917e05cd0f2a64692dddcb8f1ab6881e1bf003f1a687b70907bc634d3b286635", + "prepared_review_unit_hash": "576b3721d664a7b07420969dc1e0a2395b30b70e5c1b78cfb051ff44f9b92488", "component_budget": { "node_count": 5, "item_count": 5, @@ -15933,24 +16310,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues look like unrelated spam/placeholder entries plus one vague documentation request; there is no concrete evidence they describe the same underlying bug or change.", - "confidence": 0.94, - "canonical_issue_reason": "Issue 44418 is the most substantive of the set, with a non-spam title suggesting an actual documentation request, while the others are generic spam/placeholder posts.", + "summary": "These issues do not look like duplicates of a single underlying bug or change. Most are spam-like placeholder issues, while one is a vague documentation suggestion; there is no concrete shared problem to merge.", + "confidence": 0.96, + "canonical_issue_reason": "issue:44418 is the only non-spam, somewhat descriptive issue, so it is the best available anchor, though it is still too vague to represent a real duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44418 is the best representative issue in the cluster because it is at least semantically meaningful; the others are clearly low-signal spam or off-topic titles.", + "best_issue_reason": "issue:44418 is the most substantive and least spammy item in the set; the others are generic placeholders with no actionable content.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are generic '' placeholders; no concrete bug, change, or shared detail to justify duplicate linkage." + "reason": "Both are spam placeholders with no concrete bug or change; not the same underlying issue." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Both are generic '' placeholders with empty bodies; identical spam text is not enough to establish the same underlying issue." + "reason": "Both are spam placeholders with no actionable description; no duplicate signal beyond generic similarity." }, { "left": "issue:44371", @@ -15962,37 +16339,37 @@ "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "The titles are unrelated spam vs. a site-style prompt; no shared bug or actionable change is evident." + "reason": "Spam placeholder versus a specific titled issue; no shared underlying bug or request." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "A documentation enhancement request does not match a spam placeholder issue." + "reason": "A generic documentation suggestion is not the same as a spam placeholder." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "A documentation enhancement request does not match a spam placeholder issue." + "reason": "A generic documentation suggestion is not the same as a spam placeholder." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Although the titles match exactly, both are empty spam placeholders and do not provide enough evidence of the same underlying bug/change." + "reason": "Both are spam placeholders, but there is no evidence they refer to the same concrete issue." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder vs. unrelated branded prompt; no concrete overlap in issue content." + "reason": "Spam placeholder versus a specific titled issue; no duplicate relationship." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder vs. unrelated branded prompt; no concrete overlap in issue content." + "reason": "Spam placeholder versus a specific titled issue; no duplicate relationship." } ] }, @@ -16011,8 +16388,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45145-2", "nodes": [ @@ -16022,12 +16399,12 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "c3722fed8b89e350fc33eb1a0439d550bff7d2a63bbad35ec94f601354544e66", + "prepared_review_unit_hash": "a38699bc6b3ca7b72b39d510cc1cbc9bd205066dcdf10244bef420481c0b7222", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1645, + "serialized_chars": 1646, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -16035,7 +16412,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1645, + "serialized_chars": 1646, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -16044,28 +16421,28 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues are highly similar and likely duplicates: they have the same title, very close body lengths, and a soft-similarity signal, but the available evidence does not prove their bodies are identical. #45145 remains the best canonical issue because it was opened earlier and already has an inbound reference.", - "confidence": 0.89, - "canonical_issue_reason": "#45145 is earlier and already has an inbound reference, so it is the better canonical issue for this likely-duplicate pair.", + "summary": "The two closed issues have identical titles and very similar scope, so they look closely related, but the evidence is only soft similarity with no explicit links or shared concrete targets/files. This supports a likely-duplicate reading, not a definitive duplicate conclusion.", + "confidence": 0.73, + "canonical_issue_reason": "If one must be kept as the representative report, #45145 is the better canonical issue because it is earlier and has the same apparent scope as #45151, but the duplication signal is not definitive.", "canonical_pr_reason": null, - "best_issue_reason": "#45145 best represents the underlying report because it predates #45151 and appears to be the original submission.", + "best_issue_reason": "#45145 is the best issue representative because it is earlier and matches the same title/scope, though the evidence only supports a likely duplicate rather than a confirmed one.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", - "accept": true, - "reason": "Likely duplicate: same title, very close body size, and soft-similarity support the same underlying report. The evidence is strong, but not enough to claim an exact duplicate." + "accept": false, + "reason": "The titles match and the topics are highly similar, but there is no explicit linkage or concrete shared implementation target; with only soft-similarity evidence and deterministic false, this is not a confirmed duplicate pair." } ] }, "evaluator_result": { "accept": false, - "feedback": "The conclusion is a bit overstated for the evidence available. The packet supports that these issues are highly similar (same title, close body lengths, soft_similarity), but it does not establish that they are exact duplicates or that the bodies/content are the same. The canonical-choice reasoning is fine, but the duplicate verdict should stay conservative and say \"likely duplicate\" rather than \"exact duplicate.\"" + "feedback": "The packet supports a strong similarity signal, but not a definitive duplicate conclusion. The pair only has soft-similarity evidence, and the deterministic verdict is false. Marking it as a \"clear duplicate pair\" and setting confidence to 0.98 overstates the evidence; a more conservative verdict would be \"likely duplicate\" or \"possibly duplicate.\"" }, "evaluator_used": true, "retried": true, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -16131,8 +16508,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45672-2", "nodes": [ @@ -16142,40 +16519,40 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "fb6c3949747a04aef77cd2a107568ce6e21d1796518b38d191ab8cac74cc3cd9", + "prepared_review_unit_hash": "b74f884d6ff229fec405c7e7cfe2e7e16172a6f73047dd5b682aec67dc47df9d", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1669, - "estimated_input_tokens": 418, - "estimated_eval_tokens": 1092 + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1669, - "estimated_input_tokens": 418, - "estimated_eval_tokens": 1092 + "serialized_chars": 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 issues both involve 4-bit inference with BitsAndBytes, but they describe different failure modes: one is a Gemma4 audio-module uint8/torch.finfo TypeError, the other is a BitsAndBytesConfig lm_head exclusion/assertion regression. They are related by subsystem, not the same underlying bug.", - "confidence": 0.93, - "canonical_issue_reason": "Issue #45674 is the better canonical issue because it is more broadly framed around a specific BitsAndBytesConfig regression, has more discussion activity and inbound references, and describes a clearer configuration-driven failure path.", + "summary": "These are related only at a very broad level (4-bit inference), but they describe different bugs with different triggers and failure modes, so they should not be merged as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": "No canonical duplicate here: #45672 is about a Gemma4 audio-module uint8/torch.finfo TypeError in NF4 inference, while #45674 is about llm_int8_skip_modules unintentionally removing the default lm_head exclusion and causing an AssertionError.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #45674 is the best representative for the cluster since it appears more central and actionable, while #45672 is a model/module-specific manifestation that does not match the same defect.", + "best_issue_reason": "#45674 is the cleaner standalone report: it names the exact BitsAndBytesConfig behavior, the affected default exclusion, and the concrete assertion failure path.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Both concern 4-bit inference, but the concrete bugs differ: Gemma4 audio modules hit a torch.finfo TypeError on uint8 weights, while the other issue is about llm_int8_skip_modules removing the default lm_head exclusion and triggering an AssertionError. Too dissimilar to be duplicates." + "reason": "Reject: both concern 4-bit inference, but the root causes differ. One is a Gemma4/audio-module uint8 torch.finfo TypeError; the other is a BitsAndBytesConfig skip-modules regression that clears the default lm_head exclusion and trips an AssertionError." } ] }, @@ -16194,8 +16571,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45762-2", "nodes": [ @@ -16205,7 +16582,7 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "7f3591a82ecb08fbd76066debc5adbc149a144f00c90e8c5a6e43369076ff2de", + "prepared_review_unit_hash": "f05fd103dff83b5b4af396ecb5a9f99c9a17f1bbf180d709a52b9d9bd3c43426", "component_budget": { "node_count": 2, "item_count": 2, @@ -16227,18 +16604,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues do not look like duplicates; they are separate, unrelated low-content reports with different personal-name titles and dates.", + "summary": "These two closed issues are just short name/date entries with no bug report content; they do not describe the same underlying problem and should not be deduplicated.", "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Neither issue is a strong canonical candidate because neither contains actionable problem details; if one must be chosen, the earlier issue is only a weak placeholder.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "Only weak textual similarity from the shared surname/date pattern; there is no evidence they describe the same underlying bug or request." + "reason": "Both are bare personal-name/date posts with no shared technical problem, code path, or issue context; not a duplicate bug report." } ] }, @@ -16257,8 +16634,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45764-2", "nodes": [ @@ -16268,40 +16645,40 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "629f3f0d7104d0f39058a9afd252c277b126c748583f3b5979bd5e34c7bfb8f8", + "prepared_review_unit_hash": "9a7bb77aface30f009b30197d707ed45f241792493ebd0cd28df5af10811b0dc", "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": "Two closed issues with empty bodies and unrelated personal-name/date titles; there is no evidence they describe the same underlying bug or request.", + "summary": "The two closed issues appear to be unrelated placeholder/spam entries with different personal names and no shared technical content, so they should not be clustered as duplicates.", "confidence": 0.98, - "canonical_issue_reason": "No real canonical issue emerges here: the titles point to different names/dates, and there is no description, linkage, or shared context to unify them.", + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a strong canonical choice; if forced to pick one as a placeholder, #45764 is only marginally earlier, not substantively better.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "Reject: the only similarity is superficial string overlap in surname/date formatting; the titles refer to different individuals and provide no shared bug or task context." + "reason": "Different names, different dates, and no body or issue-link evidence indicate they are not the same underlying issue." } ] }, @@ -16320,8 +16697,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45869-5", "nodes": [ @@ -16341,91 +16718,91 @@ "issue:45871|issue:45873", "issue:45872|issue:45873" ], - "prepared_review_unit_hash": "4297ba6904697ca57d12cd03910a9c18285e68ad0551c60af44d8864e1cca0a1", + "prepared_review_unit_hash": "a206431ebe894adc7e441b69c1b009883a5b9bbb7b373d5a95cd70aa518c1f83", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5723, - "estimated_input_tokens": 1431, - "estimated_eval_tokens": 3118 + "serialized_chars": 5727, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5723, - "estimated_input_tokens": 1431, - "estimated_eval_tokens": 3118 + "serialized_chars": 5727, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster splits into two very likely duplicate issue pairs: the two \"Example: Financial time series prediction with DataForge\" issues and the two \"DataForge: Financial time series + scraping service\" issues. The dataset promo issue is only loosely related and should not be treated as a duplicate of either pair. There is no single issue that cleanly represents the whole cluster.", - "confidence": 0.95, - "canonical_issue_reason": "No single issue cleanly represents the whole cluster because it contains two separate likely-duplicate pairs plus a loosely related promo-style post. If a representative is needed, issue 45870 is a reasonable canonical for the \"Example: Financial time series prediction with DataForge\" pair because 45871 matches it in title and body size, but that only covers one subcluster.", + "summary": "This cluster splits into two separate exact-duplicate pairs: 45870/45871 and 45872/45873. Issue 45869 is only loosely finance-related and should not be merged with either pair.", + "confidence": 0.96, + "canonical_issue_reason": "45870 is the earliest copy in the exact-duplicate pair 45870/45871 and is a reasonable representative for that subcluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45870 is the best overall issue representative because it sits in a clear likely-duplicate pair and is more self-contained than the dataset promo issue or the broader \"scraping service\" request. It is still only a representative for one subcluster, not the whole cluster.", + "best_issue_reason": "45870 is the cleanest representative of one real duplicate pair, but the full set is not one single issue family; 45872 is the representative of a separate duplicate pair.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45869", "right": "issue:45870", "accept": false, - "reason": "Different subjects: a dataset promotion versus an example/tutorial request. They are only loosely related by finance/data context." + "reason": "Different artifacts: a dataset listing vs an example issue. Same finance theme, but not the same underlying request/bug." }, { "left": "issue:45869", "right": "issue:45871", "accept": false, - "reason": "Different subjects: a dataset promotion versus an example/tutorial request. Similar wording is not enough to make them the same issue." + "reason": "Different artifacts: a dataset listing vs an example issue. Only broad topic overlap, not a duplicate." }, { "left": "issue:45870", "right": "issue:45871", "accept": true, - "reason": "Same title and same body length, with only soft-similarity evidence; this is very likely the same underlying example request duplicated." + "reason": "Same title and matching metadata/body length; these look like exact duplicates of the same example issue." }, { "left": "issue:45870", "right": "issue:45872", "accept": false, - "reason": "Both mention financial time series and DataForge, but one is an example request and the other adds a scraping service. Those are distinct asks." + "reason": "Both are DataForge/finance-related, but one is an example prediction issue and the other is a scraping-service issue; not the same underlying request." }, { "left": "issue:45870", "right": "issue:45873", "accept": false, - "reason": "Related theme, but the concrete request differs from the example issue. Not the same underlying issue." + "reason": "Same as the 45870/45872 pair: related topic, but different concrete issue content." }, { "left": "issue:45871", "right": "issue:45872", "accept": false, - "reason": "Related DataForge/financial content, but different concrete requests. Not the same bug or change." + "reason": "Different concrete requests; shared finance/DataForge wording is too broad to call them duplicates." }, { "left": "issue:45871", "right": "issue:45873", "accept": false, - "reason": "Related DataForge/financial content, but different concrete requests. Not the same bug or change." + "reason": "Different concrete requests; only broad subsystem/topic overlap." }, { "left": "issue:45872", "right": "issue:45873", "accept": true, - "reason": "Same title and same body length, with only soft-similarity evidence; this is very likely the same underlying request duplicated." + "reason": "Same title and matching metadata/body length; these look like exact duplicates of the same scraping-service issue." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster interpretation is mostly grounded, but a few phrases are a bit too strong for the packet. The two same-title pairs are likely duplicates, but the evidence shown is only identical titles/body lengths plus soft-similarity, so avoid calling them an \"exact\" or \"perfect\" duplicate pair as if that were proven. Also, \"dataset promo issue is unrelated\" is slightly overstated; the safer wording is that it is only loosely related and not a duplicate." + "accept": true, + "feedback": "The summary is grounded in the packet: 45870/45871 and 45872/45873 are the only clearly tight pairs (identical titles and body lengths), while 45869 is only loosely related by theme and should not be merged. The soft-edge verdicts are conservative overall, and there is no PR-mergeability issue here." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -16433,7 +16810,7 @@ { "label": "pull_request", "component_index": 1, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16483,160 +16860,172 @@ "pull_request:44827|pull_request:45922", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "96ea4833ea1cb2ce921e5550a0c00cd4c21fe491dcdb3813e0833889bd189ec9", + "prepared_review_unit_hash": "811fad3f2ed86f4f1666fd01ae6514a9c274f9716c0cfa68ca0afe1da94176ca", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 22, - "serialized_chars": 42217, - "estimated_input_tokens": 10555, - "estimated_eval_tokens": 21366 + "serialized_chars": 42216, + "estimated_input_tokens": 10554, + "estimated_eval_tokens": 21364 }, "budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 22, - "serialized_chars": 42217, - "estimated_input_tokens": 10555, - "estimated_eval_tokens": 21366 + "serialized_chars": 42216, + "estimated_input_tokens": 10554, + "estimated_eval_tokens": 21364 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster is mostly unrelated PRs that only share broad Transformer-maintenance themes. The only strong duplicate pair is the two `fixed_cross_entropy` PRs, which address the same loss-helper change for the same underlying `cross_entropy` kwargs support.", + "summary": "This cluster is mostly unrelated PRs spanning model additions, docs, refactors, and separate bugfixes. The only true duplicate-like pair is the two `fixed_cross_entropy` PRs, which implement the same `nn.functional.cross_entropy` kwargs passthrough in `loss_utils.py`.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "`pull_request:43251` is the better canonical PR because it directly targets issue 43240, clearly states the bug fix, and is the more complete implementation of the shared `fixed_cross_entropy` change.", + "canonical_pr_reason": "PR 43251 is the best canonical PR for the loss fix: it directly targets issue #43240, changes the same code path as 43254, and is the more explicit implementation of the cross-entropy kwargs passthrough.", "best_issue_reason": null, - "best_pr_reason": "`pull_request:43251` is the best representative of the duplicate pair: same file, same bug, same functional goal, and it has the explicit tracking issue link. The other PR (`43254`) is a near-duplicate variant of the same fix.", + "best_pr_reason": "PR 43251 is the best overall representative of the only duplicated change in this cluster because it is issue-linked and fixes the exact same `fixed_cross_entropy` behavior as 43254.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Unrelated PRs: one adds VideoPrism, the other adds an Executorch dynamic-shape test. No shared code-path or concrete bug fix." + "reason": "Unrelated PRs: VideoPrism model addition vs Executorch dynamic-shape test." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Different model/task areas: Mistral tokenizer helper methods vs adding MobileLLM. Shared tokenization context is too broad to be the same change." + "reason": "Different changes: Mistral tokenizer methods vs adding a new MobileLLM model." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer utility additions and an Executorch export test are unrelated changes." + "reason": "Tokenizer API fix and Executorch export test are unrelated." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Both touch processor/model infrastructure, but they target different models and different problems. Not the same underlying bug or change." + "reason": "Processor auto-loading robustness vs new MobileLLM model; different code paths." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Loss-helper kwargs support and adding MobileLLM are unrelated; no shared code-path." + "reason": "Loss utility kwargs passthrough is unrelated to adding MobileLLM." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Both are small fixes, but one is cross-entropy kwargs handling and the other is Mistral4 test cleanup. Different code paths and goals." + "reason": "Both touch model/runtime internals but fix different problems: cross-entropy kwargs vs Mistral4 tests/model plumbing." }, { "left": "pull_request:43424", "right": "pull_request:45919", "accept": false, - "reason": "Executorch dynamic-shape export test vs adding Sapiens2 model. Not a duplicate change." + "reason": "Executorch export testing and Sapiens2 model addition are unrelated." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Different concerns: dynamic-shape export testing versus Mistral4 test fixes. No shared underlying bug." + "reason": "Dynamic export test vs Mistral4 test/model fix; not the same bug or change." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Executorch export test and MobileLLM model addition are unrelated." + "reason": "Executorch test PR and MobileLLM model addition do not address the same issue." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New model addition vs config resolution order fix. Too broad and unrelated." + "reason": "New MobileLLM model and config-resolution fix are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:45922", "accept": false, - "reason": "MobileLLM model addition and vision-model memory-leak fix are unrelated changes." + "reason": "MobileLLM model addition and vision-model memory leak fix are unrelated." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "Adding MobileLLM and refactoring Falcon output collection are different model-specific changes." + "reason": "Model addition vs Falcon refactor; different concrete changes." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon output-interface refactor and a model-creation skill are unrelated." + "reason": "Falcon output-interface refactor is unrelated to the model-creation skill PR." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon model refactor and Mistral4 test fixes do not address the same bug or code path." + "reason": "Falcon refactor and Mistral4 fixes target different models and issues." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test fixes and CLIP-like `layrnorm`\u2192`layernorm` renaming are unrelated." + "reason": "Mistral4 test fix and `layrnorm` rename are unrelated bugfixes." }, { "left": "pull_request:44827", "right": "pull_request:45795", "accept": false, - "reason": "Mistral4 test fixes and docs for audio/video processors are not the same change." + "reason": "Mistral4 fixes are unrelated to docs for audio/video processors." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 test fixes and config resolution ordering are unrelated maintenance changes." + "reason": "Mistral4 test/model work and config resolution ordering fix are different changes." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 test fixes and a model-creation skill PR are unrelated." + "reason": "Mistral4 changes are unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "New model implementation and the model-creation skill are not the same underlying change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "MobileLLM model addition and docs-only processor guide are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45922", "accept": false, - "reason": "Mistral4 test fixes and vision-model memory-leak fixes are different issues in different subsystems." + "reason": "Mistral4 test fix and vision-model memory leak fix are unrelated." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Same underlying fix in the same file: both update `fixed_cross_entropy` to support extra `nn.functional.cross_entropy` kwargs such as `weight` and `label_smoothing`. They could plausibly be merged into one PR." + "reason": "Both PRs fix the same `fixed_cross_entropy` code path by adding supported kwargs (`weight`/`label_smoothing`) to `nn.functional.cross_entropy`; they are direct alternate implementations of the same bugfix." } ] }, "evaluator_result": { "accept": true, - "feedback": "The duplicate judgment is well grounded in the packet. The only accepted pair, `pull_request:43251` and `pull_request:43254`, clearly targets the same `fixed_cross_entropy` change in the same file and the same issue (`43240`), so mergeability as one bugfix is plausible. The other soft pairs are conservatively rejected and the summary does not overstate the evidence." + "feedback": "The summary is well grounded in the packet: the non-loss PRs are supported as unrelated by titles, filenames, and diffs, and the 43251/43254 pair is a clear same-file, same-issue, same-bugfix duplicate. The soft-edge verdicts stay conservative rather than over-connecting the unrelated model/addition/docs/refactor PRs." }, "evaluator_used": true, "retried": false, @@ -16647,7 +17036,7 @@ { "label": "pull_request", "component_index": 2, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16663,7 +17052,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "75cb1bd96934f1d1dddaa97af0355bbf0daf8bdcf072e0e20ba3f047fc1fa9de", + "prepared_review_unit_hash": "e32fe2d0efa89b942eb87e67005ea7f74b9bb1f98c136655465dee25f75975c0", "component_budget": { "node_count": 2, "item_count": 2, @@ -16685,18 +17074,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs overlap heavily on VibeVoice model scaffolding, but they are not duplicates: 40546 implements the base VibeVoice model, while 42781 extends it with realtime/acoustic-tokenizer work and extra generation changes.", - "confidence": 0.88, + "summary": "These are related VibeVoice PRs, but they are not the same concrete change: one implements the base VibeVoice integration, while the other adds VibeVoice Realtime plus the acoustic tokenizer and generation tweaks. Shared filenames alone are not enough to merge them as duplicates.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 40546 is the core standalone VibeVoice implementation and has the stronger review history; 42781 is a later realtime extension rather than the same change.", + "canonical_pr_reason": "PR 40546 is the better canonical PR because it represents the core VibeVoice implementation and broader initial integration, while PR 42781 is a later, narrower follow-up for realtime/acoustic-tokenizer additions.", "best_issue_reason": null, - "best_pr_reason": "PR 40546 is the best representative of the cluster because it covers the primary VibeVoice feature without the additional realtime follow-on scope.", + "best_pr_reason": "PR 40546 is the best single representative PR for the cluster since it covers the main VibeVoice feature landing with substantial review activity and a cleaner, more general scope than the draft realtime follow-up.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "They share the VibeVoice subsystem, but 42781 adds realtime/acoustic-tokenizer functionality and extra generation changes, so it is an extension rather than the same concrete PR." + "reason": "Different feature scopes: 40546 implements VibeVoice, while 42781 adds VibeVoice Realtime and acoustic-tokenizer-related changes. They overlap on model scaffolding, but not the same underlying code-path change, so they should not be merged as duplicates." } ] }, @@ -16710,7 +17099,7 @@ { "label": "pull_request", "component_index": 3, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16726,12 +17115,12 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "e4b37e2b939feb7dd563df270c79ee68a22e6817d18608b68d582897629bc888", + "prepared_review_unit_hash": "29d1cdf2d71b399711c80a999569144467bf584170a2b6fdfe84696a407dca35", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4674, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -16739,7 +17128,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4674, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -16748,18 +17137,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "False positive cluster: one PR adds TimesFM covariate forecasting support, while the other adds DINOv3 image-classification support. They touch different models, code paths, and user-facing features.", + "summary": "The two pull requests are unrelated feature additions in different areas: TimesFM covariate forecasting vs DINOv3 image classification support. They do not look like duplicate fixes or mergeable alternatives to the same change.", "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR here: these are unrelated feature PRs for different model families and should not be deduplicated into one cluster.", + "canonical_pr_reason": "No canonical PR: the PRs target different model families and different code paths, so there is no duplicate relationship to collapse.", "best_issue_reason": null, - "best_pr_reason": "No global best PR for the cluster; each PR is independently valid but they solve different problems and belong in separate clusters.", + "best_pr_reason": "No single best PR for deduplication: neither PR is a substitute for the other, and both are independent feature work.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different model families and changesets: TimesFM covariate forecasting vs DINOv3 image classification. Not the same underlying bug or mergeable into one PR." + "reason": "Reject: the titles, touched files, and diff previews show different features in different subsystems, not the same underlying bug or change." } ] }, @@ -16773,7 +17162,7 @@ { "label": "pull_request", "component_index": 4, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16836,7 +17225,7 @@ { "label": "pull_request", "component_index": 5, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16854,46 +17243,46 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "2ec9a732cb7a092f672c42e2ea003f88ca1d890bacfc8aa0b90aa6746e991cdf", + "prepared_review_unit_hash": "a170705dd49da2d94868b0d1a40cf84380c28e0848cbf1e1960162ab75289711", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10408, - "estimated_input_tokens": 2602, - "estimated_eval_tokens": 5460 + "serialized_chars": 10409, + "estimated_input_tokens": 2603, + "estimated_eval_tokens": 5462 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10408, - "estimated_input_tokens": 2602, - "estimated_eval_tokens": 5460 + "serialized_chars": 10409, + "estimated_input_tokens": 2603, + "estimated_eval_tokens": 5462 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Three pull requests add different model integrations (DeepSeek OCR, Isaac, Kimi2-6). They overlap in boilerplate registration/docs, but they do not fix the same underlying code-path problem, so they should not be merged as duplicates.", - "confidence": 0.96, + "summary": "These are three separate model-addition PRs (DeepSeek OCR, Isaac, Kimi2-6) that share boilerplate integration files but target different models and code paths. They are not duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45630 is the strongest representative of the cluster: it has the broadest integration footprint and the highest review activity, but it is still a distinct Kimi2-6 model addition rather than the same change as the others.", + "canonical_pr_reason": "PR #45630 is the most substantial/established of the three and the best representative of the cluster, but it is not a duplicate of the others because it implements Kimi2-6-specific model, processor, and auto-mapping support.", "best_issue_reason": null, - "best_pr_reason": "PR 45630 is the best single representative because it is the most developed and actively reviewed of the three, making it the most useful anchor if this cluster needs one canonical PR.", + "best_pr_reason": "PR #45630 is the strongest standalone PR in the set: it has the highest review activity and a broad, model-specific integration. Still, it should not be merged with the other two because each PR introduces a different model family.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Both are new model additions, but they target different models and different implementation stacks (DeepSeek OCR vs Isaac). Shared auto-registration/docs files are boilerplate and not evidence of the same fix." + "reason": "Both are model-addition PRs and overlap on generic Transformers integration files, but DeepSeek OCR and Isaac are different models with different architectures and documentation/tests; they are not the same underlying change." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "These are separate model integrations for Isaac and Kimi2-6. They overlap in model registry plumbing, but they do not address the same concrete bug or change and would not plausibly be merged into one PR." + "reason": "Isaac and Kimi2-6 are distinct new model implementations. The shared auto-registration/docs patterns are boilerplate, not evidence of a single fix or mergeable duplicate PR." } ] }, @@ -16907,7 +17296,7 @@ { "label": "pull_request", "component_index": 6, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16923,12 +17312,12 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "cdb9eaaf4d1c58320dcd8eb575f4b0c13ad8cb483009f504d858f3c7297b7a7c", + "prepared_review_unit_hash": "faede77314437db271c11fac60eab3b66c4fa5b38624ff1f8fe524a7de36017b", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5935, + "serialized_chars": 5934, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -16936,7 +17325,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5935, + "serialized_chars": 5934, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -16945,18 +17334,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs both update GitHub Actions, but they target different dependency families and change sets: one is a broad Node 24 compatibility sweep for workflow actions, while the other upgrades Docker/build-related actions to newer major versions. They overlap in a few workflow files, but they do not fix the same concrete problem.", - "confidence": 0.93, + "summary": "Both PRs are broad GitHub Actions dependency bumps, but they target different actions and different failure modes: one is for GitHub Actions runtime/node24 compatibility, the other is for docker/build-push-action version updates. They are related in theme but not the same underlying change.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the better cluster representative because it is the broader, explicitly scoped workflow-actions compatibility upgrade and touches many of the same CI workflows.", + "canonical_pr_reason": "PR 42975 is the broader and more representative workflow-maintenance change, updating multiple core GitHub Actions used across many workflows for Node 24 compatibility.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the best single representative of this cluster since it captures the general GitHub Actions upgrade theme more comprehensively than the narrower Docker-action bump in 42976.", + "best_pr_reason": "PR 42975 is the best single representative of the cluster because it spans more workflows and the change is a clearer platform-wide maintenance update than the narrower Docker action bump in 42976.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Do not merge: these are separate maintenance changes. 42975 upgrades multiple GitHub Actions for Node 24 compatibility, while 42976 primarily bumps docker/build-push-action and a few other actions to latest versions. Shared workflow filenames alone are not enough to treat them as the same underlying change." + "reason": "Reject: these are separate dependency upgrades affecting different actions and code paths. 42975 updates checkout/cache/upload-artifact for workflow runtime compatibility, while 42976 only bumps docker/build-push-action in container-image workflows; they could not plausibly be merged as one duplicate PR." } ] }, @@ -16970,7 +17359,7 @@ { "label": "pull_request", "component_index": 7, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16999,12 +17388,12 @@ "pull_request:44601|pull_request:45838", "pull_request:45490|pull_request:45838" ], - "prepared_review_unit_hash": "f23405e4678881cb0d7623cf445a7666a13ad9bd6356a79ca848daaa7b7ecaf2", + "prepared_review_unit_hash": "919fa37cb19082776953bd7f18e1e3ac6405962eec55d3e1bdf5b61281402bd9", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23541, + "serialized_chars": 23542, "estimated_input_tokens": 5886, "estimated_eval_tokens": 12028 }, @@ -17012,7 +17401,7 @@ "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23541, + "serialized_chars": 23542, "estimated_input_tokens": 5886, "estimated_eval_tokens": 12028 }, @@ -17021,66 +17410,66 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly a set of unrelated PRs that happen to share Transformers boilerplate (docs TOC, auto registries, model package wiring). They cover different model families and one separate distributed-loading feature, so the soft similarities are false positives rather than duplicates.", - "confidence": 0.97, + "summary": "This cluster is a set of unrelated pull requests: several distinct model-addition PRs, one distributed pipeline-parallel infrastructure PR, and one PP-OCRv6 text-recognition PR. They share superficial patterns like docs/toctree and auto-registry edits, but not the same concrete code-path or bug fix.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical PR: the cluster does not contain duplicate changes. The PRs target different models or a separate distributed loading feature, so they should remain separate.", "best_issue_reason": null, - "best_pr_reason": "PR 45838 is the largest self-contained model-support addition in the set, but it is not actually a duplicate of the others; the cluster does not have a true canonical PR.", + "best_pr_reason": "PR 43451 is the strongest standalone representative by scope and review activity, but it is still not a duplicate of the others; it is a distinct Molmo2 model addition with broad model/processor/test coverage.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "ViT NEPA vs Molmo are different model-addition PRs; overlap is only shared docs/auto wiring." + "reason": "Different model additions: ViT NEPA vs Molmo. Shared docs/auto-registry edits are incidental, not the same underlying change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "ViT NEPA vs Molmo2 are separate model implementations, not the same underlying change." + "reason": "Different model additions: ViT NEPA vs Molmo2. No shared concrete bug or code path." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA and CTSM are distinct model-support PRs with unrelated codepaths." + "reason": "Different model additions: ViT NEPA vs CTSM. Similar scaffolding only, not duplicate work." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related in name only; they add different model families and different support code." + "reason": "Molmo and Molmo2 are related by naming, but they are distinct model integrations with different files and coverage, not one mergeable fix." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM are unrelated model additions; shared registry/docs edits are boilerplate." + "reason": "Molmo vs CTSM are separate model additions with different implementations and targets." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are different models with different modeling/configuration changes." + "reason": "Molmo2 and CTSM are different model integrations; no evidence of the same bug or feature." }, { "left": "pull_request:43973", "right": "pull_request:45838", "accept": false, - "reason": "Lfm2 Audio and PP-OCRv6 text recognition are different modalities and different feature/model stacks." + "reason": "Lfm2 Audio support and PP-OCRv6 text recognition are unrelated model additions, despite both touching docs and auto mappings." }, { "left": "pull_request:44601", "right": "pull_request:45838", "accept": false, - "reason": "Pipeline-parallel loading support is a distributed-systems change, not the same bug/change as PP-OCRv6 model support." + "reason": "Pipeline-parallel loading infrastructure is unrelated to PP-OCRv6 model support; they fix different layers and cannot plausibly be merged as one PR." }, { "left": "pull_request:45490", "right": "pull_request:45838", "accept": false, - "reason": "CTSM and PP-OCRv6 are separate model additions; only generic docs/auto files overlap." + "reason": "CTSM model support and PP-OCRv6 text recognition are distinct model additions with different code paths and tests." } ] }, @@ -17094,7 +17483,7 @@ { "label": "pull_request", "component_index": 8, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17117,70 +17506,70 @@ "pull_request:43665|pull_request:45981", "pull_request:44815|pull_request:45981" ], - "prepared_review_unit_hash": "bf9a4f5f20e7a18001cb024aa147875a5af1f87dbd7f4889f1876000048ba476", + "prepared_review_unit_hash": "1a167d54829c67ead3fec374a62639f9a65109221ac405b4288b5814acbd5689", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 9635, - "estimated_input_tokens": 2409, - "estimated_eval_tokens": 5074 + "serialized_chars": 9639, + "estimated_input_tokens": 2410, + "estimated_eval_tokens": 5076 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 9635, - "estimated_input_tokens": 2409, - "estimated_eval_tokens": 5074 + "serialized_chars": 9639, + "estimated_input_tokens": 2410, + "estimated_eval_tokens": 5076 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All four PRs are only loosely similar at the title level; they do not appear to fix the same underlying bug or change. The only substantive code fix is the FP8 dequant/loading PR, while the others are unrelated test-only changes or Whisper tokenizer work.", - "confidence": 0.9, + "summary": "The cluster is not a duplicate set: it mixes unrelated PRs across Whisper tokenization, CLIP/ViT test edits, FP8 dequant/loading logic, and a ColQwen2 test fix. The only substantial code-path fix is the FP8 dequant PR; the others are test-only or model-specific changes with no shared underlying bug.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:44815 is the strongest representative because it contains the only concrete production code fix, centered on FP8 dequant/loading behavior, with related tests.", + "canonical_pr_reason": "PR 44815 is the strongest representative because it contains a real implementation fix in core loading / FP8 integration, while the other PRs are narrow test tweaks or different model areas.", "best_issue_reason": null, - "best_pr_reason": "pull_request:44815 is the best global representative of the cluster\u2019s substantive work; the other PRs are either unrelated model tests or Whisper-specific test/tokenization changes.", + "best_pr_reason": "PR 44815 is the best standalone PR in the set; it addresses a concrete runtime bug with actual code changes and is more substantive than the test-only PRs.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Different targets and symptoms: Whisper tokenizer decoding vs CLIP/ViT test edits. Same broad \"tests\" theme only." + "reason": "Both are test-oriented, but they target different model stacks and different issues: Whisper tokenizer decode behavior vs. CLIP/ViT test edits. No shared underlying bug or mergeable single fix." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Unrelated domains and code paths: Whisper decode logic vs FP8 dequant/loading internals." + "reason": "Whisper tokenization/test changes are unrelated to the FP8 dequant/core loading fix. Different subsystems and different code paths." }, { "left": "pull_request:43291", "right": "pull_request:45981", "accept": false, - "reason": "Whisper tokenizer changes are unrelated to a ColQwen2 test device fix." + "reason": "Whisper decode logic and ColQwen2 test-device placement are unrelated model-specific changes." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "43665 is test-only and spans CLIP/ViT; 44815 is a production FP8 fix. They do not address the same bug." + "reason": "PR 43665 is effectively test noise in CLIP/ViT, while PR 44815 fixes FP8 quantization/loading behavior. They do not fix the same concrete problem." }, { "left": "pull_request:43665", "right": "pull_request:45981", "accept": false, - "reason": "Both are test-related, but they touch different model test suites and different failure modes." + "reason": "These are separate test changes for different models (CLIP/ViT vs. ColQwen2), not the same bug or change." }, { "left": "pull_request:44815", "right": "pull_request:45981", "accept": false, - "reason": "FP8 loading/dequantization code changes are unrelated to a ColQwen2 test tensor-device adjustment." + "reason": "FP8 dequant/core-loading logic is unrelated to a ColQwen2 test tensor device fix; different code paths and different failure modes." } ] }, @@ -17194,7 +17583,7 @@ { "label": "pull_request", "component_index": 9, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17210,12 +17599,12 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "93b9476c93395f3daf0e7392de20c081bf47dc1e4ef2205b5b3fa34a5685e685", + "prepared_review_unit_hash": "c028e0b0e92be0ba3c9dbd914d97cc8daa7406f0910c9f5e2e26c59557ba26fb", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4562, + "serialized_chars": 4563, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17223,7 +17612,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4562, + "serialized_chars": 4563, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17232,18 +17621,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are not duplicates: #43488 is a small repo-bot/check-formatting style change around setup/versioning and a Vit test, while #43532 is a broader workflow/test-harness update affecting CI automation and several files. They do not look like the same underlying change.", - "confidence": 0.95, + "summary": "The two PRs are not duplicates: one is a synthetic repo-bot/check PR around setup/versioning and a Vit test, while the other is a workflow/infrastructure PR spanning GitHub Actions, testing utilities, and notifications. The shared Vit test filename appears incidental.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43532 is the more representative standalone change in this cluster because it touches the actual CI/test automation path and spans multiple related files, whereas #43488 is a narrow experimental/check PR.", + "canonical_pr_reason": "PR #43532 is the better canonical representative because it is a coherent, substantive change across workflow and test infrastructure, whereas #43488 looks like a small synthetic/bot-validation PR.", "best_issue_reason": null, - "best_pr_reason": "#43532 is the best PR candidate to represent the cluster because it is more substantive and coherent as a single code-path change; #43488 is too small and unrelated in scope to serve as the canonical representative.", + "best_pr_reason": "PR #43532 is the strongest stand-alone PR in the cluster: it has a broader, internally consistent diff and appears to target a real codebase change rather than a placeholder check.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Different underlying purposes and code paths: #43488 is about setup/versioning and a Vit test, while #43532 modifies CI workflow logic, testing utilities, and notification paths. Shared Vit test file is not enough to make them the same change." + "reason": "Different underlying changes: #43488 edits setup/versioning and a Vit test for a repo-bot check, while #43532 changes CI workflows plus testing/notification code. Shared test filename is not enough to indicate the same fix." } ] }, @@ -17257,7 +17646,7 @@ { "label": "pull_request", "component_index": 10, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17273,12 +17662,12 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "4b13690079e2dd099370f78c27d5bb8ab72845d88103288b6d99d6a23b458f2e", + "prepared_review_unit_hash": "3f7c96661bd42bb001690a584d06a538a127d50c5aa66fc74af77e85275c54a3", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6083, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17286,7 +17675,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6083, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17295,18 +17684,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate feature PRs with similar scaffolding but different pipeline targets: promptable concept segmentation vs promptable visual segmentation. Shared docs/registry plumbing is not enough to treat them as the same underlying change.", - "confidence": 0.96, + "summary": "These are related by theme but are not duplicates: they add two different promptable segmentation pipelines with different targets, code paths, and model/test coverage.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the two PRs implement different pipeline features and touch different model integrations, so neither is a duplicate of the other.", + "canonical_pr_reason": "No canonical PR for duplicate triage; 43612 and 43613 implement different features (concept segmentation vs visual segmentation) rather than the same change.", "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the broader, more established feature change, but it still represents a different pipeline than 43612 and should not be merged as a duplicate representative.", + "best_pr_reason": "If a representative PR is needed, 43613 is the broader one, but it still is not a substitute for 43612 because it covers a different pipeline and different underlying models.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Reject: these add different pipelines and model integrations (concept segmentation vs visual segmentation), so they are not the same concrete change and would not be merged into one PR." + "reason": "Reject: despite overlapping docs and shared plumbing, these are distinct feature PRs for different pipelines and different underlying code/model paths, so they could not plausibly be merged into one duplicate change." } ] }, @@ -17320,7 +17709,7 @@ { "label": "pull_request", "component_index": 11, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17336,12 +17725,12 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "dddd36c9880d5e7be004f176771629ef9ac40f1da379074e6fa717c9b37a0f16", + "prepared_review_unit_hash": "3c4c88639e1f40c8087035c24fdebabbae14b7758ca831ddf0898ef85c19eeae", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4291, + "serialized_chars": 4292, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -17349,7 +17738,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4291, + "serialized_chars": 4292, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -17358,18 +17747,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate `trainer.py` pull requests with similar extensibility themes but different code paths: one changes gradient-accumulation loss scaling, the other extracts signature-column logic for overrideability. They should not be treated as duplicates.", - "confidence": 0.95, + "summary": "Two distinct trainer.py PRs: one adds a hook for gradient-accumulation loss scaling, the other adds a hook for signature-column filtering. They share a file and theme, but not the same underlying bug or change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43651 is the more concrete functional change: it alters `training_step` behavior around gradient accumulation loss scaling and adds a dedicated property to control that logic. PR 43663 is a separate refactor/API hook for signature-column filtering.", + "canonical_pr_reason": "PR 43651 is the clearer representative of a concrete trainer behavior change, with a focused code-path update in training_step and a new hook for loss scaling.", "best_issue_reason": null, - "best_pr_reason": "PR 43651 is the best representative of the cluster because it targets a specific runtime behavior fix, while PR 43663 is an unrelated trainer extensibility change despite touching the same file.", + "best_pr_reason": "PR 43651 is the strongest standalone PR in the cluster because it addresses a specific training-time bug/behavior and is easier to reason about as a representative change.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Same file and broad trainer extensibility area, but different underlying changes: GA loss scaling vs. model signature/column filtering. They do not fix the same bug and would not plausibly merge into one PR." + "reason": "Both touch transformers/trainer.py, but they fix different trainer extension points: loss scaling during gradient accumulation vs. signature-column filtering for model inputs. They are not the same concrete bug or mergeable duplicate change." } ] }, @@ -17383,7 +17772,7 @@ { "label": "pull_request", "component_index": 12, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17401,12 +17790,12 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "71930c34305857e475f8b58f5d295e317c9c9027cf8b0a764d7ed78dfc8d96fd", + "prepared_review_unit_hash": "4dea8268748b64739dc6f6ba9f690dc4f4487426af8849ad38cd0bdf8543ce9f", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, + "serialized_chars": 5991, "estimated_input_tokens": 1498, "estimated_eval_tokens": 3252 }, @@ -17414,7 +17803,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, + "serialized_chars": 5991, "estimated_input_tokens": 1498, "estimated_eval_tokens": 3252 }, @@ -17423,30 +17812,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs cluster around the same CLI `serve.py` runtime `TypeAdapter` annotation NameError. PR 43842 is the cleanest, most targeted fix; the other two are broader or alternate implementations of the same underlying issue.", - "confidence": 0.79, + "summary": "These PRs cluster around the same CLI `serve.py` annotation/runtime `TypeAdapter` NameError. PR 43842 is the cleanest narrowly-scoped fix; 43656 is related but broader, and 43836 is more refactor-heavy.", + "confidence": 0.77, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43842 is the best canonical PR: it is narrowly scoped to the reported `TypeAdapter` NameError, has an explicit issue link, and makes the smallest localized change to `serve.py`.", + "canonical_pr_reason": "pull_request:43842 is the most focused fix for the concrete `TypeAdapter` NameError in `src/transformers/cli/serve.py`, with a minimal targeted change and an explicit issue link.", "best_issue_reason": null, - "best_pr_reason": "PR 43842 most directly fixes the concrete runtime failure with minimal surface area, making it the strongest representative of this bug cluster.", + "best_pr_reason": "pull_request:43842 best represents the underlying bug fix because it directly targets the runtime/import problem with the smallest, most specific patch.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": true, - "reason": "Both address the same `serve.py` runtime `TypeAdapter` NameError caused by evaluated annotations; they are alternate fixes for the same code-path problem." + "reason": "Both address the same `TypeAdapter` NameError in `serve.py`; the fixes are different implementations of the same annotation/runtime problem and could plausibly be merged into one PR." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Both are fixing the same `serve.py` annotation-evaluation NameError around `TypeAdapter`; despite different implementation style, they target the same underlying bug." + "reason": "Both target the same `serve.py` `TypeAdapter` NameError path. Although 43836 is broader, the core bug and fix area overlap enough that they look like alternate solutions to the same issue." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: all three PRs touch `src/transformers/cli/serve.py`, two explicitly target the same `TypeAdapter` NameError issue, and PR 43842 is the smallest localized fix with an explicit issue link. The pairwise soft-edge acceptances are conservative enough given the titles, file overlap, and shared TypeAdapter/annotation-evaluation context." + "feedback": "The summary stays within the packet: all three PRs touch `src/transformers/cli/serve.py` and are plausibly part of the same `TypeAdapter`/annotation runtime issue, with 43842 the narrowest fix. The soft-edge verdicts are conservative enough, especially since 43836 and 43842 share the same issue target and 43656 is framed as a plausible alternate implementation rather than a definitive duplicate." }, "evaluator_used": true, "retried": false, @@ -17457,7 +17846,7 @@ { "label": "pull_request", "component_index": 13, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17523,7 +17912,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 2, "status": "reviewed", @@ -17579,8 +17968,8 @@ "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:44068|pull_request:44116", "pull_request:44071|pull_request:44722", "pull_request:44018|pull_request:44116", "pull_request:44018|pull_request:44086", @@ -17589,8 +17978,8 @@ "pull_request:44068|pull_request:44086", "pull_request:44059|pull_request:44086", "pull_request:44085|pull_request:44086", - "pull_request:44098|pull_request:44101", "pull_request:44059|pull_request:44722", + "pull_request:44098|pull_request:44101", "pull_request:44018|pull_request:44071", "pull_request:44017|pull_request:44722", "pull_request:44017|pull_request:44161", @@ -17601,8 +17990,8 @@ "pull_request:44017|pull_request:44071", "pull_request:44073|pull_request:44101", "pull_request:44059|pull_request:44071", - "pull_request:44056|pull_request:44101", "pull_request:44073|pull_request:44161", + "pull_request:44056|pull_request:44101", "pull_request:44059|pull_request:44068", "pull_request:44018|pull_request:44059", "pull_request:44101|pull_request:44161", @@ -17610,8 +17999,8 @@ "pull_request:43997|pull_request:44056", "pull_request:44071|pull_request:44076", "pull_request:44074|pull_request:44101", - "pull_request:43997|pull_request:44018", "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44018", "pull_request:43997|pull_request:44161", "pull_request:44074|pull_request:44161", "pull_request:44018|pull_request:44161", @@ -17635,370 +18024,298 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "bd7d6a06897f5bf88e0cd97b9af0a031b28b5fdbf55607e20ed3f38fbad1a23a", + "prepared_review_unit_hash": "14d5da96df2e714c672a3a8ef74d6d47e009fc353ed67590fc185ffbe0003af4", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, - "estimated_input_tokens": 21224, - "estimated_eval_tokens": 42704 + "serialized_chars": 84892, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 }, "budget": { "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75095, - "estimated_input_tokens": 18774, - "estimated_eval_tokens": 37804 + "serialized_chars": 75087, + "estimated_input_tokens": 18772, + "estimated_eval_tokens": 37800 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a wave of standardized output-tracing refactors across many different model families. Most pairings are not duplicates because they touch different code paths/models; only the GPT-Neo and GPT-J/CodeGen variants clearly overlap as the same underlying refactor.", - "confidence": 0.86, - "canonical_issue_reason": "Issue #43979 is the shared tracking issue explicitly referenced by the output-tracing refactor PRs, so it is the natural canonical issue for the cluster.", - "canonical_pr_reason": "PR #44722 is the strongest representative of the duplicate GPT-J/CodeGen branch: it targets the same output-tracing refactor, shares the key files, and appears to be the most complete version of that concrete change.", - "best_issue_reason": "Issue #43979 best represents the cluster because it is the common umbrella for the standardized output-tracing work across models.", - "best_pr_reason": "PR #44722 is the best single PR representative because it covers the core GPT-J/CodeGen output-tracing change and most directly reflects the shared refactor direction in the cluster.", + "summary": "This cluster is mostly a broad theme cluster of model-specific output-tracing refactors, not one single duplicate. The only true duplicate-like groups are the GPT-J/CodeGen PRs and the GPT-Neo PRs; the rest touch different model implementations and should stay separate.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44722 is the clearest representative of the repeated GPT-J/CodeGen output-tracing refactor: it targets the same standardized-decorator change, touches the same core code paths, and is the most self-contained late-stage variant in the duplicate-like subgroup.", + "best_issue_reason": null, + "best_pr_reason": "44722 best represents the main duplicate-like subgroup because it directly refactors GPT-J output tracing with the standardized decorator approach and also includes the related CodeGen companion change.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model families (CVT/FNet vs GPT-J); shared tracking theme is too broad to be a duplicate." + "reason": "Different model families and different code paths; same issue target alone is not enough." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different model families and different concrete code paths; only the output-tracing theme overlaps." + "reason": "CVT/FNet refactor is unrelated to DeBERTa V2 beyond the shared output-tracing theme." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both are GPT-J output-tracing refactors on the same file and same issue; one is just a broader variant of the same underlying change." + "reason": "Both are GPT-J output-tracing refactors in the same file and implement the same concrete change." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet/ResNet-style refactors are separate concrete model implementations, not the same bug or change." + "reason": "ResNet/RT-DETR ResNet versus EfficientNet are different model implementations and not the same duplicate." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths despite sharing the standardized-tracing theme." + "reason": "EfficientNet output tracing is unrelated to GPT-J/CodeGen output tracing." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen vs EfficientNet is a broad architectural similarity, not the same underlying change." + "reason": "Different model code paths; only the high-level refactor theme is shared." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are unrelated implementations; this is only a thematic similarity." + "reason": "MobileNetV2 and DeBERTa V2 are unrelated concrete changes." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen and MGP-STR affect different model code paths and are not the same fix." + "reason": "GPT-J/CodeGen versus MGP-STR are different underlying implementations." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen and MPT are different model-specific refactors, not one duplicate change." + "reason": "GPT-J/CodeGen and MPT are separate model-specific refactors." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "These are two GPT-Neo output-tracing refactors on the same model/file set and same underlying change." + "reason": "Same GPT-Neo file and same standardized output-tracing change; one looks like a later/alternate version of the other." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are different model families; same refactor pattern is not enough." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44066", - "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are separate model implementations, so this is not a duplicate fix." + "reason": "GPT-J/CodeGen and GPT-Neo are different code paths." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet and GPT-J/CodeGen are different concrete model paths; only the refactor theme overlaps." + "reason": "ResNet refactor is not the same underlying change as GPT-J/CodeGen." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are unrelated model-specific changes." - }, - { - "left": "pull_request:44019", - "right": "pull_request:44085", - "accept": false, - "reason": "ResNet and GPT-J are different code paths; shared issue linkage is not enough." + "reason": "MGP-STR output tracing is a different model-specific change." }, { - "left": "pull_request:44018", - "right": "pull_request:44019", - "accept": false, - "reason": "GPT-Neo and ResNet are different model families and changes." - }, - { - "left": "pull_request:44019", - "right": "pull_request:44071", - "accept": false, - "reason": "ResNet and MPT are unrelated concrete implementations." - }, - { - "left": "pull_request:44068", - "right": "pull_request:44116", - "accept": false, - "reason": "GPT-Neo and Flaubert are different model-specific output-tracing refactors." - }, - { - "left": "pull_request:44068", - "right": "pull_request:44722", + "left": "pull_request:44019", + "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different code paths despite similar refactor language." + "reason": "ResNet and GPT-J are unrelated implementations." }, { - "left": "pull_request:44071", - "right": "pull_request:44722", + "left": "pull_request:44018", + "right": "pull_request:44019", "accept": false, - "reason": "MPT and GPT-J/CodeGen are unrelated model implementations." + "reason": "GPT-Neo and ResNet are different model paths." }, { - "left": "pull_request:44018", - "right": "pull_request:44116", + "left": "pull_request:44019", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and Flaubert are different models and separate changes." + "reason": "ResNet and MPT are unrelated concrete changes." }, { - "left": "pull_request:44018", - "right": "pull_request:44086", + "left": "pull_request:44068", + "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo and MGP-STR are different concrete implementations." + "reason": "GPT-Neo versus GPT-J/CodeGen are different model refactors." }, { - "left": "pull_request:44018", + "left": "pull_request:44071", "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo and GPT-J are different model families; not the same underlying bug." + "reason": "MPT and GPT-J are different code paths." }, { - "left": "pull_request:44071", + "left": "pull_request:44068", "right": "pull_request:44086", "accept": false, - "reason": "MPT and MGP-STR are unrelated code paths." + "reason": "GPT-Neo and MGP-STR are unrelated implementations." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT2 and MGP-STR are different model-specific refactors." + "reason": "GPT-2 refactor is not the same change as MGP-STR." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J and MGP-STR are unrelated concrete changes." + "reason": "GPT-J and MGP-STR are different model-specific changes." }, { - "left": "pull_request:44098", - "right": "pull_request:44101", + "left": "pull_request:44059", + "right": "pull_request:44722", "accept": false, - "reason": "ViLT and XLM/Flaubert are distinct model implementations; same theme only." + "reason": "GPT-2 output tracing is not the same concrete bug/change as GPT-J/CodeGen." }, { - "left": "pull_request:44059", - "right": "pull_request:44722", + "left": "pull_request:44098", + "right": "pull_request:44101", "accept": false, - "reason": "GPT2 and GPT-J/CodeGen are different code paths; theme overlap is too broad." + "reason": "ViLT and Flaubert/XLM are different model families and separate changes." }, { "left": "pull_request:44018", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are separate model-specific refactors." + "reason": "GPT-Neo and MPT are unrelated model implementations." }, { "left": "pull_request:44017", "right": "pull_request:44722", "accept": false, - "reason": "SegFormer and GPT-J/CodeGen are unrelated model implementations." + "reason": "SegFormer output tracing is a different code path from GPT-J/CodeGen." }, { "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "SegFormer and LongT5 are different models and different concrete changes." + "reason": "SegFormer and LongT5 are different model-specific refactors." }, { - "left": "pull_request:44073", - "right": "pull_request:44101", + "left": "pull_request:44017", + "right": "pull_request:44073", "accept": false, - "reason": "VisualBert and Flaubert are different model code paths." + "reason": "SegFormer and VisualBert are unrelated implementations." }, { - "left": "pull_request:44056", - "right": "pull_request:44161", + "left": "pull_request:44068", + "right": "pull_request:44071", "accept": false, - "reason": "MPNet and LongT5 are unrelated concrete refactors." + "reason": "GPT-Neo and MPT are different code paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44017", + "left": "pull_request:44071", + "right": "pull_request:44086", "accept": false, - "reason": "RegNet and SegFormer are different model families; only the output-tracing theme overlaps." + "reason": "MPT and MGP-STR are unrelated model changes." }, { "left": "pull_request:43997", - "right": "pull_request:44056", - "accept": false, - "reason": "RegNet and MPNet are different code paths, not the same bug or change." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44076", + "right": "pull_request:44073", "accept": false, - "reason": "MPT and ImageGPT are different model-specific changes." + "reason": "RegNet and VisualBert are different model implementations." }, { - "left": "pull_request:44074", + "left": "pull_request:44056", "right": "pull_request:44101", "accept": false, - "reason": "TextNet and Flaubert are unrelated implementations." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44059", - "accept": false, - "reason": "GPT-Neo and GPT2 are separate model families." - }, - { - "left": "pull_request:44017", - "right": "pull_request:44071", - "accept": false, - "reason": "SegFormer and MPT are different concrete changes." - }, - { - "left": "pull_request:44017", - "right": "pull_request:44074", - "accept": false, - "reason": "SegFormer and TextNet are unrelated model implementations." - }, - { - "left": "pull_request:44059", - "right": "pull_request:44068", - "accept": false, - "reason": "GPT2 and GPT-Neo are different model families and code paths." + "reason": "MPNet and Flaubert/XLM are unrelated concrete changes." }, { "left": "pull_request:44059", "right": "pull_request:44071", "accept": false, - "reason": "GPT2 and MPT are unrelated concrete changes." + "reason": "GPT-2 and MPT are different code paths." }, { - "left": "pull_request:44101", + "left": "pull_request:44073", "right": "pull_request:44161", "accept": false, - "reason": "Flaubert/XLM and LongT5 are different model implementations." + "reason": "VisualBert and LongT5 are different model-specific refactors." }, { - "left": "pull_request:43997", - "right": "pull_request:44074", + "left": "pull_request:44056", + "right": "pull_request:44161", "accept": false, - "reason": "RegNet and TextNet are unrelated model-specific refactors." + "reason": "MPNet and LongT5 are unrelated implementations." }, { "left": "pull_request:43997", "right": "pull_request:44018", "accept": false, - "reason": "RegNet and GPT-Neo are different code paths." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44044", - "accept": false, - "reason": "SqueezeBert and DeBERTa are different model families and refactors." + "reason": "RegNet and GPT-Neo are not the same underlying change." }, { - "left": "pull_request:44044", - "right": "pull_request:44074", + "left": "pull_request:43997", + "right": "pull_request:44161", "accept": false, - "reason": "DeBERTa and TextNet are unrelated concrete changes." + "reason": "RegNet and LongT5 are separate model-specific changes." }, { - "left": "pull_request:44018", + "left": "pull_request:44071", "right": "pull_request:44129", "accept": false, - "reason": "GPT-Neo and SpeechT5 are different model code paths." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44073", - "accept": false, - "reason": "SqueezeBert and VisualBert are different implementations." + "reason": "MPT and SpeechT5 are different code paths." }, { "left": "pull_request:44010", - "right": "pull_request:44018", + "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBert and GPT-Neo are different model families." + "reason": "SqueezeBERT and MPT are unrelated implementations." }, { - "left": "pull_request:43996", + "left": "pull_request:44018", "right": "pull_request:44161", "accept": false, - "reason": "CVT/FNet and LongT5 are unrelated concrete changes." + "reason": "GPT-Neo and LongT5 are different model-specific refactors." }, { - "left": "pull_request:43996", - "right": "pull_request:44017", + "left": "pull_request:44010", + "right": "pull_request:44044", "accept": false, - "reason": "CVT/FNet and SegFormer are different code paths." + "reason": "SqueezeBERT and DeBERTa V2 are different underlying changes." }, { - "left": "pull_request:44010", - "right": "pull_request:44161", + "left": "pull_request:44044", + "right": "pull_request:44074", "accept": false, - "reason": "SqueezeBert and LongT5 are unrelated model-specific changes." + "reason": "DeBERTa V2 and TextNet are unrelated model implementations." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa and SpeechT5 are different model implementations." + "reason": "DeBERTa V2 and SpeechT5 are different code paths." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa and ViTS are unrelated concrete refactors." + "reason": "DeBERTa V2 and Vits are separate model-specific changes." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet, and the duplicate/near-duplicate calls stay conservative. The selected canonical issue/PR are supported by shared issue linkage and overlapping GPT-J/CodeGen files, and the false edges are mostly justified by distinct model families or code paths." + "feedback": "The cluster summary is grounded in the packet and stays conservative about duplicate-like relationships. The two accepted soft pairs are plausible same-file/same-bugfix variants, and the rejected pairs are appropriately split by model family or code path rather than overstating similarity." }, "evaluator_used": true, "retried": false, @@ -18009,7 +18326,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 27, + "component_count": 30, "review_unit_index": 2, "review_unit_count": 2, "status": "reviewed", @@ -18036,70 +18353,70 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "57e47d7c258906794f23d431761dea9f72023560b4f726b2dd09d2dca4d80dfd", + "prepared_review_unit_hash": "16be0a6daa058864c1b77950a1d65475c700d1dd49b3392866d821a2ab020ffd", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, - "estimated_input_tokens": 21224, - "estimated_eval_tokens": 42704 + "serialized_chars": 84892, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17122, - "estimated_input_tokens": 4281, - "estimated_eval_tokens": 8818 + "serialized_chars": 17126, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are all model-specific PRs modernizing output tracing to use capture_outputs/can_return_tuple patterns. They share a theme, but each changes a different model implementation, so they are not duplicates of the same underlying fix/change.", - "confidence": 0.94, + "summary": "All items are model-specific PRs for standardized output tracing / capture_outputs refactors. They share a theme, but they target different architectures and code paths, so they are related changes rather than duplicates.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44129 is the best representative of the cluster because it has an explicit issue target and shows a concrete, self-contained output-tracing refactor for one model; the others are similar but are separate per-model variants.", + "canonical_pr_reason": "PR 44129 is the best representative PR in this set: it has an explicit issue target, a focused single-model refactor, and appears more complete than the smaller model migrations.", "best_issue_reason": null, - "best_pr_reason": "PR 44129 is the strongest standalone PR in the set: it is clearly scoped, tied to a target issue, and implements the standardized output-capture migration in a concrete code path.", + "best_pr_reason": "PR 44129 is the strongest standalone candidate for triage because it is concrete, scoped, and anchored to a tracked issue; the others are similar refactor patterns but not interchangeable with it.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Same refactor theme, but different models and code paths (FocalNet vs ImageGPT); not the same underlying change." + "reason": "Same refactor theme, but FocalNet and ImageGPT are different model implementations with different output paths; not the same underlying change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Both modernize output tracing, but they touch different model implementations (VisualBert vs TextNet) and are not mergeable as one PR." + "reason": "Both migrate to output-capture helpers, but they touch different models and code paths, so they should not be merged as one PR." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "Related output-capture refactors, but MPNet and VisualBert are separate code paths with distinct implementation details." + "reason": "MPNet vs VisualBert is a shared pattern only; the concrete fix sites and model behavior are different." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "Same broad standardization effort, but MPNet and TextNet are different model-specific changes." + "reason": "These are separate model-specific output-tracing refactors, not one duplicate bug or change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "Both are output-tracing migrations, but RegNet and SqueezeBert are unrelated model implementations and not the same fix." + "reason": "RegNet and SqueezeBert are unrelated model code paths; similar helper migration does not make them duplicates." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "Different architectures and files (SqueezeBert vs SpeechT5); they share a modernization pattern but not the same concrete bug/change." + "reason": "Both are standardized output refactors, but SqueezeBert and SpeechT5 address different concrete implementations and cannot plausibly be one merged PR." } ] }, @@ -18113,7 +18430,7 @@ { "label": "pull_request", "component_index": 15, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18179,12 +18496,12 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "e0fc149cba7cdefdaf54a1a3d2e515a6b8cb5e2a8bf1bbc1c7ac5233c6d053aa", + "prepared_review_unit_hash": "8000c24243315a35bc317867e4a705c633c1d2f61d49fe3406528b3b12a6e428", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40178, + "serialized_chars": 40179, "estimated_input_tokens": 10045, "estimated_eval_tokens": 20346 }, @@ -18192,7 +18509,7 @@ "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40178, + "serialized_chars": 40179, "estimated_input_tokens": 10045, "estimated_eval_tokens": 20346 }, @@ -18201,246 +18518,252 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are all variants of the same broad refactor theme ('output tracing'), but they target different model implementations and forward paths. I do not see any pair that looks like the same concrete bug/change, so none should be merged as duplicates.", - "confidence": 0.87, + "summary": "All items are distinct model-specific output-tracing refactor PRs. They share a common pattern, but none appear to fix the same concrete bug or change, so I would not merge any pair as duplicates.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44025 is the cleanest representative of the cluster: it applies the tracing decorator pattern to two closely related depth-anything model files and stays narrowly scoped.", + "canonical_pr_reason": "PR 44003 is the broadest representative of the cluster, touching two closely related Mamba variants and showing the shared output-tracing refactor pattern most clearly.", "best_issue_reason": null, - "best_pr_reason": "44025 is the best overall representative because it is self-contained, model-specific, and shows the core output-tracing refactor with minimal extra scope.", + "best_pr_reason": "PR 44003 is the best global representative because it spans multiple related code paths while still being a single coherent refactor.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and code paths (timm_backbone vs upernet); only the refactor pattern is shared." + "reason": "Different models and forward paths; same refactor theme, not the same fix." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different architectures and forward implementations; same tracing cleanup theme only." + "reason": "Timm backbone vs vision-text dual encoder are unrelated code paths." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Separate model code paths; not the same underlying bug/change." + "reason": "Timm backbone and UnivNet are separate model implementations with different behavior." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "timm_backbone and mamba/falcon_mamba are unrelated concrete code paths despite similar refactor wording." + "reason": "Different model families; both refactor output handling but not the same underlying change." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different model families; no evidence of one shared fix." + "reason": "Timm backbone and RWKV are unrelated model code paths." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are unrelated implementations; the similarity is only at the refactor level." + "reason": "MobileNetV1 and UnivNet are distinct architectures; not a duplicate fix." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different model code paths and behavior; not the same change." + "reason": "MobileNetV1 vs UperNet; similar refactor pattern only." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "MobileNetV1 vs DepthAnything are distinct models; same output-tracing pattern is too broad to duplicate." + "reason": "Different models and different output-tracing surfaces; not the same PR-level change." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different encoder-decoder targets and code paths; only the wrapper refactor theme matches." + "reason": "MobileNetV1 and VisionEncoderDecoder have separate forward implementations." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "MobileNetV1 and SpeechEncoderDecoder are separate model implementations with no shared concrete bug." + "reason": "MobileNetV1 and SpeechEncoderDecoder are unrelated code paths." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Vision-text dual encoder and UnivNet are unrelated code paths; shared wording is not enough." + "reason": "Vision-text dual encoder and UnivNet fix different model outputs." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and distinct forward logic." + "reason": "Different models and different forward logic; not mergeable as one fix." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "The PRs touch different architectures and fix different model-specific tracing paths." + "reason": "Separate model families with no shared concrete bug." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different models and output pathways; not the same bug/change." + "reason": "Different model architectures; same refactor style but not the same code-path problem." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet are unrelated; only the refactor pattern is common." + "reason": "UnivNet and UperNet are unrelated implementations." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different model families and implementation details; not mergeable as one fix." + "reason": "UnivNet vs Mamba family; no shared concrete fix." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Different architectures; same tracing cleanup pattern is too generic." + "reason": "Different model code paths; only the output-tracing pattern overlaps." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet and RWKV are separate code paths with no concrete shared bug." + "reason": "UperNet and RWKV are unrelated model paths." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Different model subsystems and different forward behavior." + "reason": "Different subsystems and forward contracts; not duplicates." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Falcon/Mamba vs SuperPoint are unrelated model paths; no same underlying change." + "reason": "Mamba-family refactor vs SuperPoint feature extractor; distinct code paths." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Mamba-family refactor and CodeGen refactor are different concrete code paths." + "reason": "Mamba-family tracing changes and CodeGen cache/output changes are separate fixes." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "TimmBackbone and CodeGen are unrelated implementations; same broad refactor theme only." + "reason": "Timm backbone and CodeGen address different model internals." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "UnivNet and CodeGen touch different model logic and cannot be treated as one duplicate fix." + "reason": "UnivNet audio generation and CodeGen attention/cache code are unrelated." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "UperNet and CodeGen are unrelated model paths." + "reason": "UperNet segmentation and CodeGen are distinct code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Vision-text dual encoder and CodeGen do not share the same concrete bug." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "DepthAnything and VisionEncoderDecoder are different model wrappers; same decorator pattern is not enough." + "reason": "Depth-Anything and VisionEncoderDecoder are separate model implementations." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "DepthAnything and SpeechEncoderDecoder are distinct code paths and model families." + "reason": "Depth-Anything and SpeechEncoderDecoder are different code paths." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "DepthAnything vs SuperPoint: different architectures and different output handling details." + "reason": "Depth-Anything and SuperPoint are unrelated models." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "DepthAnything and RWKV are unrelated concrete changes." + "reason": "Depth-Anything and RWKV fix different output-tracing surfaces." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "DepthAnything and DPR are separate model implementations; no shared underlying bug." + "reason": "Depth-Anything and DPR are separate architectures and forward methods." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "VisionEncoderDecoder and RWKV are unrelated code paths." + "reason": "VisionEncoderDecoder and RWKV are unrelated model code paths." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are different wrapper implementations, not the same bug." + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are similar wrappers but still different concrete implementations." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "Different model families and forward paths; shared refactor style only." + "reason": "Different model families; no single underlying bug." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "VisionEncoderDecoder and DPR are unrelated concrete changes." + "reason": "VisionEncoderDecoder and DPR change different code paths." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "SpeechEncoderDecoder and SuperPoint are distinct model code paths." + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and output semantics; not the same fix." + "reason": "SpeechEncoderDecoder and RWKV are distinct model implementations." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "SpeechEncoderDecoder and DPR are unrelated implementations." + "reason": "SpeechEncoderDecoder and DPR do not share the same concrete change." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated model paths." + "reason": "SuperPoint and RWKV are unrelated code paths." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "SuperPoint and DPR do not share a concrete bug/change." + "reason": "SuperPoint and DPR are different model internals." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR are unrelated model implementations; same broad refactor wording is insufficient." + "reason": "RWKV and DPR are separate implementations; same pattern only." } ] }, @@ -18454,7 +18777,7 @@ { "label": "pull_request", "component_index": 16, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18473,52 +18796,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "4b9104eea730c11d022d34a781a6ceafe7f5a03da7af449298ede5be27a17716", + "prepared_review_unit_hash": "62ac0d9f71d85c36648ed78c2279275a6ae09f6d2f7afbd8c9942fa72a7d4023", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10911, - "estimated_input_tokens": 2728, - "estimated_eval_tokens": 5712 + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10911, - "estimated_input_tokens": 2728, - "estimated_eval_tokens": 5712 + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three unrelated model-addition PRs (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share only generic Transformers plumbing and docs registration, not the same underlying bug or change.", + "summary": "These are three separate model-addition PRs for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share Transformers boilerplate and auto-registration changes, but they do not appear to fix or implement the same concrete code path, so they should not be clustered as duplicates.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical PR for deduping here; the cluster is mixed. If one must be singled out, DeepSeek-OCR-2 is the most complete standalone implementation and not draft.", + "canonical_pr_reason": "PR 45075 is the best representative if one is needed: it is non-draft, has the most review activity, and looks like a full model integration with conversion, image processing, modeling, and tests.", "best_issue_reason": null, - "best_pr_reason": "DeepSeek-OCR-2 is the strongest overall candidate: non-draft, substantial model + conversion + test coverage, and appears more merge-ready than the draft Voxtral TTS PR.", + "best_pr_reason": "PR 45075 is the strongest standalone candidate because it is the most mature and complete of the three integrations, with broader implementation coverage than the others.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different models and different additions (PenguinVL vs Voxtral TTS). Shared auto/docs files are generic scaffolding, not the same code-path fix." + "reason": "Different models and different code paths: PenguinVL vs Voxtral TTS. Shared docs/auto-registry boilerplate is not enough to treat them as the same change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different model implementations (PenguinVL vs DeepSeek-OCR-2) with separate architecture, processing, and test code; only common Transformers registration plumbing overlaps." + "reason": "Different model integrations (PenguinVL vs DeepSeek-OCR-2). They both add new model packages, but not the same underlying bug or feature." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "Different model families and unrelated functionality (DeepSeek-OCR-2 vs Voxtral TTS). Similar filenames are broad integration points, not evidence of one mergeable change." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are unrelated model additions; overlap is limited to common Transformers scaffolding, so they should not be merged as duplicates." } ] }, @@ -18532,7 +18855,7 @@ { "label": "pull_request", "component_index": 17, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18548,7 +18871,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "353f85c8de0b7494a87319632d23f91a56181bd3fd07362d0755208ebfc4018f", + "prepared_review_unit_hash": "806642044db55b74098c46cfb840b289997e85cbe0386b797d5bed42638818ff", "component_budget": { "node_count": 2, "item_count": 2, @@ -18570,18 +18893,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related around fusion, but they target different mechanisms: one introduces a generic Module Fusion API, while the other implements n-to-1 kernel fusion through KernelConfig and integration changes. They are not the same underlying change and should not be merged as duplicates.", - "confidence": 0.93, + "summary": "These PRs are related to fusion infrastructure, but they change different layers and are not the same mergeable fix/change: #44979 introduces a new module fusion API, while #45363 wires kernel-config-based n-to-1 fusion into model loading and adds an example. Related theme, not a duplicate.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "#44979 is the more foundational PR: it defines the standalone Module Fusion API and test coverage, whereas #45363 is a later, narrower integration built on a different concept (KernelConfig-based kernel fusion).", "best_issue_reason": null, - "best_pr_reason": "PR 45363 is the more concrete end-user feature: it wires kernel fusion into model loading/integration and includes an example. PR 44979 is a separate API layer for module chaining/fusion, so 45363 is the better representative if one PR must be selected.", + "best_pr_reason": "#44979 is the best representative of the cluster because it is the core API change; #45363 is an application/integration of fusion ideas rather than the same concrete code-path change.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Both involve fusion, but they address different code paths and abstractions. 44979 adds a generic module-fusion API in a new module, while 45363 adds KernelConfig-driven kernel fusion and integration hooks. They could coexist, but they are not the same bug/change." + "reason": "Different concrete changes: #44979 adds a new module fusion framework in src/transformers/module_fusion.py, while #45363 adds KernelConfig-driven n-to-1 fusion plumbing across model loading/integrations. Same broad area, but not the same underlying bug or one PR that could simply absorb the other." } ] }, @@ -18595,7 +18918,7 @@ { "label": "pull_request", "component_index": 18, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18611,7 +18934,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "2bb7317ae619e4e6dbe73d4f9ebccf463c69e4a2add67e84e2a1117d56b78e00", + "prepared_review_unit_hash": "781c5b225f05a4980757f27344cb412f689767fe155734770ee5ee17be6d3494", "component_budget": { "node_count": 2, "item_count": 2, @@ -18633,18 +18956,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same Mistral regex patch bug in the same file; 45317 is the stronger candidate because it includes the same fix plus tests and a clearer scope.", - "confidence": 0.97, + "summary": "Both pull requests appear to fix the same concrete Mistral regex AttributeError in the same code path (`_patch_mistral_regex`) with essentially the same change; the later PR also adds a test, so this looks like a duplicate PR cluster.", + "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the best canonical PR: it fixes the same AttributeError as 45086, has the same code change, and adds test coverage for the behavior.", + "canonical_pr_reason": "`pull_request:45317` is the stronger canonical PR because it implements the same fix as 45086 and also includes a test update, making it the more complete representative of the shared change.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the best overall PR because it is the same fix as 45086 but more complete, with accompanying tests and clearer intent.", + "best_pr_reason": "`pull_request:45317` is the best representative overall since it addresses the same bug and adds accompanying test coverage, whereas 45086 is the narrower earlier version.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying AttributeError fix in _patch_mistral_regex on the same code path; 45317 is effectively the more complete version of 45086 and they could plausibly be merged as one PR." + "reason": "Same issue target, same file, and the diff shows the same AttributeError fix in `_patch_mistral_regex`; the second PR is essentially the same patch with added tests." } ] }, @@ -18658,7 +18981,7 @@ { "label": "pull_request", "component_index": 19, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18674,7 +18997,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "0fc5e678f311b76f1b7f3e3403137bd96f580f7492baaa76dc099ada7873cecb", + "prepared_review_unit_hash": "fd0ce53f19a9e54fe304d43cfeb0103cc64be2310004f82affd40f8c43ee1199", "component_budget": { "node_count": 2, "item_count": 2, @@ -18696,18 +19019,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs touch NemotronH internals, but they are different changes: #45115 is a refactor/conversion-mapping inheritance cleanup, while #45569 is a broader model split into NemotronHDense/NemotronHSparse with docs and tests. They are related but not the same underlying change.", - "confidence": 0.91, + "summary": "These PRs overlap on NemotronH model files, but they address different changes: one refactors NemotronH to inherit GraniteMoeHybrid and updates conversion mapping, while the other splits NemotronH into dense/sparse variants with a backward-compat dispatcher plus docs/tests. They are related, but not the same concrete fix.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45569 is the broader, more representative NemotronH change: it introduces the dense/sparse model split, updates auto-mapping/docs, and includes tests. It better captures the main architectural change in this cluster.", + "canonical_pr_reason": "PR #45569 is the more comprehensive and user-facing NemotronH change, introducing the dense/sparse model split and compatibility wrapper rather than only a conversion/refactor layer.", "best_issue_reason": null, - "best_pr_reason": "PR #45569 is the best single representative because it is the more complete and user-visible NemotronH update, whereas #45115 is a narrower refactor focused on conversion mapping and inheritance details.", + "best_pr_reason": "PR #45569 best represents the cluster because it covers the larger architectural change and the broader set of affected files, including docs and tests.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "They share NemotronH files, but the concrete changes differ: #45115 refactors inheritance/conversion mappings, while #45569 splits NemotronH into dense/sparse variants with docs and tests. Not the same code-path fix and not plausibly one merged PR." + "reason": "Both touch NemotronH internals, but #45115 is a narrow GraniteMoeHybrid inheritance/conversion-mapping refactor, while #45569 restructures NemotronH into dense/sparse models and updates docs/tests. They are not the same underlying change and would not plausibly merge as one PR." } ] }, @@ -18721,7 +19044,7 @@ { "label": "pull_request", "component_index": 20, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18737,7 +19060,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "5069797d27ef4cf3ab18fdd602a819f9ce97aeda6762560bc7483f40b572ed1b", + "prepared_review_unit_hash": "2cd1977abba5636b5a1b7db895000412206fa9ab82db242a6375172f6ef33193", "component_budget": { "node_count": 2, "item_count": 2, @@ -18759,18 +19082,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs for heterogeneous model support: one broad end-to-end implementation and one smaller config-only foundation. They are related, but not the same concrete change.", - "confidence": 0.91, + "summary": "Two related but distinct PRs: one adds per-layer heterogeneous config support, the other adds broader heterogeneous model/runtime support. They overlap in shared config plumbing and tests, but they are not the same concrete change.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes heterogeneous config handling plus model/cache/masking and GPT-OSS integration, so it best represents the overall feature effort.", + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes heterogeneous config handling plus model/cache/masking support and therefore best represents the cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the best representative PR because it covers the full heterogeneous-model support stack and subsumes the narrower config-only work in #45333.", + "best_pr_reason": "PR #45332 is the best single representative because it covers the full heterogeneous-model feature set, not just the config foundation.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Related feature slices, but not the same concrete change. #45333 is config-only per-layer configuration support, while #45332 extends into modeling/cache/masking and model integration; they could ship independently and are not safe to treat as duplicates." + "reason": "Related feature work, but not the same underlying bug or change: #45333 is config-only plumbing, while #45332 extends into model/runtime behavior. They could be separate PRs rather than one merged fix." } ] }, @@ -18784,7 +19107,7 @@ { "label": "pull_request", "component_index": 21, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18800,7 +19123,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "44f2fb48ed7693da5d93ccff5fc9274216dc7986da13657706bfbe31082d895f", + "prepared_review_unit_hash": "1b7a2c25de84c595dc7441ccef7b4bf54540635d967322c823f3620d2b1a5393", "component_budget": { "node_count": 2, "item_count": 2, @@ -18822,18 +19145,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related typing-focused PRs, but they are not duplicates: #45415 is a broad repo-wide type-checking cleanup and config change, while #45425 adds specific typing protocols/aliases and updates a few concrete call sites. They could be merged independently.", - "confidence": 0.89, + "summary": "These two PRs both touch typing-related files, but they are not the same underlying change: #45415 is a broad repository-wide type-checking sweep and config tweak, while #45425 adds specific typing helper protocols/aliases for model utility code. The overlap is incidental, not a duplicate fix.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "#45425 is the more focused and concrete change: it adds missing typing abstractions and updates the affected implementation sites, rather than making a broad type-checking sweep.", + "canonical_pr_reason": "#45425 is the more focused substantive typing-infrastructure change; #45415 is a broad type-checking cleanup pass with many unrelated file edits.", "best_issue_reason": null, - "best_pr_reason": "#45425 is the better representative PR for this cluster because it targets a specific typing gap and is less sprawling than the large type-checking enablement in #45415.", + "best_pr_reason": "#45425 is the best representative PR for the cluster because it introduces concrete typing abstractions used by multiple code paths, whereas #45415 is primarily a sweeping type-check enablement/change-set.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Shared typing-related files are incidental; #45415 is a broad type-checking/config cleanup, while #45425 introduces specific typing protocols and aliases for modeling_utils/peft-related code. They do not look like the same underlying change and should not be merged as duplicates." + "reason": "Reject: #45415 is a broad type-checking sweep/configuration update, while #45425 adds specific typing protocols and aliases. Shared files do not indicate the same bug or a single mergeable fix." } ] }, @@ -18847,7 +19170,7 @@ { "label": "pull_request", "component_index": 22, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18872,7 +19195,7 @@ "pull_request:45858|pull_request:45926", "pull_request:45890|pull_request:45926" ], - "prepared_review_unit_hash": "df0d4c7d66cd44a67337ae5153d24069ca9e38a7a7ea64bac87e0b938c7e8512", + "prepared_review_unit_hash": "893f6287bc80aa435359d4f4c5b86a9a30e2a75dd9f845c205ef7ba91a422c1e", "component_budget": { "node_count": 6, "item_count": 6, @@ -18894,48 +19217,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "No true duplicates here: the cluster only shares a broad theme of model-parallel or XPU-related changes, but the PRs target different models and different code paths. The most representative runtime fix is the AltCLIP/ChineseCLIP device-placement PR.", - "confidence": 0.94, + "summary": "These PRs are related only at a very broad theme level (model-parallel/XPU support), but they target different models and mostly different code paths. None of the soft edges look like true duplicates.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45487 is the clearest substantive bug fix in model code, addressing device placement for token_type_ids in AltCLIP/ChineseCLIP rather than only adjusting tests or touching unrelated model internals.", + "canonical_pr_reason": "PR 45817 is the strongest representative: it makes concrete code-path fixes for Gemma4 model-parallel behavior (device placement plus split-module handling) and includes tests, unlike the test-only expectation updates.", "best_issue_reason": null, - "best_pr_reason": "PR 45487 is the best representative of the cluster because it fixes an actual model-parallel runtime issue and includes focused tests; the other PRs are either different models, unrelated refactors, or test-only XPU expectation updates.", + "best_pr_reason": "PR 45817 is the best standalone candidate because it addresses an actual runtime model-parallel bug in the implementation, not just platform-specific test expectations.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:45843", "accept": false, - "reason": "Different model families and different fixes; shared 'model parallel' theme is too broad to treat as the same change." + "reason": "Both are model-parallel fixes, but for different model families and different code paths. They are not the same underlying bug and would not plausibly be merged into one PR." }, { "left": "pull_request:45487", "right": "pull_request:45926", "accept": false, - "reason": "AltCLIP/ChineseCLIP runtime device-placement fix vs HyperCLOVAX XPU test expectations; not the same underlying bug." + "reason": "AltCLIP/ChineseCLIP model-parallel device handling is unrelated to HyperCLOVAX XPU test expectations." }, { "left": "pull_request:45817", "right": "pull_request:45843", "accept": false, - "reason": "Gemma4 model-parallel helper/device-placement fix is unrelated to the DeIMv2 changes shown here." + "reason": "Gemma4 and Deimv2 are separate model-specific fixes; the shared theme is too broad to treat as a duplicate." }, { "left": "pull_request:45858", "right": "pull_request:45890", "accept": false, - "reason": "Both are test-only XPU expectation updates, but they target different models and different logits, so they are not the same change." + "reason": "Both add XPU expectations, but for different models and tests. Same pattern, not the same bug or change." }, { "left": "pull_request:45858", "right": "pull_request:45926", "accept": false, - "reason": "Same broad XPU-testing motif, but different model/test files and different expected outputs; not a duplicate bug fix." + "reason": "These are model-specific test expectation updates for different architectures, with no shared concrete code-path issue." }, { "left": "pull_request:45890", "right": "pull_request:45926", "accept": false, - "reason": "These are separate model-specific test expectation updates, not one shared code-path change." + "reason": "Different model test suites and different expectation values; not a duplicate change." } ] }, @@ -18949,7 +19272,7 @@ { "label": "pull_request", "component_index": 23, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18965,7 +19288,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "a421a3ba3b9725aabbe735eb169bbcfdb1084c88ff77b9b8b7b43c514da36698", + "prepared_review_unit_hash": "3537647a7127d65aa27f750de3ecf30a027180c35d5a3ecf43406e3296389432", "component_budget": { "node_count": 2, "item_count": 2, @@ -18987,18 +19310,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are EP-related loading fixes, but they address different failure modes: one serializes distributed_config and adds has_ep for accelerate+ZeRO-3 loading, while the other fixes expert parameter handling so rank-0 broadcast does not overwrite weights under FSDP2.", - "confidence": 0.93, + "summary": "These two PRs both concern expert parallelism loading, but they fix different failure modes on different code paths: one strips/recognizes distributed config for EP + ZeRO-3 loading, while the other prevents expert tensors from being overwritten during FSDP2/rank-0 broadcast handling.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45662 is the better canonical representative: it targets a specific runtime corruption bug in distributed loading and spans the concrete loading/MoE code path.", + "canonical_pr_reason": "No exact duplicate here; if forced to pick one representative, PR #45662 is the stronger canonical PR because it targets a concrete overwrite bug in the loading path and includes the broader set of code-path fixes.", "best_issue_reason": null, - "best_pr_reason": "PR 45662 is the strongest standalone fix in the cluster because it addresses a concrete expert-weight overwrite bug with a clear code-path change.", + "best_pr_reason": "PR #45662 is the best standalone PR because it addresses a specific, actionable loading corruption issue with clear runtime impact, whereas PR #45548 is narrower and solves a different EP/ZeRO-3 serialization/loading problem.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Not the same underlying bug. 45548 is about serializing distributed_config and detecting EP for loading via accelerate launch; 45662 is about expert parameters being overwritten by rank-0 broadcast during FSDP2 loading. Shared EP context only." + "reason": "They share expert-parallel/loading context, but the bugs and fixes differ: #45548 removes distributed_config from serialization and adds has_ep for EP + DeepSpeed ZeRO-3 loading, while #45662 changes post-shard wrapping to prevent expert parameters being overwritten under FSDP2/rank-0 broadcast. Not the same underlying bug or mergeable into one PR." } ] }, @@ -19012,7 +19335,7 @@ { "label": "pull_request", "component_index": 24, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19028,12 +19351,12 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "b0784b4571d29a4173e94337cb1dd5e5f6ad14e8110ed976f8ae7ee4f81d5c7a", + "prepared_review_unit_hash": "6e2bc6fe3a4f855d1614633ba1831711dbcf5532ec936c6ef80b03ea49319843", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4590, + "serialized_chars": 4589, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19041,7 +19364,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4590, + "serialized_chars": 4589, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19050,18 +19373,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same xdist/captured_info logging collision path in `testing_utils.py`; PR 45645 is the broader superset because it includes the worker-safe log file fix plus CI workflow changes to read multiple log files.", - "confidence": 0.91, + "summary": "Both PRs target the same xdist-safe captured_info logging problem under issue #45561; PR 45645 is the broader, more complete fix and subsumes the testing_utils changes from 45639.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the better canonical PR because it covers the same core xdist-safe captured_info fix as 45639 and also updates CI to preserve and aggregate the per-worker logs.", + "canonical_pr_reason": "PR 45645 is the best canonical PR because it includes the core xdist-safe file handling change plus the CI/workflow updates needed to aggregate multiple captured_info files, making it the more complete fix.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the strongest representative: it addresses the underlying artifact collision and the downstream log-collection path, making it the more complete fix.", + "best_pr_reason": "PR 45645 is the strongest representative because it addresses the same underlying collision bug and also preserves/debugs CI log collection across xdist workers, whereas 45639 only fixes the library-side write path.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same underlying bug in captured_info handling under xdist; 45645 subsumes 45639's file-path fix and adds the necessary CI-side log aggregation." + "reason": "Both PRs fix the same concrete captured_info xdist collision in testing_utils; 45645 is effectively an expanded version of the 45639 fix with additional workflow handling, so they are close enough to treat as the same change cluster." } ] }, @@ -19075,7 +19398,7 @@ { "label": "pull_request", "component_index": 25, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19138,7 +19461,7 @@ { "label": "pull_request", "component_index": 26, - "component_count": 27, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19204,7 +19527,73 @@ { "label": "pull_request", "component_index": 27, - "component_count": 27, + "component_count": 30, + "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-45863-2", + "nodes": [ + "pull_request:45863", + "pull_request:45986" + ], + "soft_pairs": [ + "pull_request:45863|pull_request:45986" + ], + "prepared_review_unit_hash": "7f3114ee77134795638a4283bd1af3474d358fde534abcd721fee18249cf0286", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3691, + "estimated_input_tokens": 923, + "estimated_eval_tokens": 2102 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3691, + "estimated_input_tokens": 923, + "estimated_eval_tokens": 2102 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests address the same MLX availability bug: Transformers should opt out of MLX detection when HF_USE_MLX is disabled. PR 45863 is the broader, more complete fix with docs and tests; PR 45986 is a narrower code-only variant of the same change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45863 is the better canonical representative because it implements the HF_USE_MLX opt-out and also includes documentation and test coverage, making it the more complete version of the fix.", + "best_issue_reason": null, + "best_pr_reason": "PR 45863 is the strongest overall fit for the cluster since it directly fixes the MLX detection path and provides the supporting docs/tests; PR 45986 is a partial duplicate of the same code-path change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45863", + "right": "pull_request:45986", + "accept": true, + "reason": "Both PRs fix the same concrete bug in is_mlx_available() and would plausibly be merged into one change; the second PR is a narrower variant of the same HF_USE_MLX opt-out." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet: both PRs target the same issue target and the same MLX availability code path, and the mergeability claim is conservative. The canonical pick for 45863 is also supported by the extra docs/tests it adds. " + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 28, + "component_count": 30, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19220,7 +19609,7 @@ "soft_pairs": [ "pull_request:45975|pull_request:45977" ], - "prepared_review_unit_hash": "a297f103ea738b6621d35cb6d1f962b1f7470446b084500015ff8c3368701183", + "prepared_review_unit_hash": "285d91188b4c345e9c7509db18eae662e9a523993e0d97f20fc759b3826cae18", "component_budget": { "node_count": 2, "item_count": 2, @@ -19242,18 +19631,144 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch GGUF/Apple Silicon/kernels-community, but they implement different pieces: one is an optional dequant fast-path/configuration update, the other is a new GGUF linear inference path with integration code and tests.", - "confidence": 0.94, + "summary": "Both PRs target GGUF on Apple Silicon, but they address different layers of the stack: PR 45975 adds CLI/model-manager support and an optional kernels-community dequant fast path, while PR 45977 introduces a new GgufLinear integration with model plumbing and tests. Related subsystem, but not the same underlying change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45977 is the stronger cluster representative: it introduces the core GGUF runtime change, adds integration points, and includes tests, whereas 45975 is a smaller optional fast-path/help/configuration update.", + "canonical_pr_reason": "PR 45977 is the more substantial, self-contained feature PR: it adds a new GGUF linear integration and supporting model/quantizer/test plumbing, whereas PR 45975 is mainly an optional fast-path toggle and CLI/help wiring.", "best_issue_reason": null, - "best_pr_reason": "PR 45977 is the best standalone candidate for triage because it addresses a concrete code-path change (GGUF matmul on Apple Silicon) with implementation and test coverage.", + "best_pr_reason": "PR 45977 is the strongest representative of the cluster because it makes the core implementation change and has the broadest functional surface area; PR 45975 looks like a narrower companion optimization rather than a duplicate fix.", "soft_edge_verdicts": [ { "left": "pull_request:45975", "right": "pull_request:45977", "accept": false, - "reason": "Related domain, but not the same underlying change: 45975 updates CLI/help and GGUF-related fast-path plumbing, while 45977 adds a new GgufLinear inference implementation and tests. They would not plausibly be merged into one PR as duplicate fixes." + "reason": "They both involve GGUF/Metal on Apple Silicon, but 45975 is about an optional kernels-community dequant fast path and CLI/model-manager wiring, while 45977 adds a new GgufLinear inference path. Different concrete changes, not mergeable as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 29, + "component_count": 30, + "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-45976-2", + "nodes": [ + "pull_request:45976", + "pull_request:45989" + ], + "soft_pairs": [ + "pull_request:45976|pull_request:45989" + ], + "prepared_review_unit_hash": "055ab1d620a97c8693b657a9612c592ed664686d7e55eb1aff45ceffad3fd0be", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4493, + "estimated_input_tokens": 1124, + "estimated_eval_tokens": 2504 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4493, + "estimated_input_tokens": 1124, + "estimated_eval_tokens": 2504 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related Llama4 MoE changes, but they address different layers of the stack: one fixes tensor-parallel expert calling/aggregation behavior, the other switches Llama4 experts to the standard expert implementation interface. They do not look like the same mergeable bugfix/change.", + "confidence": 0.79, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45976 is the broader, more concrete fix: it patches the tensor-parallel expert path, adds Llama4-specific model/config/test coverage, and directly addresses the crash described in the title.", + "best_issue_reason": null, + "best_pr_reason": "PR 45976 is the strongest representative of the cluster because it fixes the actual crash path and includes validation; PR 45989 is narrower and looks like an interface-adoption refactor that may complement, but not duplicate, the crash fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45976", + "right": "pull_request:45989", + "accept": false, + "reason": "They touch the same Llama4 expert subsystem, but 45976 fixes a tensor-parallel crash for pre-weighted MoE experts while 45989 adopts the standard expert implementation decorator. Different code paths, different concrete problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 30, + "component_count": 30, + "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-45991-2", + "nodes": [ + "pull_request:45991", + "pull_request:45993" + ], + "soft_pairs": [ + "pull_request:45991|pull_request:45993" + ], + "prepared_review_unit_hash": "db9dd3522f36bd4d9a61568669869bd83deb3e403c87e2e5c51163798f4bcb31", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4234, + "estimated_input_tokens": 1059, + "estimated_eval_tokens": 2374 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4234, + "estimated_input_tokens": 1059, + "estimated_eval_tokens": 2374 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are not duplicates: one enables Flash Attention 2 for T5Gemma2, the other enables flash-attn support for EOMT. They touch different model families and different code paths.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the changes target different architectures (T5Gemma2 vs EOMT) and are independent model-specific enablement patches.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a global representative of the other; if forced, 45991 is the more substantial change, but it is not a better duplicate canonical for 45993.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45991", + "right": "pull_request:45993", + "accept": false, + "reason": "Different models and different support toggles; they do not fix the same underlying bug or change and would not be merged into one PR." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 1ff253c75039ad3dda46ab372141dbfc8317dd29..39c8a6fde89d2b9727bc682bdfa113b63ea09a5d 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260515t060029z", + "analysis_id": "hybrid-model-20260515t120027z", "archived_artifacts": { - "hybrid": "snapshots/20260515T060029Z/analysis-runs/hybrid-model-20260515t060029z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260515T060029Z/analysis-runs/hybrid-model-20260515t060029z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-15T06:04:53Z", + "published_at": "2026-05-15T12:09:11Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260515T060029Z", + "snapshot_id": "20260515T120027Z", "variant": "hybrid" } diff --git a/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.json b/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..5c4b1ed8c10f297fdb405a1e1a0e2a95dbd1dfc0 --- /dev/null +++ b/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.json @@ -0,0 +1,2264 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260515T120027Z", + "generated_at": "2026-05-15T12:09:10Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43656-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43824, + "canonical_pr_number": 43656, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43656, + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43656, + "right_pr_number": 43836, + "code_similarity": 0.36, + "size_similarity": 0.176, + "file_overlap": 1.0, + "area_overlap": 0.051, + "patch_similarity": 0.048, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ] + } + ] + }, + { + "left_pr_number": 43656, + "right_pr_number": 43842, + "code_similarity": 0.405, + "size_similarity": 0.5, + "file_overlap": 1.0, + "area_overlap": 0.0, + "patch_similarity": 0.036, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + }, + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.805, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.854, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 713, + 720 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 699, + 705 + ], + [ + 1301, + 1307 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45853-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45853.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45853, + "canonical_pr_number": 45863, + "issue_numbers": [ + 45853 + ], + "pr_numbers": [ + 45863, + 45986 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45863, + "right_pr_number": 45986, + "code_similarity": 0.141, + "size_similarity": 0.156, + "file_overlap": 0.333, + "area_overlap": 0.0, + "patch_similarity": 0.066, + "shared_filenames": [ + "src/transformers/utils/import_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/utils/import_utils.py", + "left_ranges": [ + [ + 1315, + 1321 + ] + ], + "right_ranges": [ + [ + 1338, + 1345 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44018-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44068, + "issue_numbers": [], + "pr_numbers": [ + 44018, + 44068 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44018, + "right_pr_number": 44068, + "code_similarity": 0.766, + "size_similarity": 0.939, + "file_overlap": 1.0, + "area_overlap": 0.425, + "patch_similarity": 0.866, + "shared_filenames": [ + "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "tests/models/gpt_neo/test_modeling_gpt_neo.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "left_ranges": [ + [ + 26, + 46 + ], + [ + 138, + 143 + ], + [ + 182, + 187 + ], + [ + 283, + 295 + ], + [ + 327, + 341 + ], + [ + 348, + 354 + ], + [ + 360, + 369 + ], + [ + 399, + 406 + ], + [ + 411, + 419 + ], + [ + 428, + 433 + ], + [ + 472, + 492 + ], + [ + 507, + 513 + ], + [ + 519, + 528 + ], + [ + 541, + 559 + ], + [ + 562, + 567 + ], + [ + 595, + 601 + ], + [ + 607, + 614 + ], + [ + 627, + 643 + ], + [ + 685, + 690 + ], + [ + 708, + 714 + ], + [ + 720, + 727 + ], + [ + 740, + 757 + ], + [ + 761, + 766 + ], + [ + 780, + 786 + ], + [ + 791, + 798 + ], + [ + 807, + 822 + ], + [ + 840, + 845 + ] + ], + "right_ranges": [ + [ + 26, + 31 + ], + [ + 34, + 44 + ], + [ + 136, + 141 + ], + [ + 180, + 185 + ], + [ + 281, + 293 + ], + [ + 325, + 339 + ], + [ + 346, + 352 + ], + [ + 358, + 367 + ], + [ + 397, + 404 + ], + [ + 409, + 417 + ], + [ + 426, + 434 + ], + [ + 463, + 483 + ], + [ + 498, + 504 + ], + [ + 510, + 519 + ], + [ + 532, + 550 + ], + [ + 553, + 564 + ], + [ + 586, + 592 + ], + [ + 598, + 605 + ], + [ + 618, + 634 + ], + [ + 676, + 688 + ], + [ + 699, + 705 + ], + [ + 711, + 718 + ], + [ + 731, + 748 + ], + [ + 752, + 762 + ], + [ + 771, + 777 + ], + [ + 782, + 789 + ], + [ + 798, + 813 + ], + [ + 831, + 836 + ] + ] + }, + { + "filename": "tests/models/gpt_neo/test_modeling_gpt_neo.py", + "left_ranges": [ + [ + 458, + 464 + ] + ], + "right_ranges": [ + [ + 458, + 464 + ] + ] + } + ] + } + ] + } + ], + "duplicate_issues": [], + "duplicate_prs": [ + { + "cluster_id": "cluster-41115-3", + "canonical_pr_number": 45613, + "duplicate_pr_numbers": [ + 41116 + ], + "target_issue_number": 41115, + "reason": "PRs in cluster-41115-3 are treated as duplicates because they converge on issue #41115 with closing_reference evidence." + }, + { + "cluster_id": "cluster-41211-3", + "canonical_pr_number": 44339, + "duplicate_pr_numbers": [ + 41356 + ], + "target_issue_number": 41211, + "reason": "PRs in cluster-41211-3 are treated as duplicates because they converge on issue #41211 with closing_reference evidence." + }, + { + "cluster_id": "cluster-43240-3", + "canonical_pr_number": 43251, + "duplicate_pr_numbers": [ + 43254 + ], + "target_issue_number": 43240, + "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43656-4", + "canonical_pr_number": 43656, + "duplicate_pr_numbers": [ + 43836, + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43656-4 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43979-11", + "canonical_pr_number": 44007, + "duplicate_pr_numbers": [ + 43996, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "target_issue_number": 43979, + "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-45081-3", + "canonical_pr_number": 45317, + "duplicate_pr_numbers": [ + 45086 + ], + "target_issue_number": 45081, + "reason": "PRs in cluster-45081-3 are treated as duplicates because they converge on issue #45081 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45561-3", + "canonical_pr_number": 45645, + "duplicate_pr_numbers": [ + 45639 + ], + "target_issue_number": 45561, + "reason": "PRs in cluster-45561-3 are treated as duplicates because they converge on issue #45561 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45647-3", + "canonical_pr_number": 45738, + "duplicate_pr_numbers": [ + 45737 + ], + "target_issue_number": 45647, + "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-45853-3", + "canonical_pr_number": 45863, + "duplicate_pr_numbers": [ + 45986 + ], + "target_issue_number": 45853, + "reason": "PRs in cluster-45853-3 are treated as duplicates because they converge on issue #45853 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/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..a520933bbff8491c8237052fecc6554722cdc998 --- /dev/null +++ b/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,19783 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260515T120027Z", + "generated_at": "2026-05-15T12:09:10Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41093", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43425", + "issue: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:45081", + "issue:45161", + "issue:45237", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45812", + "issue:45823", + "issue:45859", + "issue:45874", + "issue:45901", + "issue:45902", + "issue:45920" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43039|issue:45161", + "issue:43975|issue:44457", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:45859|issue:45902", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:45823|issue:45874", + "issue:43425|issue:44292", + "issue:43828|issue:45161", + "issue:34928|issue:41720", + "issue:44918|issue:45161", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:45507|issue:45685", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44560|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:43039|issue:44805", + "issue:41762|issue:43596", + "issue:43901|issue:44512", + "issue:39290|issue:41720", + "issue:45237|issue:45901", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:45812|issue:45920", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:41093|issue:43638", + "issue:43792|issue:45901" + ], + "prepared_review_unit_hash": "07fbf3057b486d500f7af51353f393cc719d1228ad7d54daddf8cebcd2f36987", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 62, + "serialized_chars": 46378, + "estimated_input_tokens": 11595, + "estimated_eval_tokens": 23446 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are only loosely related by subsystem or error shape. I accepted just two true duplicate clusters: the BertModel/DeepSpeed ZeRO-3 index-0 OOB reports, and the AutoTokenizer v4\u2192v5 token-id regression reports. There are no PRs in this set.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45920 is the best canonical issue: it is an open, broad report of the AutoTokenizer wrong-token-IDs regression across multiple model families, so it best anchors the accepted tokenizer duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the strongest issue candidate overall because it is open, broad, and captures the underlying tokenizer regression more generally than the narrower Granite-only report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different models and failure modes: missing Qwen3_5Config field vs streaming chat/completions failure." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated hardware/backend errors: AMD GPU model load vs MPS histogram op not implemented." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different bug: dtype mismatch in image preprocessing/model vs AMD GPU load failure." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Both are dtype-related, but they affect different models and code paths; not the same underlying bug." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different MoE/model-specific failures; not the same concrete error path." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different models and symptoms; no clear shared underlying bug." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "DeepSpeed collective mismatch is unrelated to ModernBERT ONNX export." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Both involve model loading/export issues, but these are different models and distinct failures." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export error is unrelated to Qwen3 auto device mapping cudaErrorAssert." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs cleanups, but they target different removed references and are not the same change." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export failure is unrelated to the GenerationMixin import error." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Generic mask-shape mismatch is not the same as Gemma4 PLE device mismatch." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Different failures: DeepSpeed ZeRO-3 index error vs mask/tensor shape mismatch." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different symptoms and code paths; the shared 'IndexError' wording is too broad to treat as duplicate." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Mask-shape IndexError and GPT-OSS tensor-parallel issue are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different model/trainer path; no evidence of the same bug." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice preset bug is unrelated to ModernBERT ONNX export." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both mention DeepSpeed, but one is a collective mismatch and the other is a BertModel index error." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3/BertModel out-of-bounds index failure; only the wording differs (init/training, pretrained/non-pretrained)." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy call issue is unrelated to GPT-OSS tensor-parallel failure." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different problems: detokenization regression vs LoRA merge/save/reload mismatch." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Unrelated model execution error vs LoRA weight merge inconsistency." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation-checkpointing/FSDP recomputation error is unrelated to the mask-shape IndexError." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both are DeepSpeed-related, but they are different runtime errors on different code paths." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": false, + "reason": "Both involve Qwen3_5MoeTextRotaryEmbedding, but one is CPU offload compatibility and the other is uninitialized-memory materialization; not the same bug." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Different model/setup and different error shape." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "FSDP checkpointing tensor-size mismatch is unrelated to the CustomTrainer signature change." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "DeepSpeed/BertModel index error is unrelated to GPT-OSS tensor-parallel behavior." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model families and failures; not the same underlying bug." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3 vLLM config attribute error is unrelated to the Mistral tokenizer regex crash." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Different Gemma4 issues: device mismatch in forward vs expensive reverse embedding lookup." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version incompatibility is unrelated to Qwen-3-8B-NVFP4 runtime error." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Both are MoE-related, but the actual failures and code paths differ." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "TRL SFT input-embedding unpacking issue is unrelated to GPT-OSS TP failure." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different model/backend errors; no shared concrete bug." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Mixtral torch-dynamo grouped_mm tracing failure is unrelated to Mistral-3 dtype mismatch." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Both are dtype/model execution issues, but they are different models and distinct failures." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Invalid method call in GraniteMoEHybrid is unrelated to the MPS histogram op issue." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model-specific runtime failures." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Different model families and failure modes." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy call vs TRL SFT embedding unpacking are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Both mention ZeRO-3 and index errors, but Gemma3 loading and BertModel training are different concrete bugs." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions, but they refer to different removed v5 artifacts and different pages." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different model-specific errors: image-preprocessor dtype mismatch vs video StopIteration." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different code paths and backends; no duplicate evidence." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Video embedding StopIteration and MPS histogram implementation error are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Both are model/runtime issues, but not the same bug or change." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch is unrelated to the trainer signature TypeError." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Activation checkpointing/FSDP error is unrelated to GenerationMixin import failure." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger Kernel cross-entropy invocation is unrelated to mask/tensor shape IndexError." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": false, + "reason": "Both are ZeRO-3 loading/index issues, but they affect different models and likely different root causes." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "TextClassificationPipeline docs issue is unrelated to the removed transformers run command docs issue." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different models and errors: Gemma3 config attribute missing vs Qwen3 device-mapping assert." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "GPT-OSS AMD GPU failure is unrelated to table-question-answering crash." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral is unrelated to Gemma4 device mismatch." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger Kernel cross-entropy issue is unrelated to Qwen3-vl video StopIteration." + }, + { + "left": "issue:45812", + "right": "issue:45920", + "accept": true, + "reason": "Same AutoTokenizer v4\u2192v5 wrong-token-ID regression affecting multiple model families; 45920 is the broader report." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Corrupted Ovis2 checkpoint and NemotronH checkpoint-loading failure are different issues." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Different models and failure types; no shared root cause." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are IndexErrors, but mask/tensor mismatch is not the same as the ZeRO-3 BertModel zero-size index error." + }, + { + "left": "issue:43792", + "right": "issue:45901", + "accept": false, + "reason": "Whisper run failure and table-question-answering crash are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The two accepted duplicate pairs are well supported by the packet: issue:43596/issue:43638 share the same ZeRO-3/BertModel index-out-of-bounds pattern, and issue:45812/issue:45920 clearly match the same AutoTokenizer v4\u2192v5 regression with 45920 being the broader canonical issue. The remaining pairs are mostly appropriately rejected on differing model, backend, or error-path evidence. 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": 1, + "component_count": 17, + "review_unit_index": 2, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36010", + "issue:39186", + "issue:39290", + "issue:40990", + "issue:41093", + "issue:41762", + "issue:42915", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43645", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43866", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44530", + "issue:44589", + "issue:44841", + "issue:44918", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45084", + "issue:45161", + "issue:45362", + "issue:45399", + "issue:45464", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45901", + "issue:45902" + ], + "soft_pairs": [ + "issue:39290|issue:43531", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43975|issue:45901", + "issue:45362|issue:45464", + "issue:43792|issue:45070", + "issue:44292|issue:45901", + "issue:43404|issue:43866", + "issue:39290|issue:45823", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:44841|issue:45084", + "issue:36010|issue:39290", + "issue:41093|issue:41762", + "issue:45800|issue:45823", + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:45020|issue:45800", + "issue:43531|issue:45070", + "issue:41093|issue:43596", + "issue:43541|issue:44589", + "issue:43054|issue:43994", + "issue:45542|issue:45800", + "issue:45759|issue:45902", + "issue:40990|issue:44960", + "issue:43716|issue:44918", + "issue:39186|issue:44918", + "issue:45632|issue:45698", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:44530|issue:45005", + "issue:42915|issue:45399" + ], + "prepared_review_unit_hash": "3d8e8814e89a6c3e00f5b875435285b92d3c5b0534bcfba2067a918879de8a30", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38764, + "estimated_input_tokens": 9691, + "estimated_eval_tokens": 19638 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a collection of distinct Transformers regression reports spanning different models, backends, and failure modes. The soft-similarity edges are largely false positives; at most they share broad themes like version compatibility, dtype issues, or loading problems, but not the same concrete bug.", + "confidence": 0.39, + "canonical_issue_reason": "issue:45020 is the broadest umbrella-style report in the set, centered on recent-version breakage for remote-code/custom models, so it is the best anchor for this heterogeneous cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most general and reusable representative among these issues; it can subsume nearby custom-loading/version-regression reports better than the model-specific crashes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Both mention sliding window, but they hit different models and different failure modes; not the same bug." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "One is a torch-version compatibility complaint, the other is a PretrainedConfig/pydantic regression; unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "DeepSpeed ZeRO-3 loading error and a torch/transformers version incompatibility are distinct problems." + }, + { + "left": "issue:43975", + "right": "issue:45901", + "accept": false, + "reason": "Detokenization on DeepSeek Coder and a table-question-answering crash are unrelated code paths." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Both involve Qwen3.5 chat usage, but one is a model crash and the other is a streaming API failure; not clearly the same defect." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper inference failure and a pydantic PretrainedConfig breakage do not match." + }, + { + "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "Qwen NVFP4 loading/runtime issues are unrelated to table-question-answering crashes." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Missing tied weights in Mistral3 and a corrupted Ovis2 checkpoint are different root causes." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3 sliding_window_pattern and Gemma4 device_map mismatch are separate model bugs." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3.5 streaming API failure and an MPS int histogram error are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Mixtral torch-dynamo grouped_mm failure and an MPS backend error are different code paths." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Both mention numeric/dtype problems, but they affect different models and operations; not the same bug." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "PaddleOCR-VL processor failure and a template-node compilation error are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "Importing GenerationMixin and Gemma3 sliding_window_pattern are separate issues." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are IndexError-shaped failures, but one is a mask/tensor size mismatch and the other is zero-sized loading with ZeRO-3; not the same bug." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "A torch/transformers version incompatibility is not the same as a Gemma4 device placement mismatch." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "PaddleOCR-VL loading failure and GGUF gpt-oss support are different feature areas." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is a specific config regression, not the pydantic PretrainedConfig field issue." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Int4 memory growth/OOM and tied-weights handling are different problems." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Grouped_mm tracing failure in Mixtral and GPT-OSS tensor-parallel issues do not share the same code path." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Phi dtype mismatch under autocast and Qwen3.5 streaming API failures are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "init_empty_weights argument handling and a pydantic PretrainedConfig regression are distinct." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF architecture support and streaming chat failures on Qwen3.5 are different issues." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Remote-code breakage and torch version incompatibility are only loosely related compatibility reports, not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and a pydantic config-field regression do not match." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are IndexErrors, but the model context and failure mechanics differ too much to be the same defect." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Mixtral grouped_mm tracing and missing Float8 storage are different backend/runtime problems." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Both concern SigLIP2 quality, but one is embedding quality and the other is nonsensical AutoModel/pipeline outputs; not enough to treat as the same bug." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard-without-TensorFlow backend error and torch/transformers incompatibility are unrelated." + }, + { + "left": "issue:45759", + "right": "issue:45902", + "accept": false, + "reason": "Composite config unwrapping and uninitialized rotary frequency after to_empty(cuda) are different bugs." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on gpt-oss and a GLM5 issue are not the same underlying problem." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Mistral-3 image-preprocessor dtype mismatch and Qwen3.5 embedding unpacking in TRL are separate failures." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP weight-shape error and Qwen3.5 embedding unpacking are different code paths." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom code loading, but one is a cache-path collision and the other is wrong module selection after save/load; not the same concrete bug." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but they concern different model families and likely different tie-weight regressions." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Custom-model notebook initialization and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache linear_attention support and translation-model tied weights are distinct issues." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "FineGrainedFP8Config failure on Qwen3Moe and flash-attn fallback blocking are different configuration problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 3, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:39692", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43493", + "issue:43643", + "issue:43644", + "issue:43782", + "issue:43828", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44492", + "issue:44512", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45237", + "issue:45507", + "issue:45520", + "issue:45663", + "issue:45701", + "issue:45800", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:44360|issue:44512", + "issue:43873|issue:45005", + "issue:44863|issue:45005", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:44292|issue:45507", + "issue:39692|issue:43054", + "issue:43644|issue:43950", + "issue:43828|issue:44928", + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:43866|issue:44403", + "issue:43950|issue:45902", + "issue:43872|issue:44589", + "issue:43054|issue:45701", + "issue:41553|issue:43883", + "issue:38175|issue:43054", + "issue:44910|issue:45859", + "issue:45663|issue:45902", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:43054|issue:43493", + "issue:44403|issue:44451", + "issue:43643|issue:45020", + "issue:43975|issue:45520", + "issue:43975|issue:45237", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:43881|issue:43883", + "issue:41762|issue:42915", + "issue:43782|issue:44960" + ], + "prepared_review_unit_hash": "2a861e141f00c9594184fd25c446b41d681a31a55bf395f76f53980e0ccb6dae", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36585, + "estimated_input_tokens": 9147, + "estimated_eval_tokens": 18550 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a loose mix of unrelated Transformers issues. The only clear duplicate family is the non-persistent-buffer regression; the rest are separate model-, loading-, or environment-specific bugs.", + "confidence": 0.87, + "canonical_issue_reason": "issue:43950 is the clearest umbrella report for the non-persistent-buffer regression, and the nearby reports (43644, 44534, 45902) read like narrower manifestations of the same bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 has the strongest, most general title and explicitly frames the problem as a Transformers 5.x regression, making it the best representative issue in this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "Completely different topics: DSA indexer behavior vs docs mentioning a removed command." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior and tied-weights translation-model issues are unrelated bugs." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "Model checkpoint loading failure does not match the tied-weights translation-model regression." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo and a removed-command docs issue are not the same bug." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Different model/code paths: TRL SFT embedding unpacking vs a GraniteMoEHybrid method call error." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Detokenization regression and Qwen NVFP4 runtime failure are distinct issues." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Both report the same non-persistent-buffer corruption/junk regression in Transformers 5.x." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Unrelated model failures with different symptoms and likely different root causes." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Both mention SigLIP2, but one is a docs/example error and the other is a model quality complaint." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Same underlying regression: non-persistent buffers being filled or returned with junk in Transformers 5.x." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Both involve precision/memory symptoms, but they are different models and different failure mechanisms." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Trainer API signature mismatch and DeepSpeed loading IndexError are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Import/export issue for AutoImageProcessor is unrelated to torch-version compatibility loading problems." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Checkpoint corruption and loading-log noise are not the same underlying bug." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": true, + "reason": "45902 appears to be a specific manifestation of the same non-persistent-buffer materialization corruption described in 43950." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Different incompatibilities: bitsandbytes parameter handling vs missing Float8 storage support." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality and tokenization changes are different problems." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error handling for Voxtral is unrelated to a Molmo attribute error." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both are SigLIP2-related, but zero probabilities and worse embeddings are not clearly the same defect." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "FlashAttention crash from 3D position_ids is unrelated to CPU-offload incompatibility in Qwen3_5MoeTextRotaryEmbedding." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "A per-layer shared_kv_states KeyError is a different code path from uninitialized rotary-embedding memory." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different models and errors: Voxtral tokenizer loading vs GLM4V loading failure." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing with LoRA and int4 quantization OOM are separate memory-related issues." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "SigLIP2 embedding quality complaint and HF-vs-JAX discrepancy are related in theme but not clearly the same bug." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Docs/noise when loading a transformer does not match a specific model loading failure." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "A specific trust_remote_code AutoConfig field-loss bug is broader than, and not identical to, general remote_code breakage." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization behavior and a Python 3.13 flash_attn import KeyError are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "DeepSeek detokenization and AMD GPU support are unrelated issues." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "A generic loading-noise complaint is not the same as a model-specific loading failure." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "Both mention memory, but LoRA checkpointing inefficiency and Qwen3 MoE training memory usage are different problems." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Different models and failures: GLM4V loading failure vs Molmo missing all_tied_weights_keys." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading IndexError and Qwen3 MoE FP8 failure are unrelated." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and GLM5 are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analyst output is grounded in the packet and stays conservative on the soft-edge pairs. The non-persistent-buffer regression family is the only clearly supported duplicate cluster, and the other pairings are mostly reasonable rejections based on distinct titles and bug surfaces." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 4, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36331", + "issue:41093", + "issue:41553", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43366", + "issue:43404", + "issue:43638", + "issue:43742", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43872", + "issue:43940", + "issue:43950", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44560", + "issue:44661", + "issue:44805", + "issue:44863", + "issue:44928", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45305", + "issue:45313", + "issue:45325", + "issue:45356", + "issue:45399", + "issue:45538", + "issue:45588", + "issue:45685", + "issue:45823", + "issue:45902", + "issue:45923" + ], + "soft_pairs": [ + "issue:45685|issue:45823", + "issue:42491|issue:44368", + "issue:43824|issue:43872", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:44991|issue:45399", + "issue:43828|issue:45823", + "issue:45081|issue:45399", + "issue:43827|issue:44509", + "issue:45020|issue:45356", + "issue:43404|issue:43950", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43257|issue:43866", + "issue:43638|issue:45823", + "issue:43792|issue:44220", + "issue:43872|issue:44291", + "issue:43940|issue:45313", + "issue:42915|issue:43872", + "issue:41553|issue:44991", + "issue:43854|issue:44863", + "issue:36331|issue:41093", + "issue:42947|issue:45923", + "issue:43257|issue:45305", + "issue:44928|issue:45588", + "issue:41093|issue:44805", + "issue:43872|issue:45538", + "issue:41553|issue:44488", + "issue:44530|issue:44863", + "issue:44479|issue:44560", + "issue:24643|issue:30064", + "issue:45325|issue:45902", + "issue:43366|issue:43828" + ], + "prepared_review_unit_hash": "2f0ff435e57b6ca7fe6d0425da9e5fbf7d1e469a01a9d47d5510d4183333fd4c", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 38065, + "estimated_input_tokens": 9517, + "estimated_eval_tokens": 19290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are unrelated model-specific regressions; only a few soft edges look like true duplicates, mainly exact error matches or the same docs cleanup.", + "confidence": 0.76, + "canonical_issue_reason": "issue:45020 is the broadest umbrella-style report in the set and best matches the recurring theme of recent-version compatibility regressions across model loading paths.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most representative issue overall: it is high-signal, broadly scoped, and can serve as the anchor for adjacent model-loading breakages.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "Different failures: MPS int-histogram support vs Gemma4 device placement mismatch." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Related Qwen3-MoE naming, but one is a LoRA compatibility break and the other is a config warning about tied embeddings." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Different bugs: missing Qwen2.5-VL import vs bitsandbytes/_is_hf_initialized incompatibility." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Broad remote_code regression vs a specific Gemma4 forward device mismatch; not the same bug." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Tokenizer-mapping edge case vs remote_code loading regressions; different code paths." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading failure vs flash-attn fallback gating; unrelated issues." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Different symptoms and subsystems: autocast dtype mismatch vs device-map forward mismatch." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex patch crash vs flash-attn fallback logic; not the same underlying bug." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Same docs regression: both report obsolete pipeline-task references after v5 removals." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Generic remote_code compatibility break vs a specific Kimi-K2.5 tokenizer regression." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Weight tying bug in Mistral3 vs from_pretrained buffer corruption; different mechanisms." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "Model load/key error vs flash-attn fallback gating; not the same issue." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "LoRA model compatibility across versions vs broad remote_code breakage; different problems." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "DeepSpeed weight conversion failure vs corrupted Ovis2 checkpoint; different failure modes." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "Zero3 index-out-of-bounds on Bert vs Gemma4 device mismatch; unrelated." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper runtime failure is too broad to equate to the specific fbank-feature helper issue." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same `_is_hf_initialized` / init_empty_weights incompatibility, just described from different entry points." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both are ZeRO-3 weight-loading failures, but for different Qwen model variants and reported at different submodules." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "LoRA/version incompatibility vs bitsandbytes init argument error; different code paths." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Tokenizer error messaging for Voxtral vs tokenizer loading failure for EMBEDDIA/est-roberta; unrelated." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different model-load failures with different causes; no shared concrete bug is evident." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Different TypeErrors/IndexErrors with unrelated triggers." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "Gradient checkpointing symptom vs missing supports_gradient_checkpointing flag; not the same bug." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "DeepSpeed weight conversion bug vs gradient averaging bug; different training failures." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF NaN/SDPA fallback problem vs flash-attn auxiliary-state AttributeError; different failure modes." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same mask-vs-tensor shape mismatch IndexError; titles differ only in the concrete dimensions shown." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes init-arg incompatibility vs CLIPTokenizer max-length bug; unrelated." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Both are tokenizer/model loading complaints, but for different models and likely different root causes." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash vs NemotronH checkpoint loading failure; different bugs." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": true, + "reason": "Both describe the same v5.3.0 Qwen video-input regression; one is the broader family report, the other a specific model manifestation." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "DeepSpeed training weight-shape runtime error vs image processor void-segmentation-map failure; unrelated." + }, + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "Both touch Qwen rotary/position-id internals, but one is a video rope-scaling regression and the other is uninitialized-memory after to_empty()." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss architecture support vs Phi-tiny-MoE autocast dtype mismatch; different issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet: the canonical issue choice is defensible, the summary stays conservative, and the accepted soft edges are supported by the issue titles (docs cleanup, identical `_is_hf_initialized` incompatibility, matching mask-shape IndexErrors, and the Qwen video regression family). Rejected pairs also read as appropriately cautious rather than overstated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 5, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42617", + "issue:42915", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43632", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43720", + "issue:43824", + "issue:43854", + "issue:43931", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44960", + "issue:44977", + "issue:45030", + "issue:45276", + "issue:45313", + "issue:45357", + "issue:45584", + "issue:45663", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:45663|issue:45823", + "issue:44155|issue:45584", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:43824|issue:43957", + "issue:43645|issue:43646", + "issue:43366|issue:44589", + "issue:42915|issue:43957", + "issue:44560|issue:44918", + "issue:42617|issue:43366", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:38175|issue:43994", + "issue:43632|issue:45834", + "issue:44560|issue:44805", + "issue:44877|issue:45030", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:43317|issue:44756", + "issue:43644|issue:44534", + "issue:38175|issue:39692", + "issue:44960|issue:44977", + "issue:42491|issue:43720", + "issue:45313|issue:45357", + "issue:41720|issue:42915", + "issue:44451|issue:44488", + "issue:42491|issue:45276", + "issue:42915|issue:44756", + "issue:43708|issue:44075", + "issue:43854|issue:43931" + ], + "prepared_review_unit_hash": "7b3da719f3300b3ad40bbef27e9ce16301be60a882346540ef0e0dfe6c5e26d4", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37193, + "estimated_input_tokens": 9299, + "estimated_eval_tokens": 18854 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a Transformers v5 regression cluster, with a few strong same-bug pairs around buffer corruption and some closely related model-specific failures; I kept the duplicate language conservative where the packet only shows similarity, not proof of identity.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43644 is the clearest representative of the non-persistent-buffer regression cluster: its title is concise and specific, and issue:44534 repeats essentially the same symptom wording, so 43644 is a good anchor without claiming an exact duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the best overall issue anchor because it is the most concise and generalizable report of the Transformers v5 non-persistent-buffer bug; nearby reports read as related variants or follow-ups rather than a separate class.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Same model family only; one is an FSDP2 KeyError, the other is a device-map mismatch. Different code paths." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "Different models and failures: AudioFlamingo3 track leakage vs Whisper empty-transcription generation." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Both are Qwen/LLM-adjacent, but one is GGUF architecture support and the other is a sliding-window bug." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Both are loading problems, but one is non-persistent buffers and the other is long OCR index handling." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different models and distinct failure modes: torch.compile/SDPA vs flash-attention illegal memory access." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "ImportError for a specific class vs meta-device loading failures; no clear shared bug." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Very likely the same custom-model initialization regression, with one report adding Jupyter as the environment." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated issues: GGUF architecture support vs missing Float8 storage during load." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Different regressions: Qwen3Moe FP8 failure vs generic meta-device model loading breakage." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both mention Qwen3.x and embeddings, but the concrete failures are different (video StopIteration vs TRL SFT unpacking)." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel runtime failure and GGUF gpt-oss support are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "Import path breakage for GenerationMixin vs Qwen3Moe FP8 runtime failure." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer-mapping edge case and Gemma4 device mismatch are different bugs." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 base model and overlapping incorrect-output symptom; this looks like a closely related same-model regression, though the packet does not prove an exact duplicate." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "General _is_hf_initialized regression vs Kosmos2.5 long-input index error; no shared code path is evident." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Both are tensor-shape failures, but the affected models and mechanisms differ." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": true, + "reason": "Both point to overly strict config validation blocking model loading; likely the same root cause." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "Different failures: DeepSpeed ZeRO-3 on non-pretrained BertModel vs add-new-model-like/tokenizer mapping behavior." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "IndexError during ZeRO-3 init is unrelated to TOKENIZER_MAPPING_NAMES handling." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer-mapping registration bug vs mask/tensor shape mismatch; no duplicate evidence." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Both involve loading/offload, but one is dequantized model offload and the other is mmap OOM on Strix Halo." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Very close same-symptom Transformers v5 non-persistent-buffer report; the titles are nearly identical, but the metadata alone doesn't prove an exact duplicate." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Same model family, but one is bad outputs and the other is a documentation example with multiple separate errors." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Different GLM/Qwen3.5 generation issues with no evidence of a shared bug." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "LoRA/Qwen3_moe incompatibility and BitNet packed-weight loading are unrelated." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Same model family, but one is ZeRO-3 weight loading and the other is save_pretrained visual-encoder key regression." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Qwen3 auto device-map CUDA assert and Qwen3Moe FP8 failure are different problems." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading failures, but the specific models differ and the bug mechanism is not shown to be the same." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Distinct model-loading errors: unit-test failure for GLM-4.7-Flash vs Qwen3-VL weight-shape mismatch." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster summary is broadly grounded, but a few claims are too strong for the packet. In particular, calling issue:44534 an \"exact duplicate\" of issue:43644 is not supported by the metadata shown, and \"reproducible\" is also not evidenced in the packet. The accepted soft pair issue:38175/issue:43994 is similarly a bit strong for the available evidence; it should be softened to something like \"closely related same-model regression\" rather than \"same underlying regression.\" Please keep the canonical/best-issue wording more conservative and based only on the observed similarity and titles." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 6, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44488", + "issue:44743", + "issue:44756", + "issue:44910", + "issue:44912", + "issue:44960", + "issue:44991", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:45488|issue:45812", + "issue:39692|issue:43994", + "issue:43257|issue:43854", + "issue:44488|issue:44991", + "issue:42491|issue:43931", + "issue:43856|issue:43873", + "issue:43644|issue:43645", + "issue:45362|issue:45406", + "issue:43856|issue:44387", + "issue:44910|issue:45588", + "issue:42491|issue:45292", + "issue:45276|issue:45335", + "issue:44164|issue:44291", + "issue:43404|issue:43454", + "issue:36010|issue:39404", + "issue:41720|issue:44155", + "issue:44402|issue:44488", + "issue:39692|issue:44960", + "issue:43425|issue:43957", + "issue:42947|issue:45704", + "issue:45663|issue:45759", + "issue:43873|issue:44387", + "issue:43335|issue:45663", + "issue:45663|issue:45859", + "issue:44291|issue:44756", + "issue:44155|issue:45823", + "issue:44292|issue:44912", + "issue:44387|issue:44756", + "issue:43854|issue:45216", + "issue:44743|issue:44960", + "issue:43957|issue:44756", + "issue:45276|issue:45292", + "issue:45684|issue:45698" + ], + "prepared_review_unit_hash": "ed0cb8e771db94991ca45cc6934afc841c9f5f17403d8587a07ac9f60a2542e6", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37767, + "estimated_input_tokens": 9442, + "estimated_eval_tokens": 19140 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: tokenizer regressions, quantization/offload issues, save/load bugs, and several model-specific generation/loading failures. A few pairs are superficially similar, especially the resize_token_embeddings reports, but none are safe duplicate merges on the evidence provided.", + "confidence": 0.84, + "canonical_issue_reason": "No single canonical issue is safe here; the cluster spans multiple unrelated code paths and model families, so there isn\u2019t a trustworthy umbrella duplicate target.", + "canonical_pr_reason": "No PRs in the cluster.", + "best_issue_reason": "Issue 45276 is the strongest local representative of the only weak mini-cluster (resize_token_embeddings propagation), because it is specific and actionable, but it still does not safely subsume the broader cluster.", + "best_pr_reason": "No PRs in the cluster.", + "soft_edge_verdicts": [ + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and failure modes; not the same bug." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Both mention SigLIP2, but one is a docs/example mismatch and the other is a model/pipeline correctness issue." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Different models and different loading paths; no sign of a shared underlying defect." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading problems, but they hit different checkpoints and likely different model-specific fixes." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Both involve Qwen3, but one is LoRA/hf4.x compatibility and the other is a Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both are memory-related, but one is Qwen3 MoE training efficiency and the other is quantization/offloading behavior." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers 5.0 regressions, but they describe unrelated bugs in different subsystems." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different models and different failures: chat crashing for Qwen3.5 versus a Gemma4 processor attribute error." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both touch memory usage, but one is training inefficiency and the other is int4 quantization causing OOM." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both involve flash attention, but the concrete bug and trigger are different." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "LoRA/branch compatibility and resize_token_embeddings propagation are unrelated bugs." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "These are similar at a high level, but they affect different model families and different embedding members, so not a safe duplicate." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "One is extra_state handling in save/from_pretrained, the other is init_empty_weights passing an unexpected argument." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both are weight-tying complaints, but they concern different models and likely distinct implementation paths." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "An import error for GenerationMixin is unrelated to Whisper return_language pipeline behavior." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Different models and unrelated runtime failures; no common code-path bug." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer vocab-size mismatch versus a model loading failure; not the same issue." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Both mention model examples, but the affected models and failures are entirely different." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "One is a Torch version compatibility complaint, the other is a meta-device loading regression." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing/LoRA and an apex RMSNorm memory leak are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Both involve composite models, but one is an FSDP2 KeyError and the other is AutoModel config unwrapping." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both are memory/quantization themed, but the symptoms and code paths differ." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction is unrelated to Gemma4 FSDP2 shared_kv_states rebuilding." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Both are model-internal bugs, but one is Gemma4 FSDP2 and the other is Qwen3 MoE CPU offload." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "Meta-initialization argument handling and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "Different model families and different runtime errors; no duplicate evidence." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Both are quantization load issues, but they involve different models and quantization formats." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Int4 quantization OOM and mmap-related OOM are different underlying problems." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "A model loading/test failure and a save_pretrained regression are different bugs." + }, + { + "left": "issue:44743", + "right": "issue:44960", + "accept": false, + "reason": "Recurrent-state caching in modular_qwen3_5 is unrelated to GLM5." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading regressions are unrelated to disabling mmap for Strix Halo." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": false, + "reason": "Both are resize_token_embeddings regressions, but the affected outputs/components differ and there is no evidence of one shared code-path bug." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Both concern save_pretrained/from_pretrained with custom modules, but one is permissions propagation and the other is wrong module loading." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 7, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36032", + "issue:39404", + "issue:42947", + "issue:43257", + "issue:43299", + "issue:43381", + "issue:43425", + "issue:43452", + "issue:43596", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43716", + "issue:43828", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44265", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44671", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44928", + "issue:44991", + "issue:45084", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:42947|issue:43381", + "issue:44479|issue:44877", + "issue:43646|issue:43708", + "issue:45588|issue:45663", + "issue:45292|issue:45335", + "issue:43645|issue:44164", + "issue:43257|issue:44863", + "issue:44402|issue:44451", + "issue:43828|issue:43957", + "issue:43425|issue:43828", + "issue:44589|issue:44756", + "issue:44683|issue:45823", + "issue:39404|issue:45701", + "issue:43931|issue:44863", + "issue:43906|issue:44530", + "issue:43425|issue:45823", + "issue:43611|issue:43645", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:43901|issue:44509", + "issue:39404|issue:44912", + "issue:44265|issue:44898", + "issue:44479|issue:44805", + "issue:43994|issue:44079", + "issue:43299|issue:43931", + "issue:43425|issue:44918", + "issue:39404|issue:44671", + "issue:44589|issue:45084", + "issue:44164|issue:45759", + "issue:36032|issue:43452", + "issue:43596|issue:44683", + "issue:44671|issue:44991" + ], + "prepared_review_unit_hash": "9a838c87bdddb78bb342934dea77559ef8e1548a93a3b8429eed72f4262300ea", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37971, + "estimated_input_tokens": 9493, + "estimated_eval_tokens": 19242 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issues with one likely duplicate pair around resize_token_embeddings behavior. No PRs were provided. Best representative issue is the broader embedding-resize report.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45292 is the broadest and clearest representative of the resize_token_embeddings propagation bug, and issue:45335 looks like the same defect in the t5gemma path.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 has the most general title and would best anchor a fix that also covers the narrower t5gemma-specific report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Both mention training/gradient topics, but one is eval-mode checkpointing and the other is a Qwen3.5 RLHF NaN issue with a different root cause." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "save/from_pretrained extra_state handling and Strix Halo mmap OOM are unrelated bugs." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both involve gradient checkpointing, but LoRA ineffectiveness and eval-mode incompatibility are different problems." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video input regression in Qwen VL models and strict config loading for granite_speech are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization in notebooks is unrelated to Trainer max_steps recalculation on checkpoint resume." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "One is a flash_attention None-handling crash; the other is a Gemma4 FSDP2 shared_kv_states KeyError." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Both report resize_token_embeddings failing to update the output-side embeddings; 45335 is a model-specific manifestation of the same bug." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Jupyter custom-model initialization and extra_state save/load failure do not describe the same code path." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MOE conversion under accelerate/deepspeed and NemotronH checkpoint loading are distinct model-loading issues." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Both are tokenizer-loading complaints, but they concern different models and likely different tokenizer defects." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch on Phi-tiny-MoE and meta-device loading failures are different loading/runtime issues." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch 2.10 incompatibility and an autocast dtype mismatch are not the same defect." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device-map mismatch are separate issues." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper return_language pipeline regression and tokenization changes across versions are different problems." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and NemotronH checkpoint loading are unrelated model-loading bugs." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "An isolated reproduction of another issue and a PagedAttentionCache linear_attention crash do not match." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch version incompatibility and Gemma4 forward device mismatch are different defects." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "base_model_prefix loading breakage and custom model initialization in notebooks are not the same root cause." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "General Torch incompatibility and a specific Mistral-3 dtype mismatch are unrelated." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash and non-template-node compile TypeError are different code paths." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but they cover different deprecated pipeline/task references." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline language return regression and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export/torch_compilable_check failure and Perceiver interpolation failure are different model/export issues." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Qwen VL video-input regression and a generic mask-shape IndexError are not the same bug." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both touch Qwen3-VL loading, but one is a version-specific MoE loading regression and the other is a specific weight-shape mismatch report; not enough evidence they are the same bug." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch 2.10 incompatibility and Qwen3.5 embedding unpacking in TRL are different problems." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline language handling and CamemBERT masked LM prediction errors are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup and non-template-node compile errors do not match." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "extra_state save/load failure and AutoModelForCausalLM.from_config text_config unwrapping are different loading behaviors." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5Tokenizer special-tokens conflict and gguf_file breaking from_pretrained are unrelated tokenizer/model-loading issues." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Zero3 init IndexError with BertModel and compiled flex_attention torch>=2.9 are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT MLM prediction regression and tokenizer loading failure for EMBEDDIA/est-roberta are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the one accepted soft-edge pair (45292/45335) is a conservative duplicate call based on the shared resize_token_embeddings propagation failure. The other verdicts stay appropriately negative given the titles alone, and no PR mergeability issue applies because no PRs were provided." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 8, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42915", + "issue:43089", + "issue:43317", + "issue:43404", + "issue:43421", + "issue:43452", + "issue:43482", + "issue:43541", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43716", + "issue:43856", + "issue:43883", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44661", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45507", + "issue:45584", + "issue:45859", + "issue:45987" + ], + "soft_pairs": [ + "issue:32090|issue:39404", + "issue:43856|issue:44756", + "issue:44991|issue:45081", + "issue:44737|issue:45859", + "issue:44164|issue:44479", + "issue:43582|issue:43632", + "issue:44488|issue:45081", + "issue:44661|issue:44683", + "issue:40990|issue:43421", + "issue:44488|issue:44987", + "issue:43611|issue:43644", + "issue:44206|issue:44220", + "issue:43716|issue:45084", + "issue:43883|issue:44488", + "issue:43643|issue:44530", + "issue:36032|issue:42915", + "issue:44811|issue:45584", + "issue:34567|issue:40444", + "issue:44464|issue:45987", + "issue:43644|issue:43646", + "issue:44451|issue:44987", + "issue:43452|issue:43482", + "issue:43541|issue:45084", + "issue:42915|issue:44530", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:36032|issue:43645", + "issue:44987|issue:44991", + "issue:43883|issue:44991", + "issue:43404|issue:44466", + "issue:43089|issue:45987", + "issue:45084|issue:45507" + ], + "prepared_review_unit_hash": "935733371e0282169a8f50808adc185ebaf51fbd4f63d5ea2c1dd9c8ba5dcae9", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37262, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of Transformers issue reports with overlapping buzzwords (v5 regressions, loading, tokenizers, device/offload), but no pair looks like the same concrete bug/change. No PRs were present.", + "confidence": 0.71, + "canonical_issue_reason": "issue:43644 is the broadest, most central regression report in the set (v5.0.0 non-persistent buffer corruption) and is the best umbrella anchor among these mostly unrelated issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the best global issue candidate because it describes a core, actionable v5 regression with potential downstream impact on model initialization/loading paths.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Different failures: Trainer GPU broadcast NoneType error vs Whisper pipeline return_language regression." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both are memory-related, but one is Qwen3 MoE training efficiency and the other is Strix Halo mmap OOM; not the same bug." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both concern tokenizer loading, but one is an est-roberta tokenizer failure and the other is a Mistral regex patch crash; different code paths." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both involve device placement, but XLNet CPU arange overhead and Qwen3_5Moe CPU offload incompatibility are distinct issues." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "save/from_pretrained extra_state handling is unrelated to the Qwen video-input regression." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon caching_allocator_warmup TypeError and the _is_hf_initialized regression are separate failures." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Different model-loading bugs; shared tokenization context is too broad to treat as one defect." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Tokenizer mapping/add-new-model-like failure is unrelated to compiled flex_attention on torch>=2.9." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity regression on gpt-oss-20b is not the same as runtime post-processor updates for special tokens." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are model-loading complaints, but they target different models and failure modes." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer junk are different code-path bugs." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "FeatureExtractor center-arg regression and _torch_extract_fbank_features problems are related audio code, but not the same concrete issue." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral image dtype mismatch is unrelated to the template-node compilation TypeError." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing all_tied_weights_keys in Molmo is unrelated to loading sleng-bert." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "AutoConfig trust_remote_code field loss and Qwen3.5 PagedAttentionCache invalid group type are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer special-token conflict and Qwen3Moe FP8 config failure are different bugs." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper/special-token themed, but batch_decode skip_special_tokens is distinct from empty-transcription generation failure." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counter bug and Qwen2.5-VL iterable dataset multi-image finetuning failure are unrelated." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is not the same as StaticCache.get_seq_length returning a tensor." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Related v5 initialization complaints, but one is buffer corruption and the other is custom model initialization; not the same defect." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different model-loading failures for different repositories; no evidence of one shared underlying bug." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both involve GGUF loading, but one is a general gguf_file API break and the other is a Qwen2.5-GGUF-specific failure." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Mixtral grouped_mm tracing error and template-node compile TypeError are distinct compiler/runtime problems." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Different Qwen-family issues: FP8 training failure vs PagedAttentionCache linear_attention crash." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "device_map auto offload loading failure and Qwen2.5-GGUF v5 loading failure are not the same code path." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Qwen3.5 output_hidden_states bug and Qwen2.5-VL rope indexing bug are unrelated model-specific regressions." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "T5 tokenizer special-token conflict is unrelated to custom model initialization in notebooks." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Different model/tokenizer loading failures for different checkpoints; no shared concrete bug." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Molmo tied-weights attribute error is unrelated to tokenizer loading for EMBEDDIA/est-roberta." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Mistral3 lm_head tying bug and lm_head serialization inconsistency are related to weights, but not the same failure mode." + }, + { + "left": "issue:43089", + "right": "issue:45987", + "accept": false, + "reason": "Generation GPU sync/dispatch overhead is unrelated to StaticCache.get_seq_length return type." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Template compilation error and GraniteMoEHybrid invalid method calls are different bugs in different subsystems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 9, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43540", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43819", + "issue:43994", + "issue:44062", + "issue:44079", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44479", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44877", + "issue:44987", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45542", + "issue:45663" + ], + "soft_pairs": [ + "issue:43262|issue:43377", + "issue:43994|issue:44610", + "issue:43646|issue:44534", + "issue:43322|issue:43540", + "issue:43645|issue:44534", + "issue:44403|issue:45081", + "issue:43377|issue:43819", + "issue:42915|issue:45084", + "issue:44265|issue:44610", + "issue:44451|issue:45081", + "issue:45216|issue:45357", + "issue:44987|issue:45081", + "issue:44220|issue:44683", + "issue:43404|issue:45127", + "issue:42915|issue:44291", + "issue:43632|issue:44756", + "issue:44062|issue:44987", + "issue:44479|issue:45325", + "issue:36032|issue:43742", + "issue:42915|issue:44589", + "issue:43296|issue:43531", + "issue:40444|issue:45325", + "issue:43531|issue:44877", + "issue:43611|issue:44534", + "issue:36032|issue:41720", + "issue:43425|issue:44403", + "issue:41553|issue:43582", + "issue:44079|issue:45663", + "issue:40990|issue:44811", + "issue:43632|issue:44534", + "issue:42175|issue:45542" + ], + "prepared_review_unit_hash": "a989dbb9af60ea95d02438feb2c78afe783af51168a5c35f029f8d3d36996c42", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36391, + "estimated_input_tokens": 9098, + "estimated_eval_tokens": 18452 + }, + "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 with only broad topical overlap (especially around Transformers v5 and Qwen variants). None of the soft pairs look like the same concrete underlying bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "issue:43646 is the broadest, most umbrella-like Transformers v5 regression in the set, so it is the best canonical issue anchor if one must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the most generally framed issue and the most plausible duplicate target among the items, even though the cluster is not truly a duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Different subsystems and failure modes: audio chat template sample-rate handling vs MIMI encoder padding-mask batching." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision/model-quality reports, but one is nonsensical outputs from AutoModel/pipeline and the other is a processor size mismatch for OmDet-Turbo." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Both touch Transformers v5 init/load behavior, but one is custom-model initialization and the other is non-persistent buffer corruption; not the same bug." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Llava Next loading segfault and Qwen3OmniMoe video ValueError are unrelated code paths." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook/custom model initialization breakage is a different issue from junk-filled non-persistent buffers." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic loading noise and a Mistral tokenizer regex patch crash are not the same defect." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI batching/padding-mask mismatch is unrelated to DAC latent decoding without STE." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and template-compilation errors have different root causes and code paths." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export with torch_compilable_check and OmDet processor resolution mismatch are distinct issues." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Model loading failure for ScandiBERT and tokenizer backend attribute crash are unrelated." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": false, + "reason": "Both concern Qwen3.5 save_pretrained regressions, but one is incorrect checkpointing generally and the other is specific visual encoder key naming; not clearly the same bug." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Physical-intelligence/fast loading regression and Mistral tokenizer regex patch crash are different problems." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Audio feature extraction bug and compiled flex_attention failure on newer torch are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Untied lm_head weights in Mistral3 and LoRA merge collapse after vocab extension are different model-state issues." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "FineGrainedFP8Config failure and unexpected _is_hf_initialized argument during init_empty_weights are distinct Transformers v5 regressions." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized flag breakage and mmap/OOM on Strix Halo are unrelated." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizers AddedToken special-flag conflict does not match the physical-intelligence/fast loading regression." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Video-input regression across Qwen models and still-image temporal position scaling are separate Qwen2.5-VL/Qwen3-VL bugs." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "T5Tokenizer special-token method conflict and MobileLLM key error are different loading failures." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and missing Float8 storage lookup are not the same error path." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window behavior are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "IterableDataset multi-image finetuning failure and Qwen2.5-VL still-image rope scaling are different multimodal bugs." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug and granite_speech strict-config loading failure do not share a concrete root cause." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "base_model_prefix loading regression is not the same as non-persistent buffer corruption." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer attribute conflict and Qwen3 auto device mapping cudaErrorAssert are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch version incompatibility and generic loading noise are not duplicates." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error for Voxtral and AppleSilicon caching_allocator_warmup TypeError are unrelated." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment bug and Gemma4 FSDP2 shared_kv_states rebuild failure are different issues." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and Whisper batch_decode skip_special_tokens behavior are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "The _is_hf_initialized flag regression and non-persistent buffer junk issue are separate Transformers v5 breakages." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "TensorFlow missing from a torch-only install and undefined tf backend from tensorboard-only install are related packaging themes but not the same defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 10, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:33666", + "issue:35707", + "issue:40444", + "issue:41720", + "issue:42175", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43381", + "issue:43421", + "issue:43454", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43749", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44466", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44829", + "issue:44898", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45812", + "issue:45834", + "issue:45923" + ], + "soft_pairs": [ + "issue:43421|issue:44568", + "issue:43792|issue:44589", + "issue:43818|issue:45357", + "issue:44683|issue:45020", + "issue:44403|issue:44991", + "issue:44462|issue:45812", + "issue:33666|issue:40444", + "issue:44829|issue:45479", + "issue:43317|issue:43856", + "issue:43482|issue:45538", + "issue:43381|issue:45923", + "issue:35707|issue:40444", + "issue:44079|issue:44534", + "issue:44291|issue:44589", + "issue:43482|issue:43525", + "issue:43377|issue:45491", + "issue:43749|issue:44079", + "issue:40444|issue:45381", + "issue:43644|issue:44079", + "issue:41720|issue:45081", + "issue:43531|issue:44291", + "issue:44265|issue:45072", + "issue:45325|issue:45381", + "issue:43632|issue:45072", + "issue:43994|issue:44898", + "issue:43611|issue:43646", + "issue:42175|issue:43296", + "issue:43454|issue:44466", + "issue:45325|issue:45834" + ], + "prepared_review_unit_hash": "d008e177a7ef4168cbc1f22b10d2fcbd333f817f4f08d893bd171aece99f1e4b", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36580, + "estimated_input_tokens": 9145, + "estimated_eval_tokens": 18546 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated issue reports, many around Transformers v5 regressions. None of the proposed soft pairs look like true duplicates of the same concrete bug. The broadest umbrella issue in the set is the remote_code regression report.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45020 is the broadest, most umbrella-style report and has active discussion/references; it best represents the cluster if one issue must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most suitable representative issue because it spans multiple affected models and a common regression class rather than a narrow model-specific failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer-related, but one is about updating the post-processor after runtime special-token changes while the other is about add_special_tokens not adding BOS/EOS; different bugs." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated failure modes: Whisper model loading versus missing Float8 storage handling." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Different models and defects: Video-LLaVA tower architecture issue versus Qwen3.5 save_pretrained key serialization." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Both involve recent version regressions, but one is a torch.compile/flex_attention breakage and the other is a remote_code model-loading regression." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "One is generic loading noise, the other is a tokenizer-loading regression for a specific model; not the same bug." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both concern AutoTokenizer behavior, but one ignores tokenizer.json while the other returns wrong token IDs for Granite models." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Different scenarios: multi-GPU training for Qwen2-VL versus IterableDataset failures with multiple images per prompt." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Both affect classification training, but the triggers differ: flash_attention_3 degeneration versus num_labels=1 zero-loss behavior." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Different problems: device_map/offload loading failure versus inefficient memory usage during Qwen3 MoE training." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "Different tokenizer/model-loading issues: GGUF loading failure versus CLIPTokenizer max_length behavior." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "One is eval-mode gradient checkpointing usage, the other is a missing supports_gradient_checkpointing flag on a remote-code variant." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Different generation/training contexts and different root causes; not the same bug." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "Different internal behaviors: ModelOutput key assignment versus non-persistent buffer serialization." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Both are v5 compatibility issues, but one is init_empty_weights argument handling and the other is Float8 storage resolution." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Both are loading issues, but one is GGUF/v5 compatibility and the other is missing pad_token_id on Llama4Config." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Both mention batched/padding-related failures, but they affect different models and code paths." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP RAM-efficient loading and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Different Qwen2.5-VL bugs: multi-image IterableDataset finetuning versus video vision_position_ids." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk filling is unrelated to ModelOutput key bookkeeping." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Different failures in different models: cudaErrorAssert on Qwen3 auto device mapping versus Mistral tokenizer regex patch crash." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE is not the same as unexpected _is_hf_initialized argument in init_empty_weights." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export with torch_compilable_check and bfloat16 dtype mismatches are different bugs." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Same model family, but one is still-image temporal position scaling and the other is video vision_position_ids; not the same concrete defect." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "Different v5 regressions: _is_hf_initialized flag handling versus bfloat16 dtype mismatch." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Different vision-model failures: siglip2 nonsensical outputs versus Perceiver resolution/interpolation issue." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 model-init regressions, but one is base_model_prefix loading and the other is custom initialization behavior." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Package backend inclusion and PaddleOCR-VL load failure are unrelated." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "One is a specific AyaVision weight-tying bug; the other is inconsistent lm_head serialization across devices." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Both involve Qwen2.5-VL OCR/position behavior, but one is temporal position scaling and the other is long OCR input index errors." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 11, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43701", + "issue:43746", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43957", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44479", + "issue:44488", + "issue:44568", + "issue:44610", + "issue:44617", + "issue:44877", + "issue:44898", + "issue:45072", + "issue:45325", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45920", + "issue:45923" + ], + "soft_pairs": [ + "issue:43792|issue:43957", + "issue:42915|issue:43482", + "issue:43296|issue:45800", + "issue:44387|issue:44617", + "issue:43701|issue:45325", + "issue:44479|issue:45823", + "issue:43881|issue:44488", + "issue:43606|issue:44265", + "issue:44291|issue:44877", + "issue:44568|issue:45920", + "issue:43262|issue:43746", + "issue:40990|issue:45584", + "issue:34634|issue:35707", + "issue:43873|issue:45701", + "issue:44186|issue:44265", + "issue:35707|issue:41720", + "issue:43606|issue:43819", + "issue:41720|issue:45823", + "issue:43454|issue:43550", + "issue:43377|issue:44610", + "issue:43317|issue:43873", + "issue:39692|issue:40444", + "issue:43572|issue:45759", + "issue:43454|issue:45072", + "issue:43257|issue:45923", + "issue:43377|issue:44898", + "issue:43526|issue:43883", + "issue:40990|issue:42947" + ], + "prepared_review_unit_hash": "06c12f4633bba68c0ccf7ddfe73859d54b9c8f1fc2dd090180f41cb05c3944ba", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35605, + "estimated_input_tokens": 8902, + "estimated_eval_tokens": 18060 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are a heterogeneous mix of unrelated bugs/regressions across model loading, tokenization, offloading, multimodal processors, and training utilities. None of the soft pairs look like the same concrete underlying issue, so there is no single canonical duplicate to keep for this cluster.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Both involve loading/runtime failures, but one is Whisper-specific and the other is a broad meta-device loading issue affecting different models; not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Qwen3 MoE FP8 config failure and Qwen2.5 GGUF load failure under v5 are different code paths and symptoms." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "One is a PaddleOCR-VL load problem in vLLM; the other is a general torch/transformers version incompatibility. Too broad to be the same fix." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both mention OOM, but one is an int4 quantization reserved-memory regression and the other is a video model memory issue." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL rope index scaling for still-image temporal positions." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Video-input regression in Qwen VL models and Gemma4 PLE device mismatch are separate forward-path bugs." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different model families and failure modes: glm-4v-9b load failure versus sleng-bert load failure." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch for Bark is unrelated to torch.export failures caused by torch_compilable_check." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Unexpected init_empty_weights argument and strict config loading for granite_speech are distinct loading/config issues." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "Specific special-token insertion regression for one tokenizer is not the same as wrong token IDs across several models." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sampling-rate default is unrelated to PEFT checkpoint loading for GraniteSpeech." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and Whisper empty-transcription failure are unrelated generation issues." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset malfunction and progressive generation with inputs_embeds/past_key_values are different APIs and bugs." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Quantization/offloading behavior and tokenizer-version changes do not share the same concrete failing code path." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crash on NER/padding is unrelated to torch.export with torch_compilable_check." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation with inputs_embeds is unrelated to Qwen3 auto device mapping cudaErrorAssert." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Both are model-runtime bugs, but CPU offload device mismatch and DAC.from_latents/STE mismatch are separate implementations." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Auto device mapping assert on Qwen3 and Gemma4 PLE device mismatch are different model-specific failures." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Weight tying/generation corruption in AyaVision is unrelated to Bamba-9B-v2 torch.compile SDPA failure." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Missing padding-mask support in MIMI encoder and OmDet-Turbo processor image-size mismatch are different bugs." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Loading dequantized models with device_map=auto and general offloading-not-working reports are related in theme but not the same concrete issue." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 doc-example/model-processor mismatch and Qwen2.5-VL iterable multi-image finetuning failure are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig and text_config unwrapping for composite Qwen multimodal configs are distinct config issues." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "AyaVision lm_head tying bug and bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel are different failures." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate+deepspeed is unrelated to a missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "MIMI padding-mask divergence and Perceiver non-default-resolution failure are separate model/processor problems." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast reduce_labels bug and Molmo missing all_tied_weights_keys are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity evaluation issue and ineffective gradient checkpointing with PEFT LoRA are unrelated training/inference bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 12, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43296", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43404", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43873", + "issue:43881", + "issue:44008", + "issue:44186", + "issue:44387", + "issue:44423", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44610", + "issue:44671", + "issue:44743", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45161", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45823" + ], + "soft_pairs": [ + "issue:44466|issue:45357", + "issue:43881|issue:44991", + "issue:43749|issue:44534", + "issue:43454|issue:43720", + "issue:41720|issue:43322", + "issue:43296|issue:44877", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:43404|issue:45357", + "issue:42617|issue:42915", + "issue:40990|issue:45701", + "issue:44186|issue:45072", + "issue:45632|issue:45684", + "issue:44423|issue:45406", + "issue:43577|issue:43708", + "issue:44387|issue:45704", + "issue:43873|issue:44756", + "issue:36331|issue:42617", + "issue:44877|issue:44991", + "issue:36331|issue:42915", + "issue:43550|issue:43720", + "issue:43450|issue:45701", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:44479|issue:44918", + "issue:43550|issue:43606", + "issue:41720|issue:42617", + "issue:43316|issue:44913", + "issue:42915|issue:43317", + "issue:43295|issue:45701", + "issue:43526|issue:43881", + "issue:44671|issue:44743", + "issue:41720|issue:45161" + ], + "prepared_review_unit_hash": "75511809c79ebbb90733b24087c08a93c04f6557362370d47acfe4cc46c3f1d2", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37665, + "estimated_input_tokens": 9417, + "estimated_eval_tokens": 19090 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is dominated by superficially similar Transformers issues, but the paired items mostly describe distinct bugs, models, or code paths. I do not see any soft pair that is a safe duplicate merge candidate.", + "confidence": 0.91, + "canonical_issue_reason": "Best representative is issue 43873: it is open, has the most discussion/inbound references, and covers a broad, active offloading+quantization problem.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the strongest cluster anchor because it is current, broadly scoped, and appears to be the most central active regression in the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both mention save/pretrained and tied weights, but they target different models and different failures (serialization inconsistency vs incorrect visual encoder keys)." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Unrelated problems: one is a model loading failure for glm-4v-9b, the other is tokenizer loading for est-roberta." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "Different bugs: FSDP CPU-efficient loading regression versus non-persistent buffers being filled with junk." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different code paths and symptoms: weight tying in AyaVision versus unpacking packed BitNet weights during accelerate loading." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Both are model-load failures, but they are different models and failure modes (cuda assert on A800 vs segmentation fault on Llava Next)." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "Different issues: vLLM/PaddleOCR-VL load failure versus strict config blocking granite_speech config loading." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Same general Qwen area, but the concrete bugs differ: auto device mapping assert versus flash-attention generation regression." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Different Gemma models and different failures: variable-name collision in Gemma3n versus device mismatch in Gemma4 PLE." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Both involve save_pretrained/tied weights, but one is about lm_head tying in Mistral3ForConditionalGeneration and the other about visual encoder keys in Qwen3.5." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "Different failures: running 3d_parallel.py versus FineGrainedFP8Config on Qwen3Moe." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Tokenization may affect perplexity, but these are not the same underlying bug; one is a perplexity report, the other is a tokenizer-version behavior change." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Different subsystems entirely: tokenizer padding/NER crashes versus dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Both touch save/load workflows, but one is a cache-path collision and the other is permission propagation from custom-model source files." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both are serve-time multimodal crashes, but the actual root causes differ (string `.to()` misuse vs missing `_tokenizer` on Gemma4Processor)." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "Unrelated: BLIP2 dtype loading bug versus resume_from_checkpoint max_steps calculation." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Both are memory-related, but one is int4 quantization OOM behavior and the other is an apex RMSNorm leak in T5." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Different memory/offload issues: quantization offloading failure versus disabling mmap on Strix Halo to avoid OOM." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Completely different failures: CustomTrainer API break versus 3d_parallel.py runtime issue." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Different config/loading bugs: strict Granite config handling versus tokenizer loading for est-roberta." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "No shared underlying bug; trainer keyword-argument regression is unrelated to Qwen3Moe FP8 loading." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "Different problems in different execution paths: torch.compile+SDPA on Bamba versus accelerate loading of packed BitNet weights." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video processor batch-shape bug is unrelated to tokenization-version differences." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both involve image size/processor expectations, but they affect different models and are not the same defect." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer NER/padding crash and OmDet-Turbo image-size mismatch are different issues." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Different Qwen3.5-related bugs: video-input regression versus unpacking embeddings with trl SFT trainer." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Different device/execution problems: torch.compile+SDPA versus CPU-offload device mismatch." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Different models and failure modes; no shared code-path bug is evident." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Both concern config behavior, but one is an API discrepancy and the other is a rotary_pct reload regression." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Different issues: Qwen3Moe FineGrainedFP8Config failure versus dequantized model loading with gpu+cpu offload." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Processor/tokenizer regression in v4.57.5 is not the same as version-dependent tokenization changes." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different defects: BeitImageProcessorFast label reduction versus glm-4v-9b loading failure." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "Masked LM prediction bug in CamemBERT is unrelated to Qwen3.5 recurrent-state reset behavior." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "The memory symptoms differ enough that they are not the same underlying bug; one is quantization offload, the other is mmap-induced OOM." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both mention Qwen/GPT-OSS style loading/runtime issues, but the concrete bug here is auto device mapping on Qwen3, not TP on GPT-OSS MoE." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 13, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:30064", + "issue:33357", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:41720", + "issue:42490", + "issue:42617", + "issue:42915", + "issue:43322", + "issue:43329", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43873", + "issue:43927", + "issue:44186", + "issue:44361", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44625", + "issue:44898", + "issue:44991", + "issue:45059", + "issue:45072", + "issue:45081", + "issue:45357", + "issue:45381", + "issue:45406", + "issue:45464", + "issue:45479", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812" + ], + "soft_pairs": [ + "issue:45081|issue:45812", + "issue:43531|issue:43572", + "issue:43540|issue:43782", + "issue:36010|issue:42617", + "issue:43421|issue:45812", + "issue:44186|issue:44361", + "issue:42915|issue:43322", + "issue:43388|issue:45059", + "issue:45406|issue:45464", + "issue:33357|issue:35707", + "issue:44492|issue:44509", + "issue:43421|issue:45701", + "issue:43606|issue:43720", + "issue:30064|issue:34634", + "issue:41720|issue:43746", + "issue:43550|issue:43653", + "issue:43873|issue:45704", + "issue:44514|issue:44545", + "issue:44625|issue:45479", + "issue:43606|issue:43653", + "issue:43531|issue:45759", + "issue:42490|issue:43329", + "issue:34634|issue:41720", + "issue:34567|issue:35707", + "issue:43421|issue:43927", + "issue:44368|issue:45357", + "issue:43782|issue:45381", + "issue:44898|issue:45072", + "issue:44451|issue:44991" + ], + "prepared_review_unit_hash": "a41525236d4f2eb9e8c505fc5d0514aa1567eda3841a9b76a40850b1232467e7", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36655, + "estimated_input_tokens": 9164, + "estimated_eval_tokens": 18584 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is still mostly a set of unrelated Transformers issues that only share broad thematic similarity. The only clear duplicate pair is issue:44514/issue:44545. For the tokenization-regression subset, issue:45812 is a strong representative, but it should be described as one of the more referenced issues rather than the most referenced one.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45812 is a strong canonical issue because it is open, specific, and describes a concrete silent AutoTokenizer regression in Granite models; it is one of the more referenced issues in the packet.", + "canonical_pr_reason": "No PRs are present in this cluster.", + "best_issue_reason": "issue:45812 is the best issue representative because it is the clearest concrete regression in the tokenization subset and can anchor that theme without overgeneralizing.", + "best_pr_reason": "No PRs are present in this cluster.", + "soft_edge_verdicts": [ + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Different tokenizer bugs: Mistral regex/backend-tokenizer crash vs Granite token-ID regression." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different config/model bugs: Qwen3-MoE sliding_window vs StableLmConfig pad_token_idx." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Different Qwen failures and code paths: video-input processing vs weight_only loading." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to the 3d_parallel.py runtime failure." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer-related, but runtime post-processor updates and Granite wrong token IDs are different bugs." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer crashes affecting different models and inputs." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "FP8Config behavior in Qwen3Moe is unrelated to the Llava Next load-time segfault." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Trainer metric label handling and SAM3 text/bbox behavior are unrelated." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Different processors and failures: Gemma4Processor missing _tokenizer vs Qwen3.5 streaming API crash." + }, + { + "left": "issue:33357", + "right": "issue:35707", + "accept": false, + "reason": "MacOS bus error with CLIP is unrelated to progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A typo in cache strategy text is not the same as stale docs for removed pipeline tasks." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Generic tokenization changes and runtime special-token post-processing are too broad to be the same bug." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Different accelerate/offload bugs affecting different models and loading paths." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Image segmentation-map processing and BarkProcessor voice_preset are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "CUDA assert during auto device mapping is unrelated to PEFT checkpoint loading for GraniteSpeech." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Torch.compile/SDPA failure and tokenizer special-token registration are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization offloading behavior is unrelated to the T5 apex RMSNorm memory leak." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same concrete crash in Qwen2_5_VLProcessor.apply_chat_template with batched input and padding=False." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Different classification bugs: num_labels propagation vs degenerate zero loss for num_labels=1." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to BigBirdTokenizer mask token registration." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Sliding_window behavior in Qwen3-MoE is unrelated to from_config not unwrapping text_config." + }, + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "Trailing-slash import warning is unrelated to the undefined-name video branch bug." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice_preset bug is unrelated to Qwen3 auto device mapping CUDA asserts." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counting and progressive generation are different subsystems and failures." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Runtime special-token post-processing and save/load losing custom token IDs are different bugs." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A tie_word_embeddings warning during LoRA fine-tuning is unrelated to incorrect visual encoder keys in save_pretrained." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Different Qwen VL bugs: weight_only loading error vs video vision_position_ids mismatch." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver resolution handling and dtype mismatch in inference are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer-loading regressions for different models; not the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster summary is mostly conservative, but the canonical/best-issue rationale overstates the evidence: issue:45812 does not have the most inbound references in the packet (issue:45701 has 6 vs 45812\u2019s 5). Please revise the representative selection or soften that claim. The duplicate call on issue:44514/44545 looks grounded." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 14, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:39692", + "issue:40444", + "issue:42886", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43618", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43819", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44451", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44843", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:45042", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45859", + "issue:45907", + "issue:45923" + ], + "soft_pairs": [ + "issue:44077|issue:44625", + "issue:44987|issue:45042", + "issue:45759|issue:45859", + "issue:43531|issue:44589", + "issue:44062|issue:44451", + "issue:45704|issue:45923", + "issue:39692|issue:44610", + "issue:44918|issue:44936", + "issue:43421|issue:43653", + "issue:45663|issue:45923", + "issue:45588|issue:45759", + "issue:42886|issue:44843", + "issue:43381|issue:43844", + "issue:43421|issue:44186", + "issue:43994|issue:44671", + "issue:43525|issue:43531", + "issue:45704|issue:45859", + "issue:45081|issue:45356", + "issue:45356|issue:45907", + "issue:39692|issue:43873", + "issue:43746|issue:43873", + "issue:43596|issue:44220", + "issue:40444|issue:43746", + "issue:43746|issue:45381", + "issue:43720|issue:43819", + "issue:43540|issue:44008", + "issue:44220|issue:44661", + "issue:45183|issue:45479", + "issue:43618|issue:43697", + "issue:30064|issue:36010", + "issue:43653|issue:43720" + ], + "prepared_review_unit_hash": "aa8273ba0c49a27ab7db44218cd286c8526dc51224cc6f35f92dc353e37fadd3", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37377, + "estimated_input_tokens": 9345, + "estimated_eval_tokens": 18946 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most candidates are unrelated model/tokenizer bugs. The only strong duplicate-looking pair is the offline tokenizer regression in 42886 and 44843; the rest are distinct issues in different code paths.", + "confidence": 0.79, + "canonical_issue_reason": "44843 most directly identifies the root cause: `_patch_mistral_regex` unconditionally calling `model_info()`, which matches the offline/cache failure described in 42886.", + "canonical_pr_reason": null, + "best_issue_reason": "44843 is the clearest representative of the one real overlap in this cluster and gives the most actionable root-cause description.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Different models and failures: patchtsmixer `post_init` policy vs Qwen3.5 `num_labels` propagation." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Both are loading/processor issues, but they describe different bugs and code paths; not the same underlying change." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Different Qwen 3.5/3.6 problems: config unwrapping vs CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated failures: Qwen3-MoE sliding window logic vs Float8 storage deserialization." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "A tokenizer constructor argument conflict is not the same bug as a model-specific load failure for ScandiBERT." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "T5 RMSNorm memory leak and missing gradient-checkpointing flag are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both involve vision processors, but the specific model mismatch and failure modes differ." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer failures: embedding unpacking with SFT trainer vs evaluate-after-train lifecycle issue." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both mention special tokens, but one is runtime post-processor updates and the other is BigBird mask-token registration." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "FSDP2 shared-kv state rebuilding and a trust_remote_code checkpointing flag are not the same bug." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention sink handling and multimodal config unwrapping are different code paths." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Same offline tokenizer regression: both point to tokenizer loading failing because `_patch_mistral_regex`/`model_info()` is invoked in offline mode." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Eval-mode checkpointing restriction is unrelated to ZeRO-3 gradient inflation during training." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Both are tokenizer bugs, but the concrete failures differ and do not look like one fix." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Different models and behaviors: SigLIP2 bad outputs vs CamemBERT MLM regression." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Different subsystems: missing `pad_token_id` on Llama4Config vs Qwen3-MoE sliding-window handling." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "RMSNorm memory leak and CPU-offload rotary embedding are unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both touch `_patch_mistral_regex`, but one is a crash on loading Mistral tokenizer and the other is a Kimi-K2.5 regression/warning issue; not clearly the same bug." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer-regex regression vs `list_repo_files` revision forwarding are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 example issues and quantization offloading are different problems." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "Local checkpoint loading with PEFT adapters is unrelated to quantized offloading behavior." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "DeepSpeed/BertModel initialization error vs audio feature extraction bug." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "Multimodal iterable dataset training failure is unrelated to GraniteSpeech checkpoint loading." + }, + { + "left": "issue:43746", + "right": "issue:45381", + "accept": false, + "reason": "PEFT local checkpoint loading and Qwen2.5-VL video position IDs are different issues." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "BitNet packed-weight loading and DAC `from_latents`/STE mismatch are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Qwen3OmniMoe video-processing error and Gemma 3n variable collision are different bugs." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction and `add-new-model-like` tokenizer mapping logic are unrelated." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Input validation messaging and sequence-classification zero-loss behavior are separate issues." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "CLIP attention output regression and RTDetrV2 output drift are different model behaviors." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Void segmentation-map processing and a `GenerationMixin` import error are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "BigBird special-token decode bug and BitNet packed-weight loading are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is conservative and grounded in the packet. The single accepted overlap, 42886/44843, is directly supported by the titles: both concern `_patch_mistral_regex`/`model_info()` breaking offline tokenizer loading. The remaining soft-edge rejections are appropriately cautious and do not overstate evidence for duplicate bugs or mergeable PRs." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 15, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:30064", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43716", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43950", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44448", + "issue:44485", + "issue:44488", + "issue:44509", + "issue:44561", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45381", + "issue:45584", + "issue:45685", + "issue:45834", + "issue:45987" + ], + "soft_pairs": [ + "issue:43335|issue:43756", + "issue:43716|issue:44008", + "issue:43295|issue:45834", + "issue:43550|issue:45072", + "issue:43550|issue:43819", + "issue:44062|issue:44488", + "issue:43322|issue:45685", + "issue:43950|issue:45987", + "issue:44186|issue:44898", + "issue:44843|issue:45081", + "issue:43531|issue:43643", + "issue:43653|issue:43819", + "issue:43643|issue:44877", + "issue:43577|issue:43818", + "issue:43421|issue:44811", + "issue:43540|issue:45381", + "issue:43782|issue:44977", + "issue:44448|issue:44671", + "issue:45584|issue:45834", + "issue:43825|issue:43994", + "issue:44561|issue:45020", + "issue:39692|issue:45834", + "issue:44821|issue:45084", + "issue:30064|issue:36331", + "issue:41720|issue:44991", + "issue:44485|issue:44509" + ], + "prepared_review_unit_hash": "2c6a970724dfc40de87dc9b6a17b08caab0a1433266bd724db94ac812edf2fc3", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35169, + "estimated_input_tokens": 8793, + "estimated_eval_tokens": 17842 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue reports across model-specific regressions, tokenizer/config edge cases, and docs/errors. No soft pair looks like the same concrete bug, though several are loosely in the remote_code / model-loading regression family.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the broadest representative of the recurring remote_code/model-loading regression family; it best anchors the cluster even though the overall set is heterogeneous.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different model bugs: sparse-layer construction vs RoPE-layer dropping." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different code paths and models: image preprocessor dtype mismatch vs Gemma3n variable-name collision." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Both are processor-related, but one is a regression in processor/tokenizer access while the other is a long-OCR index error in Kosmos2.5." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Different models and failures: Bamba torch.compile+SDPA vs SwitchTransformers/TimmWrapper bfloat16 mismatches." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Unrelated bugs in different subsystems: Bamba compilation failure vs DAC latent reconstruction mismatch." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "Both touch tokenizers, but one is an AddedToken argument error and the other is a tokenizer load failure for a specific model." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Different backend/runtime issues: Llava Next load segfault vs MPS histogram not implemented for int." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Both are API regressions, but one corrupts non-persistent buffers and the other returns the wrong type from StaticCache.get_seq_length()." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "Different models and symptoms: LayoutLMv2 tokenizer crashes vs Perceiver image-classification failures." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Same helper area (_patch_mistral_regex), but these are different failures: offline model_info access vs missing backend_tokenizer attribute." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Unrelated: Qwen3-MoE sliding-window behavior vs trust_remote_code config field loss." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Different bugs: BigBird special-token registration vs DAC forward/from_latents mismatch." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config loading, but one is missing fields under trust_remote_code and the other is strict config rejection for granite_speech." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Different model-specific issues: BLIP2 dtype propagation vs Video-LLaVA temporal-attention/weight-sharing problem." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Both involve token handling, but one is runtime post-processor updates and the other is Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both are video-input bugs in Qwen models, but they appear to be distinct failures with different versions and code paths." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Different Qwen models and failures: weight_only loading error vs flash-attention generation issue." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Both are output regressions, but they affect different models/tasks and do not share a concrete code path." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Unrelated: Whisper empty-transcription generation vs Kosmos2.5 long-input index error." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Different issues in the pipeline stack: a bad error message vs incorrect/nonsensical model outputs." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Related theme, but not the same concrete bug: one is a specific is_torch_fx_available regression, the other is a broader remote_code breakage report." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "Different problems: SigLIP2 docs/example errors vs Kosmos2.5 OCR long-input failure." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "Different failures: AutoImageProcessor URL loading vs template-node compilation error." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Completely unrelated: segmentation-map processing vs CustomTrainer compute_loss signature mismatch." + }, + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Different models and subsystems: Qwen3 auto device mapping crash vs tokenizer loading regression for EMBEDDIA/est-roberta." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE discussion is unrelated to docs still mentioning removed pipeline tasks." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 16, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:34634", + "issue:36010", + "issue:36331", + "issue:42175", + "issue:43262", + "issue:43329", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43638", + "issue:43644", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:44060", + "issue:44186", + "issue:44291", + "issue:44368", + "issue:44442", + "issue:44479", + "issue:44554", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45406", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45701", + "issue:45803", + "issue:45834" + ], + "soft_pairs": [ + "issue:43644|issue:43749", + "issue:44186|issue:44442", + "issue:44479|issue:45834", + "issue:43577|issue:43582", + "issue:43606|issue:45072", + "issue:43825|issue:43827", + "issue:44805|issue:44936", + "issue:44671|issue:45701", + "issue:34634|issue:36010", + "issue:44610|issue:45072", + "issue:43782|issue:45325", + "issue:43720|issue:45072", + "issue:42175|issue:45081", + "issue:45081|issue:45406", + "issue:43749|issue:44291", + "issue:43650|issue:43906", + "issue:44060|issue:44368", + "issue:43582|issue:44857", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:43526|issue:44554", + "issue:45459|issue:45803", + "issue:34634|issue:36331", + "issue:45084|issue:45538", + "issue:43653|issue:44912", + "issue:43742|issue:45020", + "issue:43329|issue:45600", + "issue:43638|issue:44936" + ], + "prepared_review_unit_hash": "6de2f9fdad2a73d5134527e1afc5b2ee8da69ab339b3b9caccfed4d27b8fc7c1", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36473, + "estimated_input_tokens": 9119, + "estimated_eval_tokens": 18494 + }, + "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 issues. The soft links mostly share broad themes like loading, tokenization, multimodal inputs, or dtype regressions, but not the same concrete bug or code path.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue stands out: the cluster spans many unrelated subsystems and failure modes, so any representative would be arbitrary.", + "canonical_pr_reason": null, + "best_issue_reason": "No strong global best issue for deduping; the items are too heterogeneous to anchor a single duplicate cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both involve loading/memory behavior, but one is junk non-persistent buffers and the other is broken FSDP CPU RAM-efficient loading; different bugs." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Tokenizer-related failures, but different tokenizer classes and different crash conditions; not the same code path." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Both are multimodal input bugs, but they affect different model families and different preprocessing/indexing paths." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Completely different problems: BLIP2 dtype handling vs Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Both mention inference mismatches, but they are model-specific and caused by different mechanisms." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Related to v5 pipeline removals, but one is a runtime error message and the other is docs cleanup; not one bug." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Generic runtime errors in training/eval, but no shared concrete defect or code path." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "One is a CamemBERT masked-LM regression; the other is a broad tokenization change report." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "Unrelated: Bark voice_preset issue vs GenerationMixin import error." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Different models and different failures; input-size mismatch is unrelated to dtype mismatch." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Both are Qwen VL issues, but they concern different functions and distinct bugs." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight loading failure is unrelated to bfloat16 dtype mismatch." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Backend packaging/install issue vs tokenizer regex patch crash; unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both are attribute errors during loading, but they hit different objects and different fixes." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both are model-loading problems, but the root causes are different initialization/loading APIs." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "The first is a nonspecific title; the second is a reproduction of another issue, not the same bug." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weights warnings, but the specific warning and root cause differ." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Allocator warmup TypeError on Apple Silicon is unrelated to AMP/CUDA loss crash." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Both are audio-related, but one is chat-template sampling rate and the other is DAC latent reconstruction." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Vision-model regressions, but different components and different symptoms." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "No meaningful overlap beyond being correctness issues." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both involve exception handling that hides errors, but they are different functions and different failure modes." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "Completely unrelated bug reports." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation error vs tokenizer model_max_length issue; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer special-token bug vs quantization fallback bug; no shared underlying defect." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Specific model loading key error vs broad remote_code regression claim; too different to be duplicates." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Both are CI/regression flavored, but they affect different modules and unrelated code paths." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Different training/evaluation failures with no shared root cause." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 17, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:34567", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:42490", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43454", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43643", + "issue:43645", + "issue:43696", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44291", + "issue:44479", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44977", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45356", + "issue:45357", + "issue:45488", + "issue:45538", + "issue:45701", + "issue:45759", + "issue:45859" + ], + "soft_pairs": [ + "issue:43452|issue:44991", + "issue:43746|issue:44811", + "issue:44589|issue:45042", + "issue:38175|issue:44610", + "issue:43854|issue:44977", + "issue:43819|issue:43927", + "issue:39692|issue:44912", + "issue:43257|issue:43329", + "issue:36010|issue:43645", + "issue:43550|issue:44912", + "issue:43720|issue:44610", + "issue:43257|issue:43696", + "issue:43454|issue:43577", + "issue:43329|issue:44479", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:42490|issue:43257", + "issue:36010|issue:36331", + "issue:44568|issue:45356", + "issue:43749|issue:44756", + "issue:43643|issue:45759", + "issue:44568|issue:45488", + "issue:34567|issue:40990", + "issue:43329|issue:43450", + "issue:43257|issue:43931", + "issue:43606|issue:45859", + "issue:44849|issue:45701", + "issue:43697|issue:45357", + "issue:44987|issue:45538", + "issue:44291|issue:45042" + ], + "prepared_review_unit_hash": "b0878c291f3d3af8a807a818a106e91faf5316d082284c0215ebf9d527d2ec82", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36973, + "estimated_input_tokens": 9244, + "estimated_eval_tokens": 18744 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft pair looks like the same underlying bug or change; most are only loosely related by subsystem (tokenization, video, loading, offload, etc.). If a single issue must anchor the cluster, the broad open tokenization regression report is the best representative.", + "confidence": 0.83, + "canonical_issue_reason": "issue:45701 is the broadest, most umbrella-like report in the set, with the most inbound references and a title that can absorb nearby tokenization regressions better than the more narrowly scoped bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45701 is the best overall representative because it is open, broad in scope, and appears most central to the tokenization-related slice of this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Different failure modes: gguf_file handling for from_pretrained vs a tokenizer-loading regression for a specific model." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Unrelated bugs: PEFT/local checkpoint loading vs Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Different subsystems and symptoms: float8 storage lookup vs PIL image processors requiring torchvision." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision-related, but one is zero probabilities in SigLIP2 and the other is an OmDet processor/model image-size mismatch." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Different models and issues: GLM-4.7-Flash loading test failure vs Qwen3.5 flash-attention generation regression." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent reconstruction mismatch is unrelated to DiaConfig losing custom token IDs after save/load." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Both mention quantization, but one is a SigLIP2 docs example with model/processor mismatch and the other is a git-oss-20b MXFP4 loading fallback." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Distinct code paths: Qwen3 MoE accelerate/deepspeed weight conversion vs multimodal token counting in a video branch." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "ImportError for GenerationMixin is not the same as notebook-specific custom model initialization breakage." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "Different model/runtime problems: torch.compile with SDPA vs MXFP4 quantization fallback on a different model." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to an image processor output-size mismatch." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "MoE weight conversion/loading bug is not the same as a CUDA OOM report for GPT-oss-20b." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision lm_head tying issue is unrelated to Blip2 dtype propagation for the main model and qformer." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Related video area, but not the same bug: undefined helpers in token counting vs a broader Qwen video-input regression." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE has no connection to PIL backend torchvision requirements." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting is unrelated to Whisper batch_decode token-skipping." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Local-path trailing-slash import warning is not the same as Qwen3 MoE accelerate/deepspeed weight conversion." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Importing GenerationMixin and compute_loss signature changes are separate trainer/library issues." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer regressions affecting different models and behaviors: BOS/EOS insertion vs codec/warning handling." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "FSDP CPU RAM-efficient loading breakage is not the same as disabling mmap to avoid OOM on Strix Halo." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading is distinct from unwrapping text_config for composite multimodal configs." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both are tokenization regressions, but they affect different tokenizer implementations and different concrete behaviors." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "TrainerState token counters and GPT-oss-20b perplexity are unrelated problems." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Undefined helpers in video token counting are different from batched video processor shape errors." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "MoE weight conversion during accelerate/deepspeed loading is separate from Qwen3-VL weight-shape mismatch on load." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Both mention CPU offload, but they involve different models and different failure mechanisms." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 hidden-state output bug is not the same as a broader tokenization change regression." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output differences and Qwen3.5 save_pretrained visual-key regression are unrelated model bugs." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "A model-loading failure for physical-intelligence/fast is not the same as CLIPTokenizer's model_max_length bug." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized TypeError is unrelated to PIL backend processors depending on torchvision." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 18, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:28282", + "issue:29127", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:38175", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43782", + "issue:43824", + "issue:43906", + "issue:43927", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44737", + "issue:44821", + "issue:44898", + "issue:44912", + "issue:44938", + "issue:44987", + "issue:44991", + "issue:45072", + "issue:45137", + "issue:45325", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45538", + "issue:45588", + "issue:45823", + "issue:45907", + "issue:45987" + ], + "soft_pairs": [ + "issue:43257|issue:43756", + "issue:44479|issue:45381", + "issue:42915|issue:43742", + "issue:41720|issue:43540", + "issue:43452|issue:43582", + "issue:44987|issue:45907", + "issue:33357|issue:34567", + "issue:42915|issue:44821", + "issue:42915|issue:45538", + "issue:43927|issue:44912", + "issue:43317|issue:45538", + "issue:42175|issue:43824", + "issue:43540|issue:44479", + "issue:43540|issue:44560", + "issue:44062|issue:44991", + "issue:43577|issue:45072", + "issue:42175|issue:44938", + "issue:38175|issue:44898", + "issue:43404|issue:45987", + "issue:42175|issue:44488", + "issue:45137|issue:45405", + "issue:43906|issue:45381", + "issue:28282|issue:34689", + "issue:43742|issue:44291", + "issue:42915|issue:43749", + "issue:44737|issue:45588", + "issue:43526|issue:45479", + "issue:43540|issue:45823", + "issue:43756|issue:45325", + "issue:43582|issue:43782", + "issue:28282|issue:29127" + ], + "prepared_review_unit_hash": "314aaaeef15f08bed36cc02b76409f702aea634ba7c99538d92ca4ee87491c90", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36533, + "estimated_input_tokens": 9134, + "estimated_eval_tokens": 18524 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is still mostly a grab bag of distinct Transformer bugs. Most soft edges are appropriately rejected; the only correction is to treat 44479 \u2194 45381 as merely related Qwen VL video-input regressions, not confirmed duplicates.", + "confidence": 0.69, + "canonical_issue_reason": "Issue 44479 remains the broadest representative of the Qwen video-input regression cluster, but the evidence is not strong enough to collapse 45381 into it as the same underlying bug.", + "canonical_pr_reason": null, + "best_issue_reason": "44479 is still the best cluster representative because it captures the broad v5.3.0 Qwen VL video regression framing more generally than 45381, even though the two should only be considered possibly related.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different bugs: MoE weight conversion during load vs Smollm3 RoPE layer selection." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": false, + "reason": "The titles point to related Qwen2.5-VL video-input regressions, but the packet does not show enough shared traceback, code path, or concrete overlap to call them the same bug." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Unrelated failures: Qwen3Moe FineGrainedFP8Config vs MobileLLM key error on load." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Both Qwen-related, but different code paths and failures: auto device mapping CUDA assert vs video-input ValueError." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Tokenizer/model gguf loading issue vs Apple Silicon allocator warmup TypeError; not the same bug." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Different concerns: model loading failure vs repo file listing not forwarding revision." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Mac CLIP bus error and TrainerState token counting are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3Moe FP8 load failure vs AutoImageProcessor URL loading problem." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "FP8 config failure vs CLIPTokenizer max_length behavior; different artifacts and code paths." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Config save/load token ID loss is not the same as MXFP4 quantization fallback." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "device_map/offload loading failure vs tokenizer max_length constant; unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Packaging/backend availability issue vs missing Qwen2_5_VL class import." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Both video-related, but different models and errors; not enough to treat as the same concrete bug." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Different video-input failures in different Qwen variants; no clear shared code-path bug from the titles alone." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "AddedToken special-arg error vs tokenizer loading regression for a specific model." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "BLIP2 dtype persistence bug and CI dtype mismatches in other models are not the same issue." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Backend-install packaging problem vs Python 3.14 import failure." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Unexpected zero probabilities and Perceiver interpolation failure are distinct model behaviors." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "lm_head tying bug vs StaticCache seq-length return type mismatch." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Package backend composition issue vs inability to load a specific model." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error is unrelated to the PEFT version pinning problem." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "One is a repro of an older issue; the other is a specific Qwen2.5-VL video regression." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Missing PyTorch ImportError vs Llama 3.2 Vision loading regression are different causes." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "MobileLLM key error and unexpected _is_hf_initialized argument are separate load-time bugs." + }, + { + "left": "issue:42915", + "right": "issue:43749", + "accept": false, + "reason": "Qwen3Moe FP8 issue and FSDP CPU RAM efficient loading are unrelated." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU arange issue vs flash_attention sink-less crash are distinct implementation bugs." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to the sequence-classification zero-loss issue." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Qwen3OmniMoe video processing error and Gemma4 device mismatch are different failures." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Smollm3 RoPE-layer behavior and Qwen2.5-VL temporal position scaling are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Apple Silicon caching allocator TypeError vs Qwen3VL weight_only load error are different bugs." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "AutoModel missing PyTorch and LayoutLMv3 box-information message clarity are unrelated." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster-level summary is mostly grounded, but one soft-edge verdict is too strong for the evidence in the packet. The 44479 \u2194 45381 link is plausible from the titles, yet the packet does not provide enough direct overlap to assert they are the same underlying bug; this should be framed more conservatively (e.g. \"likely related\" / \"possible duplicate\") or left unaccepted. The rest of the verdicts look appropriately conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 19, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:24643", + "issue:29127", + "issue:34567", + "issue:36331", + "issue:41762", + "issue:43295", + "issue:43452", + "issue:43493", + "issue:43531", + "issue:43577", + "issue:43643", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43819", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44466", + "issue:44484", + "issue:44488", + "issue:44514", + "issue:44589", + "issue:44625", + "issue:44704", + "issue:44792", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44964", + "issue:45005", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45290", + "issue:45356", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45600", + "issue:45823", + "issue:45920" + ], + "soft_pairs": [ + "issue:43493|issue:43994", + "issue:34567|issue:36331", + "issue:44062|issue:45081", + "issue:44291|issue:44821", + "issue:45357|issue:45920", + "issue:43643|issue:45375", + "issue:43452|issue:44488", + "issue:44792|issue:44964", + "issue:45042|issue:45081", + "issue:43742|issue:44589", + "issue:43531|issue:44821", + "issue:45405|issue:45600", + "issue:43697|issue:45216", + "issue:43688|issue:43749", + "issue:44514|issue:45381", + "issue:44484|issue:44704", + "issue:43720|issue:44898", + "issue:41762|issue:44936", + "issue:24643|issue:29127", + "issue:44625|issue:44877", + "issue:44514|issue:45290", + "issue:43452|issue:44843", + "issue:43452|issue:43577", + "issue:44466|issue:45005", + "issue:43295|issue:45356", + "issue:43819|issue:44811", + "issue:44936|issue:45823" + ], + "prepared_review_unit_hash": "632b64d2460915bba5e36985386642433964426f1eb9a33b8aa2c70da634243d", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36184, + "estimated_input_tokens": 9046, + "estimated_eval_tokens": 18348 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose collection of Transformers regressions around loading, tokenization, configs, and save_pretrained behavior. A few pairs look like true duplicates, but most are only broadly similar.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45920 is the broadest current regression report in the set: it spans multiple model families and the tokenizer/output corruption theme that recurs elsewhere in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best representative issue for this cluster because it is the most general, user-facing tokenizer regression and could absorb related follow-ups.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 implementation bug: both report incorrect outputs from the HF SigLIP2 path, just from different entry points." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Trainer bookkeeping bug vs custom compute_loss signature mismatch; different code paths and symptoms." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "AddedToken constructor conflict vs Mistral regex patch crash; unrelated tokenizer failures." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized loading error vs AutoImageProcessor URL loading; different subsystems." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Qwen3.5 save_pretrained visual-encoder key serialization vs tokenizer ID regression across models; not the same bug." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Generic trust_remote_code AutoConfig field loss vs a specific Qwen3.5 vision config field omission; different defects." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "GGUF loading regression vs a model-specific load failure; different mechanisms." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Janus generate_images test failure vs Phi-4 multimodal model load failure; different models and code paths." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "Image processor torchvision dependency regression vs tokenizer regex crash; unrelated." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "MobileLLM key error vs Float8 storage deserialization issue; distinct loading bugs." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug vs image-processor URL loading; unrelated." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "PEFT version pin problem vs removed config references in auto_mappings; different maintenance issues." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "RTDetrV2 output drift vs Qwen3.5 save_pretrained regression; different models and code paths." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization bug vs FSDP CPU RAM efficient loading; different training/load problems." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL, but one is a chat-template batching crash and the other is wrong vision_position_ids; not the same concrete defect." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "save_pretrained shard-size question vs AutoProcessor kwarg forwarding bug; not duplicates." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight loading vs Perceiver interpolation/classification issue; unrelated." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed ZeRO-3 loading error vs trainer.evaluate() failing after train; different issues." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed training runtime error vs LayoutLMv3 error-message clarity; unrelated." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3.5 num_labels propagation bug vs strict config rejecting granite_speech; different config paths." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both hit apply_chat_template, but the triggers differ: batched padding=False crash vs tool-call/no-content crash." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "GGUF loading regression vs offline model_info call in _patch_mistral_regex; different loading bugs." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "GGUF/model loading regression vs BLIP2 dtype propagation; unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": true, + "reason": "Both describe the same tied-weights/save_pretrained regression in v5, with device-dependent lm_head serialization and translation-model tied weights." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Processor.tokenizer regression vs Kimi-K2.5 codec/fix_mistral_regex warning issue; different bugs." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC latent round-trip bug vs Whisper batch_decode skip_special_tokens handling; unrelated." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "trainer.evaluate() after train vs Gemma4 PLE device mismatch; different runtime problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays appropriately cautious. The two accepted soft pairs are plausible duplicates, and the rejected pairs are consistently conservative rather than overstated. The canonical issue choice (45920) is well supported as the broadest tokenizer regression in the set." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 20, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:28282", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:38175", + "issue:41720", + "issue:43122", + "issue:43278", + "issue:43295", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43825", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44451", + "issue:44464", + "issue:44479", + "issue:44554", + "issue:44561", + "issue:44568", + "issue:44610", + "issue:44625", + "issue:44743", + "issue:44821", + "issue:44843", + "issue:44977", + "issue:44991", + "issue:45440", + "issue:45588", + "issue:45701", + "issue:45704" + ], + "soft_pairs": [ + "issue:43653|issue:44568", + "issue:38175|issue:43295", + "issue:43653|issue:44361", + "issue:43643|issue:44561", + "issue:44361|issue:44442", + "issue:30064|issue:33666", + "issue:44464|issue:44743", + "issue:41720|issue:43906", + "issue:43688|issue:45440", + "issue:43688|issue:45704", + "issue:28282|issue:32090", + "issue:43577|issue:43697", + "issue:28282|issue:33357", + "issue:28282|issue:35141", + "issue:44843|issue:44991", + "issue:43646|issue:43749", + "issue:43688|issue:45701", + "issue:43653|issue:43927", + "issue:43531|issue:43742", + "issue:43550|issue:43927", + "issue:44464|issue:44977", + "issue:44479|issue:44625", + "issue:43550|issue:44361", + "issue:43122|issue:43906", + "issue:43577|issue:44554", + "issue:43577|issue:45588", + "issue:43504|issue:43720", + "issue:43504|issue:43550", + "issue:32090|issue:34567", + "issue:41720|issue:44464", + "issue:43504|issue:44610", + "issue:32090|issue:33666", + "issue:43452|issue:44451", + "issue:43742|issue:44821", + "issue:43278|issue:43688", + "issue:43493|issue:43825" + ], + "prepared_review_unit_hash": "a47a6e14523fc9450088f5c09f8c07974418c6a1b1ddd5eda9880393c4a5b236", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38477, + "estimated_input_tokens": 9620, + "estimated_eval_tokens": 19496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All soft edges look like false positives: they share broad subsystem themes, but not the same concrete bug or fix path. The set is heterogeneous across tokenizer loading, model init, training, generation, and device/runtime issues.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue is a clear canonical representative; the items are too heterogeneous to form one duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to pick an anchor, issue 45701 is the broadest tokenization-regression report and has the most inbound references, but it still does not represent the rest of the mixed set well.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both concern tokenizers and special tokens, but they are different tokenizers with different failures and code paths." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Unrelated problems: SigLIP2 probability behavior vs processor/tokenizer API regression." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer classes and symptoms; special-token decode bug is not the same as an AttributeError on tasks." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both involve trust_remote_code, but one is missing config fields and the other is a removed helper breaking imports." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Separate tokenizer-loading failures for different models and failure modes." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Image-processor segmentation-map bug vs multi-GPU training issue; no shared underlying bug." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both are generation/cache related, but one is compiled-forward inconsistency and the other is recurrent-state reset logic." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "An A800 cuda assert with auto device mapping is not the same as an isolated reproduction of a different issue." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Different MoE model bugs with different implementations and likely different fixes." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Aux-loss normalization bug is unrelated to a T5 apex RMSNorm memory leak." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "PyTorch-missing ImportError vs Trainer GPU broadcast NoneType TypeError; unrelated." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Dtype loading mismatch for BLIP2 is not the same as RT-DETR v5 output divergence." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "ImportError about missing PyTorch and a Mac bus error are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "No common code path beyond generic loading/model usage." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer loading regressions, but they stem from different mechanisms and models." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Custom model init breakage and FSDP RAM-efficient loading are distinct failures." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization in specific MoE models is not the same as a broad tokenization-version change." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Tokenizer special-token decode bug and DiaConfig custom token ID persistence are different problems." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding-window logic and a MobileLLM key error are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile SDPA failure and config token-ID persistence do not share the same fix path." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both mention generation, but one is compiled-forward inconsistency and the other is flash-attention behavior in Qwen3.5." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video input regression and num_labels propagation are separate issues." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Different models and failure modes; no common underlying bug." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Generic tokenization change report vs an isolated reproduction of another issue." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype loading bug and MPS attention correctness issue are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Different subsystems: dtype propagation vs flash_attention crash on sink-less models." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Legacy-field model loading bug and packed-weight unpacking bug are different code paths." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Different model families and distinct loading/compile issues." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast NoneType error vs token-count state not updating; not the same defect." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Auto device mapping cuda assert and chunked generation inconsistency are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Pretrained preset loading failure and processor size mismatch are separate bugs." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer GPU broadcast error and Qwen2-VL multi-GPU training question are not the same issue." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "GGUF loading breakage and a model-specific tokenizer load failure are different root causes." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Model config loading key error vs AutoImageProcessor-from-URL failure." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Training/eval dtype mismatch is unrelated to MoE auxiliary-loss normalization." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and an error-message wording bug are not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 21, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:28218", + "issue:33357", + "issue:33666", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:43257", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43540", + "issue:43572", + "issue:43606", + "issue:43646", + "issue:43720", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43927", + "issue:44291", + "issue:44361", + "issue:44466", + "issue:44488", + "issue:44568", + "issue:44589", + "issue:44625", + "issue:44843", + "issue:44849", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45357", + "issue:45405", + "issue:45520", + "issue:45584", + "issue:45759", + "issue:45803", + "issue:45812", + "issue:45823", + "issue:45987" + ], + "soft_pairs": [ + "issue:33666|issue:36010", + "issue:44849|issue:45357", + "issue:43606|issue:43927", + "issue:44568|issue:45812", + "issue:43720|issue:43927", + "issue:43525|issue:43572", + "issue:43262|issue:43295", + "issue:43756|issue:44913", + "issue:43720|issue:44361", + "issue:28218|issue:33357", + "issue:33666|issue:36331", + "issue:39692|issue:43493", + "issue:43540|issue:44977", + "issue:43493|issue:43844", + "issue:44964|issue:45405", + "issue:45803|issue:45987", + "issue:43334|issue:43572", + "issue:43278|issue:43844", + "issue:44625|issue:45584", + "issue:43257|issue:43299", + "issue:43756|issue:45083", + "issue:44488|issue:44843", + "issue:45200|issue:45229", + "issue:43334|issue:45759", + "issue:43824|issue:44589", + "issue:39692|issue:43295", + "issue:43646|issue:44466", + "issue:45229|issue:45823", + "issue:43504|issue:43606", + "issue:43572|issue:44291", + "issue:44589|issue:45520", + "issue:33357|issue:33666", + "issue:43927|issue:44361" + ], + "prepared_review_unit_hash": "996e68aed3375b661a22c6be681166785e69cdfe3ec414640df964eab05a2ce8", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37873, + "estimated_input_tokens": 9469, + "estimated_eval_tokens": 19194 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are broadly heterogeneous; none look like the same underlying bug or change, so no duplicates should be merged.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the best canonical-style issue: it is open, broad in impact, and clearly describes a specific regression with multiple references.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Different problems: Qwen2-VL training vs a GenerationMixin import failure." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is output_hidden_states behavior and the other is save_pretrained key serialization." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to DiaConfig token ID loss on save/load." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer regressions, but different models and different failure modes." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "BitNet accelerate loading bug is unrelated to DiaConfig token serialization." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both involve missing pad token fields, but they affect different configs and code paths." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat template sampling-rate default is unrelated to processor.tokenizer/image handling." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "One is a RoPE layer-count bug, the other is config reload losing rotary_pct." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight loading and tokenizer AttributeError are different bugs." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer spacing bug and MacOS bus error are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training support is unrelated to compute_loss signature mismatch." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Same model family, but doc example mistakes are not the same as implementation discrepancies." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Video input processing in Qwen3OmniMoe is unrelated to flash-attention generation issues." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient growth are unrelated." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model loading failure and an unreleased PEFT version bump are unrelated." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except in tensor conversion is unrelated to StaticCache return-type mismatch." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both mention missing token IDs, but they are different model/config regressions." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift and gradient instability under ZeRO-3 are different issues." + }, + { + "left": "issue:44625", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 num_labels propagation is unrelated to Whisper empty-transcription behavior." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen MoE loading, but the concrete failure modes and model variants differ." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "RoPE-layer truncation and feature-length helper behavior are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "Model load failure and offline model_info regression are different code paths." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Text-only mm_token_type_ids defaulting and multi-GPU CUDA OOM are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_id and text_config unwrapping are different multimodal config bugs." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Import error for a model class is unrelated to Float8 storage lookup failure." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Documentation example errors are unrelated to processor.tokenizer regression." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model init breakage and lm_head serialization inconsistency are different regressions." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "OOM during inference and a device mismatch bug are not the same failure." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field load failure in BEiT is unrelated to bark-small CPU offload issues." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Missing pad_token_idx and unexpected _is_hf_initialized are separate loading regressions." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage lookup and flash_attn KeyError are unrelated." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS bus error on CLIP and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "Config token persistence bug and MLukeTokenizer task AttributeError 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": 1, + "component_count": 17, + "review_unit_index": 22, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29942", + "issue:30333", + "issue:34567", + "issue:37428", + "issue:38175", + "issue:42490", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43575", + "issue:43582", + "issue:43606", + "issue:43653", + "issue:43696", + "issue:43701", + "issue:43844", + "issue:43957", + "issue:43994", + "issue:44112", + "issue:44315", + "issue:44423", + "issue:44464", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44610", + "issue:44734", + "issue:44792", + "issue:44849", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45084", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45356", + "issue:45405", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45823" + ], + "soft_pairs": [ + "issue:44423|issue:44734", + "issue:43504|issue:43653", + "issue:44464|issue:45584", + "issue:43606|issue:44112", + "issue:43994|issue:44493", + "issue:43575|issue:45405", + "issue:43278|issue:43701", + "issue:44792|issue:45405", + "issue:44521|issue:45290", + "issue:29942|issue:30333", + "issue:42490|issue:43696", + "issue:43844|issue:44964", + "issue:28218|issue:34567", + "issue:44554|issue:45446", + "issue:45084|issue:45520", + "issue:43582|issue:44977", + "issue:43540|issue:45200", + "issue:15354|issue:38175", + "issue:43232|issue:44849", + "issue:45072|issue:45198", + "issue:37428|issue:43957", + "issue:45200|issue:45823", + "issue:44315|issue:44849", + "issue:43493|issue:43701", + "issue:43295|issue:44610", + "issue:44554|issue:45356" + ], + "prepared_review_unit_hash": "e3f355efbedb0a8e6c7c661c0628ffec379763b934922cc42472b212446efbc7", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 34969, + "estimated_input_tokens": 8743, + "estimated_eval_tokens": 17742 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a grab-bag of unrelated Transformers bug reports across tokenization, generation, multimodal processing, device/dtype issues, and CI failures. None of the soft pairs look like true duplicates of the same underlying bug; a few are superficially similar but differ in concrete failure mode or code path.", + "confidence": 0.62, + "canonical_issue_reason": "issue:44521 is the most central active report in the only loosely related multimodal/chat-template subgroup and has inbound references, making it the best representative issue for this mixed cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the strongest issue anchor here: open, referenced by others, and thematically closest to several multimodal/tokenization reports without being too specific.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve/runtime generation crashes, but one is a multimodal `.to()` attribute error and the other is KV-cache tensor indexing; different bugs." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "BEiT legacy-field loading and BigBirdTokenizer special-token decoding are unrelated subsystems and failure modes." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is not the same as empty-transcription failure after `align_special_tokens`." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Both mention device mismatch, but one is a real CPU-offload bug and the other is a stale CI test for GraniteSpeech." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 output discrepancies and unexpected position-id keys are different model behaviors with no shared code-path evidence." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "Tensor-parallel OOM for a model load and an unmet PEFT version requirement are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "BF16/FP32 dtype drift in evaluation is not the same as resume-from-checkpoint key mismatch." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "Janus image-generation test failure and PEFT version pinning are unrelated." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both touch `apply_chat_template`, but one is all-zero assistant masks for multimodal inputs while the other is a crash on tool-call assistant messages; different defects." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures and MLflow job-status reporting are different CI/training issues." + }, + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Import warning for trailing-slash local paths is unrelated to CUDA OOM on GPT-oss-20b." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient explosion and Phi-4 multimodal load failure are different problems." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer extra-space behavior and TrainerState token-count updates do not describe the same bug." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness and a PyTorch version check in flex_attention are unrelated." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Non-template-node compilation error and missing `flash_attn` import key on Python 3.13 are different import/runtime issues." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention generation bug are separate platform/model issues." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing error in Qwen3OmniMoe and Gemma4 token-type defaults are not the same underlying bug." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure and SigLIP2 zero probabilities are different vision-model issues." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after `sync_gpus` and Qwen3.5 hidden-states output are distinct generation-path bugs." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "bfloat16 dtype mismatches in inference and Wav2Vec2 save/tokenization failures are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Missing flash-attention helper import and meta-device loading breakage are different compatibility issues." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 text-only token-type defaults and PLE device mismatch with `device_map=\"auto\"` are separate forward-pass problems." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applied in `model_init` is unrelated to Qwen3.5 hidden-state output behavior." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 HF-vs-JAX discrepancy and checkpoint resume key mismatch are not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor/tokenizer regression for multimodal custom code and OmDet-Turbo image-size mismatch are different processor bugs." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness issue and Kimi tokenizer codec regression are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 23, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:28218", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43388", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43575", + "issue:43653", + "issue:43819", + "issue:43824", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43957", + "issue:43975", + "issue:44112", + "issue:44206", + "issue:44442", + "issue:44466", + "issue:44514", + "issue:44521", + "issue:44610", + "issue:44792", + "issue:44857", + "issue:44898", + "issue:44936", + "issue:44987", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45245", + "issue:45325", + "issue:45412", + "issue:45563", + "issue:45584" + ], + "soft_pairs": [ + "issue:44898|issue:45412", + "issue:44466|issue:45127", + "issue:44792|issue:45563", + "issue:43572|issue:44987", + "issue:45200|issue:45325", + "issue:43572|issue:43957", + "issue:37428|issue:43824", + "issue:43844|issue:44936", + "issue:43295|issue:43450", + "issue:43334|issue:43525", + "issue:43824|issue:43975", + "issue:43295|issue:43873", + "issue:43388|issue:43526", + "issue:38175|issue:45412", + "issue:42915|issue:43824", + "issue:44514|issue:44521", + "issue:38175|issue:43493", + "issue:44442|issue:45198", + "issue:28218|issue:35141", + "issue:43278|issue:43856", + "issue:42490|issue:43493", + "issue:43653|issue:44112", + "issue:43827|issue:43901", + "issue:43450|issue:43575", + "issue:44206|issue:45584", + "issue:45127|issue:45245", + "issue:43819|issue:45083", + "issue:43819|issue:44112", + "issue:43262|issue:43450", + "issue:44610|issue:44857" + ], + "prepared_review_unit_hash": "03f6cf3f0514350557fb16e8e0ae9058a824da5400dc878b8a0d08eeb84e0790", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36949, + "estimated_input_tokens": 9238, + "estimated_eval_tokens": 18732 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items do not form a true duplicate cluster; they span unrelated tokenizer, import, processor, training, and model-specific bugs. I reject all soft edges and pick the most concrete, well-documented issue as the best standalone representative.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43824 is the strongest standalone report here: it has the highest engagement, a precise import failure, and a clear reproduction path.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43824 is the best issue candidate because it is specific, broadly actionable, and better evidenced than the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Different bugs: Perceiver resolution handling vs RT-DETR memory cleanup." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both involve weights/serialization, but one is device-dependent lm_head serialization and the other is LoRA merge collapse." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to a stale generate() warning." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "StableLm pad_token_idx regression is unrelated to loading physical-intelligence/fast." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma 4 token-type defaults and Qwen2.5-VL temporal rope scaling are different code paths." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is not the same as meta-device model loading failures." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Different missing imports in different modules and model families." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed gradient growth and trainer.evaluate() failure are unrelated training issues." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor.tokenizer regression with images is not the same as batched video shape output." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Both mention pad_token_id, but they are separate model configs and not clearly one bug." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "Import error for Qwen2.5-VL is unrelated to DeepSeek detokenization." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor API regression is not the same as quantization/offloading behavior." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both are label-handling bugs, but in different utilities with different failure modes." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 numerical issue and RT-DETR memory retention are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3Moe FP8 config failure is unrelated to a Qwen2.5-VL import error." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Batched padding crash and zero assistant masks are different apply_chat_template failures." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "SigLIP2 implementation discrepancy is not the same as a separate vision-model processor bug." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizer failures for different model families and different operations." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing bug is unrelated to embedding reinitialization after resize." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype drift in eval is unrelated to Qwen3 MoE memory usage." + }, + { + "left": "issue:42490", + "right": "issue:43493", + "accept": false, + "reason": "Local-path import warning is unrelated to SigLIP2 implementation discrepancy." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and GraniteSpeech CI failure are different issues." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs-related, but they concern different pipeline APIs and different behavior changes." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batched video output shape and Qwen2-57B TP OOM are unrelated." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Feature-extractor center-arg regression and Whisper empty-transcription failure are different code paths." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA merge/tied-weights collapse is unrelated to category-count limits." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent/STE mismatch is unrelated to Qwen3 Omni MoE feature-length helper behavior." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "Different subsystems: DAC quantization logic vs GraniteSpeech device override test." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate default and batched video processor shape are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor image-size mismatch and AMP/CUDA loss crash 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": 1, + "component_count": 17, + "review_unit_index": 24, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:42490", + "issue:43278", + "issue:43335", + "issue:43425", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43825", + "issue:43854", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44292", + "issue:44351", + "issue:44360", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45520", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:37428|issue:43425", + "issue:45290|issue:45381", + "issue:43335|issue:43550", + "issue:43606|issue:45083", + "issue:44448|issue:44743", + "issue:44857|issue:45593", + "issue:45200|issue:45588", + "issue:44360|issue:44561", + "issue:43278|issue:43825", + "issue:29942|issue:32090", + "issue:37428|issue:44351", + "issue:43611|issue:43931", + "issue:44206|issue:45823", + "issue:39692|issue:43526", + "issue:43335|issue:43653", + "issue:43819|issue:44493", + "issue:43550|issue:44112", + "issue:43335|issue:43504", + "issue:45310|issue:45478", + "issue:44855|issue:45083", + "issue:43335|issue:45083", + "issue:29127|issue:32090", + "issue:45588|issue:45859", + "issue:39692|issue:44493", + "issue:44292|issue:45520", + "issue:44448|issue:44779", + "issue:38175|issue:44493", + "issue:43335|issue:45072", + "issue:44462|issue:44561", + "issue:44561|issue:44779", + "issue:43720|issue:44112", + "issue:43335|issue:45593", + "issue:44977|issue:45229", + "issue:42490|issue:43854" + ], + "prepared_review_unit_hash": "7653befb2093dfb26871099e882f47404bdf00e442b3a4a8eb1530bdb3c08198", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37851, + "estimated_input_tokens": 9463, + "estimated_eval_tokens": 19182 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous and does not look like a single duplicate set. The only clear duplicate soft edge is the Qwen3.5 MoE from_pretrained regression pair; the rest are distinct bugs/regressions across unrelated code paths.", + "confidence": 0.61, + "canonical_issue_reason": "issue:43611 is the broadest, clearest user-facing regression in this set: model loading breaks generically for models using `base_model_prefix`, which makes it a strong cluster anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the most representative and broadly applicable issue here, with a concrete loading-path failure that could plausibly attract related duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "Flash-attention import failure vs a general Torch 2.10 compatibility issue; different root causes." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Chat template crash on tool-call messages vs Qwen2.5-VL video position-id bug; unrelated code paths." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug vs Bamba torch.compile/SDPA failure; not the same bug." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch in bark-small vs qwen3_omni_moe output-length helper behavior; different failures." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output regression vs recurrent-state reset in modular_qwen3_5; separate model issues." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "AMP/CUDA loss crash vs missing auxiliary losses when denoising is off; unrelated functionality." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 token-type defaulting issue vs flash_attention s_aux=None crash; different affected components." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer ReLU comment vs removal of `is_torch_fx_available`; no shared underlying defect." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "BF16-to-FP32 eval dtype drift vs pipeline translation error messaging; not the same problem." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures vs `_gpu_broadcast_one` NoneType error in Trainer; distinct issues." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Missing `_flash_supports_window_size` import vs missing `HybridCache` import; separate import regressions." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Generic model-loading regression vs Qwen3-VL weight-shape mismatch; different failure modes." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "LaserFeatureExtractor `center` arg crash vs Gemma4 PLE device mismatch; unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 docs example problems vs BeitImageProcessorFast `reduce_labels` bug; different artifacts." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation bug vs BigBirdTokenizer special-token decode issue; not the same underlying bug." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC `from_latents` mismatch vs unexpected position-id key behavior; unrelated model internals." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba SDPA/compile bug vs GraniteSpeech stale device-override CI failure; different scopes." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers sparse-layer config issue vs Beit semantic-segmentation legacy-field loading issue; separate bugs." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same title and same Qwen3.5 MoE from_pretrained failure; these appear to be duplicates of the same regression." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 IndentationError in DebertaV2Model import vs qwen3_omni_moe feature-length helper bug; unrelated." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers sparse-layer bug vs qwen3_omni_moe helper behavior; different code paths." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 error-message clarity issue vs Trainer `_gpu_broadcast_one` NoneType crash; unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "flash_attention sink-less `s_aux=None` crash vs Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility; separate failures." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 docs example errors vs unexpected position-id key warnings; not the same bug." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime issue vs Python 3.13 `flash_attn` import KeyError; distinct causes." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output drift across versions vs Deepseek tokenizer regression in v5; different models and behaviors." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 zero-probability output vs position-id key warning; unrelated symptoms." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Sparse-layer creation bug vs bfloat16 dtype mismatch in inference; not the same code-path problem." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "AutoTokenizer ignoring `tokenizer.json` vs removal of `is_torch_fx_available`; unrelated loading regressions." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "`is_torch_fx_available` removal breakage vs Deepseek tokenizer regression; no shared root cause." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight unpacking bug vs GraniteSpeech stale device override CI failure; separate issues." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "SwitchTransformers sparse-layer bug vs D-FINE auxiliary-loss behavior; unrelated model logic." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug vs Gemma4 multi-GPU CUDA OOM; different failure modes." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Trailing-slash local-path import warning vs GLM-4.7-Flash unit-test load failure; not the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet and stays conservative on the soft edges. The single accepted duplicate pair (issue:45310 / issue:45478) is well-supported by the identical title and same Qwen3.5 MoE from_pretrained regression, and the remaining rejections do not overclaim shared root cause." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 25, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:10000", + "issue:15354", + "issue:28218", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:40444", + "issue:41720", + "issue:42490", + "issue:43065", + "issue:43278", + "issue:43329", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43701", + "issue:43723", + "issue:43873", + "issue:43927", + "issue:43976", + "issue:43994", + "issue:44448", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44857", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45712", + "issue:45803" + ], + "soft_pairs": [ + "issue:40444|issue:43526", + "issue:34689|issue:35141", + "issue:43606|issue:44857", + "issue:44448|issue:44977", + "issue:43723|issue:44554", + "issue:44857|issue:45072", + "issue:44977|issue:45563", + "issue:44568|issue:45491", + "issue:28218|issue:32090", + "issue:43927|issue:45698", + "issue:43701|issue:45083", + "issue:43550|issue:45083", + "issue:45198|issue:45803", + "issue:37428|issue:44987", + "issue:45372|issue:45588", + "issue:29942|issue:35141", + "issue:45459|issue:45712", + "issue:43873|issue:44493", + "issue:32090|issue:33357", + "issue:43873|issue:45229", + "issue:45245|issue:45563", + "issue:43412|issue:45588", + "issue:41720|issue:45229", + "issue:43278|issue:43329", + "issue:43976|issue:45440", + "issue:10000|issue:15354", + "issue:45372|issue:45406", + "issue:42490|issue:43575", + "issue:43065|issue:43994" + ], + "prepared_review_unit_hash": "05b3d6e92b6291034d8febae792ffb359f3897317620cba0cfa05fc5e85ffbe9", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36594, + "estimated_input_tokens": 9149, + "estimated_eval_tokens": 18554 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the soft pairs mostly share broad subsystem vocabulary, but they do not look like the same underlying bug or change. I found no strong duplicate PR/issue center, so the best representative is only a loose cluster hub rather than a true canonical duplicate.", + "confidence": 0.67, + "canonical_issue_reason": "issue:43873 is the broadest open infra bug in the set ('offloading not working as expected with quantization') and has the most inbound references, so it is the closest thing to a hub; the other items are mostly model-specific and not true duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the safest global representative because it is broad, still active, and most likely to attract related reports, even though the cluster overall is too mixed to form a real duplicate group.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Different problems: multimodal finetuning with multiple images vs a BeitImageProcessorFast label-reduction bug." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "One is a model-loading regression for Llama 3.2 Vision, the other is embedding reinitialization during resize/eval." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch and float16 AMP loss crashes are unrelated failure modes." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different concrete bugs: Pegasus output drift across versions vs Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are not the same code-path." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "These are different dtype-related issues in different paths: AMP loss crash vs inference dtype mismatch." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Generation correctness with flash-attention is not the same as a stale warning about num_return_sequences." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token omission and Gemma3 NaN embeddings are unrelated bugs." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Added-token spacing behavior and Trainer broadcast NoneType errors are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both touch save/load, but one loses custom token IDs in config while the other restores the wrong custom module; different serialization paths." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA failure and feature-length calculation bugs are different issues." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure and a bare-except bug in Fuyu tensor conversion are not the same defect." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "The first is a missing flash-attn import symbol; the second is a generic model-loading failure with no clear same root cause." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 processor import dependency failure and flash_attention.py s_aux handling are distinct bugs." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures and embedding reinitialization on resize are unrelated." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer error masking from protobuf handling and dummy-class cleanup/dir leakage are different concerns." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior and unexpected position-id key warnings do not share a concrete root cause." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast NoneType and a MacOS CLIP bus error are not the same failure." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Both involve large-model resource issues, but offloading/quantization misbehavior is not the same as multi-GPU OOM." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "A category-count runtime limit and a stale generation warning are unrelated." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export problems and a sink-less flash-attention AttributeError are different code paths." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Auto device-mapping cudaErrorAssert and multi-GPU OOM are different resource failures." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "BF16-to-FP32 dtype drift and an undefined-variable multimodal token helper bug are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version incompatibility and DeepSeekV3MoE divergence are not the same bug." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBertModel error and torch.jit GeneratorExp export support are unrelated." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both mention Gemma4, but one is an import dependency issue and the other is a missing _tokenizer attribute in serve." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "A trailing-slash import warning and tensor-parallel OOM are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Dummy Conv2d cleanup in Sam3PixelDecoder and SigLIP2 nonsensical outputs 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": 1, + "component_count": 17, + "review_unit_index": 26, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:25251", + "issue:28218", + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:39692", + "issue:42490", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43257", + "issue:43278", + "issue:43381", + "issue:43421", + "issue:43653", + "issue:43756", + "issue:43873", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520", + "issue:45588", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:28218|issue:29127", + "issue:43065|issue:45412", + "issue:45372|issue:45459", + "issue:44857|issue:45588", + "issue:44448|issue:44466", + "issue:43653|issue:44743", + "issue:45588|issue:45823", + "issue:43278|issue:43381", + "issue:43066|issue:44462", + "issue:44206|issue:44479", + "issue:43994|issue:45412", + "issue:25251|issue:32090", + "issue:44186|issue:45198", + "issue:44451|issue:45520", + "issue:44361|issue:45198", + "issue:42915|issue:42994", + "issue:44871|issue:44977", + "issue:44265|issue:45198", + "issue:43756|issue:45440", + "issue:43421|issue:45491", + "issue:29942|issue:30064", + "issue:43257|issue:43278", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:44610|issue:45412", + "issue:32090|issue:33290", + "issue:42490|issue:43873", + "issue:45440|issue:45593" + ], + "prepared_review_unit_hash": "3af4d7545024d9f5120b1043c2dce1be20a68aa6d9d4a7fed36bc6f661835c34", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35486, + "estimated_input_tokens": 8872, + "estimated_eval_tokens": 18000 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster looks heterogeneous rather than like one duplicate family; all soft-pair candidates are distinct bugs/features and should be kept separate.", + "confidence": 0.86, + "canonical_issue_reason": "issue:44462 is the most representative standalone bug here: concrete, reproducible, user-facing, and with inbound references; the rest of the items are a mix of unrelated tokenizer, training, vision, quantization, and runtime issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the best anchor for triage because it is narrowly scoped, clearly described, and has external references that suggest real impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Different subsystems and failure modes: tokenizer spacing vs. LayoutLMv3 error-message clarity." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "No shared code-path: Sam3PixelDecoder dummy layer is unrelated to RT-DETR memory cleanup." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma processor import breakage is unrelated to tokenizer error masking when protobuf is missing." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "Different bugs in different paths: LwDetr loss under AMP vs flash-attention crash on sink-less models." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Both are version/regression complaints, but one is generation output drift and the other is serialization of tied weights." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "Tokenizer special-token registration bug is unrelated to Qwen3.5 recurrent-state reset logic." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "One is a flash-attention attribute error; the other is a device-map forward mismatch in Gemma4 PLE." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype mismatch in eval is not the same issue as gradient checkpointing being disallowed in eval mode." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer decoder-type regression is a different loading bug than ignoring tokenizer.json from a repo." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Feature extractor center-arg crash and Qwen video-input regression are unrelated code paths." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 model/pipeline output corruption is unrelated to RT-DETR memory release behavior." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nesting bug is unrelated to Trainer broadcast failing on NoneType." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 tokenizer NER/padding crash is unrelated to Wav2Vec2 save_pretrained/tokenization failures." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model-loading failure for a specific checkpoint is unrelated to a flash_attn import KeyError on Python 3.13." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and Wav2Vec2 save/tokenization failure are distinct tokenizer/model issues." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "One concerns Qwen3 MoE loading with FP8 config; the other is quantized model saving." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "EOS-token config inconsistency is unrelated to Qwen3.5 flash-attention generation problems." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failure from torch_compilable_check is a different export path than Wav2Vec2 save/tokenization." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Different models and different defects: Smollm3 RoPE-layer mismatch vs DeepseekV3MoE implementation divergence." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime special-token post-processor update bug is unrelated to Gemma3 NaN embeddings in mixed-length batches." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 CI failures and void segmentation-map processing are unrelated regressions." + }, + { + "left": "issue:43257", + "right": "issue:43278", + "accept": false, + "reason": "Qwen3 MoE weight-conversion failure is unrelated to embedding dtype changing between train and eval." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS CLIP bus error and SigLIP2 docs-example errors are not the same bug or code path." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "Clarity of a layoutlmv3 error message is unrelated to TrainerState token-count tracking not updating." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor resolution mismatch is unrelated to RT-DETR object lifetime/memory release." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer NoneType broadcast error and DeepSpeed Adafactor OOM are different training failures." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Local-path import warning is unrelated to quantization offloading behavior." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepseekV3MoE implementation drift and D-FINE auxiliary-loss omission are different model-specific issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 27, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:33357", + "issue:35141", + "issue:36010", + "issue:42490", + "issue:42915", + "issue:43232", + "issue:43262", + "issue:43334", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43646", + "issue:43653", + "issue:43701", + "issue:43723", + "issue:43761", + "issue:43824", + "issue:43931", + "issue:44062", + "issue:44077", + "issue:44079", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44977", + "issue:45003", + "issue:45072", + "issue:45103", + "issue:45245", + "issue:45372", + "issue:45440", + "issue:45479", + "issue:45491", + "issue:45588", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:43824|issue:44279", + "issue:43653|issue:44442", + "issue:43761|issue:45859", + "issue:43526|issue:45834", + "issue:45103|issue:45372", + "issue:43381|issue:43701", + "issue:43526|issue:44186", + "issue:29942|issue:36010", + "issue:29127|issue:33357", + "issue:43334|issue:43531", + "issue:44977|issue:45245", + "issue:29127|issue:35141", + "issue:44464|issue:45491", + "issue:42915|issue:43931", + "issue:44442|issue:45072", + "issue:43262|issue:44206", + "issue:43526|issue:44857", + "issue:42490|issue:43381", + "issue:44062|issue:45907", + "issue:43441|issue:45588", + "issue:43232|issue:43388", + "issue:44743|issue:44811", + "issue:43646|issue:44077", + "issue:43575|issue:43701", + "issue:43761|issue:44079", + "issue:43575|issue:44387", + "issue:45003|issue:45440", + "issue:43723|issue:45479" + ], + "prepared_review_unit_hash": "72f91e550386cdbb74aee4678444bebbd63dcfe75dee13476ebd6039d6d6da79", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36208, + "estimated_input_tokens": 9052, + "estimated_eval_tokens": 18360 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the items span unrelated tokenizer, generation, model-loading, training, flash-attention, and processor bugs. None of the soft pairs look like the same underlying defect, so no duplicate merges are warranted.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45003 is the best representative issue because it is a concrete, self-contained core-library bug in modeling_utils with a clear code path and broad impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Different failure modes: Qwen2.5-VL import error vs a vague dependency issue; no shared code path." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "Both involve tokenizers, but one is a BigBird special-token decoding bug and the other is an AutoTokenizer load failure for a different model." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVision hidden_states regression and Qwen3_5Moe CPU offload incompatibility are unrelated model-specific bugs." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "Different processors and symptoms: Beit reduce_labels bug vs Kosmos2.5 OCR index error." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation parsing crash is unrelated to the Gemma 4 processor import failure." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Training-loop issues in different places: gradient checkpointing eval-mode restriction vs checkpoint key mismatch." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Both are vision/text preprocessing issues, but they hit different classes and code paths with different root causes." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention test failures and a GenerationMixin import error are not the same bug." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "A poor error message in LayoutLMv3 is unrelated to a MacOS bus error loading a CLIP model." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Both mention Qwen3, but one is missing pad_token_id and the other is a sliding_window regression in MoE models." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug and category-count limit error are completely different issues." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 box-validation messaging and token-embedding reinit after resize are unrelated." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is not the same as Gemma3 NaN embeddings from sliding-window attention." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen3-VL weight-shape mismatch are distinct loading/configuration problems." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch in model wrappers do not share the same underlying defect." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate default bug and LasrFeatureExtractor center-arg crash are unrelated processor issues." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "Beit reduce_labels truncation and LwDetrImageLoss AMP/CUDA crash are different components and failure modes." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Import warning on local-path loading is unrelated to gradient checkpointing in eval mode." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken keyword duplication and list_repo_files revision forwarding are different API bugs." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Different flash-attention problems: Ministral v5 RC failure vs s_aux=None crash in integrations/flash_attention.py." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs sync after sync_gpus and metric-gathering label truncation are separate training/eval bugs." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3_5 recurrent-state reset and Whisper batch_decode skip_special_tokens are unrelated behavioral bugs." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Custom model init breakage in Transformers 5.0.0 and patchtsmixer's post_init constraint are not the same issue." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Tensor-parallel OOM on Qwen2-57B and resume_from_checkpoint key mismatch do not overlap." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "A CLIPVision forward regression is not the same as a generic ModelOutput key-assignment bug." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is TP load OOM for a specific model and the other is increased reserved memory under int4 quantization." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils and DeepseekV3MoE divergence from remote implementation are different code paths." + }, + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "AutoTokenizer loading failure and zero-loss classification behavior are unrelated problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 28, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:33290", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41628", + "issue:42175", + "issue:42490", + "issue:42907", + "issue:43316", + "issue:43381", + "issue:43404", + "issue:43441", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43611", + "issue:43643", + "issue:43720", + "issue:43749", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44188", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44743", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45372", + "issue:45491", + "issue:45698", + "issue:45759", + "issue:45803" + ], + "soft_pairs": [ + "issue:44442|issue:45803", + "issue:44479|issue:45290", + "issue:43761|issue:44188", + "issue:43316|issue:43525", + "issue:42907|issue:45698", + "issue:44442|issue:44898", + "issue:42490|issue:44743", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:39692|issue:45491", + "issue:33290|issue:35141", + "issue:33290|issue:34689", + "issue:43931|issue:45216", + "issue:43381|issue:43873", + "issue:43493|issue:43827", + "issue:44077|issue:44479", + "issue:43316|issue:45759", + "issue:43720|issue:44442", + "issue:41628|issue:45372", + "issue:43643|issue:44913", + "issue:43749|issue:43931", + "issue:34689|issue:36010", + "issue:43873|issue:44871", + "issue:33290|issue:36331", + "issue:44190|issue:44496", + "issue:44855|issue:45137", + "issue:43540|issue:44514", + "issue:43316|issue:44877", + "issue:42175|issue:43316", + "issue:43404|issue:43441" + ], + "prepared_review_unit_hash": "03b9cab88a02228737fbda707b821ebb276a1152d6ba851ef14d84c2e35fec37", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36437, + "estimated_input_tokens": 9110, + "estimated_eval_tokens": 18476 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: the soft pairs cover unrelated bugs across tokenizers, vision, config reloads, multimodal chat, trainer APIs, and loading/saving regressions. None of the proposed soft edges look like true duplicates of the same underlying defect, so I reject them all.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical duplicate exists in this set. If one issue must serve as an anchor, issue #43749 has the strongest triage signal (discussion plus inbound references) and is a broad runtime/regression report.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #43749 is the best single representative by external signal and breadth of impact, but it still does not match the rest closely enough to act as a true duplicate hub.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Different bugs: FastSpeech2Conformer tokenizer loading vs a Fuyu bare-except masking errors/KeyboardInterrupt." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Both are multimodal/chat regressions, but one is a video-input regression and the other is an assistant tool-call chat_template crash." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "Unrelated code paths: CLIPVision hidden_states handling vs attention-kernel divergence under torch.compile." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both concern config APIs, but they are different model-specific attribute mismatches with different symptoms and fixes." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Save/load are both involved, but one is dequantized model saving and the other is loading the wrong custom module after save_pretrained." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Different model families and failures: tokenizer import/loading vs Perceiver image-classification resize/interpolation behavior." + }, + { + "left": "issue:42490", + "right": "issue:44743", + "accept": false, + "reason": "Completely different areas: local-path import warning vs recurrent state reset with cache in modular Qwen3.5 code." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "AdaFactor/DeepSpeed OOM is unrelated to TrainerState.num_input_tokens_seen not updating." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both are loading regressions, but one is a Llama vision model breakage and the other is a base_model_prefix-related loading issue." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "Docs-example errors are unrelated to Gemma3 NaN embeddings in mixed-length GPU batching." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "Different subsystems: optimizer memory blow-up vs embedding resize/post_init reinitialization." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "No shared bug: DeepSpeed optimizer OOM is unrelated to model-loading failure." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Both mention Qwen models, but one is a shape-mismatch load failure and the other is an incorrect save_pretrained regression." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to quantization/offloading behavior." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "A model-implementation discrepancy is not the same as stale docs still referencing removed pipeline() APIs." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTSTMixer post_init policy and Qwen video-input regression are different bugs." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config shape, but Gemma3TextConfig API inconsistency is not the same as Qwen multimodal config unwrapping in from_config." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading and tokenizer import failure are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Both are import errors, but they come from different symbols, dependencies, and processor-loading paths." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "Different config persistence bugs: trust_remote_code missing fields vs GPTNeoX rotary_pct resetting on reload." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM-efficient loading and Qwen3-VL weight-shape mismatch are different loading failures." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Model-loading breakage and GenerationMixin import failure are not the same underlying issue." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to Gemma-3 eos_token_id config inconsistency." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed OOM is unrelated to CustomTrainer.compute_loss receiving an unexpected keyword argument." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an image-classification script is unrelated to an unrecognized model/config_type error." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 torch.jit parsing/IndentationError is unrelated to DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Both are Qwen multimodal issues, but one is video-input processing and the other is chat-template handling for tool calls." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Different config issues for different models; not the same API discrepancy." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "TensorFlow backend packaging is unrelated to Gemma3TextConfig behavior." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Mistral3 lm_head tying and Ministral FlashAttention failure are different bugs with different code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 29, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:25251", + "issue:28282", + "issue:32090", + "issue:35141", + "issue:41950", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43388", + "issue:43452", + "issue:43475", + "issue:43504", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43688", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43825", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44871", + "issue:44913", + "issue:44977", + "issue:45127", + "issue:45200", + "issue:45406", + "issue:45563", + "issue:45584", + "issue:45698" + ], + "soft_pairs": [ + "issue:43065|issue:44617", + "issue:43673|issue:44743", + "issue:43295|issue:43825", + "issue:25251|issue:28282", + "issue:44162|issue:44792", + "issue:43388|issue:43688", + "issue:41950|issue:43475", + "issue:44077|issue:44534", + "issue:16998|issue:22355", + "issue:43550|issue:43701", + "issue:44871|issue:45584", + "issue:43606|issue:43701", + "issue:43761|issue:44479", + "issue:45127|issue:45200", + "issue:43295|issue:44871", + "issue:42617|issue:43575", + "issue:43452|issue:44496", + "issue:43575|issue:43742", + "issue:44734|issue:45406", + "issue:43646|issue:44913", + "issue:43504|issue:45698", + "issue:44617|issue:45584", + "issue:43931|issue:44060", + "issue:43761|issue:44242", + "issue:45563|issue:45584", + "issue:32090|issue:35141", + "issue:44464|issue:44871", + "issue:43065|issue:44610", + "issue:44792|issue:44977", + "issue:44479|issue:44734" + ], + "prepared_review_unit_hash": "5aaf6fc09974e85d2fda2229f6e2f9723f80cc45baa7f826133142af95d25183", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36084, + "estimated_input_tokens": 9021, + "estimated_eval_tokens": 18298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is heterogeneous: the issues span unrelated Transformers bugs across loading, generation, processors, training, and model-specific regressions. None of the soft-similarity pairs look like the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:45698 is the broadest and most active report in the set, but the overall collection is too heterogeneous to treat as a true duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 has the strongest discussion/inbound-reference signal and is the best single anchor if one must be chosen, though it does not represent the unrelated reports well.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Both are SAM3/video-related, but one is a dummy layer issue and the other is an OOM report; different code paths and failure modes." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both involve cache behavior, but one is missing GenerationMixin cache in chunked prefill and the other resets recurrent states in modular_qwen3_5; not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Both are v5 regressions, but one is a processor/tokenizer API break and the other is a pipeline error-message problem; unrelated fixes." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Top-k output nesting and a missing PyTorch import are unrelated issues." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 breakage and a Janus image-generation test failure are model-specific and unrelated." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "One is a last-batch label-dropping bug in gather_for_metrics; the other is auxiliary-loss normalization in MoE models." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "A pipeline processor-selection bug and a missing Sam3VisionEncoderOutput attribute are different failures." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Optional post_init handling and non-persistent buffer junk are separate initialization/state bugs." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Model_max_length on DeBERTa-V3 and a missing transformers.onnx module are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "A torch.compile/SDPA OOM in Bamba and a resume_from_checkpoint key mismatch are different problems." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Both concern generation/token IDs, but Gemma eos_token_id inconsistency and Whisper empty-transcription failure are distinct bugs." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch and checkpoint key mismatch are unrelated." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and a Qwen video-input regression affect different models/code paths." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge collapse with tied embeddings and Gemma 4 mm_token_type_ids defaults are different bugs." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Processor/tokenizer regression and eos_token_id configuration mismatch are not the same underlying issue." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "Running 3d_parallel.py and loading Qwen2-57B with tensor parallelism are different distributed/runtime failures." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "gguf_file loading breaks specific from_pretrained paths, while the other is an unrecognized model_type config issue." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Qwen2-57B TP OOM and MobileLLM key-error loading are unrelated model-loading failures." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation indexing in serve and a missing _tokenizer attribute on Gemma4Processor are different code paths." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model initialization breakage in v5 and GPTNeoXConfig rotary_pct reload drift are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Legacy preset loading for BEiT segmentation and wrong custom-module loading after save/load are both loading-related but not the same bug." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Sam3Video OOM and Whisper empty-transcription handling are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and Qwen3-Next tied-weights warning are different model/config issues." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "A CLIP vision hidden-states regression and a missing load-balancing loss are unrelated." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "A stale num_return_sequences warning and Whisper align_special_tokens failure are different generation bugs." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "GPU broadcast NoneType handling and token-embedding resize reinitialization are unrelated." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Chunked-generation inconsistency with compiled forward and Gemma eos_token_id mismatch are not the same bug." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "SAM3 dummy Conv2d and OmDet-Turbo processor/model size mismatch are different vision-model issues." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "A Janus image-generation test failure and a Qwen3.5 flash-attention generation bug are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Qwen video-input regression and serve KV-cache continuation crash are distinct regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 30, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:35141", + "issue:39692", + "issue:41720", + "issue:42490", + "issue:43335", + "issue:43388", + "issue:43540", + "issue:43550", + "issue:43582", + "issue:43644", + "issue:43650", + "issue:43827", + "issue:43906", + "issue:43976", + "issue:43994", + "issue:44077", + "issue:44079", + "issue:44112", + "issue:44190", + "issue:44220", + "issue:44462", + "issue:44464", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44734", + "issue:44737", + "issue:44792", + "issue:44855", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:44964", + "issue:45127", + "issue:45245", + "issue:45276", + "issue:45290", + "issue:45357", + "issue:45362", + "issue:45381", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45803", + "issue:45907" + ], + "soft_pairs": [ + "issue:44521|issue:45381", + "issue:43906|issue:45290", + "issue:43827|issue:43994", + "issue:44464|issue:45563", + "issue:44534|issue:44913", + "issue:44190|issue:44964", + "issue:44933|issue:45362", + "issue:41720|issue:45245", + "issue:44792|issue:45600", + "issue:44855|issue:45588", + "issue:44737|issue:45803", + "issue:45127|issue:45357", + "issue:43388|issue:43582", + "issue:35141|issue:42490", + "issue:44462|issue:45907", + "issue:44077|issue:44079", + "issue:44938|issue:45542", + "issue:43335|issue:44855", + "issue:43550|issue:44190", + "issue:43976|issue:44855", + "issue:43644|issue:44913", + "issue:43540|issue:44734", + "issue:44112|issue:45600", + "issue:43650|issue:44220", + "issue:44496|issue:45803", + "issue:43335|issue:44190", + "issue:45276|issue:45584", + "issue:39692|issue:44190", + "issue:45245|issue:45584" + ], + "prepared_review_unit_hash": "7638ebc92705cea9ef77496ffc819edcd8892c59cfc3d743e30af37b43eaa4b4", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35918, + "estimated_input_tokens": 8980, + "estimated_eval_tokens": 18216 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated bug reports; none of the suggested soft pairs are true duplicates. The only loosely related subgroup is around token-embedding resize/output-embedding behavior, but even there the evidence is not strong enough to merge the other pairs.", + "confidence": 0.94, + "canonical_issue_reason": "issue:35141 is the best anchor for the only coherent subgroup here: it states the underlying resize_token_embeddings/post_init bug in general terms, while the other embedding-related report is a model-specific variant.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:35141 is the strongest issue to keep as the representative bug report because it describes a concrete code-path regression with a clear root cause and broader applicability than the more model-specific variants.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal-related, but one is about all-zero assistant masks in apply_chat_template while the other is about wrong vision_position_ids for Qwen2.5-VL video input; different failures and likely different fixes." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "The first is an isolated reproduction of an older issue, while the second is a crash with tool-call assistant messages; they do not describe the same bug." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() and SigLIP2 producing bad outputs are unrelated problems." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Chunked generation inconsistencies with compiled forward and a stale paged-generate warning are different generation issues." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer junk and GPTNeoX rotary_pct reload behavior affect different code paths." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Dataset-loading failure in an example script and a model config/load failure for Phi-4 multimodal instruct are not the same bug." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "A missing import from image_utils is unrelated to Qwen3.5 chat crashes." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Auto device mapping on Qwen3 and a categories-limit RuntimeError are different failures." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "A Janus generation test failure and stale auto_mappings references to removed configs do not share the same underlying defect." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 import parsing failure in DebertaV2 and a flash_attention crash on s_aux=None are unrelated." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "CPU placement in XLNet relative positional encoding and a bare except swallowing errors in FuyuBatchFeature are different bugs." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge collapse with extended vocabulary and incorrect visual encoder keys in save_pretrained are not the same code-path issue." + }, + { + "left": "issue:43388", + "right": "issue:43582", + "accept": false, + "reason": "A last-batch label handling bug and an Apple Silicon TypeError in caching_allocator_warmup are unrelated." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "resize_token_embeddings/post_init behavior and a trailing-slash import warning are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json and list_repo_files not forwarding revision target different repository/file-resolution paths." + }, + { + "left": "issue:44077", + "right": "issue:44079", + "accept": false, + "reason": "patchtsmixer post_init policy and ModelOutput key assignment with None are different issues." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 load failure and a tf-backend warning when only tensorboard is installed are separate compatibility problems." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and DebertaV2 import parsing are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba and a local dataset-loading example failure are not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python version support mismatch and DebertaV2 import parsing under Python 3.13 are different compatibility failures." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer initialization junk and GPTNeoX rotary_pct reload are separate state-loading issues." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Qwen3OmniMoe video processing ValueError and KV-cache continuation tensor indexing are different runtime failures." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "A stale CI test in GraniteSpeech and broken auto_mappings entries for removed configs are unrelated maintenance issues." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "The placeholder issue and the _torch_extract_fbank_features bug are not duplicates." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "Unrecognized model loading via missing model_type and a bare-except bug in FuyuBatchFeature are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers sparse-layer behavior and local dataset loading in an example script are unrelated." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 resize_token_embeddings/output_embeddings behavior and Whisper 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": 1, + "component_count": 17, + "review_unit_index": 31, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:42490", + "issue:42907", + "issue:43065", + "issue:43295", + "issue:43299", + "issue:43404", + "issue:43441", + "issue:43479", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43673", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44112", + "issue:44186", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44336", + "issue:44466", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44913", + "issue:44933", + "issue:44964", + "issue:44987", + "issue:45003", + "issue:45042", + "issue:45216", + "issue:45276", + "issue:45335", + "issue:45375", + "issue:45446", + "issue:45600", + "issue:45632" + ], + "soft_pairs": [ + "issue:41950|issue:44016", + "issue:43479|issue:45375", + "issue:43295|issue:45276", + "issue:36246|issue:41628", + "issue:36246|issue:38617", + "issue:44186|issue:44734", + "issue:38175|issue:43065", + "issue:44683|issue:45446", + "issue:42175|issue:44279", + "issue:44016|issue:44220", + "issue:44466|issue:44913", + "issue:43404|issue:45216", + "issue:44561|issue:45632", + "issue:44734|issue:45632", + "issue:44246|issue:45003", + "issue:42490|issue:45632", + "issue:43643|issue:44496", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:42907|issue:43441", + "issue:43854|issue:44964", + "issue:44016|issue:44062", + "issue:43976|issue:44987", + "issue:43295|issue:45335", + "issue:43673|issue:44336", + "issue:43531|issue:45600", + "issue:43824|issue:44933", + "issue:44496|issue:45042", + "issue:43526|issue:43901", + "issue:43299|issue:45216" + ], + "prepared_review_unit_hash": "06324f74e335087e67daa6dc63a556e7384fc527dde3e2c5b1b69571dff62c4e", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36738, + "estimated_input_tokens": 9185, + "estimated_eval_tokens": 18626 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are largely heterogeneous; none of the soft pairs look like the same underlying bug or change, so I would not collapse any of them as duplicates. If a representative issue must be chosen, issue 43824 is the strongest anchor because it is a concrete import regression with the most external signal.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43824 is the best canonical anchor: it has the clearest, concrete failure mode (missing top-level import) and the strongest signal (multiple inbound refs and active discussion), making it more representative than the others.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43824 is the most actionable and well-evidenced issue in the set; the rest are scattered across unrelated models, config fields, pipelines, and regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Video-classification pipeline lookup bug vs notebook syntax error; unrelated symptoms and code paths." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Both involve multimodal config handling, but they target different models and different bugs (default config init vs strict field dropping)." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Different regressions: processor/tokenizer image handling vs resize_token_embeddings not updating Gemma4 embeddings." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different exported symbols and different breakages." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Unrelated import failures: Qwen2.5 VL image processor vs layer_type_validation." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Different failures in different subsystems: tokenizer padding/NER vs serving KV-cache continuation indexing." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Siglip2 zero-probabilities issue and Sam3PixelDecoder dummy Conv2d are unrelated model bugs." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both touch flex_attention/PyTorch gating, but one is a compile/runtime failure on torch>=2.9 and the other is an incorrect version check for an import path." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Dependency installation issue vs vague dependency issue; no shared concrete code-path or fix." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error vs _torch_extract_fbank_features failure; unrelated." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Both concern serialization/reload, but one is tied lm_head weights and the other is a GPTNeoXConfig field reset." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Different model families and different bugs: Mistral3 weight tying vs Qwen3.5 checkpoint save regression." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Both involve trust_remote_code, but one is a removed API breakage and the other is a local-model cache-path collision." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serving KV-cache continuation crash vs trust_remote_code cache collision; different mechanisms and fixes." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import performance issue vs unsafe sys.modules access; not the same bug." + }, + { + "left": "issue:42490", + "right": "issue:45632", + "accept": false, + "reason": "Both are local path handling problems, but one is a trailing-slash warning and the other is a cache collision between leaf-name matches." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Both are config/loading failures, but one is trust_remote_code missing fields and the other is an unrecognized model/type key problem." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Different model-loading/CI failures with no shared code-path." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI test flake in GraniteSpeech vs Phi-4 multimodal loading regression; unrelated." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Both mention Ministral/Devstral, but save-dequantized failure and FlashAttention failure are distinct bugs." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Different model load failures affecting different model families and failure points." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error vs AddedToken keyword-argument TypeError; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python-version compatibility issue vs a specific model-loading failure; not the same underlying defect." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Different embedding-update regressions in different models; not mergeable as one fix." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache bug vs ANSI formatting in loading_report; unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior vs stale auto_mappings references; different areas and fixes." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but one is a missing model class export and the other is a missing image_utils export; different symbols and root causes." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model/config issue vs PIL image processors incorrectly requiring torchvision; unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs documentation drift for return_all_scores; not the same issue." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both are version regressions for model loading/saving, but they affect different Qwen variants and different code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 32, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:33290", + "issue:38175", + "issue:39692", + "issue:41950", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43577", + "issue:43650", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44075", + "issue:44242", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44351", + "issue:44368", + "issue:44462", + "issue:44496", + "issue:44521", + "issue:44617", + "issue:44683", + "issue:44779", + "issue:45020", + "issue:45081", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45325", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45584", + "issue:45593", + "issue:45656", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45834", + "issue:45907" + ], + "soft_pairs": [ + "issue:44075|issue:44368", + "issue:45335|issue:45584", + "issue:43976|issue:44279", + "issue:43381|issue:45593", + "issue:43299|issue:45357", + "issue:43901|issue:44496", + "issue:44496|issue:45759", + "issue:44521|issue:45325", + "issue:41950|issue:45020", + "issue:44351|issue:45278", + "issue:43976|issue:45405", + "issue:44242|issue:45200", + "issue:43479|issue:43525", + "issue:44779|issue:45812", + "issue:41950|issue:45823", + "issue:43577|issue:45216", + "issue:44683|issue:45542", + "issue:38175|issue:44617", + "issue:39692|issue:43901", + "issue:43299|issue:43854", + "issue:44279|issue:45405", + "issue:41950|issue:43650", + "issue:43295|issue:44779", + "issue:44462|issue:45081", + "issue:44297|issue:44462", + "issue:45081|issue:45907", + "issue:44016|issue:44291", + "issue:43441|issue:45834", + "issue:33290|issue:45656" + ], + "prepared_review_unit_hash": "0a634433dd61ed2343f10287f8d37e82bee7123eafe43d635d84b633ab24be8f", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35828, + "estimated_input_tokens": 8957, + "estimated_eval_tokens": 18170 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous rather than duplicate-heavy: it mixes unrelated Transformers issues spanning tokenizers, multimodal configs, pipelines, docs, DeepSpeed/optimizer behavior, and model-loading regressions. None of the soft edges looks like the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue: the cluster spans unrelated bugs/regressions across tokenizers, multimodal configs, pipelines, docs, and DeepSpeed/optimizer behavior.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue cleanly serves as an umbrella; the broadest report (#45020) is still too general to represent the rest of the items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Optimizer-arg handling is unrelated to the tie_word_embeddings warning; different symptoms and code paths." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "resize_token_embeddings on t5gemma decoder is unrelated to Whisper empty-transcription failure after align_special_tokens." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python-version compatibility and a generic dependency issue are not the same defect." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to D-FINE auxiliary-loss behavior when denoising is off." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Model loading regression and save_pretrained key regression affect different code paths." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to an unrecognized-model/config loading error." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "One is config/model recognition failure; the other is from_config failing to unwrap text_config in multimodal configs." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "All-zero assistant masks and rope-index scaling are distinct multimodal internals." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "A pipeline processor lookup bug is not the same as a broad remote_code compatibility regression." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "Missing HybridCache import and broad import errors after upgrade are not a single concrete bug." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python support breakage is unrelated to the PEFT minimum-version bump." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Missing load-balancing loss and default mm_token_type_ids are separate modeling issues." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Default multimodal config initialization is unrelated to Llama4Config missing pad_token_id." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but for different model families and failure modes; no evidence of one shared bug." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video pipeline processor lookup and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "Blip2 dtype propagation and Qwen3.5 save_pretrained corruption are different bugs." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "torch>=2.9 flex_attention failure is unrelated to the tensorboard/TensorFlow backend error." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero-probability outputs and Sam3Video OOM are clearly different model-specific problems." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Both involve docs, but they concern different APIs and unrelated fixes." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3VL loading breakage and GLM-4.7-Flash unit-test loading failures are different models and code paths." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A dependency issue and a PEFT version requirement bump are not the same defect." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "The video-classification processor bug is unrelated to the placeholder 'ADD THE DATA' issue." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Processor/tokenizer regression in v4.57.5 is unrelated to DeepSeek tokenizer output changes in v5." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json and Mistral regex patch crashes are different tokenizer bugs." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch is separate from AutoTokenizer ignoring tokenizer.json." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "A tokenizer regex crash and list_repo_files not forwarding revision are unrelated." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error and init_empty_weights argument handling are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "FlashAttention failure in Ministral-3 and long-input OCR index errors in Kosmos2.5 are distinct issues." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "DeepSpeed-related optimizer OOM and optimizer step being called twice are different failure modes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 33, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:42175", + "issue:42994", + "issue:43065", + "issue:43122", + "issue:43262", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43525", + "issue:43643", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43784", + "issue:43824", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44188", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44297", + "issue:44336", + "issue:44361", + "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:45397", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45712", + "issue:45823" + ], + "soft_pairs": [ + "issue:45600|issue:45712", + "issue:43450|issue:44279", + "issue:43065|issue:44898", + "issue:42994|issue:43317", + "issue:44466|issue:45276", + "issue:44261|issue:44263", + "issue:43650|issue:45290", + "issue:44623|issue:45397", + "issue:43441|issue:44683", + "issue:44623|issue:44749", + "issue:43653|issue:45593", + "issue:43262|issue:44521", + "issue:43723|issue:44162", + "issue:44016|issue:45823", + "issue:43673|issue:43761", + "issue:42175|issue:43976", + "issue:44361|issue:45593", + "issue:44671|issue:44779", + "issue:43784|issue:45542", + "issue:43901|issue:43994", + "issue:44987|issue:45542", + "issue:43122|issue:43650", + "issue:43824|issue:43976", + "issue:44297|issue:45397", + "issue:43525|issue:43881", + "issue:44188|issue:44336", + "issue:43525|issue:43643", + "issue:43450|issue:44617" + ], + "prepared_review_unit_hash": "e9a4a570caf81a6c125f97c9b8073c3f1c4adb608c09311853339cc809d9a709", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35940, + "estimated_input_tokens": 8985, + "estimated_eval_tokens": 18226 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the issues share broad Transformers/v5 regression language, but the paired items point to different code paths and failure modes, so I would not deduplicate any soft-edge pair. The strongest representative issue is the open multimodal `apply_chat_template` regression.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44521 is the clearest ongoing, well-documented regression in the set: open, actively discussed, with a concrete repro and multiple references.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the most actionable representative issue in this mixed cluster because it is open and has the richest current discussion/repro context.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both are repo-hygiene/dummy-object problems, but one is stale auto-mapping references and the other is leftover dummy classes; different fixes." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batch shape bug vs a dependency issue; unrelated failure modes." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Both touch vision models, but one is a dummy Conv2d in Sam3PixelDecoder and the other is Perceiver resizing behavior; not the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Both involve quantization/dequantization, but one is save failure and the other is device_map offload load failure; distinct code paths." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "lm_head serialization/tied-weights issue vs Gemma4 embedding resize propagation; different underlying problems." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "MLA layernorm epsilon precision issue vs torch.split return handling in GlmMoeDsaIndexer; unrelated." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "Generic placeholder issue vs a specific tool-call assistant message crash in apply_chat_template; no same bug." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing processor save files vs Gemma-4 ZeRO-3 from_pretrained loading; different symptoms and paths." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Model-specific FlashAttention failure vs compiled flex_attention failure on torch>=2.9; not the same fix target." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Processor save_pretrained missing files vs a severe data filtering slowdown; unrelated." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug vs D-FINE auxiliary-loss behavior; different subsystems." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant masks; distinct bugs." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer loading regression vs ESM2 model breakage; no shared concrete code path." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error vs Gemma4 device-mismatch runtime bug; unrelated." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache/chunked_prefill issue vs CLIPVision hidden_states regression; different components." + }, + { + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "Packaging/backend dependency problem vs Python version compatibility issue; separate causes." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer task AttributeError vs D-FINE auxiliary-loss logic; unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Both are v5 regressions affecting outputs, but one is masked LM predictions and the other is tokenizer correctness; not the same underlying bug." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "sentence-transformers import NameError vs missing TensorFlow backend due to only tensorboard installed; different root causes." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores vs a bad model/pipeline output regression; not duplicates." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Specific model loading failure vs TensorFlow backend installation problem; unrelated." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenizer version regression vs a placeholder/data request issue; no overlap in bug." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Missing exported class import vs Python 3.9+ compatibility problem; different issues." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save metadata mismatch vs Gemma-4 zero3 loading failure; distinct behavior." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config vs glm-4v-9b loading failure; not the same concrete defect." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "torch.compile attention-branch divergence vs ANSI code emission in loading_report; unrelated." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "The latter is a general missing-fields issue with trust_remote_code, but the former is a specific Llama4Config attribute absence; too weak to merge as one bug." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Batched video shape bug vs CUDA OOM in Sam3Video; different failure modes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 34, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:43065", + "issue:43232", + "issue:43299", + "issue:43352", + "issue:43408", + "issue:43526", + "issue:43531", + "issue:43596", + "issue:43673", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44373", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44589", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44987", + "issue:45003", + "issue:45200", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45593", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:43901|issue:44246", + "issue:45561|issue:45563", + "issue:42491|issue:43299", + "issue:44336|issue:44373", + "issue:44242|issue:45593", + "issue:44295|issue:45397", + "issue:41950|issue:44220", + "issue:44246|issue:44496", + "issue:43531|issue:45362", + "issue:43352|issue:45250", + "issue:36246|issue:42757", + "issue:43526|issue:45003", + "issue:36246|issue:44351", + "issue:44336|issue:44485", + "issue:45003|issue:45561", + "issue:43673|issue:44561", + "issue:44246|issue:44871", + "issue:44242|issue:44857", + "issue:44162|issue:45200", + "issue:44295|issue:44749", + "issue:36246|issue:43596", + "issue:44877|issue:45375", + "issue:44779|issue:45292", + "issue:45292|issue:45584", + "issue:43901|issue:45003", + "issue:45292|issue:45701", + "issue:43232|issue:44336", + "issue:44987|issue:45459", + "issue:43065|issue:43408", + "issue:44496|issue:45003", + "issue:45375|issue:45759" + ], + "prepared_review_unit_hash": "1ed288d19888d5534e09e7dc41e84d48d4a0d1010a630bdd555692f00a1a02ef", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37278, + "estimated_input_tokens": 9320, + "estimated_eval_tokens": 18896 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly loosely related Transformers issues, but the suggested soft pairs are not true duplicates: they mix different models, different code paths, or unrelated docs/perf/config problems.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43299 is the most concrete version-regression model-loading report in the set, so it works best as a representative anchor; the rest are mostly separate bugs rather than one duplicate thread.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43299 has a clear reproduction scope and a specific failing path (Qwen3VL MoE loading on v5.0.0.dev0), making it the strongest single issue to triage from this mixed cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Different failures: float8 storage lookup vs a Qwen3.5 chat crash." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Import error for AutoImageProcessor vs a Python-version compatibility problem." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs mismatch in a pipeline vs slow package import; unrelated code paths." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "pytest-xdist file race vs a stale generation warning; no shared bug." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen/MoE, but they are different model families and different load failures." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI output in loading_report vs a wrong docstring; not the same issue." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Different loss-missing bugs in different models and settings." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Position_ids buffer access vs Gemma-4 Zero3 loading; unrelated." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video pipeline image-processor lookup vs audio fbank feature extraction; different subsystems." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import latency vs unrecognized model/config loading; not duplicates." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Different Qwen bugs: sliding window behavior vs a chat crash." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Specific Nemotron Flash Attention support bug vs a generic Flash Attention issue." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Different missing-symbol imports from different packages." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BeitImageProcessorFast label reduction vs sys.modules access in modeling_utils." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different exported symbols and different failure modes." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "Terminal ANSI leakage vs GLM-5 RoPE implementation; unrelated." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Unsafe sys.modules access vs a test-file race condition; different bugs." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Generation cache handling vs removal of an import helper for trust_remote_code models." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Slow import vs inconsistent eos_token_id config; unrelated." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Missing load-balancing loss vs a float16 CUDA loss crash; not the same code path." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage vs Gemma-4 token-type defaults; different models and fixes." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Buffer registration error vs a tokenizer/filtering slowdown after upgrade." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "ImportError on Qwen image processor vs a zero3/BertModel IndexError." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Strict config loading granite_speech vs missing deepstack_visual_indexes in Qwen vision config." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer output regression vs resize_token_embeddings not updating output embeddings." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize bug vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Pipeline docs mismatch vs unsafe sys.modules access; no overlap." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Embedding resize/output mismatch vs version-dependent tokenization changes." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwarg update bug vs terminal ANSI output in loading_report." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure on v5.1.0 vs tokenizer error masking when protobuf is missing." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Dummy conv in Sam3PixelDecoder vs a model-type mismatch warning for sam3_video/sam3_tracker." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Config/model-type resolution failure vs unsafe sys.modules access; distinct problems." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Missing strict field in a Qwen vision config vs AutoModelForCausalLM not unwrapping text_config; related domain but different concrete bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 35, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:42371", + "issue:42886", + "issue:42994", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43475", + "issue:43482", + "issue:43540", + "issue:43643", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43931", + "issue:44038", + "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:45092", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45230", + "issue:45278", + "issue:45310", + "issue:45335", + "issue:45356", + "issue:45381", + "issue:45397", + "issue:45459", + "issue:45563", + "issue:45588", + "issue:45600", + "issue:45656" + ], + "soft_pairs": [ + "issue:42886|issue:45229", + "issue:43257|issue:45137", + "issue:43262|issue:44246", + "issue:44995|issue:45200", + "issue:43475|issue:43540", + "issue:44060|issue:44077", + "issue:44466|issue:45335", + "issue:43653|issue:44162", + "issue:45397|issue:45656", + "issue:44995|issue:45588", + "issue:44368|issue:45563", + "issue:44368|issue:44977", + "issue:43673|issue:44734", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44933|issue:45459", + "issue:44869|issue:45356", + "issue:44297|issue:44623", + "issue:43232|issue:43673", + "issue:44361|issue:44749", + "issue:43646|issue:44162", + "issue:43673|issue:45278", + "issue:44623|issue:45656", + "issue:44749|issue:45656", + "issue:44749|issue:45310", + "issue:42994|issue:43482", + "issue:28282|issue:30990", + "issue:45230|issue:45397", + "issue:42371|issue:45092", + "issue:43475|issue:43643", + "issue:44038|issue:44623", + "issue:43475|issue:45381" + ], + "prepared_review_unit_hash": "b99a8b016c653fb8a6af484cfad62016b4495c0fb83f4d55adb645fc70a44571", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37146, + "estimated_input_tokens": 9287, + "estimated_eval_tokens": 18830 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: loading/import errors, generation-cache bugs, tokenizer/processor save issues, multimodal model-specific failures, and unrelated deepspeed/CI regressions. I don\u2019t see a single duplicate family here, so all soft-edge pairs should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache loading and Gemma 4 multi-GPU OOM are unrelated failure modes." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed is not the same bug as the ZeRO3 deque IndexError." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio processor sample-rate defaulting and slow import are different subsystems and symptoms." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "GlmMoeDsa stale indexer cache is unrelated to Gemma 4 mm_token_type_ids defaults." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Both are multimodal, but SAM3 encoder attribute failure and Qwen3OmniMoe video-processing ValueError are different code paths." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Incorrect tied-weights warning and patchtsmixer post_init policy are unrelated model/config issues." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both mention tied embeddings, but one is serialization inconsistency and the other is resize_token_embeddings not updating decoder embeddings." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and ESM2 breakage are unrelated." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 Zero3 from_pretrained failure is not the same as deepspeed calling optimizer.step twice." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale indexer cache in GlmMoeDsa and flash_attention.py crashing on s_aux=None are separate bugs." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "A tied-word-embeddings warning in ms-swift fine-tuning is unrelated to paged generate() warning behavior." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3.5 tied-embedding warning and flash-attention generation failure do not share the same underlying defect." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation/cache, but chunked_prefill cache handling and /v1/responses continuation indexing are different code paths." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "ZeRO3 deque underflow and auto_mappings references to removed Sam3LiteText configs are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and Qwen3.5 tied-embeddings warning are different model initialization problems." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Missing image_utils import and protobuf-decode-error handling are different import/error-reporting bugs." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper word-timestamp crash and Kimi-K2.5 tokenizer codec regression are both tokenizer-related but not the same bug." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Tokenizer save_pretrained writes the wrong tokenizer_class, while processor.save_pretrained is missing files; these are distinct save-path issues." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "sync_gpus generation-kwargs update and missing GenerationMixin cache in chunked_prefill are separate generation bugs." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and a data-filtering slowdown after upgrade are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Transformers 5 custom model init breakage and ESM2 breakage are different model-loading failures." + }, + { + "left": "issue:43673", + "right": "issue:45278", + "accept": false, + "reason": "A generation cache bug and broad import errors after upgrade are not the same underlying issue." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Processor save_pretrained missing files is unrelated to deepspeed double optimizer stepping." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Performance regression in filtering does not match a deepspeed optimizer-step duplication bug." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "The filtering slowdown and Qwen3.5 MoE from_pretrained error are separate issues." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are opposite directions and different formats." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch-missing AutoModel ImportError and Sentence Transformers loading hang are not the same bug." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "A generic bug report cannot be merged with a specific Gemma-4 Zero3 from_pretrained failure." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 configuration guidance and InternVL2 meta-initialization incompatibility are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "SAM3 video encoder missing attribute and trust_remote_code AutoConfig field loss are different failures." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe transformers v5 bug and processor.save_pretrained missing files are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "SAM3 Video missing fpn_position_embeddings and Qwen2.5-VL wrong vision_position_ids are separate video-model bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 36, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:30990", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43377", + "issue:43475", + "issue:43479", + "issue:43504", + "issue:43525", + "issue:43526", + "issue:43673", + "issue:43704", + "issue:43873", + "issue:43976", + "issue:44038", + "issue:44079", + "issue:44164", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44792", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:45081", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45375", + "issue:45478", + "issue:45561", + "issue:45712", + "issue:45753" + ], + "soft_pairs": [ + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:43475|issue:44661", + "issue:42994|issue:43525", + "issue:45375|issue:45478", + "issue:43232|issue:44188", + "issue:42673|issue:43704", + "issue:45310|issue:45375", + "issue:43873|issue:44945", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:44945|issue:45753", + "issue:44222|issue:45310", + "issue:43673|issue:44188", + "issue:36010|issue:41628", + "issue:42994|issue:44164", + "issue:42222|issue:45200", + "issue:42175|issue:45712", + "issue:43232|issue:44792", + "issue:44038|issue:45310", + "issue:43526|issue:45561", + "issue:43504|issue:45561", + "issue:44496|issue:45561", + "issue:43377|issue:44242", + "issue:44964|issue:45137", + "issue:42175|issue:44933", + "issue:42898|issue:44568", + "issue:30990|issue:35141", + "issue:43976|issue:44933", + "issue:43479|issue:44869", + "issue:43479|issue:44079", + "issue:44623|issue:45310" + ], + "prepared_review_unit_hash": "7957d1c363d0912b679721c9d5578077f12198ad39f70297c1fdc3ac73dbfcec", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36576, + "estimated_input_tokens": 9144, + "estimated_eval_tokens": 18544 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous and does not contain any true duplicate pairs. The strongest apparent overlaps are superficial topical similarities around import regressions, Qwen/MoE loading, and save/load behavior, but each points to a different code path.", + "confidence": 0.74, + "canonical_issue_reason": "issue:41628 is the clearest representative of the import/export regression mini-theme and the most broadly phrased among the similar-looking issues, even though the cluster overall is not a single duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41628 is the best single anchor for triage because it is concrete, library-wide, and sits closest to the other import-related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import failures, but they target different missing exports/modules (`AutoImageProcessor` vs `image_utils`) and likely different fixes." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Different failure modes: Mistral regex patching vs auto-docstring annotation handling." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "SAM3 vision output attribute breakage vs tokenizer-mapping/model-registration logic; not the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving failure and `Llama4Config.pad_token_id` are separate config/persistence problems." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same model family, but one is a missing config field and the other is a `from_pretrained` loading regression; different underlying issues." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "One is generation kwargs handling after `sync_gpus`; the other is attention-kernel branching under `torch.compile`." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": false, + "reason": "Same title, but the reports are separate instances and there is no evidence they are the same concrete leak." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "`from_pretrained` error for Qwen3.5 MoE vs missing `deepstack_visual_indexes` config field; not one fix." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization/offloading behavior and pipeline-parallelism output correctness are unrelated code paths." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols (`AutoImageProcessor` vs `HybridCache`) and likely different export points." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "FP8 accuracy regression vs FP8 save/pretrained failure; one is numerical correctness, the other serialization." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline parallelism output mismatch vs Qwen3_5 image infinite loop; unrelated behaviors." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5/MoE, but one is FP8 saving and the other is loading via `from_pretrained`; different bugs." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Chunked-prefill cache handling vs compile-time attention-kernel branching are distinct generation internals." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import-related, but the missing symbol and module path differ (`GenerationMixin` vs `AutoImageProcessor`)." + }, + { + "left": "issue:42994", + "right": "issue:44164", + "accept": false, + "reason": "Quantized saving failure and `extra_state` handling in save/from_pretrained are separate persistence bugs." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Different model families and different fixes: ViTPose breakage vs Gemma 4 multimodal token-type defaults." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Packaging/backend dependency issue vs dummy class cleanup in repo checks; unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs update bug vs Janus image-generation test failure; different models and paths." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Related Qwen/MoE family, but one is Qwen3-VL-Moe loading and the other is Qwen3.5 MoE `from_pretrained`; not the same concrete bug." + }, + { + "left": "issue:43526", + "right": "issue:45561", + "accept": false, + "reason": "Beit image processor label reduction vs pytest-xdist file race; unrelated subsystems." + }, + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "Legacy-field pretrained loading vs pytest-xdist race; no shared code path." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized-model/config loading failure vs testing-utils race condition; unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "MIMI padding-mask discrepancy vs MoE load-balancing loss omission; different model components." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Phi-4 multimodal loading issue vs DeepSpeed ZeRO3 deque error; unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Tensorflow extra/backend packaging issue vs nonexistent import from `image_utils`; unrelated." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer cleanup behavior change vs BOS/EOS special-token insertion bug; distinct tokenization behaviors." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence Transformers loading hang vs embedding resize/reinit bug; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python-version compatibility problem vs image_utils import failure; unrelated." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Phi4 multimodal default-config initialization vs Whisper timestamp decode crash; different subsystems." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Default multimodal config init vs `ModelOutput` key assignment semantics; unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Processor save_pretrained missing files vs Qwen3.5 MoE loading error; persistence vs loading bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 37, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30333", + "issue:33290", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43116", + "issue:43232", + "issue:43278", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:44060", + "issue:44188", + "issue:44190", + "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:44933", + "issue:44977", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45310", + "issue:45356", + "issue:45405", + "issue:45656", + "issue:45712", + "issue:45812", + "issue:45834" + ], + "soft_pairs": [ + "issue:43784|issue:43824", + "issue:44188|issue:44373", + "issue:42898|issue:45812", + "issue:43278|issue:45137", + "issue:44734|issue:45103", + "issue:30333|issue:33290", + "issue:43723|issue:44568", + "issue:43874|issue:45092", + "issue:42898|issue:45356", + "issue:44060|issue:45125", + "issue:42898|issue:44779", + "issue:45405|issue:45712", + "issue:42898|issue:44448", + "issue:44295|issue:45656", + "issue:44933|issue:45712", + "issue:44222|issue:44297", + "issue:44297|issue:45656", + "issue:43116|issue:44190", + "issue:43479|issue:43644", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:44206|issue:45103", + "issue:41628|issue:42757", + "issue:22355|issue:28282", + "issue:30333|issue:36331", + "issue:44297|issue:45310", + "issue:30333|issue:34689", + "issue:44222|issue:44484", + "issue:43232|issue:45834", + "issue:43723|issue:44977", + "issue:28282|issue:30333", + "issue:44263|issue:45092", + "issue:30333|issue:35141" + ], + "prepared_review_unit_hash": "337840a5810e4c271382568acc62e5505032ce82763fc387c9fd450a30dd46c3", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37572, + "estimated_input_tokens": 9393, + "estimated_eval_tokens": 19042 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of Transformers issues with superficial overlap around tokenizer/regression reports; none of the soft pairs look like the same underlying bug or change, so no duplicate merges are warranted.", + "confidence": 0.43, + "canonical_issue_reason": "issue:42898 is the closest representative of the recurring v5 tokenizer-regression theme and has the broadest, most explicit behavioral description among the set, though it is not a duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42898 is the strongest standalone issue to anchor the cluster because it describes a concrete, versioned tokenizer behavior change and is central to the small tokenizer-related subtheme here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import failures in unrelated packages/models: sentence-transformers import vs missing Qwen2_5_VL class." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "One is a torch.compile attention-kernel divergence; the other is a docstring mismatch for position_ids." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenization regressions, but one is about clean_up_tokenization_spaces behavior and the other about Granite token IDs; different bugs/code paths." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift in evaluation vs a DeepSpeed ZeRO3 deque error are unrelated failures." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "KV-cache indexing crash in serving is unrelated to auto_docstring annotation handling." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on training failure and adafactor OOM in deepspeed are different training problems." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but one is a generic from_pretrained loading issue and the other is add_special_tokens/BOS-EOS behavior." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing image patch count in a fast image processor is not the same bug as remote-code checkpoint/meta-init incompatibility." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but the specific failures differ: whitespace cleanup behavior vs codec/fix_mistral_regex handling." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Incorrect tied-weights warning for Qwen3-Next is unrelated to Qwen3_5Moe missing _tp_plan." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both mention tokenizer regressions, but Deepseek tokenization output mismatch is a different concrete issue than clean_up_tokenization_spaces." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "A dependency-version bump and leftover dummy classes failing repo checks are unrelated." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Pegasus output drift across v4/v5 is a generation/model-output regression, not the same as clean_up_tokenization_spaces." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "A position_ids buffer-reading error and a double optimizer-step issue with DeepSpeed are different failure modes." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Missing import from image_utils is unrelated to dummy classes leaking into dir(transformers)." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "Both involve save_pretrained, but one is FP8 MoE serialization and the other is tokenizer config metadata; not the same bug." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer config mismatch has no relation to DeepSpeed calling optimizer.step twice." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Example-script multi-label classification output bug and local dataset loading failure are different script-level issues." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Bad default multimodal config initialization is not the same as non-persistent buffers being filled with junk." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Both are save_pretrained-related, but they affect different objects and different serialization outputs." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FineGrainedFP8 accuracy degradation is unrelated to processor save_pretrained missing files." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature extractor center-arg regression and auto_docstring annotation crash do not share a code path." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Different missing imports from different packages: transformers vs huggingface_hub." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Missing transformers.onnx module and missing PyTorch dependency are separate environment/import problems." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLflow reporting on failure and Trainer.compute_loss signature breakage are unrelated trainer issues." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer save metadata mismatch is not the same as Qwen3.5 MoE from_pretrained load failure." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "Failed MLflow reporting and Llama 3.2 Vision model loading regression are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE save_pretrained bug and max_shard_size default question are different save_pretrained concerns." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to long-ocr-input index errors in Kosmos2.5." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Generic tokenizer loading issues and Qwen3.5 flash-attention generation failures are different problems." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "AutoModel missing PyTorch and MLflow-not-reported-on-failure are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "torch.split return handling in a MoE indexer is unrelated to meta-initialization incompatibility." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "MLflow reporting on failed training and embedding reinitialization during resize are distinct bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 38, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:30990", + "issue:33357", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42994", + "issue:43066", + "issue:43122", + "issue:43232", + "issue:43479", + "issue:43576", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44521", + "issue:44568", + "issue:44623", + "issue:44704", + "issue:44871", + "issue:44913", + "issue:44991", + "issue:45092", + "issue:45103", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45593", + "issue:45753" + ], + "soft_pairs": [ + "issue:44483|issue:45406", + "issue:44263|issue:44360", + "issue:44373|issue:44485", + "issue:44295|issue:44623", + "issue:44514|issue:45103", + "issue:44261|issue:45092", + "issue:45092|issue:45357", + "issue:43723|issue:44871", + "issue:43723|issue:44991", + "issue:30990|issue:38175", + "issue:43723|issue:44442", + "issue:41628|issue:43824", + "issue:43479|issue:44913", + "issue:42831|issue:45310", + "issue:44263|issue:44373", + "issue:39401|issue:44568", + "issue:42831|issue:44038", + "issue:42757|issue:45278", + "issue:42886|issue:42994", + "issue:43232|issue:45593", + "issue:43756|issue:44060", + "issue:43576|issue:43784", + "issue:42831|issue:45753", + "issue:42886|issue:43066", + "issue:43122|issue:44521", + "issue:42371|issue:44263", + "issue:22355|issue:28218", + "issue:44117|issue:44704", + "issue:30990|issue:33357" + ], + "prepared_review_unit_hash": "26b759fa9f72b604900b7dbc09793524144ce3820d4e67ca39562d3753991247", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 35994, + "estimated_input_tokens": 8999, + "estimated_eval_tokens": 18254 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a grab-bag of unrelated Transformers regression reports; the only strong common thread is tokenizer/loading-related breakage, but the pairs are still too specific to merge together confidently.", + "confidence": 0.68, + "canonical_issue_reason": "issue:43723 is the broadest and most representative user-facing regression here, centered on tokenizer loading via AutoTokenizer.from_pretrained in v5.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43723 is the best anchor for this cluster because it is generic, high-signal, and closest to several tokenizer-related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Different failures and code paths: chat/completions request validation vs Gemma4Processor missing _tokenizer in transformers serve." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA, but one is about torch.split return values and the other about a missing ReLU in the indexer; not the same bug." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Docstring/position_ids documentation issue vs GLM-5 RoPE implementation bug; unrelated symptoms." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Registering position_ids as a buffer causing read errors is unrelated to processor.save_pretrained missing files." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "apply_chat_template batching crash is unrelated to auto_docstring failing under future annotations." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "Layer norm epsilon precision mismatch is not the same as old InternVL2 remote-code checkpoints failing meta initialization." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Different multimodal Qwen/InternVL save/load problems; one is meta-init incompatibility, the other is wrong visual encoder keys on save." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Both are tokenizer-related, but one is generic loading failure and the other is eos_token_id config inconsistency for a specific model." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": false, + "reason": "Both involve AutoTokenizer loading, but the affected models and failure mode are not shown to be the same bug." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence Transformers loading hang and SigLIP2 zero probabilities are different model/runtime issues." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "FastSpeech2ConformerTokenizer load failure is a separate model-specific tokenizer issue, not clearly the same as the v5 AutoTokenizer regression." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Import errors for different symbols do not indicate the same underlying export bug." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Different config bugs: multimodal default config initialization vs GPTNeoX rotary_pct not persisting on reload." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy issues are unrelated to Qwen3.5 MoE from_pretrained errors." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "Different DSA/position_ids problems with no shared concrete code-path." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer offset_mapping regression and missing BOS/EOS insertion are different tokenizer behaviors." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Different problems: FP8 accuracy vs Qwen3-VL-Moe bug in v5." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "A single huggingface_hub import symbol issue is not the same as a broad report of many import errors after upgrade." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading and quantized model saving are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus is unrelated to D-FINE auxiliary-loss behavior." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch and Qwen3-Next tied-weights warning are different model/config issues." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "CLI env command breakage and sentence-transformers import NameError are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FP8 accuracy issues are unrelated to Qwen3_5 infinite-loop behavior on a specific image." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading and wrong tokenizer decoder type are different tokenizer failures." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Different multimodal/tokenization regressions: changed tokenization across versions vs all-zero assistant masks." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 API guidance and a DSA torch.split issue are unrelated." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "onnx import failure and extra space after added token are unrelated issues." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Tokenizer mapping returning None and AutoProcessor not forwarding kwargs to cached_file are separate loader bugs." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Sentence Transformers loading hang and MacOS bus error with CLIP are different failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 39, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:29127", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42907", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43278", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43493", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44222", + "issue:44261", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44360", + "issue:44373", + "issue:44485", + "issue:44488", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44743", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45290", + "issue:45446", + "issue:45478", + "issue:45600", + "issue:45753" + ], + "soft_pairs": [ + "issue:44295|issue:44297", + "issue:43232|issue:44743", + "issue:44704|issue:45290", + "issue:42907|issue:44945", + "issue:43122|issue:44514", + "issue:43976|issue:44945", + "issue:41628|issue:45278", + "issue:39401|issue:44488", + "issue:43784|issue:45600", + "issue:44261|issue:44373", + "issue:43408|issue:43475", + "issue:42907|issue:43937", + "issue:44360|issue:44485", + "issue:44625|issue:44829", + "issue:39401|issue:44521", + "issue:43116|issue:45200", + "issue:44038|issue:44297", + "issue:29127|issue:30990", + "issue:42907|issue:44964", + "issue:43122|issue:44779", + "issue:44038|issue:44295", + "issue:36296|issue:43116", + "issue:42907|issue:43452", + "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:45216|issue:45478", + "issue:42757|issue:44351", + "issue:43278|issue:44945", + "issue:43493|issue:45753", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43992|issue:44704", + "issue:43784|issue:45446" + ], + "prepared_review_unit_hash": "8b1a2a1e18838fa8da6d21b0b8896a7972f98c962a1ae00a2c50ae875afa4ffe", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37225, + "estimated_input_tokens": 9307, + "estimated_eval_tokens": 18870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft pairs look like true duplicates; the set is mostly unrelated issue reports across different models, import paths, tokenizer behavior, and generation bugs. The most central issue is the open multimodal apply_chat_template report with the highest activity and references.", + "confidence": 0.91, + "canonical_issue_reason": "issue:44521 is the most active and referenced report, and it has a concrete, reproducible bug description in a currently open area.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the best cluster anchor because it has the strongest discussion/inbound-reference signal and a clearly scoped user-facing failure mode.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Both are tokenizer/model serialization issues, but one is about reading registered buffer position_ids and the other is about tokenizer_class metadata in tokenizer_config.json; different failure modes and code paths." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/cache state, but one is about _update_model_kwargs_for_generation after sync_gpus and the other about recurrent state reset in modular_qwen3_5.py; not the same bug." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor kwargs forwarding and apply_chat_template crashes with tool-call assistant messages are distinct processor/template bugs." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals and incorrect pipeline-parallel LLM output are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer behavior changes across versions and a batched apply_chat_template padding crash are different issues." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version compatibility is unrelated to pipeline parallelism output corruption." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "A missing AutoImageProcessor import and a broad wave of import errors after upgrade may be thematically similar, but they are not the same concrete broken symbol or code path." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping correctness and failure to load a specific model are different problems." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "sentence-transformers import NameError and stale auto_mappings references to removed configs are separate import-time regressions." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "One is a numerical precision/config issue in MLA q_a_layernorm; the other is a wrong docstring for position_ids." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "A model-type mismatch warning and a missing fpn_position_embeddings attribute in SAM 3 video are not the same defect." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Dequantized save failures and invalid GenerationConfig for GLM-5 are unrelated." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA indexer activation logic and GLM-5 RoPE implementation are entirely different areas." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation in Qwen3.5 config and flash_attention_3 degenerate training are different behaviors." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer offset_mapping correctness and multimodal assistant_masks being all-zero are different apply_chat_template/tokenizer bugs." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Empty multi-label classification outputs in an example script and Gemma 4 mm_token_type_ids defaults are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "A Qwen3-VL-Moe load bug and tokenizer_class mismatch on save are different code paths." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error messaging and Sentence Transformers loading hang are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals and loading Phi-4 multimodal instruct are different model-specific failures." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both concern tokenization regressions, but for different model families and different observable failures." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Qwen3-VL-Moe loading and position_ids buffer access are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training bugs and multi-label classification empty outputs are different domains." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Dequantized save issues and gguf_file failures in from_pretrained are separate loading/saving problems." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Both are missing imports, but they are different symbols from different subsystems and not one shared underlying bug." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe load failure and FP8 save_pretrained for moe are different change points." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5 and newer versions, but one is about save_pretrained checkpoints and the other about from_pretrained loading errors; not the same concrete failure." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Missing is_offline_mode from huggingface_hub and missing HybridCache from transformers are unrelated import errors." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Embedding dtype drift between train/eval and incorrect pipeline-parallel output are different bugs." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 implementation mismatch and Qwen3_5 infinite loop on a specific image are unrelated multimodal problems." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both touch MoE/saving, but one is dequantized model save failure and the other is FP8 save_pretrained behavior; not the same issue." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer differences across versions and Qwen3.5 flash-attention generation failure are separate regressions." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embed_tokens.weight in UMT5Encoder and cached_file kwargs forwarding are unrelated model-loading issues." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "sentence-transformers import NameError and a PyTorch version check bug in flex_attention are different import-time problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 40, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:43064", + "issue:43066", + "issue:43116", + "issue:43421", + "issue:43441", + "issue:43450", + "issue:43493", + "issue:43673", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44291", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44779", + "issue:44936", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", + "issue:45083", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45357", + "issue:45405", + "issue:45446", + "issue:45478", + "issue:45561", + "issue:45563", + "issue:45588" + ], + "soft_pairs": [ + "issue:43066|issue:44779", + "issue:38617|issue:45278", + "issue:42673|issue:45072", + "issue:43937|issue:44485", + "issue:22355|issue:29127", + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:43064|issue:43673", + "issue:43116|issue:43493", + "issue:42222|issue:43441", + "issue:44075|issue:44936", + "issue:43116|issue:43825", + "issue:45357|issue:45478", + "issue:44038|issue:45478", + "issue:43937|issue:45563", + "issue:45083|issue:45446", + "issue:44117|issue:45588", + "issue:33453|issue:39401", + "issue:39401|issue:44779", + "issue:43827|issue:45446", + "issue:43937|issue:44977", + "issue:42673|issue:43906", + "issue:44291|issue:45071", + "issue:43450|issue:43986", + "issue:45405|issue:45446", + "issue:45341|issue:45561", + "issue:44117|issue:45081", + "issue:38617|issue:41628", + "issue:39401|issue:43421", + "issue:44410|issue:45310", + "issue:44484|issue:45310" + ], + "prepared_review_unit_hash": "3b8a61bb52959381db3effb138e257402a71e8dc3ab1e052e1fc8711992f6000", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36739, + "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 not a true duplicate set: the issues span many unrelated bugs (tokenizers, training, vision, imports, docs, version checks). I would not merge any of the proposed soft pairs.", + "confidence": 0.95, + "canonical_issue_reason": "If a single representative is required, issue:45561 is the most concrete and actively discussed report, but the cluster is too heterogeneous for a real canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45561 is the clearest actionable bug report with the strongest current activity, though it should not be treated as a global duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they describe different models and different failure modes; no evidence of the same code-path bug." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "45278 is a broad collection of import errors, while 38617 is one specific missing symbol; too general to be the same issue." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in threaded inference and dtype mismatch in bfloat16 inference are unrelated bugs." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "A GenerationConfig validation error and a RoPE implementation discussion are different problems." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "ONNX import failure and LayoutLMv3 box-validation messaging are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API guidance and a missing image-patch helper are different subsystems and different bugs." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility and a PyTorch version check bug are not the same underlying issue." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Wrong optimizer state handling in FSDP/PEFT and missing GenerationMixin cache in chunked prefill are distinct training/generation bugs." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example-script multi-label output handling and SigLIP2 HF/JAX mismatch are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "VitPose model breakage and Ministral flash-attention failure affect different models and code paths." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "SGD args being ignored and train/evaluate failing after train are different trainer bugs." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "A classification example bug and a pipeline error-message issue are unrelated." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5, but one is save_pretrained key serialization and the other is from_pretrained loading; not the same defect." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen variants and different failure symptoms; too broad to merge as one bug." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig invalidity and a stale warning about num_return_sequences are separate issues." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Feature-extraction length behavior and a version-check import guard are unrelated." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer mapping fallback behavior and a flash-attention crash on s_aux=None are different problems." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Both are tokenizer regressions, but one is loading regression and the other is wrong offset mapping; not the same bug." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Different tokenizer models and different symptoms; similar theme is not enough to treat as duplicates." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Documentation lag around pipeline removal and a PyTorch version check bug are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig validation and flash-attention generation failure are distinct code paths." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "No concrete shared bug is visible; 43906 is only an isolated reproduction of another issue, while 42673 is a VRAM leak report." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument handling and PreTrainedConfig type-checking are separate compatibility regressions." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video processor shape handling and missing torchvision crash are different video-processing issues." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "PEFT minimum-version bump and an AuxRequest PyTorch version check are unrelated." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Both mention testing_utils, but one is a general bug and the other is a specific xdist race; not the same fix." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping assumptions and a Mistral regex patch crash are unrelated tokenizer bugs." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and likely different causes." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Wrong offset mapping and runtime post-processor updates for special tokens are different tokenizer behaviors." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "qwen3next missing projections and Qwen3.5 MoE from_pretrained errors are different model-specific bugs." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "A max_shard_size question and a from_pretrained regression are not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 41, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42490", + "issue:42617", + "issue:42673", + "issue:42831", + "issue:43012", + "issue:43066", + "issue:43097", + "issue:43122", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43577", + "issue:43582", + "issue:43673", + "issue:43742", + "issue:43874", + "issue:43931", + "issue:43937", + "issue:43986", + "issue:44038", + "issue:44075", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44496", + "issue:44829", + "issue:44933", + "issue:45003", + "issue:45071", + "issue:45216", + "issue:45278", + "issue:45341", + "issue:45459", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45656" + ], + "soft_pairs": [ + "issue:44829|issue:45216", + "issue:42371|issue:44261", + "issue:42673|issue:43582", + "issue:43408|issue:43742", + "issue:42617|issue:45341", + "issue:44933|issue:45278", + "issue:42222|issue:45542", + "issue:42490|issue:42673", + "issue:43937|issue:44496", + "issue:42175|issue:42222", + "issue:44483|issue:45464", + "issue:38617|issue:44220", + "issue:42371|issue:42831", + "issue:43066|issue:43122", + "issue:44075|issue:45656", + "issue:43673|issue:45341", + "issue:43012|issue:43577", + "issue:43874|issue:44261", + "issue:44484|issue:45478", + "issue:44410|issue:45478", + "issue:43097|issue:44493", + "issue:44263|issue:44485", + "issue:43012|issue:43408", + "issue:41628|issue:45071", + "issue:42222|issue:45459", + "issue:43441|issue:44829", + "issue:45071|issue:45542", + "issue:43931|issue:44410", + "issue:43335|issue:45071", + "issue:43931|issue:44038", + "issue:45003|issue:45341", + "issue:43097|issue:43452", + "issue:43986|issue:45341" + ], + "prepared_review_unit_hash": "5d5b20b2dd186fe1ac3bebc18bd70b3355b8002ca634968dcaad4a0ff423c170", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37204, + "estimated_input_tokens": 9301, + "estimated_eval_tokens": 18858 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly noisy and heterogeneous: the issues cover unrelated Transformers v5 regressions, model-loading failures, tokenizer changes, backend packaging, and optimizer/runtime bugs. I don\u2019t see any soft pair that looks like the same underlying bug or change.", + "confidence": 0.95, + "canonical_issue_reason": "issue:45278 is the broadest representative item, summarizing a general v5 import-regression theme that overlaps with several other reports more than any single narrow bug does.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best cluster representative because it is the most umbrella-like report and closest to the shared import/regression flavor among otherwise distinct issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "FlashAttention-3 training degeneration and a Qwen3.5 save_pretrained checkpoint regression are different bugs with different failure modes." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API guidance and an MLA rms_norm_eps precision issue are unrelated." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "VRAM leakage across dataloader threads is not the same as an Apple Silicon TypeError in caching_allocator_warmup." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "A sam3 model-type warning and a MobileLLM key error are distinct loading problems." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel.py runtime failure and a testing_utils bug do not share the same underlying issue." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": false, + "reason": "The first is a specific missing import from image_utils; the second is a broad v5 import-regression report." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "A broken vitpose model and a missing-TensorFlow backend packaging issue are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:42673", + "accept": false, + "reason": "Local-path import warning behavior and a VRAM leak in dataloader threads are different code paths." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "Invalid GenerationConfig and unrecognized model/config.json errors are different model-loading failures." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "TensorFlow not being included in a torch extra install is unrelated to vitpose model breakage." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both mention chat/completions, but one is a general request rejection and the other is a streaming-specific Qwen3.5 failure." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "An import error from configuration_utils and an audio feature-extraction issue are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 API behavior and FineGrainedFP8 accuracy are different precision-related problems." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "A wrong tokenizer decoder type and changed tokenization output are related broadly to tokenization, but not the same concrete bug." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "Unused SGD arguments and double optimizer stepping under deepspeed are different optimizer bugs." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "Generation cache missing during chunked_prefill and a testing_utils bug are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "A PyTorch warning during bfloat16 compilation and BLIP2 dtype fields staying float32 are different dtype issues." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "A missing image-patch count method and an rms_norm_eps precision mismatch are unrelated multimodal/model bugs." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "A save_pretrained shard-size question and a Qwen3.5 MoE from_pretrained error do not describe the same bug." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Missing layer projections in qwen3next and a Qwen3.5 MoE loading error are different model-specific failures." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Removed tie_embeddings_and_encoder_decoder and unexpected position-id keys are different regressions." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "A torch.split return-value issue in GlmMoeDsaIndexer is not the same as a GLM-5 RoPE implementation problem." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "These concern unrelated dtype-warning behavior and sam3 model-type warnings." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "An AutoImageProcessor import failure and a PretrainedConfig type-checking regression are separate API breakages." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "A broken vitpose model and tokenizer error handling when protobuf is absent are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Ministral FlashAttention failure and FlashAttention-3 training degeneration are not the same concrete bug." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "PretrainedConfig type checking and a missing-TensorFlow backend error are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and qwen3next missing projections are distinct model-loading issues." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "A SwitchTransformersConfig sparse-layer bug and a PretrainedConfig type-check regression are different failures." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Qwen3-VL shape mismatch and Qwen3-VL-Moe bug reports are different model-specific problems." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils and a testing_utils bug are unrelated." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "A removed config field and gguf_file breaking from_pretrained are different regressions." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "A missing-torchvision crash in AutoProcessor and a testing_utils bug are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 42, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:38617", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43352", + "issue:43381", + "issue:43408", + "issue:43502", + "issue:43531", + "issue:43550", + "issue:43824", + "issue:43825", + "issue:43873", + "issue:43874", + "issue:43901", + "issue:43906", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44380", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44987", + "issue:45071", + "issue:45103", + "issue:45245", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45588", + "issue:45753" + ], + "soft_pairs": [ + "issue:44117|issue:44987", + "issue:43986|issue:44484", + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:43976|issue:45071", + "issue:43986|issue:45372", + "issue:44829|issue:45245", + "issue:43531|issue:45341", + "issue:38617|issue:42757", + "issue:44261|issue:44485", + "issue:43064|issue:44315", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:44062|issue:44117", + "issue:43097|issue:45588", + "issue:44038|issue:44410", + "issue:44704|issue:45103", + "issue:43502|issue:43992", + "issue:43986|issue:44117", + "issue:43097|issue:43873", + "issue:43824|issue:43986", + "issue:43066|issue:43906", + "issue:43097|issue:43901", + "issue:43825|issue:44655", + "issue:43992|issue:44484", + "issue:43208|issue:43550", + "issue:43012|issue:44368", + "issue:43012|issue:43550", + "issue:42886|issue:43381", + "issue:43352|issue:44380", + "issue:42907|issue:45753", + "issue:42907|issue:44655" + ], + "prepared_review_unit_hash": "ff9adebd2232d78a24639231f15017a3a66bf272c20ce0d0cd022bb43ea08a10", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37187, + "estimated_input_tokens": 9297, + "estimated_eval_tokens": 18850 + }, + "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 soft-similarity pairs generally share a subsystem or symptom class, but not the same concrete bug, so I would not collapse any of them as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": "No single true canonical issue stands out because the set is heterogeneous. If one representative is needed, issue 43873 is the strongest anchor: it is open, has substantial discussion, and describes a concrete runtime problem with quantization/offloading.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the most suitable representative because it is active, detailed, and has the clearest broad user impact among this mostly unrelated set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Both involve loading/tokenizer resolution, but 44117 is a generic mapping bug while 44987 is a model-specific load failure; not the same underlying code path." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "One is an AutoProcessor/video-model crash without torchvision; the other is about save_pretrained shard sizing. Different features and failure modes." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "These concern unrelated model/config warnings in different architectures; they do not describe the same bug." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Both are GLM-related, but one is an image-processor multimodal token AttributeError and the other is a torch.split indexing issue in a different component." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "A Python-version compatibility regression is not the same as a PreTrainedConfig type-checking breakage." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Both are processor-loading failures, but caused by different missing dependencies/symbols and different model families." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "These are unrelated training/runtime problems: flash_attention_3 degeneracy versus a categorical-cardinality RuntimeError." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and a testing_utils bug are unrelated." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols from different modules; not the same concrete breakage." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "One is an eps/config precision mismatch in MLA layernorm; the other is a RoPE implementation question. Different code paths." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to Liger Kernel application with model_init." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen-family model/config issues, but one is missing attention projections and the other is a dropped vision config field." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Both are import failures, but they involve different missing exports and different modules." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "An AddedToken constructor argument conflict is not the same issue as TOKENIZER_MAPPING_NAMES returning None." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "A removed config API and a flash_attention runtime AttributeError are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "These are different Qwen-related bugs; one is a broader v5 compatibility issue, the other is a specific missing-layer-projection defect." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Passing kwargs to cached_file and an auto_docstring annotations crash are separate utility-layer bugs." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "local_files_only network leakage and a missing embed_tokens.weight load path are distinct from each other." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "A video-model processor crash without torchvision and a tokenizer mapping None bug are different subsystems and failures." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Removal of a config attribute and quantization/offloading failure are not the same underlying bug." + }, + { + "left": "issue:43824", + "right": "issue:43986", + "accept": false, + "reason": "One is a missing class export/import error; the other is a processor crash due to missing torchvision. Different root causes." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Wrong tokenizer decoder type in v5 and a reproduction of another issue are not the same defect." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "A config API removal and a docs/behavior mismatch for return_all_scores are unrelated." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "These both touch pipeline behavior, but one is an error-message issue and the other is save_pretrained support; not mergeable as one fix." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing encoder weights on load and save_pretrained shard sizing are separate save/load concerns." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training blockers and Bamba SDPA/torch.compile failures are different model-specific problems." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "A float32 warning on bfloat16 compilation and a tie_word_embeddings warning are unrelated warnings with different triggers." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "These are different failure modes: a precision warning versus a torch.compile backend bug." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading and gradient checkpointing in eval mode are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Both mention attention backends, but one is explicit FA2 support gating and the other is GPT-2 attention scaling behavior; not the same bug." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Dequantized model saving and a Qwen3.5 image infinite loop are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Saving dequantized models and saving Pipeline objects are different save_pretrained problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 43, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43502", + "issue:43525", + "issue:43526", + "issue:43582", + "issue:43611", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43867", + "issue:43901", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44188", + "issue:44222", + "issue:44230", + "issue:44242", + "issue:44263", + "issue:44380", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:44938", + "issue:45216", + "issue:45290", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45479", + "issue:45593", + "issue:45753" + ], + "soft_pairs": [ + "issue:44380|issue:45479", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:44483|issue:44514", + "issue:36683|issue:43582", + "issue:43208|issue:43526", + "issue:44222|issue:45478", + "issue:42490|issue:43012", + "issue:43618|issue:43761", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:43618|issue:44380", + "issue:38617|issue:43502", + "issue:44483|issue:45290", + "issue:44038|issue:44230", + "issue:43299|issue:43867", + "issue:44483|issue:45381", + "issue:43756|issue:44485", + "issue:43901|issue:44655", + "issue:43299|issue:45753", + "issue:36683|issue:43475", + "issue:42994|issue:44655", + "issue:43352|issue:43937", + "issue:43867|issue:45216", + "issue:44077|issue:44380", + "issue:36010|issue:42757", + "issue:36683|issue:44077", + "issue:43066|issue:45381", + "issue:43611|issue:44655", + "issue:43976|issue:44938", + "issue:36683|issue:43525", + "issue:43352|issue:45593", + "issue:44263|issue:45440", + "issue:43618|issue:45216", + "issue:36683|issue:44242", + "issue:44188|issue:44380" + ], + "prepared_review_unit_hash": "b13199a9087816e3b325d254134c5600ef1f368e73461cecb6258910e21ccea5", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38176, + "estimated_input_tokens": 9544, + "estimated_eval_tokens": 19344 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of Transformers regression reports, import errors, and model-specific bugs. The items are not strong duplicates overall; they share broad v5-regression language but usually hit different code paths or models.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 43611 is the broadest and most representative regression report in the set: a general Transformers 5.0 model-loading break tied to base_model_prefix handling.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43611 is the clearest, most actionable cluster representative because it describes a concrete, user-facing regression with a broad impact across models.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Different subsystems: attention scaling backend behavior vs sequence-classification loss computation." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Unrelated problems: FlashAttention support for a model vs Python-version compatibility." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Distributed training optimizer-state bug is unrelated to GPT-2 attention scaling." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Both involve chat/template paths, but one is request acceptance and the other is batched chat-template crashing." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Different model/config attribute error vs Apple Silicon allocator TypeError." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs are unrelated to BeitImageProcessorFast label reduction." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Save-pretrained FP8 MoE bug and from-pretrained Qwen3.5 MoE load error are not the same concrete failure." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Trailing-slash import warning and bf16 compiler warning are unrelated issues." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP regressions, but the titles point to different missing outputs and no shared concrete failure is shown." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "PyTorch precision warning is unrelated to compiled flex_attention failure on newer torch." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Different missing imports from different packages and different symbols." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP output-field regression is unrelated to GPT-2 attention scaling config being ignored." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Import error in configuration_utils is unrelated to local_files_only network requests." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Chat-completions request rejection and tool-call template crashing are different code paths." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Generic Qwen3-VL-Moe breakage and FP8 inference support are not the same bug." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Model-loading failure for Qwen3VL MoE differs from a sorted-state_dict load error." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "API request validation and Qwen2.5-VL video position-id issues are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch is unrelated to GLM-5 RoPE implementation discussion." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to Pipeline save_pretrained failure." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Qwen3VL MoE loading failure and a specific-image infinite loop are different defects." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config missing vocab_size and SAM3 missing fpn_position_embeddings are distinct model attribute bugs." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model saving failure is not the same as Pipeline save_pretrained failure." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "FlashAttention unsupported-model issue is unrelated to GLM-5 generation config validation." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "State-dict ordering load error and Qwen3.5 checkpoint save regression are different save/load paths." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "post_init contract issue in patchtsmixer is unrelated to GPT-2 attention scaling." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Different missing imports from different modules and symbols." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Gemma3 config attribute missing is unrelated to patchtsmixer post_init policy." + }, + { + "left": "issue:43066", + "right": "issue:45381", + "accept": false, + "reason": "Tokenizer decoder type bug is unrelated to Qwen2.5-VL vision_position_ids." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "Base-model-prefix loading regression is unrelated to Pipeline serialization." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Different Python compatibility failures affecting different versions and environments." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Different missing config attributes on different model families." + }, + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "FlashAttention support issue is unrelated to D-FINE auxiliary-loss behavior." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "torch.split indexing behavior is unrelated to DeepSeekV3 implementation divergence." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIP output regression is unrelated to Qwen3.5 save_pretrained checkpoint corruption." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3 config attribute error is unrelated to MoE load-balancing loss omission." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "torch.compile branching divergence is unrelated to GPT-2 attention scaling config handling." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 44, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42490", + "issue:42890", + "issue:43010", + "issue:43064", + "issue:43352", + "issue:43502", + "issue:43575", + "issue:43618", + "issue:43723", + "issue:43867", + "issue:43931", + "issue:43976", + "issue:43992", + "issue:44062", + "issue:44075", + "issue:44077", + "issue:44112", + "issue:44222", + "issue:44246", + "issue:44355", + "issue:44360", + "issue:44387", + "issue:44484", + "issue:44492", + "issue:44556", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45125", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45561", + "issue:45600", + "issue:45850" + ], + "soft_pairs": [ + "issue:43064|issue:44492", + "issue:43352|issue:43931", + "issue:43992|issue:45310", + "issue:43010|issue:45278", + "issue:43867|issue:45375", + "issue:44355|issue:44855", + "issue:41669|issue:44246", + "issue:36683|issue:43064", + "issue:42890|issue:45561", + "issue:44938|issue:45071", + "issue:43867|issue:45357", + "issue:43010|issue:45850", + "issue:43992|issue:45478", + "issue:43010|issue:43976", + "issue:44938|issue:45381", + "issue:43618|issue:44077", + "issue:42490|issue:44075", + "issue:36296|issue:43575", + "issue:44360|issue:45440", + "issue:28282|issue:33453", + "issue:43867|issue:44484", + "issue:43618|issue:44857", + "issue:43618|issue:44977", + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43723|issue:44556", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:44387|issue:44556" + ], + "prepared_review_unit_hash": "7a999fb156dbf30a17af3bfa72a43e0fc6598f1906ad207ce0301f2c3282bf69", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36452, + "estimated_input_tokens": 9113, + "estimated_eval_tokens": 18482 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of Transformer v5 regression reports, especially model-loading/import/tokenizer failures, with several unrelated training, quantization, and test issues mixed in. The soft similarity links are largely false positives.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the best umbrella representative: it explicitly captures the broad post-upgrade import/regression theme that most of the cluster superficially resembles, while still being a concrete user report.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most representative issue for this cluster because it is broad, recent, and aligned with the dominant failure mode seen across the grouped issues (v5 upgrade regressions and import/load breakage).", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Different problems: distributed training optimizer-state corruption vs a cache-strategy typo." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Different models and failure modes: Flash Attention support error vs Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Both are loading errors, but they affect different models and concrete code paths; too broad to be the same bug." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "One is about adding @torch.no_grad to cache update methods; the other is a broad import-regression report. Not the same change/bug." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "State-dict loading order issue vs missing config field in Qwen3.5 Vision config; distinct root causes." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Both mention import-time failures, but one is compiled Python files and the other is a Python 3.13 torch.jit parsing/IndentationError issue." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": false, + "reason": "Both concern import performance, but one is a specific import-* cleanup change and the other is a generic slow-import report; not the same concrete bug." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Gemma3Config missing vocab_size is unrelated to the FSDP2+PEFT optimizer-state bug." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Test flakiness from missing set_seed() is different from an xdist race on captured_info.txt." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Python 3.14 import failure and PretrainedConfig type-checking breakage are different regressions." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen3.5 issues: generic state_dict loading error vs incorrect visual encoder keys saved by save_pretrained." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "CLIPOutput attentions regression and patchtsmixer post_init validation are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:44075", + "accept": false, + "reason": "Local-files-only path warning and unused SGD args are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Generic tensor-parallel training bug and OOM when loading a specific Qwen2 model are not the same underlying issue." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer/ReLU discussion is unrelated to DeepseekV3MoE implementation divergence." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "PyTorch missing dependency error and tokenizer-loading regression are unrelated." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Model-loading failure vs save_pretrained shard-size question; not the same bug." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to LwDetrImageLoss AMP/CUDA crash." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Different failures: CLIPOutput attentions assignment vs Qwen3.5 flash-attention generation bug." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "Test seeding flake is unrelated to Phi-4-multimodal model loading failure." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "A stale GraniteSpeech CI test and a missing set_seed() issue are different test problems." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "Patched testing-utils xdist race and auto_mappings CI breakage are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "local_files_only network leakage and AddedToken keyword-argument conflict are different tokenizer/download bugs." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading regression in v5 and checkpoint reload incompatibility after version upgrade are related only at a very broad level, but not the same concrete bug." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "Missing set_seed() test flakiness is unrelated to the testing_utils typo bug." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained issue and missing _tp_plan for tensor parallelism are different Qwen-related bugs." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization memory regression and checkpoint reload failures are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 45, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "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:43065", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43526", + "issue:43576", + "issue:43673", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:44222", + "issue:44230", + "issue:44261", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44749", + "issue:44908", + "issue:44938", + "issue:44961", + "issue:45071", + "issue:45125", + "issue:45230", + "issue:45362", + "issue:45375", + "issue:45468", + "issue:45478", + "issue:45850" + ], + "soft_pairs": [ + "issue:42548|issue:44351", + "issue:43010|issue:43065", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:30990|issue:31795", + "issue:43010|issue:43232", + "issue:45125|issue:45375", + "issue:30333|issue:33453", + "issue:43299|issue:44556", + "issue:42831|issue:43874", + "issue:43502|issue:44222", + "issue:44315|issue:44360", + "issue:43502|issue:44961", + "issue:44355|issue:45071", + "issue:30333|issue:36296", + "issue:44355|issue:44655", + "issue:43827|issue:44961", + "issue:44222|issue:44230", + "issue:33453|issue:34689", + "issue:42757|issue:43576", + "issue:33453|issue:36296", + "issue:43576|issue:43824", + "issue:43576|issue:45071", + "issue:31795|issue:38617", + "issue:44961|issue:45468", + "issue:41628|issue:42548", + "issue:38617|issue:43576", + "issue:43576|issue:44938", + "issue:43673|issue:44492", + "issue:44908|issue:44961", + "issue:44485|issue:44961", + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:45362|issue:45850", + "issue:44261|issue:44360", + "issue:44623|issue:45230" + ], + "prepared_review_unit_hash": "c5e31dea24d7b009784b14d779c4b9571f31b849064f06e35b8ce17b2048351f", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 38, + "serialized_chars": 37735, + "estimated_input_tokens": 9434, + "estimated_eval_tokens": 19124 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly false positives: the set mixes unrelated Transformers bugs, import failures, docs issues, and version-regression reports. No soft pair looks like the same concrete underlying bug or fix.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45850 is the broadest umbrella ('Since 5.0 version it breaks too many models') and best matches the cluster\u2019s repeated v5 regression theme, though it is very generic.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the most suitable cluster representative because it can absorb many of the v5-breakage complaints; it is still too vague to be an ideal canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different breakages." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Different problems: cache update no_grad behavior vs a dummy Conv2d in Sam3PixelDecoder." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Unrelated code paths: local_files_only network requests vs GLM-5 RoPE implementation." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "One is compiled Python file errors; the other is a data filtering slowdown after upgrade." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5 MoE, but one is tensor-parallel planning and the other is from_pretrained loading." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence Transformers loading hang is unrelated to documentation confusion about forward arguments." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Cache no_grad decoration and generation kwargs after sync_gpus are different generation bugs." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen3.5 MoE-related, but one is tensor parallelism and the other is a missing config field." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLFlow job status reporting and tokenizer loading regression are different failures." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Different version regressions affecting different model-loading paths." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy and missing image-patch counting are unrelated bugs." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Both involve saving/loading behavior, but one is offline API requests and the other is FP8 moe save_pretrained." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger kernel application in model_init is unrelated to a missing ReLU in the DSA indexer." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "local_files_only networking bug and a standalone 'racoon' issue are not the same problem." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled Python file errors are unrelated to PretrainedConfig type checking in v5.4.0." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLFlow reporting on training failure and tensor parallel training are different subsystems." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled file execution errors are unrelated to Pipeline save_pretrained support." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still mentioning pipeline() and an unrelated 'racoon' issue share no underlying bug." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both are FP8/moe themed, but one is save_pretrained and the other is inference support." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading are not the same failure." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Importing is_offline_mode and the transformers env command are different breakages." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading and tensor parallel training bugs do not share a concrete code path." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Broken env command and missing Qwen2.5-VL import are unrelated v5 issues." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "CLI env command failure and PretrainedConfig type checking are different features." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Docs confusion about forward arguments is unrelated to a missing layer_type_validation import." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "A placeholder 'racoon' issue is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "AutoImageProcessor import failure and PreTrainedModel import failure are different missing-export issues." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "Missing layer_type_validation import and broken env command are different regressions." + }, + { + "left": "issue:43576", + "right": "issue:44938", + "accept": false, + "reason": "CLI env command breakage and Python 3.14 load failure are not the same bug." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Missing GenerationMixin cache in chunked_prefill is unrelated to a typo in cache strategies." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling and an unrelated placeholder issue are different problems." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "GLM-5 RoPE implementation and an unrelated placeholder issue are not duplicates." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor parallel training and TextClassificationPipeline docs are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Missing AutoImageProcessor export and compiled Python file errors are different issues." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor parallel training and BeitImageProcessorFast label reduction are unrelated bugs." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Qwen3.5 chat crash and the broad 'many models break' report are related only by general version complaints, not the same concrete bug." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "RMS norm epsilon precision discussion and DSA indexer missing ReLU are different code paths." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing processor save_pretrained files and a generic bug report are not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 46, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43704", + "issue:43827", + "issue:43874", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44246", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44945", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478", + "issue:45542", + "issue:45753", + "issue:45850" + ], + "soft_pairs": [ + "issue:44273|issue:45542", + "issue:44273|issue:45003", + "issue:44393|issue:45753", + "issue:44393|issue:45071", + "issue:44038|issue:45125", + "issue:43576|issue:44556", + "issue:43525|issue:45850", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:44492|issue:45850", + "issue:43572|issue:45850", + "issue:42371|issue:44492", + "issue:44704|issue:44908", + "issue:42890|issue:44908", + "issue:45278|issue:45850", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:44297|issue:45230", + "issue:43576|issue:44908", + "issue:44295|issue:45230", + "issue:44908|issue:45071", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:43874|issue:45850", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:44315|issue:44829", + "issue:43576|issue:44273", + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:41669|issue:43704" + ], + "prepared_review_unit_hash": "dedf8843e9a9926d998c7c17091d0ffd9ca24dd19469a177b3829b70a447d4e3", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 41, + "serialized_chars": 39338, + "estimated_input_tokens": 9835, + "estimated_eval_tokens": 19926 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose grab-bag of unrelated Transformers v5 regressions, model-specific bugs, and a few docs/perf complaints. The titles are superficially similar, but the concrete failure modes do not line up closely enough for duplicate merging.", + "confidence": 0.9, + "canonical_issue_reason": "No single issue is a reliable canonical for this cluster; it spans many distinct bugs and regressions rather than one underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to pick the closest umbrella, issue:44273 is the broadest open item, but it is still too vague to serve as a true duplicate anchor for the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Generic lazy-loading complaint vs TensorBoard-without-TF backend error; different subsystems and root causes." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading failure vs unsafe sys.modules access in modeling_utils; not the same bug." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Qwen3-VL 2D box hallucination/error vs infinite loop on one image; distinct symptoms and likely causes." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Model output bug vs PretrainedConfig type-checking regression; unrelated code paths." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Qwen3-VL-Moe bug vs missing _tp_plan for Qwen3_5Moe tensor parallelism; separate model features." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Broken `transformers env` command vs checkpoint reload failure after upgrade; not the same issue." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Llama4 pad_token_id AttributeError vs broad complaint that many models break in v5." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-* slowdown/explosion vs GenerationMixin cache missing during chunked_prefill; different failure modes." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both upgrade-related, but one is checkpoint reload regression and the other is meta-init incompatibility for old remote-code checkpoints." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "Cache-strategy typo vs generic v5 breakage report; not the same concrete problem." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig vs vague 'many models break' complaint." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API-setting warning vs cache-strategy typo; unrelated topics." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs not forwarded to cached_file vs inverse_sqrt scheduler kwargs ignored; different components." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Missing set_seed in SamHQ tests vs scheduler kwargs bug; no shared underlying defect." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Many import errors after upgrade vs generic v5 breakage complaint; too broad to be duplicates." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Importing transformers is slow sometimes vs lazy loading not working properly; related theme, but not the same bug." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "sam3_video/sam3_tracker model-type warning vs Liger Kernel not applied with model_init; different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility issue vs Qwen3-VL 2D bbox output bug; unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 unsupported for Nemotron vs Qwen3-VL hallucination/error; different models and failures." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer_class mismatch on save_pretrained vs a vague generic bug report; no shared concrete issue." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "`transformers env` command broken vs scheduler kwargs ignored; unrelated functionality." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "position_ids buffer AttributeError vs generic bug report; not the same problem." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwarg omission vs PretrainedConfig type checking regression; separate bugs." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-* slowdown vs cannot import HybridCache; both import-related but clearly different causes." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import-* slowdown vs a small testing_utils bug; unrelated." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache-strategy typo vs incorrect LLM output under pipeline parallelism; different areas." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "GLM46V processor missing method vs generic v5 breakage complaint; not duplicates." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL bbox issue vs Qwen3.5 Moe from_pretrained error; separate models and failures." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "patchtsmixer post_init policy vs _tied_weight_keys list AttributeError; unrelated model utilities." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still reference pipeline() vs scheduler kwargs ignored; docs issue vs runtime bug." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Documentation confusion in model.forward vs tokenizer loading regression; unrelated issue types." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import-* slowdown vs scheduler kwargs bug; no shared underlying code path." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel application with model_init vs degenerate training under flash_attention_3; different behaviors." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Broken `transformers env` command vs lazy loading malfunction; different features." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving Pipeline objects vs tied weight keys AttributeError; unrelated internals." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer/ReLU discussion vs Gemma-4 audio positional encoding bug; not the same bug." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report vs specific Qwen3.5 Moe from_pretrained error; no matching concrete failure." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading problem vs inverse_sqrt scheduler kwargs bug; separate concerns." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp calculation bug vs GLM-5 RoPE implementation discussion; distinct models/issues." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Qwen3VL timestamp bug vs scheduler kwargs bug; unrelated." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-* slowdown vs VRAM leak across dataloader threads; different symptom and subsystem." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 47, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-402", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:37428", + "issue:38617", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43606", + "issue:43618", + "issue:43704", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45850" + ], + "soft_pairs": [ + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468", + "issue:44261|issue:45468", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:44492|issue:44998", + "issue:44998|issue:45850", + "issue:43618|issue:44998", + "issue:44998|issue:45341", + "issue:43525|issue:44861", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:31515|issue:31795", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "98f6e14948d3aa984537c0b0a85be964cf212a28dada1f1bf72c0d6904e73731", + "component_budget": { + "node_count": 402, + "item_count": 402, + "soft_pair_count": 1503, + "serialized_chars": 775573, + "estimated_input_tokens": 193894, + "estimated_eval_tokens": 388044 + }, + "budget": { + "node_count": 35, + "item_count": 35, + "soft_pair_count": 29, + "serialized_chars": 28342, + "estimated_input_tokens": 7086, + "estimated_eval_tokens": 14428 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous; the soft-similarity links are mostly superficial and none look like true duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45092 is the clearest representative of the v5/model-loading regression subset, but the overall cluster is too mixed to be treated as one duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45092 is the most concrete, user-facing regression among the mixed reports, so it is the best single issue to anchor the cluster if one must be chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion about forward args vs a specific model-loading regression; different problems." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Docs wording issue vs flash-attention import failure; unrelated code paths." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel not applied with model_init vs remote-code/meta-init incompatibility; not the same bug." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE implementation vs Gemma4 audio positional encoding; different model families and failures." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM threading vs GLM-5 RoPE math; unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 API migration notice vs a memory leak bug; no shared code-path." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only still triggers requests vs timestamp calculation in a processor; distinct behaviors." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Processor timestamp bug vs missing save_pretrained files; different processor issues." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Processor timestamp calculation vs VRAM leak in causal LM usage; unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return handling in an indexer vs audio positional encoding; different components." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch vs audio positional encoding; unrelated failure modes." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Layernorm epsilon precision issue vs audio positional encoding; not the same underlying bug." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both concern tokenizer changes in v5, but one is general behavioral drift and the other is a decoder-type bug; too broad to merge." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs bug vs an off-topic/invalid issue; no duplicate relationship." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weights key crash vs chat template crash with tool calls; different code paths." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "Cache-strategy typo vs an unrelated issue; not duplicates." + }, + { + "left": "issue:44998", + "right": "issue:45850", + "accept": false, + "reason": "Unrelated issue text vs broad v5 regression complaint; no shared concrete bug." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIPOutput attentions regression vs unrelated issue; no overlap." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated issue text vs testing_utils bug; different artifacts." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config vs tied-weights key crash; different subsystems." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig vs tied-weights key crash; unrelated." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow checkpoint loading vs import error for layer_type_validation; different symptoms and code paths." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "fp8 inference support request vs processor save_pretrained file omission; unrelated." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow status reporting on failed training vs slow from_pretrained loading; different areas." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Slow checkpoint loading vs tensor-parallel training bug; not the same bug." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Loading performance regression vs documentation confusion; unrelated." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "fp8 support for qwen3-vl/qwen3.5 moe vs from_pretrained error in transformers>=5.4.0; different problems." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow checkpoint loading vs tokenizer loading regression; related topic but not the same concrete failure." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching support for audio models vs fp8 inference support; different 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": 2, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "e88daaae9626e68719478e7d4036d6089bc3864f97b3c13bdf192f369e1f34ee", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2479, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2479, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three issues are not true duplicates. Two are about model-loading/tokenization behavior in unrelated contexts, but the concrete problems differ: one is Tapas tokenization mismatch, one is a private-model auth/error-message problem, and one is a generic failure to load bert-base-uncased.", + "confidence": 0.85, + "canonical_issue_reason": "Issue #16618 is the broadest and most central model-loading complaint in the cluster, so it is the best single issue to represent the cluster if one must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "#16618 is the most generally framed and likely to attract related model-loading reports, unlike the more specific Tapas tokenization and private-model login issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tapas tokenization mismatch is a specific preprocessing/implementation issue, while #16618 is a generic model-loading failure for bert-base-uncased; they do not describe the same bug." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "#15980 is specifically about the error message when downloading a private model while logged out, whereas #16618 concerns failure to load bert-base-uncased; the underlying failures are different." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "368ce75a4fa55bb21be0d293db4a24e26bc300daf8b31ce38440df972765776e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: one asks for Flash Attention 2 support across more architectures, the other asks for GGUF support across more architectures. They share a generic framing but target different features/code paths.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:26350 is the older, more actively discussed request, so it is the better representative issue if one must be chosen, but it is not a duplicate of issue:33260.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different requested capabilities (Flash Attention 2 vs GGUF) with no indication of the same underlying bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-5", + "nodes": [ + "issue:27088", + "issue:28936", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:27088|issue:28936", + "issue:28936|issue:43834", + "issue:28936|issue:44365", + "issue:28936|issue:44370", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "d4d14e48950bf859b7e0938466fbc5370276ac7ca0b4183957eb0711a5a7feff", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6441, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6441, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster splits into one near-duplicate trio of generic i18n translation issues and two standalone language-specific requests (Turkish, Spanish). Only the three placeholder-titled issues look like the same underlying issue; the language-specific ones are separate requests.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43834 is the earliest of the near-identical generic translation issues and serves as the cleanest representative of that duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43834 is the best overall issue representative because it is the oldest member of the duplicate trio and matches the shared generic translation request most cleanly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Different language targets: Turkish vs generic placeholder translation request. Same broad i18n theme, but not the same concrete issue." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Turkish docs translation request is distinct from the generic placeholder issue; no evidence they track the same language or task." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Different language-specific request versus generic placeholder issue; too broad to call duplicates." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Turkish and Spanish translations are separate language requests, not the same underlying issue." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Spanish request is distinct from the generic placeholder translation issue; same subsystem, different concrete target." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Spanish docs translation request does not match the generic placeholder issue at the concrete level." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Spanish versus generic placeholder translation request; not the same underlying issue." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": true, + "reason": "Near-identical titles and extremely high body similarity indicate the same generic translation issue." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": true, + "reason": "These look like duplicate copies of the same placeholder translation issue with only minor wording/metadata differences." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": true, + "reason": "The two issues are effectively identical generic translation requests and plausibly one duplicate set." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The clustering is well grounded in the packet: the three placeholder-titled issues have near-identical titles and very high similarity, while the Turkish and Spanish issues are meaningfully different, language-specific requests. The soft-edge verdicts are conservative and consistent with 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": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-15", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:36879|issue:37015", + "issue:37015|issue:42503", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43671|issue:43909", + "issue:43837|issue:43909", + "issue:43837|issue:45322", + "issue:43837|issue:44121", + "issue:43909|issue:44205", + "issue:44121|issue:45322", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "6aab5a3bbc399cb4ee5ba9918efd769ea68ea55641896e4a3ca26192ce33d491", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20710, + "estimated_input_tokens": 5178, + "estimated_eval_tokens": 10612 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20710, + "estimated_input_tokens": 5178, + "estimated_eval_tokens": 10612 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are separate model-support requests for different architectures and modalities (e.g., EuroBert, RF-DETR, NeoBERT, MiniCPM3, Qwen3-ASR/TTS, Voxtral, EUPE). The soft links reflect topical similarity only; none look like the same underlying bug or change.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical issue: the items are distinct model requests, not duplicates of one underlying report or implementation.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative because the cluster spans unrelated model additions with different code paths and model families.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different model requests: EuroBert config support vs DEIMv2. Same broad task type, not the same change." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config support and Qwen3-TTS support are unrelated model families and code paths." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert and RF-DETR are distinct models; not the same implementation request." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are different vision models, so this is only category-level similarity." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR and LFM2.5 Audio 1.5B are unrelated modalities and changes." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR and a weight-sparse transformer request are different model additions." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR vs Qwen3-ASR support: different model families and tasks." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR vs Qwen3-TTS support are distinct requests, not one bug." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are unrelated architectures and code paths." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT support and a sparse-transformer request do not describe the same change." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT and LFM2.5 Audio 1.5B are different model support requests." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are different model families; no duplicate evidence beyond similarity." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are separate model additions, not one underlying fix." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are different tasks." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 and the sparse-transformer request target different model architectures." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are distinct model support requests." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 vs Voxtral TTS support are unrelated model families and modalities." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are different model requests, not the same code change." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are separate model additions." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT and Qwen3-TTS are unrelated model requests." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT models and BERT-like models with RoPE are only loosely related by BERT naming." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like RoPE support and Voxtral TTS support are different model behaviors." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR are sister models, but they are separate support requests and code paths." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS and Voxtral TTS are different TTS models with different implementations." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated modalities and model families." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS support and sparse-transformer support are unrelated requests." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are different audio-model additions." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are separate audio model requests." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR and EUPE are different model families and tasks." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR support and sparse-transformer support are not the same underlying change." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio 1.5B and SAM3-LiteText are unrelated models/modalities." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Sparse-transformer support and EUPE support are different model implementations." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral-4B-TTS are different speech models and fixes." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT and Voxtral-4B-TTS target completely different code paths." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR support and DeepSeek-OCR2 support are separate model additions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 6, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "6ef6af7df13263c80867dbcaae899bd61e99222a39b689e9a93adce905da9fd6", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: normalization implementation, Mask2Former loss plumbing, generic kwargs propagation, a config type-hint typo, a quantization typo, and a tokenizer warning regression. The only commonality is loose text similarity, not the same underlying bug.", + "confidence": 0.97, + "canonical_issue_reason": "No clear canonical issue: the items describe distinct bugs across unrelated modules and change types, so there is no single duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to name a representative issue, #43240 is the broadest concrete bug report, but it still does not unify the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Different problems: a model norm implementation question vs. an incorrect type hint in a config class." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Both involve losses, but one is Mask2Former ignore_value handling and the other is generic kwargs plumbing; not the same bug." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Unrelated: Mask2Former loss config vs. tokenizer regex warning regression." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former loss behavior and a quantization typo are different code paths and fix types." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Different components and bug classes: model loss handling vs. config annotation typo." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Generic loss kwargs bug does not overlap with a ModernBERT config type-hint issue." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "Config typing issue and tokenizer warning regression are unrelated." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "A type-hint correction and a typo in a different symbol are 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": 7, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "b40c999af3fb40266822aff110e744baba9b5d23b3e5e7ef2ac378b888296405", + "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": "These two issues are not duplicates: one is a vague request about block decoding, the other is a model-specific feature request for DeepSeek v3.2 support.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical duplicate issue can be chosen because the titles and likely scope are unrelated.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43037 is the more concrete and actionable request; 41084 is too broad/vague to serve as a clear representative.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different underlying concerns: block decoding implementation vs support for a specific model version. 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": 8, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "b1eb4e98536b0066491fd13618064228aa8c4526283c94443a20555ff5795d91", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are related only at a very high level (custom Trainer behavior) but they describe different problems and different code paths, so they should not be treated as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 43598 is the more concrete Trainer customization request; issue 43600 is a separate FLOPS-estimation concern.", + "canonical_pr_reason": null, + "best_issue_reason": "43598 is the better representative issue because it is specific and directly about a single Trainer behavior change, while 43600 is a distinct performance/accounting topic.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Reject: the titles and likely fixes target different behaviors in Trainer\u2014unused-column handling vs FLOPS estimation for custom trainers\u2014so they are 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": 9, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "f799de03a450a9b17304c04cb1762353586a62cfa6b66ed255fddf6a58fb3778", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related only at a very broad AutoModel-support level, but they request different capabilities for different model/config combinations. They should not be treated as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43684 is the broader AutoModel registration request and is the better representative of the cluster\u2019s auto-class support theme.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43684 is the more general feature request; 44405 is a separate AutoModelForSequenceClassification request for a different config.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different underlying changes: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs Qwen3.5 sequence-classification support. They touch different model families and different auto heads." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43835-4", + "nodes": [ + "issue:43835", + "issue:43845", + "issue:43846", + "issue:43859" + ], + "soft_pairs": [ + "issue:43835|issue:43845", + "issue:43835|issue:43846", + "issue:43835|issue:43859", + "issue:43845|issue:43846", + "issue:43845|issue:43859", + "issue:43846|issue:43859" + ], + "prepared_review_unit_hash": "4528debffbb114be8ae3eb249f5137032d095023a38c451210b571731d45a982", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4263, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4263, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three issues appear to be near-identical duplicates of the vague \"huggingface \" report; the \"Fett\" issue looks unrelated. No PRs are present.", + "confidence": 0.76, + "canonical_issue_reason": "Issue 43845 is the earliest of the three identical \"huggingface \" issues and is the safest representative for the duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43845 is the best single issue to keep because it matches the repeated title, is earliest, and has no sign of being distinct from the other two huggingface reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no evidence they describe the same problem; \"Fett\" does not align with the huggingface reports." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no shared concrete bug details; likely unrelated." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles and no shared concrete bug details; likely unrelated." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same title and no distinguishing details; they look like duplicate reports of the same underlying issue." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same title and no distinguishing details; they look like duplicate reports of the same underlying issue." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same title and no distinguishing details; they look like duplicate reports of the same underlying issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: three issues share the same title, 43845 is the earliest of that group, and 43835 has a clearly different title. The soft-edge calls are conservative enough overall given the limited evidence; no PR-related claim is made." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "576b3721d664a7b07420969dc1e0a2395b30b70e5c1b78cfb051ff44f9b92488", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5791, + "estimated_input_tokens": 1448, + "estimated_eval_tokens": 3152 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5791, + "estimated_input_tokens": 1448, + "estimated_eval_tokens": 3152 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues do not look like duplicates of a single underlying bug or change. Most are spam-like placeholder issues, while one is a vague documentation suggestion; there is no concrete shared problem to merge.", + "confidence": 0.96, + "canonical_issue_reason": "issue:44418 is the only non-spam, somewhat descriptive issue, so it is the best available anchor, though it is still too vague to represent a real duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44418 is the most substantive and least spammy item in the set; the others are generic placeholders with no actionable content.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are spam placeholders with no concrete bug or change; not the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam placeholders with no actionable description; no duplicate signal beyond generic similarity." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam and the other is a vague documentation suggestion; they do not describe the same problem." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder versus a specific titled issue; no shared underlying bug or request." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A generic documentation suggestion is not the same as a spam placeholder." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "A generic documentation suggestion is not the same as a spam placeholder." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam placeholders, but there is no evidence they refer to the same concrete issue." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder versus a specific titled issue; no duplicate relationship." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "Spam placeholder versus a specific titled issue; no duplicate relationship." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 12, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "a38699bc6b3ca7b72b39d510cc1cbc9bd205066dcdf10244bef420481c0b7222", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues have identical titles and very similar scope, so they look closely related, but the evidence is only soft similarity with no explicit links or shared concrete targets/files. This supports a likely-duplicate reading, not a definitive duplicate conclusion.", + "confidence": 0.73, + "canonical_issue_reason": "If one must be kept as the representative report, #45145 is the better canonical issue because it is earlier and has the same apparent scope as #45151, but the duplication signal is not definitive.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best issue representative because it is earlier and matches the same title/scope, though the evidence only supports a likely duplicate rather than a confirmed one.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "The titles match and the topics are highly similar, but there is no explicit linkage or concrete shared implementation target; with only soft-similarity evidence and deterministic false, this is not a confirmed duplicate pair." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports a strong similarity signal, but not a definitive duplicate conclusion. The pair only has soft-similarity evidence, and the deterministic verdict is false. Marking it as a \"clear duplicate pair\" and setting confidence to 0.98 overstates the evidence; a more conservative verdict would be \"likely duplicate\" or \"possibly duplicate.\"" + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "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": "b74f884d6ff229fec405c7e7cfe2e7e16172a6f73047dd5b682aec67dc47df9d", + "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 are related only at a very broad level (4-bit inference), but they describe different bugs with different triggers and failure modes, so they should not be merged as duplicates.", + "confidence": 0.95, + "canonical_issue_reason": "No canonical duplicate here: #45672 is about a Gemma4 audio-module uint8/torch.finfo TypeError in NF4 inference, while #45674 is about llm_int8_skip_modules unintentionally removing the default lm_head exclusion and causing an AssertionError.", + "canonical_pr_reason": null, + "best_issue_reason": "#45674 is the cleaner standalone report: it names the exact BitsAndBytesConfig behavior, the affected default exclusion, and the concrete assertion failure path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Reject: both concern 4-bit inference, but the root causes differ. One is a Gemma4/audio-module uint8 torch.finfo TypeError; the other is a BitsAndBytesConfig skip-modules regression that clears the default lm_head exclusion and trips an AssertionError." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 15, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45762-2", + "nodes": [ + "issue:45762", + "issue:45763" + ], + "soft_pairs": [ + "issue:45762|issue:45763" + ], + "prepared_review_unit_hash": "f05fd103dff83b5b4af396ecb5a9f99c9a17f1bbf180d709a52b9d9bd3c43426", + "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 are just short name/date entries with no bug report content; they do not describe the same underlying problem and should not be deduplicated.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a strong canonical candidate because neither contains actionable problem details; if one must be chosen, the earlier issue is only a weak placeholder.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Both are bare personal-name/date posts with no shared technical problem, code path, or issue context; not a duplicate 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": 16, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "9a7bb77aface30f009b30197d707ed45f241792493ebd0cd28df5af10811b0dc", + "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 appear to be unrelated placeholder/spam entries with different personal names and no shared technical content, so they should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "Different names, different dates, and no body or issue-link evidence indicate they are not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 17, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45869-5", + "nodes": [ + "issue:45869", + "issue:45870", + "issue:45871", + "issue:45872", + "issue:45873" + ], + "soft_pairs": [ + "issue:45869|issue:45870", + "issue:45869|issue:45871", + "issue:45870|issue:45871", + "issue:45870|issue:45872", + "issue:45870|issue:45873", + "issue:45871|issue:45872", + "issue:45871|issue:45873", + "issue:45872|issue:45873" + ], + "prepared_review_unit_hash": "a206431ebe894adc7e441b69c1b009883a5b9bbb7b373d5a95cd70aa518c1f83", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5727, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5727, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster splits into two separate exact-duplicate pairs: 45870/45871 and 45872/45873. Issue 45869 is only loosely finance-related and should not be merged with either pair.", + "confidence": 0.96, + "canonical_issue_reason": "45870 is the earliest copy in the exact-duplicate pair 45870/45871 and is a reasonable representative for that subcluster.", + "canonical_pr_reason": null, + "best_issue_reason": "45870 is the cleanest representative of one real duplicate pair, but the full set is not one single issue family; 45872 is the representative of a separate duplicate pair.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Different artifacts: a dataset listing vs an example issue. Same finance theme, but not the same underlying request/bug." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Different artifacts: a dataset listing vs an example issue. Only broad topic overlap, not a duplicate." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Same title and matching metadata/body length; these look like exact duplicates of the same example issue." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Both are DataForge/finance-related, but one is an example prediction issue and the other is a scraping-service issue; not the same underlying request." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Same as the 45870/45872 pair: related topic, but different concrete issue content." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Different concrete requests; shared finance/DataForge wording is too broad to call them duplicates." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Different concrete requests; only broad subsystem/topic overlap." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Same title and matching metadata/body length; these look like exact duplicates of the same scraping-service issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: 45870/45871 and 45872/45873 are the only clearly tight pairs (identical titles and body lengths), while 45869 is only loosely related by theme and should not be merged. The soft-edge verdicts are conservative overall, and there is no PR-mergeability issue here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 30, + "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-39895-15", + "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", + "pull_request:45919", + "pull_request:45922" + ], + "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:45919", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:45922", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:45213", + "pull_request:43995|pull_request:44827", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:45795", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43823|pull_request:45795", + "pull_request:44827|pull_request:45922", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "811fad3f2ed86f4f1666fd01ae6514a9c274f9716c0cfa68ca0afe1da94176ca", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 22, + "serialized_chars": 42216, + "estimated_input_tokens": 10554, + "estimated_eval_tokens": 21364 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 22, + "serialized_chars": 42216, + "estimated_input_tokens": 10554, + "estimated_eval_tokens": 21364 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly unrelated PRs spanning model additions, docs, refactors, and separate bugfixes. The only true duplicate-like pair is the two `fixed_cross_entropy` PRs, which implement the same `nn.functional.cross_entropy` kwargs passthrough in `loss_utils.py`.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43251 is the best canonical PR for the loss fix: it directly targets issue #43240, changes the same code path as 43254, and is the more explicit implementation of the cross-entropy kwargs passthrough.", + "best_issue_reason": null, + "best_pr_reason": "PR 43251 is the best overall representative of the only duplicated change in this cluster because it is issue-linked and fixes the exact same `fixed_cross_entropy` behavior as 43254.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Unrelated PRs: VideoPrism model addition vs Executorch dynamic-shape test." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Different changes: Mistral tokenizer methods vs adding a new MobileLLM model." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer API fix and Executorch export test are unrelated." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-loading robustness vs new MobileLLM model; different code paths." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Loss utility kwargs passthrough is unrelated to adding MobileLLM." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Both touch model/runtime internals but fix different problems: cross-entropy kwargs vs Mistral4 tests/model plumbing." + }, + { + "left": "pull_request:43424", + "right": "pull_request:45919", + "accept": false, + "reason": "Executorch export testing and Sapiens2 model addition are unrelated." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "Dynamic export test vs Mistral4 test/model fix; not the same bug or change." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Executorch test PR and MobileLLM model addition do not address the same issue." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "New MobileLLM model and config-resolution fix are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45922", + "accept": false, + "reason": "MobileLLM model addition and vision-model memory leak fix are unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "Model addition vs Falcon refactor; different concrete changes." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon output-interface refactor is unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon refactor and Mistral4 fixes target different models and issues." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fix and `layrnorm` rename are unrelated bugfixes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 fixes are unrelated to docs for audio/video processors." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test/model work and config resolution ordering fix are different changes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 changes are unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "New model implementation and the model-creation skill are not the same underlying change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "MobileLLM model addition and docs-only processor guide are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45922", + "accept": false, + "reason": "Mistral4 test fix and vision-model memory leak fix are unrelated." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs fix the same `fixed_cross_entropy` code path by adding supported kwargs (`weight`/`label_smoothing`) to `nn.functional.cross_entropy`; they are direct alternate implementations of the same bugfix." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: the non-loss PRs are supported as unrelated by titles, filenames, and diffs, and the 43251/43254 pair is a clear same-file, same-issue, same-bugfix duplicate. The soft-edge verdicts stay conservative rather than over-connecting the unrelated model/addition/docs/refactor PRs." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 30, + "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": "e32fe2d0efa89b942eb87e67005ea7f74b9bb1f98c136655465dee25f75975c0", + "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": "These are related VibeVoice PRs, but they are not the same concrete change: one implements the base VibeVoice integration, while the other adds VibeVoice Realtime plus the acoustic tokenizer and generation tweaks. Shared filenames alone are not enough to merge them as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 40546 is the better canonical PR because it represents the core VibeVoice implementation and broader initial integration, while PR 42781 is a later, narrower follow-up for realtime/acoustic-tokenizer additions.", + "best_issue_reason": null, + "best_pr_reason": "PR 40546 is the best single representative PR for the cluster since it covers the main VibeVoice feature landing with substantial review activity and a cleaner, more general scope than the draft realtime follow-up.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Different feature scopes: 40546 implements VibeVoice, while 42781 adds VibeVoice Realtime and acoustic-tokenizer-related changes. They overlap on model scaffolding, but not the same underlying code-path change, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 30, + "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": "29d1cdf2d71b399711c80a999569144467bf584170a2b6fdfe84696a407dca35", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two pull requests are unrelated feature additions in different areas: TimesFM covariate forecasting vs DINOv3 image classification support. They do not look like duplicate fixes or mergeable alternatives to the same change.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the PRs target different model families and different code paths, so there is no duplicate relationship to collapse.", + "best_issue_reason": null, + "best_pr_reason": "No single best PR for deduplication: neither PR is a substitute for the other, and both are independent feature work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Reject: the titles, touched files, and diff previews show different features in different subsystems, not the same underlying bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 30, + "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": 30, + "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": "a170705dd49da2d94868b0d1a40cf84380c28e0848cbf1e1960162ab75289711", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10409, + "estimated_input_tokens": 2603, + "estimated_eval_tokens": 5462 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10409, + "estimated_input_tokens": 2603, + "estimated_eval_tokens": 5462 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition PRs (DeepSeek OCR, Isaac, Kimi2-6) that share boilerplate integration files but target different models and code paths. They are not duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45630 is the most substantial/established of the three and the best representative of the cluster, but it is not a duplicate of the others because it implements Kimi2-6-specific model, processor, and auto-mapping support.", + "best_issue_reason": null, + "best_pr_reason": "PR #45630 is the strongest standalone PR in the set: it has the highest review activity and a broad, model-specific integration. Still, it should not be merged with the other two because each PR introduces a different model family.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Both are model-addition PRs and overlap on generic Transformers integration files, but DeepSeek OCR and Isaac are different models with different architectures and documentation/tests; they are not the same underlying change." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Isaac and Kimi2-6 are distinct new model implementations. The shared auto-registration/docs patterns are boilerplate, not evidence of a single fix or mergeable duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 30, + "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": "faede77314437db271c11fac60eab3b66c4fa5b38624ff1f8fe524a7de36017b", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5934, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5934, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs are broad GitHub Actions dependency bumps, but they target different actions and different failure modes: one is for GitHub Actions runtime/node24 compatibility, the other is for docker/build-push-action version updates. They are related in theme but not the same underlying change.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42975 is the broader and more representative workflow-maintenance change, updating multiple core GitHub Actions used across many workflows for Node 24 compatibility.", + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the best single representative of the cluster because it spans more workflows and the change is a clearer platform-wide maintenance update than the narrower Docker action bump in 42976.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Reject: these are separate dependency upgrades affecting different actions and code paths. 42975 updates checkout/cache/upload-artifact for workflow runtime compatibility, while 42976 only bumps docker/build-push-action in container-image workflows; they could not plausibly be merged as one duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 30, + "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": "919fa37cb19082776953bd7f18e1e3ac6405962eec55d3e1bdf5b61281402bd9", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23542, + "estimated_input_tokens": 5886, + "estimated_eval_tokens": 12028 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23542, + "estimated_input_tokens": 5886, + "estimated_eval_tokens": 12028 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is a set of unrelated pull requests: several distinct model-addition PRs, one distributed pipeline-parallel infrastructure PR, and one PP-OCRv6 text-recognition PR. They share superficial patterns like docs/toctree and auto-registry edits, but not the same concrete code-path or bug fix.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the cluster does not contain duplicate changes. The PRs target different models or a separate distributed loading feature, so they should remain separate.", + "best_issue_reason": null, + "best_pr_reason": "PR 43451 is the strongest standalone representative by scope and review activity, but it is still not a duplicate of the others; it is a distinct Molmo2 model addition with broad model/processor/test coverage.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different model additions: ViT NEPA vs Molmo. Shared docs/auto-registry edits are incidental, not the same underlying change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different model additions: ViT NEPA vs Molmo2. No shared concrete bug or code path." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "Different model additions: ViT NEPA vs CTSM. Similar scaffolding only, not duplicate work." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are related by naming, but they are distinct model integrations with different files and coverage, not one mergeable fix." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo vs CTSM are separate model additions with different implementations and targets." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are different model integrations; no evidence of the same bug or feature." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45838", + "accept": false, + "reason": "Lfm2 Audio support and PP-OCRv6 text recognition are unrelated model additions, despite both touching docs and auto mappings." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45838", + "accept": false, + "reason": "Pipeline-parallel loading infrastructure is unrelated to PP-OCRv6 model support; they fix different layers and cannot plausibly be merged as one PR." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45838", + "accept": false, + "reason": "CTSM model support and PP-OCRv6 text recognition are distinct model additions with different code paths and tests." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 30, + "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:45981" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43291|pull_request:45981", + "pull_request:43665|pull_request:44815", + "pull_request:43665|pull_request:45981", + "pull_request:44815|pull_request:45981" + ], + "prepared_review_unit_hash": "1a167d54829c67ead3fec374a62639f9a65109221ac405b4288b5814acbd5689", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 9639, + "estimated_input_tokens": 2410, + "estimated_eval_tokens": 5076 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 9639, + "estimated_input_tokens": 2410, + "estimated_eval_tokens": 5076 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster is not a duplicate set: it mixes unrelated PRs across Whisper tokenization, CLIP/ViT test edits, FP8 dequant/loading logic, and a ColQwen2 test fix. The only substantial code-path fix is the FP8 dequant PR; the others are test-only or model-specific changes with no shared underlying bug.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44815 is the strongest representative because it contains a real implementation fix in core loading / FP8 integration, while the other PRs are narrow test tweaks or different model areas.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 is the best standalone PR in the set; it addresses a concrete runtime bug with actual code changes and is more substantive than the test-only PRs.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Both are test-oriented, but they target different model stacks and different issues: Whisper tokenizer decode behavior vs. CLIP/ViT test edits. No shared underlying bug or mergeable single fix." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper tokenization/test changes are unrelated to the FP8 dequant/core loading fix. Different subsystems and different code paths." + }, + { + "left": "pull_request:43291", + "right": "pull_request:45981", + "accept": false, + "reason": "Whisper decode logic and ColQwen2 test-device placement are unrelated model-specific changes." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "PR 43665 is effectively test noise in CLIP/ViT, while PR 44815 fixes FP8 quantization/loading behavior. They do not fix the same concrete problem." + }, + { + "left": "pull_request:43665", + "right": "pull_request:45981", + "accept": false, + "reason": "These are separate test changes for different models (CLIP/ViT vs. ColQwen2), not the same bug or change." + }, + { + "left": "pull_request:44815", + "right": "pull_request:45981", + "accept": false, + "reason": "FP8 dequant/core-loading logic is unrelated to a ColQwen2 test tensor device fix; different code paths and different failure modes." + } + ] + }, + "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": 30, + "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": "c028e0b0e92be0ba3c9dbd914d97cc8daa7406f0910c9f5e2e26c59557ba26fb", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are not duplicates: one is a synthetic repo-bot/check PR around setup/versioning and a Vit test, while the other is a workflow/infrastructure PR spanning GitHub Actions, testing utilities, and notifications. The shared Vit test filename appears incidental.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43532 is the better canonical representative because it is a coherent, substantive change across workflow and test infrastructure, whereas #43488 looks like a small synthetic/bot-validation PR.", + "best_issue_reason": null, + "best_pr_reason": "PR #43532 is the strongest stand-alone PR in the cluster: it has a broader, internally consistent diff and appears to target a real codebase change rather than a placeholder check.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Different underlying changes: #43488 edits setup/versioning and a Vit test for a repo-bot check, while #43532 changes CI workflows plus testing/notification code. Shared test filename is not enough to indicate the same fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 30, + "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": "3f7c96661bd42bb001690a584d06a538a127d50c5aa66fc74af77e85275c54a3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related by theme but are not duplicates: they add two different promptable segmentation pipelines with different targets, code paths, and model/test coverage.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR for duplicate triage; 43612 and 43613 implement different features (concept segmentation vs visual segmentation) rather than the same change.", + "best_issue_reason": null, + "best_pr_reason": "If a representative PR is needed, 43613 is the broader one, but it still is not a substitute for 43612 because it covers a different pipeline and different underlying models.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Reject: despite overlapping docs and shared plumbing, these are distinct feature PRs for different pipelines and different underlying code/model paths, so they could not plausibly be merged into one duplicate change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 30, + "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": "3c4c88639e1f40c8087035c24fdebabbae14b7758ca831ddf0898ef85c19eeae", + "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": "Two distinct trainer.py PRs: one adds a hook for gradient-accumulation loss scaling, the other adds a hook for signature-column filtering. They share a file and theme, but not the same underlying bug or change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43651 is the clearer representative of a concrete trainer behavior change, with a focused code-path update in training_step and a new hook for loss scaling.", + "best_issue_reason": null, + "best_pr_reason": "PR 43651 is the strongest standalone PR in the cluster because it addresses a specific training-time bug/behavior and is easier to reason about as a representative change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Both touch transformers/trainer.py, but they fix different trainer extension points: loss scaling during gradient accumulation vs. signature-column filtering for model inputs. They are not the same concrete bug or mergeable duplicate change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 30, + "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": "4dea8268748b64739dc6f6ba9f690dc4f4487426af8849ad38cd0bdf8543ce9f", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5991, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5991, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs cluster around the same CLI `serve.py` annotation/runtime `TypeAdapter` NameError. PR 43842 is the cleanest narrowly-scoped fix; 43656 is related but broader, and 43836 is more refactor-heavy.", + "confidence": 0.77, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:43842 is the most focused fix for the concrete `TypeAdapter` NameError in `src/transformers/cli/serve.py`, with a minimal targeted change and an explicit issue link.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:43842 best represents the underlying bug fix because it directly targets the runtime/import problem with the smallest, most specific patch.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": true, + "reason": "Both address the same `TypeAdapter` NameError in `serve.py`; the fixes are different implementations of the same annotation/runtime problem and could plausibly be merged into one PR." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "Both target the same `serve.py` `TypeAdapter` NameError path. Although 43836 is broader, the core bug and fix area overlap enough that they look like alternate solutions to the same issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays within the packet: all three PRs touch `src/transformers/cli/serve.py` and are plausibly part of the same `TypeAdapter`/annotation runtime issue, with 43842 the narrowest fix. The soft-edge verdicts are conservative enough, especially since 43836 and 43842 share the same issue target and 43656 is framed as a plausible alternate implementation rather than a definitive duplicate." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 30, + "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": 30, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44066|pull_request:44071", + "pull_request:44018|pull_request:44068", + "pull_request:44066|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44722", + "pull_request:44068|pull_request:44116", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44018|pull_request:44086", + "pull_request:44018|pull_request:44085", + "pull_request:44071|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44059|pull_request:44722", + "pull_request:44098|pull_request:44101", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44073|pull_request:44161", + "pull_request:44056|pull_request:44101", + "pull_request:44059|pull_request:44068", + "pull_request:44018|pull_request:44059", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44018", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:44018|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44018|pull_request:44129", + "pull_request:44010|pull_request:44073", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44071|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "14d5da96df2e714c672a3a8ef74d6d47e009fc353ed67590fc185ffbe0003af4", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84892, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75087, + "estimated_input_tokens": 18772, + "estimated_eval_tokens": 37800 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a broad theme cluster of model-specific output-tracing refactors, not one single duplicate. The only true duplicate-like groups are the GPT-J/CodeGen PRs and the GPT-Neo PRs; the rest touch different model implementations and should stay separate.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44722 is the clearest representative of the repeated GPT-J/CodeGen output-tracing refactor: it targets the same standardized-decorator change, touches the same core code paths, and is the most self-contained late-stage variant in the duplicate-like subgroup.", + "best_issue_reason": null, + "best_pr_reason": "44722 best represents the main duplicate-like subgroup because it directly refactors GPT-J output tracing with the standardized decorator approach and also includes the related CodeGen companion change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families and different code paths; same issue target alone is not enough." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "CVT/FNet refactor is unrelated to DeBERTa V2 beyond the shared output-tracing theme." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors in the same file and implement the same concrete change." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "ResNet/RT-DETR ResNet versus EfficientNet are different model implementations and not the same duplicate." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet output tracing is unrelated to GPT-J/CodeGen output tracing." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "Different model code paths; only the high-level refactor theme is shared." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa V2 are unrelated concrete changes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen versus MGP-STR are different underlying implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are separate model-specific refactors." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Same GPT-Neo file and same standardized output-tracing change; one looks like a later/alternate version of the other." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are different code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet refactor is not the same underlying change as GPT-J/CodeGen." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR output tracing is a different model-specific change." + }, + { + "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 model paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT are unrelated concrete changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo versus GPT-J/CodeGen are different model refactors." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44085", + "accept": false, + "reason": "MPT and GPT-J are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated implementations." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 refactor is not the same change as MGP-STR." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are different model-specific changes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 output tracing is not the same concrete bug/change as GPT-J/CodeGen." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are different model families and separate changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are unrelated model implementations." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "SegFormer output tracing is a different code path from GPT-J/CodeGen." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "SegFormer and LongT5 are different model-specific refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "SegFormer and VisualBert are unrelated implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "MPT and MGP-STR are unrelated model changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44073", + "accept": false, + "reason": "RegNet and VisualBert are different model implementations." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are unrelated concrete changes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-2 and MPT are different code paths." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "VisualBert and LongT5 are different model-specific refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are unrelated implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are not the same underlying change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 are separate model-specific changes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are different code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBERT and MPT are unrelated implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44161", + "accept": false, + "reason": "GPT-Neo and LongT5 are different model-specific refactors." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBERT and DeBERTa V2 are different underlying changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa V2 and TextNet are unrelated model implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa V2 and SpeechT5 are different code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa V2 and Vits are separate model-specific changes." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays conservative about duplicate-like relationships. The two accepted soft pairs are plausible same-file/same-bugfix variants, and the rejected pairs are appropriately split by model family or code path rather than overstating similarity." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 30, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request:44024", + "pull_request:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44129" + ], + "soft_pairs": [ + "pull_request:44024|pull_request:44076", + "pull_request:44073|pull_request:44074", + "pull_request:44056|pull_request:44073", + "pull_request:44056|pull_request:44074", + "pull_request:43997|pull_request:44010", + "pull_request:44010|pull_request:44129" + ], + "prepared_review_unit_hash": "16be0a6daa058864c1b77950a1d65475c700d1dd49b3392866d821a2ab020ffd", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84892, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17126, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All items are model-specific PRs for standardized output tracing / capture_outputs refactors. They share a theme, but they target different architectures and code paths, so they are related changes rather than duplicates.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44129 is the best representative PR in this set: it has an explicit issue target, a focused single-model refactor, and appears more complete than the smaller model migrations.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 is the strongest standalone candidate for triage because it is concrete, scoped, and anchored to a tracked issue; the others are similar refactor patterns but not interchangeable with it.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Same refactor theme, but FocalNet and ImageGPT are different model implementations with different output paths; not the same underlying change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Both migrate to output-capture helpers, but they touch different models and code paths, so they should not be merged as one PR." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet vs VisualBert is a shared pattern only; the concrete fix sites and model behavior are different." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "These are separate model-specific output-tracing refactors, not one duplicate bug or change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated model code paths; similar helper migration does not make them duplicates." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "Both are standardized output refactors, but SqueezeBert and SpeechT5 address different concrete implementations and cannot plausibly be one merged PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 30, + "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": "8000c24243315a35bc317867e4a705c633c1d2f61d49fe3406528b3b12a6e428", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40179, + "estimated_input_tokens": 10045, + "estimated_eval_tokens": 20346 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40179, + "estimated_input_tokens": 10045, + "estimated_eval_tokens": 20346 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All items are distinct model-specific output-tracing refactor PRs. They share a common pattern, but none appear to fix the same concrete bug or change, so I would not merge any pair as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44003 is the broadest representative of the cluster, touching two closely related Mamba variants and showing the shared output-tracing refactor pattern most clearly.", + "best_issue_reason": null, + "best_pr_reason": "PR 44003 is the best global representative because it spans multiple related code paths while still being a single coherent refactor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models and forward paths; same refactor theme, not the same fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Timm backbone vs vision-text dual encoder are unrelated code paths." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Timm backbone and UnivNet are separate model implementations with different behavior." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families; both refactor output handling but not the same underlying change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Timm backbone and RWKV are unrelated model code paths." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "MobileNetV1 and UnivNet are distinct architectures; not a duplicate fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "MobileNetV1 vs UperNet; similar refactor pattern only." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "Different models and different output-tracing surfaces; not the same PR-level change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "MobileNetV1 and VisionEncoderDecoder have separate forward implementations." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "MobileNetV1 and SpeechEncoderDecoder are unrelated code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Vision-text dual encoder and UnivNet fix different model outputs." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models and different forward logic; not mergeable as one fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Separate model families with no shared concrete bug." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model architectures; same refactor style but not the same code-path problem." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "UnivNet and UperNet are unrelated implementations." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "UnivNet vs Mamba family; no shared concrete fix." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model code paths; only the output-tracing pattern overlaps." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "UperNet and RWKV are unrelated model paths." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "Different subsystems and forward contracts; not duplicates." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "Mamba-family refactor vs SuperPoint feature extractor; distinct code paths." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Mamba-family tracing changes and CodeGen cache/output changes are separate fixes." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Timm backbone and CodeGen address different model internals." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet audio generation and CodeGen attention/cache code are unrelated." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "UperNet segmentation and CodeGen are distinct code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Vision-text dual encoder and CodeGen do not share the same concrete bug." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Depth-Anything and VisionEncoderDecoder are separate model implementations." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Depth-Anything and SpeechEncoderDecoder are different code paths." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Depth-Anything and SuperPoint are unrelated models." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Depth-Anything and RWKV fix different output-tracing surfaces." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Depth-Anything and DPR are separate architectures and forward methods." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "VisionEncoderDecoder and RWKV are unrelated model code paths." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are similar wrappers but still different concrete implementations." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Different model families; no single underlying bug." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "VisionEncoderDecoder and DPR change different code paths." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "SpeechEncoderDecoder and RWKV are distinct model implementations." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "SpeechEncoderDecoder and DPR do not share the same concrete change." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are unrelated code paths." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "SuperPoint and DPR are different model internals." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are separate implementations; same pattern only." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 30, + "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": "62ac0d9f71d85c36648ed78c2279275a6ae09f6d2f7afbd8c9942fa72a7d4023", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition PRs for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share Transformers boilerplate and auto-registration changes, but they do not appear to fix or implement the same concrete code path, so they should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45075 is the best representative if one is needed: it is non-draft, has the most review activity, and looks like a full model integration with conversion, image processing, modeling, and tests.", + "best_issue_reason": null, + "best_pr_reason": "PR 45075 is the strongest standalone candidate because it is the most mature and complete of the three integrations, with broader implementation coverage than the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different models and different code paths: PenguinVL vs Voxtral TTS. Shared docs/auto-registry boilerplate is not enough to treat them as the same change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "Different model integrations (PenguinVL vs DeepSeek-OCR-2). They both add new model packages, but not the same underlying bug or feature." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are unrelated model additions; overlap is limited to common Transformers scaffolding, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 30, + "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": "806642044db55b74098c46cfb840b289997e85cbe0386b797d5bed42638818ff", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are related to fusion infrastructure, but they change different layers and are not the same mergeable fix/change: #44979 introduces a new module fusion API, while #45363 wires kernel-config-based n-to-1 fusion into model loading and adds an example. Related theme, not a duplicate.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "#44979 is the more foundational PR: it defines the standalone Module Fusion API and test coverage, whereas #45363 is a later, narrower integration built on a different concept (KernelConfig-based kernel fusion).", + "best_issue_reason": null, + "best_pr_reason": "#44979 is the best representative of the cluster because it is the core API change; #45363 is an application/integration of fusion ideas rather than the same concrete code-path change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Different concrete changes: #44979 adds a new module fusion framework in src/transformers/module_fusion.py, while #45363 adds KernelConfig-driven n-to-1 fusion plumbing across model loading/integrations. Same broad area, but not the same underlying bug or one PR that could simply absorb the other." + } + ] + }, + "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": 30, + "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": "781c5b225f05a4980757f27344cb412f689767fe155734770ee5ee17be6d3494", + "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 appear to fix the same concrete Mistral regex AttributeError in the same code path (`_patch_mistral_regex`) with essentially the same change; the later PR also adds a test, so this looks like a duplicate PR cluster.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "`pull_request:45317` is the stronger canonical PR because it implements the same fix as 45086 and also includes a test update, making it the more complete representative of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "`pull_request:45317` is the best representative overall since it addresses the same bug and adds accompanying test coverage, whereas 45086 is the narrower earlier version.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same issue target, same file, and the diff shows the same AttributeError fix in `_patch_mistral_regex`; the second PR is essentially the same patch with added tests." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 30, + "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": "fd0ce53f19a9e54fe304d43cfeb0103cc64be2310004f82affd40f8c43ee1199", + "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": "These PRs overlap on NemotronH model files, but they address different changes: one refactors NemotronH to inherit GraniteMoeHybrid and updates conversion mapping, while the other splits NemotronH into dense/sparse variants with a backward-compat dispatcher plus docs/tests. They are related, but not the same concrete fix.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the more comprehensive and user-facing NemotronH change, introducing the dense/sparse model split and compatibility wrapper rather than only a conversion/refactor layer.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 best represents the cluster because it covers the larger architectural change and the broader set of affected files, including docs and tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Both touch NemotronH internals, but #45115 is a narrow GraniteMoeHybrid inheritance/conversion-mapping refactor, while #45569 restructures NemotronH into dense/sparse models and updates docs/tests. They are not the same underlying change and would not plausibly merge 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": 20, + "component_count": 30, + "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": "2cd1977abba5636b5a1b7db895000412206fa9ab82db242a6375172f6ef33193", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5397, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5397, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two related but distinct PRs: one adds per-layer heterogeneous config support, the other adds broader heterogeneous model/runtime support. They overlap in shared config plumbing and tests, but they are not the same concrete change.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes heterogeneous config handling plus model/cache/masking support and therefore best represents the cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the best single representative because it covers the full heterogeneous-model feature set, not just the config foundation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature work, but not the same underlying bug or change: #45333 is config-only plumbing, while #45332 extends into model/runtime behavior. They could be separate PRs rather than one merged fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 30, + "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": "1b7a2c25de84c595dc7441ccef7b4bf54540635d967322c823f3620d2b1a5393", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs both touch typing-related files, but they are not the same underlying change: #45415 is a broad repository-wide type-checking sweep and config tweak, while #45425 adds specific typing helper protocols/aliases for model utility code. The overlap is incidental, not a duplicate fix.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45425 is the more focused substantive typing-infrastructure change; #45415 is a broad type-checking cleanup pass with many unrelated file edits.", + "best_issue_reason": null, + "best_pr_reason": "#45425 is the best representative PR for the cluster because it introduces concrete typing abstractions used by multiple code paths, whereas #45415 is primarily a sweeping type-check enablement/change-set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Reject: #45415 is a broad type-checking sweep/configuration update, while #45425 adds specific typing protocols and aliases. Shared files do not indicate the same bug or a single mergeable fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 22, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45487-6", + "nodes": [ + "pull_request:45487", + "pull_request:45817", + "pull_request:45843", + "pull_request:45858", + "pull_request:45890", + "pull_request:45926" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:45843", + "pull_request:45487|pull_request:45926", + "pull_request:45817|pull_request:45843", + "pull_request:45858|pull_request:45890", + "pull_request:45858|pull_request:45926", + "pull_request:45890|pull_request:45926" + ], + "prepared_review_unit_hash": "893f6287bc80aa435359d4f4c5b86a9a30e2a75dd9f845c205ef7ba91a422c1e", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 6, + "serialized_chars": 14717, + "estimated_input_tokens": 3680, + "estimated_eval_tokens": 7616 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 6, + "serialized_chars": 14717, + "estimated_input_tokens": 3680, + "estimated_eval_tokens": 7616 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are related only at a very broad theme level (model-parallel/XPU support), but they target different models and mostly different code paths. None of the soft edges look like true duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45817 is the strongest representative: it makes concrete code-path fixes for Gemma4 model-parallel behavior (device placement plus split-module handling) and includes tests, unlike the test-only expectation updates.", + "best_issue_reason": null, + "best_pr_reason": "PR 45817 is the best standalone candidate because it addresses an actual runtime model-parallel bug in the implementation, not just platform-specific test expectations.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel fixes, but for different model families and different code paths. They are not the same underlying bug and would not plausibly be merged into one PR." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45926", + "accept": false, + "reason": "AltCLIP/ChineseCLIP model-parallel device handling is unrelated to HyperCLOVAX XPU test expectations." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Gemma4 and Deimv2 are separate model-specific fixes; the shared theme is too broad to treat as a duplicate." + }, + { + "left": "pull_request:45858", + "right": "pull_request:45890", + "accept": false, + "reason": "Both add XPU expectations, but for different models and tests. Same pattern, not the same bug or change." + }, + { + "left": "pull_request:45858", + "right": "pull_request:45926", + "accept": false, + "reason": "These are model-specific test expectation updates for different architectures, with no shared concrete code-path issue." + }, + { + "left": "pull_request:45890", + "right": "pull_request:45926", + "accept": false, + "reason": "Different model test suites and different expectation values; not a duplicate change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 30, + "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": "3537647a7127d65aa27f750de3ecf30a027180c35d5a3ecf43406e3296389432", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs both concern expert parallelism loading, but they fix different failure modes on different code paths: one strips/recognizes distributed config for EP + ZeRO-3 loading, while the other prevents expert tensors from being overwritten during FSDP2/rank-0 broadcast handling.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "No exact duplicate here; if forced to pick one representative, PR #45662 is the stronger canonical PR because it targets a concrete overwrite bug in the loading path and includes the broader set of code-path fixes.", + "best_issue_reason": null, + "best_pr_reason": "PR #45662 is the best standalone PR because it addresses a specific, actionable loading corruption issue with clear runtime impact, whereas PR #45548 is narrower and solves a different EP/ZeRO-3 serialization/loading problem.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "They share expert-parallel/loading context, but the bugs and fixes differ: #45548 removes distributed_config from serialization and adds has_ep for EP + DeepSpeed ZeRO-3 loading, while #45662 changes post-shard wrapping to prevent expert parameters being overwritten under FSDP2/rank-0 broadcast. Not the same underlying bug or 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": 24, + "component_count": 30, + "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": "6e2bc6fe3a4f855d1614633ba1831711dbcf5532ec936c6ef80b03ea49319843", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4589, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4589, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs target the same xdist-safe captured_info logging problem under issue #45561; PR 45645 is the broader, more complete fix and subsumes the testing_utils changes from 45639.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the best canonical PR because it includes the core xdist-safe file handling change plus the CI/workflow updates needed to aggregate multiple captured_info files, making it the more complete fix.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 is the strongest representative because it addresses the same underlying collision bug and also preserves/debugs CI log collection across xdist workers, whereas 45639 only fixes the library-side write path.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Both PRs fix the same concrete captured_info xdist collision in testing_utils; 45645 is effectively an expanded version of the 45639 fix with additional workflow handling, so they are close enough to treat as the same change cluster." + } + ] + }, + "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": 30, + "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": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 27, + "component_count": 30, + "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-45863-2", + "nodes": [ + "pull_request:45863", + "pull_request:45986" + ], + "soft_pairs": [ + "pull_request:45863|pull_request:45986" + ], + "prepared_review_unit_hash": "7f3114ee77134795638a4283bd1af3474d358fde534abcd721fee18249cf0286", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3691, + "estimated_input_tokens": 923, + "estimated_eval_tokens": 2102 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3691, + "estimated_input_tokens": 923, + "estimated_eval_tokens": 2102 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests address the same MLX availability bug: Transformers should opt out of MLX detection when HF_USE_MLX is disabled. PR 45863 is the broader, more complete fix with docs and tests; PR 45986 is a narrower code-only variant of the same change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45863 is the better canonical representative because it implements the HF_USE_MLX opt-out and also includes documentation and test coverage, making it the more complete version of the fix.", + "best_issue_reason": null, + "best_pr_reason": "PR 45863 is the strongest overall fit for the cluster since it directly fixes the MLX detection path and provides the supporting docs/tests; PR 45986 is a partial duplicate of the same code-path change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45863", + "right": "pull_request:45986", + "accept": true, + "reason": "Both PRs fix the same concrete bug in is_mlx_available() and would plausibly be merged into one change; the second PR is a narrower variant of the same HF_USE_MLX opt-out." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet: both PRs target the same issue target and the same MLX availability code path, and the mergeability claim is conservative. The canonical pick for 45863 is also supported by the extra docs/tests it adds. " + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 28, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45975-2", + "nodes": [ + "pull_request:45975", + "pull_request:45977" + ], + "soft_pairs": [ + "pull_request:45975|pull_request:45977" + ], + "prepared_review_unit_hash": "285d91188b4c345e9c7509db18eae662e9a523993e0d97f20fc759b3826cae18", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4523, + "estimated_input_tokens": 1131, + "estimated_eval_tokens": 2518 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4523, + "estimated_input_tokens": 1131, + "estimated_eval_tokens": 2518 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs target GGUF on Apple Silicon, but they address different layers of the stack: PR 45975 adds CLI/model-manager support and an optional kernels-community dequant fast path, while PR 45977 introduces a new GgufLinear integration with model plumbing and tests. Related subsystem, but not the same underlying change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45977 is the more substantial, self-contained feature PR: it adds a new GGUF linear integration and supporting model/quantizer/test plumbing, whereas PR 45975 is mainly an optional fast-path toggle and CLI/help wiring.", + "best_issue_reason": null, + "best_pr_reason": "PR 45977 is the strongest representative of the cluster because it makes the core implementation change and has the broadest functional surface area; PR 45975 looks like a narrower companion optimization rather than a duplicate fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45975", + "right": "pull_request:45977", + "accept": false, + "reason": "They both involve GGUF/Metal on Apple Silicon, but 45975 is about an optional kernels-community dequant fast path and CLI/model-manager wiring, while 45977 adds a new GgufLinear inference path. Different concrete changes, not mergeable as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 29, + "component_count": 30, + "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-45976-2", + "nodes": [ + "pull_request:45976", + "pull_request:45989" + ], + "soft_pairs": [ + "pull_request:45976|pull_request:45989" + ], + "prepared_review_unit_hash": "055ab1d620a97c8693b657a9612c592ed664686d7e55eb1aff45ceffad3fd0be", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4493, + "estimated_input_tokens": 1124, + "estimated_eval_tokens": 2504 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4493, + "estimated_input_tokens": 1124, + "estimated_eval_tokens": 2504 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related Llama4 MoE changes, but they address different layers of the stack: one fixes tensor-parallel expert calling/aggregation behavior, the other switches Llama4 experts to the standard expert implementation interface. They do not look like the same mergeable bugfix/change.", + "confidence": 0.79, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45976 is the broader, more concrete fix: it patches the tensor-parallel expert path, adds Llama4-specific model/config/test coverage, and directly addresses the crash described in the title.", + "best_issue_reason": null, + "best_pr_reason": "PR 45976 is the strongest representative of the cluster because it fixes the actual crash path and includes validation; PR 45989 is narrower and looks like an interface-adoption refactor that may complement, but not duplicate, the crash fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45976", + "right": "pull_request:45989", + "accept": false, + "reason": "They touch the same Llama4 expert subsystem, but 45976 fixes a tensor-parallel crash for pre-weighted MoE experts while 45989 adopts the standard expert implementation decorator. Different code paths, different concrete problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 30, + "component_count": 30, + "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-45991-2", + "nodes": [ + "pull_request:45991", + "pull_request:45993" + ], + "soft_pairs": [ + "pull_request:45991|pull_request:45993" + ], + "prepared_review_unit_hash": "db9dd3522f36bd4d9a61568669869bd83deb3e403c87e2e5c51163798f4bcb31", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4234, + "estimated_input_tokens": 1059, + "estimated_eval_tokens": 2374 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4234, + "estimated_input_tokens": 1059, + "estimated_eval_tokens": 2374 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are not duplicates: one enables Flash Attention 2 for T5Gemma2, the other enables flash-attn support for EOMT. They touch different model families and different code paths.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the changes target different architectures (T5Gemma2 vs EOMT) and are independent model-specific enablement patches.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a global representative of the other; if forced, 45991 is the more substantial change, but it is not a better duplicate canonical for 45993.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45991", + "right": "pull_request:45993", + "accept": false, + "reason": "Different models and different support toggles; they do not fix the same underlying bug or change and would not be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/manifest.json b/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..65abf9eb9002ae3c8a479fd087d73aa3a1528321 --- /dev/null +++ b/snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260515t120027z", + "artifacts": { + "hybrid": "snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-15T12:09:11Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260515T120027Z", + "variant": "hybrid" +} diff --git a/snapshots/20260515T120027Z/manifest.json b/snapshots/20260515T120027Z/manifest.json index 065cdcd698acb6e2df0a7aec1e07da5280bf8aa7..46453c50a3aa09e85834caa2c5cdeed86b011d1d 100644 --- a/snapshots/20260515T120027Z/manifest.json +++ b/snapshots/20260515T120027Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 478 }, "extracted_at": "2026-05-15T12:00:27Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260515t120027z", + "runs": { + "hybrid-model-20260515t120027z": { + "analysis_id": "hybrid-model-20260515t120027z", + "artifacts": { + "hybrid": "snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260515T120027Z/analysis-runs/hybrid-model-20260515t120027z/manifest.json", + "model": null, + "published_at": "2026-05-15T12:09:11Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260515T120027Z", "watermark": {