diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index 2969b2c895f4ce5252e26095537cbaf120e26923..d8a377e9c66bd7f45a86e4dcef04da01e6338129 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": "20260516T060035Z", - "generated_at": "2026-05-16T06:02:30Z", + "snapshot_id": "20260516T120032Z", + "generated_at": "2026-05-16T12:09:06Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1148,6 +1148,204 @@ } ] }, + { + "cluster_id": "cluster-43656-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43824, + "canonical_pr_number": 43656, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43656, + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43656, + "right_pr_number": 43836, + "code_similarity": 0.36, + "size_similarity": 0.176, + "file_overlap": 1.0, + "area_overlap": 0.051, + "patch_similarity": 0.048, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ] + } + ] + }, + { + "left_pr_number": 43656, + "right_pr_number": 43842, + "code_similarity": 0.405, + "size_similarity": 0.5, + "file_overlap": 1.0, + "area_overlap": 0.0, + "patch_similarity": 0.036, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + }, + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, { "cluster_id": "cluster-43240-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", @@ -1422,76 +1620,6 @@ } ] }, - { - "cluster_id": "cluster-43824-3", - "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", - "status": "open", - "confidence": 0.75, - "canonical_issue_number": 43824, - "canonical_pr_number": 43836, - "issue_numbers": [ - 43824 - ], - "pr_numbers": [ - 43836, - 43842 - ], - "evidence_types": [ - "closing_reference", - "shared_issue_target" - ], - "pr_comparisons": [ - { - "left_pr_number": 43836, - "right_pr_number": 43842, - "code_similarity": 0.332, - "size_similarity": 0.088, - "file_overlap": 1.0, - "area_overlap": 0.033, - "patch_similarity": 0.017, - "shared_filenames": [ - "src/transformers/cli/serve.py" - ], - "shared_file_areas": [ - { - "filename": "src/transformers/cli/serve.py", - "left_ranges": [ - [ - 11, - 18 - ], - [ - 359, - 429 - ], - [ - 584, - 590 - ], - [ - 1892, - 1910 - ], - [ - 1917, - 1923 - ] - ], - "right_ranges": [ - [ - 54, - 61 - ], - [ - 587, - 593 - ] - ] - } - ] - } - ] - }, { "cluster_id": "cluster-45081-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", @@ -1684,6 +1812,35 @@ } ] }, + { + "cluster_id": "cluster-44002-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44002, + "issue_numbers": [], + "pr_numbers": [ + 44002, + 44029 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44002, + "right_pr_number": 44029, + "code_similarity": 0.135, + "size_similarity": 0.43, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, { "cluster_id": "cluster-44018-2", "summary": "Cluster of 2 related pull requests linked by soft_similarity.", @@ -1989,6 +2146,16 @@ "target_issue_number": 43240, "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." }, + { + "cluster_id": "cluster-43656-4", + "canonical_pr_number": 43656, + "duplicate_pr_numbers": [ + 43836, + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43656-4 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target, soft_similarity evidence." + }, { "cluster_id": "cluster-43698-3", "canonical_pr_number": 43779, @@ -1998,15 +2165,6 @@ "target_issue_number": 43698, "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." }, - { - "cluster_id": "cluster-43824-3", - "canonical_pr_number": 43836, - "duplicate_pr_numbers": [ - 43842 - ], - "target_issue_number": 43824, - "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." - }, { "cluster_id": "cluster-43979-11", "canonical_pr_number": 44007, @@ -2024,6 +2182,15 @@ "target_issue_number": 43979, "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." }, + { + "cluster_id": "cluster-44002-2", + "canonical_pr_number": 44002, + "duplicate_pr_numbers": [ + 44029 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44002-2 are treated as duplicates because they share soft_similarity evidence." + }, { "cluster_id": "cluster-44018-2", "canonical_pr_number": 44068, diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index afa055c208b530a8b601e549708277cca0d3a996..6320a6af0f9d156d477d5c1006d18196d53dfcff 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": "20260516T060035Z", - "generated_at": "2026-05-16T06:02:30Z", + "snapshot_id": "20260516T120032Z", + "generated_at": "2026-05-16T12:09:06Z", "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:24643", "issue:30277", @@ -32,11 +32,11 @@ "issue:42915", "issue:43039", "issue:43425", + "issue:43531", "issue:43541", "issue:43596", "issue:43638", "issue:43716", - "issue:43792", "issue:43827", "issue:43828", "issue:43854", @@ -128,397 +128,379 @@ "issue:45812|issue:45920", "issue:43866|issue:44863", "issue:43854|issue:43866", - "issue:41093|issue:43638", - "issue:43792|issue:45901" + "issue:39290|issue:43531", + "issue:41093|issue:43638" ], - "prepared_review_unit_hash": "4a9071dcd5cd890b54780b931e3b8b16f18611bd6590e7ed282fa1d5dfb3fe8d", + "prepared_review_unit_hash": "da6a3f199e7807061fab7cb571fb9b918b1be1615fe85a514fa79539e21d5134", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 62, - "serialized_chars": 46368, - "estimated_input_tokens": 11592, - "estimated_eval_tokens": 23440 + "serialized_chars": 46384, + "estimated_input_tokens": 11596, + "estimated_eval_tokens": 23448 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous cluster of unrelated issue reports, but there are two genuine duplicate pockets: DeepSpeed ZeRO-3/BERT size-0 index failures and AutoTokenizer wrong-token-ID v5 regressions. No pull requests are present.", - "confidence": 0.84, - "canonical_issue_reason": "issue:43596 is the clearest canonical anchor for the repeated DeepSpeed ZeRO-3/BERT \"index 0 is out of bounds for dimension 0 with size 0\" failure and is the best match to its near-duplicate 43638.", + "summary": "This cluster is mostly heterogeneous, but it contains two clear duplicate subgroups: ZeRO-3/Bert index-out-of-bounds failures and the v5 AutoTokenizer wrong-token-ID regression. Most other pairs share a broad subsystem but look like distinct bugs or regressions.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45920 is the broadest and most representative issue in the tokenizer regression subgroup, covering multiple model families; issue:45812 looks like a narrower Granite-specific instance of the same v5 token-ID bug.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43596 is the best overall issue to keep as canonical because it captures the most concrete, repeated bug in the cluster and cleanly represents the closest duplicate pair.", + "best_issue_reason": "issue:45920 is the best single anchor for the cluster because it captures the widest concrete bug pattern among the listed issues and is likely to subsume related reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different symptoms: Qwen3.5 config AttributeError vs streaming chat/completions failure." + "reason": "Different failures: Qwen3.5 config attribute access vs streaming chat/completions handling." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Different bugs: AMD GPU runtime failure vs MPS histogram op unsupported for Int." + "reason": "Different model/runtime problems; shared GPU/MoE context is too broad to call duplicate." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Different models and failure modes: Mistral-3 dtype mismatch vs GPT-OSS on AMD GPUs." + "reason": "Both are model-specific device/dtype issues, but with different models and failure modes." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Autocast dtype mismatch in Phi-tiny-MoE vs AMD GPU execution failure in GPT-OSS." + "reason": "Different concrete dtype/device mismatch cases; not the same bug." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Different code paths: AMD GPU runtime issue vs invalid method call in GraniteMoEHybrid." + "reason": "AMD loading issue vs GraniteMoEHybrid invalid-method call are unrelated code-paths." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Qwen-3-8B NVFP4 runtime failure vs AMD GPU failure; not the same bug." + "reason": "Different Qwen NVFP4 runtime error vs AMD GPU loading failure." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch vs ModernBERT ONNX export; unrelated." + "reason": "Collective mismatch under DeepSpeed Zero3 vs ONNX export failure are unrelated." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "Both are model issues, but ModernBERT ONNX export and Qwen3Moe FP8 failure are different code paths." + "reason": "Both are model/export related, but one is ONNX export and the other is FineGrainedFP8 runtime behavior." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "ModernBERT ONNX export vs Qwen3 auto device-map cuda assert; unrelated." + "reason": "ONNX export error and cudaErrorAssert during auto device mapping are different bugs." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are docs regressions, but they cover different removed v5 topics (pipeline tasks vs run command)." + "reason": "Both are v5 docs cleanup, but they target different removed features and likely separate edits." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "ModernBERT ONNX export vs GenerationMixin import failure; unrelated." + "reason": "ONNX export issue and GenerationMixin import breakage are unrelated." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Mask-shape IndexError vs Gemma4 device mismatch are different failures." + "reason": "Similar-looking tensor/device errors, but different models and failure surfaces." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Different concrete errors: ZeRO-3/Bert size-0 index error vs mask/tensor shape mismatch." + "reason": "Both mention index/mask shape failures, but the model/setup context is different enough that they do not clearly match." }, { "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "Different concrete errors: ZeRO-3/Bert size-0 index error vs mask/tensor shape mismatch." + "reason": "Same general IndexError family, but one is ZeRO-3/Bert size-0 initialization and the other is a mask-shape mismatch." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Mask-shape IndexError vs GPT-OSS TP-only failure; different bugs." + "reason": "Different problems: generic mask/tensor shape mismatch vs GPT-OSS MoE tensor-parallel failure." }, { "left": "issue:44805", "right": "issue:44918", "accept": false, - "reason": "Mask-shape IndexError vs Qwen3.5 embedding unpacking failure with TRL; not the same bug." + "reason": "Different model/trainer paths; no clear same underlying bug." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "BarkProcessor voice_preset bug vs ModernBERT ONNX export; unrelated." + "reason": "BarkProcessor voice_preset vs ModernBERT ONNX export are unrelated." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Different DeepSpeed failures: collective mismatch vs BertModel size-0 index error." + "reason": "Different models and failure modes under DeepSpeed; not the same bug." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3/BERT size-0 index-out-of-bounds load failure; only the model wording differs." + "reason": "Same ZeRO-3/Bert index-0-out-of-bounds failure; the newer report is just a non-pretrained Bert variant." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger Kernel cross_entropy call vs GPT-OSS TP-only issue; different code paths." + "reason": "Liger Kernel cross-entropy call vs GPT-OSS MoE tensor-parallel failure are unrelated." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Different symptoms and scope: detokenization regression for DeepSeek-Coder vs LoRA merge/save/reload mismatch." + "reason": "Different bugs: detokenization regression vs LoRA merge/save/load mismatch." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "NVFP4 runtime failure vs LoRA merge/save/reload mismatch; unrelated." + "reason": "Quantized Qwen runtime error and LoRA merge mismatch are unrelated." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "Activation checkpointing/FSDP recompute mismatch vs mask-shape IndexError; different bugs." + "reason": "Activation checkpointing/FSDP recomputation mismatch is not the same as a mask indexing error." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "DeepSpeed weight 2-D error vs collective mismatch; distinct training failures." + "reason": "Both involve DeepSpeed, but one is a 2-D weight training error and the other is a collective mismatch." }, { "left": "issue:45859", "right": "issue:45902", "accept": false, - "reason": "Both involve Qwen3_5Moe rotary embeddings, but CPU offload incompatibility vs uninitialized memory after to_empty(cuda) are different concrete bugs." + "reason": "Same Qwen3_5Moe embedding class, but one is CPU-offload incompatibility and the other is uninitialized-memory after materialization; not clearly the same bug." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "Bert ZeRO-3 size-0 index error vs GPT-OSS TP-only issue; unrelated." - }, - { - "left": "issue:34928", - "right": "issue:36331", - "accept": false, - "reason": "FSDP activation checkpointing mismatch vs CustomTrainer compute_loss kwarg change; not the same issue." - }, - { - "left": "issue:43596", - "right": "issue:45161", - "accept": false, - "reason": "Bert ZeRO-3 size-0 index error vs GPT-OSS TP-only issue; unrelated." - }, - { - "left": "issue:43716", - "right": "issue:45507", - "accept": false, - "reason": "Mistral-3 dtype mismatch vs GraniteMoEHybrid invalid method; unrelated." - }, - { - "left": "issue:39290", - "right": "issue:45081", - "accept": false, - "reason": "Gemma3 config missing field in vLLM vs Mistral tokenizer regex patch crash." - }, - { - "left": "issue:45823", - "right": "issue:45874", - "accept": false, - "reason": "Gemma4 device mismatch vs expensive reverse embedding lookup; same family but different failures." - }, - { - "left": "issue:43425", - "right": "issue:44292", - "accept": false, - "reason": "Torch 2.10 compatibility vs Qwen-3-8B NVFP4 runtime failure; unrelated." - }, - { - "left": "issue:43828", - "right": "issue:45161", - "accept": false, - "reason": "Phi autocast dtype mismatch vs GPT-OSS TP-only failure; different code paths." - }, - { - "left": "issue:44918", - "right": "issue:45161", - "accept": false, - "reason": "Qwen3.5 embedding unpacking with TRL vs GPT-OSS TP-only failure; unrelated." + "reason": "Both involve zero-3 / model-parallel contexts, but the specific failure paths differ." }, { "left": "issue:43716", "right": "issue:45685", "accept": false, - "reason": "Mistral-3 dtype mismatch vs MPS histogram_mps Int error; unrelated." + "reason": "Different model families and different runtime errors." }, { "left": "issue:43828", "right": "issue:44292", "accept": false, - "reason": "Phi autocast dtype mismatch vs Qwen-3-8B NVFP4 runtime failure; unrelated." + "reason": "Different dtype/device issues in different models; too broad to merge." }, { - "left": "issue:43716", + "left": "issue:43425", "right": "issue:44292", "accept": false, - "reason": "Mistral-3 image-preprocessor dtype mismatch vs Qwen-3-8B NVFP4 runtime failure; unrelated." - }, - { - "left": "issue:44292", - "right": "issue:44918", - "accept": false, - "reason": "Qwen-3-8B NVFP4 runtime vs Qwen3.5 embedding unpacking; different failures." - }, - { - "left": "issue:43039", - "right": "issue:44918", - "accept": false, - "reason": "Liger Kernel cross_entropy issue vs Qwen3.5 embedding unpacking; not the same bug." - }, - { - "left": "issue:41762", - "right": "issue:43638", - "accept": false, - "reason": "Both are Zero-3 index errors, but on different model families and load paths; not enough evidence of the same bug." - }, - { - "left": "issue:43827", - "right": "issue:44512", - "accept": false, - "reason": "Outdated docs on removed pipeline tasks vs outdated docs on removed run command; different cleanup items." - }, - { - "left": "issue:43716", - "right": "issue:44560", - "accept": false, - "reason": "Mistral-3 dtype mismatch vs Qwen3-vl video StopIteration; unrelated." + "reason": "Torch version compatibility and NVFP4 runtime error are unrelated." }, { "left": "issue:43828", "right": "issue:45685", "accept": false, - "reason": "Phi autocast dtype mismatch vs MPS histogram_mps Int error; unrelated." + "reason": "Different model/runtime problems despite both being numerical/backend issues." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Qwen3-vl video StopIteration vs MPS histogram_mps Int error; unrelated." + "reason": "Video StopIteration in Qwen3-vl-embedding is unrelated to MPS histogram support." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Liger Kernel cross_entropy issue vs Phi autocast dtype mismatch; different code paths." + "reason": "Different failures in different code paths; only broad backend overlap." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed collective mismatch vs Trainer compute_loss signature change; unrelated." + "reason": "DeepSpeed collective mismatch vs trainer signature change are unrelated." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "FSDP activation checkpointing mismatch vs GenerationMixin import failure; unrelated." + "reason": "FSDP activation-checkpointing mismatch and GenerationMixin import breakage are unrelated." }, { "left": "issue:43039", "right": "issue:44805", "accept": false, - "reason": "Liger Kernel cross_entropy issue vs mask-shape IndexError; unrelated." + "reason": "Different runtime bugs; no shared concrete code path." }, { "left": "issue:41762", "right": "issue:43596", "accept": false, - "reason": "Gemma3 ZeRO-3 load error vs Bert ZeRO-3 load error; similar surface area but not clearly the same bug." + "reason": "Both are index-out-of-bounds under ZeRO-3, but different models and likely different root causes." }, { "left": "issue:43901", "right": "issue:44512", "accept": false, - "reason": "Different docs regressions: return_all_scores mention vs removed run command." + "reason": "Different docs issues: return_all_scores behavior vs removed run command reference." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Gemma3 config missing field in vLLM vs Qwen3 auto device-map cuda assert; unrelated." + "reason": "Gemma3 sliding_window/vLLM attribute issue and Qwen3 auto device mapping cuda assert are different." }, { "left": "issue:45237", "right": "issue:45901", "accept": false, - "reason": "AMD GPU GPT-OSS failure vs table-question-answering crash; unrelated." + "reason": "Different product areas: AMD GPU loading vs table-question-answering crash." }, { "left": "issue:44841", "right": "issue:45823", "accept": false, - "reason": "Voxtral processor failure vs Gemma4 device mismatch; unrelated." + "reason": "Processor failure and device-mismatch forward error are not the same underlying bug." }, { "left": "issue:43039", "right": "issue:44560", "accept": false, - "reason": "Liger Kernel cross_entropy issue vs Qwen3-vl video StopIteration; unrelated." + "reason": "Liger Kernel cross-entropy invocation and video StopIteration are unrelated." }, { "left": "issue:45812", "right": "issue:45920", "accept": true, - "reason": "Same AutoTokenizer wrong-token-ID v5 regression; 45920 broadens the affected model list but points to the same tokenizer path." + "reason": "Same v5 AutoTokenizer wrong-token-ID regression; 45920 is the broader multi-model umbrella report." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Ovis2 checkpoint corrupted vs NemotronH checkpoint loading implementation issue; different root causes." + "reason": "Checkpoint corruption and NemotronH checkpoint-loading failure are different issues." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "GLM-4.7-Flash unit test load failure vs Ovis2 checkpoint corrupted; not the same bug." + "reason": "Unit-test load failure vs checkpoint corruption are not the same bug." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/Gemma sliding-window problems with distinct symptoms and models." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Mask/tensor shape IndexError vs Bert ZeRO-3 size-0 index error; different error signatures." + "reason": "Both are shape/index errors, but the reported models and contexts differ enough that they do not clearly duplicate." }, { - "left": "issue:43792", - "right": "issue:45901", + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Dtype mismatch in Mistral-3 vs GraniteMoEHybrid invalid method call are unrelated." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Invalid method call in GraniteMoEHybrid vs MPS histogram unsupported type are different bugs." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model families and different backend failures." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Different model/runtime contexts; not the same concrete bug." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Qwen NVFP4 runtime error and TRL SFT unpacking failure are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy call and TRL SFT trainer unpacking issue are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Both are ZeRO-3 index-out-of-bounds reports, but the model families and likely root causes differ." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions in v5, but they refer to different removed features and should not be merged as duplicates." + }, + { + "left": "issue:39290", + "right": "issue:43531", "accept": false, - "reason": "Whisper can't run vs table-question-answering crash; unrelated." + "reason": "Different Qwen/Gemma sliding-window failures, not the same code-path problem." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Mask/index shape mismatch and ZeRO-3 Bert zero-size index error are different failures." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative on the soft edges. The two accepted duplicate pockets are well supported by the issue titles: 43596/43638 for the ZeRO-3/BERT size-0 index error and 45812/45920 for the AutoTokenizer v5 regression. The rejected pairs are appropriately treated as distinct based on differing symptoms or scopes, and there are no PRs to evaluate." + "feedback": "The summary is grounded in the packet: it identifies the two clearly supported duplicate subgroups (43596/43638 and 45812/45920) and otherwise treats the remaining pairs conservatively as likely distinct issues. The accepted soft-edge verdicts are supported by the issue titles and stay within the evidence available." }, "evaluator_used": true, "retried": false, @@ -534,10 +516,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36010", "issue:39186", @@ -589,20 +571,20 @@ "issue:45902" ], "soft_pairs": [ - "issue:39290|issue:43531", + "issue:43792|issue:45901", "issue:43425|issue:45070", "issue:43596|issue:45800", "issue:43975|issue:45901", "issue:43792|issue:45070", "issue:45362|issue:45464", "issue:44292|issue:45901", - "issue:43404|issue:43866", "issue:39290|issue:45823", + "issue:43404|issue:43866", "issue:45464|issue:45685", "issue:43541|issue:45685", "issue:43541|issue:43828", - "issue:44841|issue:45084", "issue:36010|issue:39290", + "issue:44841|issue:45084", "issue:41093|issue:41762", "issue:45800|issue:45823", "issue:43296|issue:43366", @@ -628,20 +610,20 @@ "issue:44530|issue:45005", "issue:42915|issue:45399" ], - "prepared_review_unit_hash": "affc09d5b1fde44ca16ec08628b0d3f70d3f30e30e357457030661e3bd868fcd", + "prepared_review_unit_hash": "760f2b5f3289c04cd12e4a07530fe4a5fc9b83dde8ab9e673816e6bd3fbe2de2", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 38, - "serialized_chars": 38767, + "serialized_chars": 38765, "estimated_input_tokens": 9692, "estimated_eval_tokens": 19640 }, @@ -650,250 +632,28 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of distinct model- and runtime-specific issues rather than true duplicates. The only clear soft duplicate here is the remote_code/custom-module loading pair; the rest share broad themes but not the same concrete bug path.", - "confidence": 0.71, - "canonical_issue_reason": "issue:45020 is the broadest open report and the best umbrella for the cluster\u2019s strongest shared theme: recent-version regressions in remote_code model loading. The other issues are narrower or point to different failures.", + "summary": "Mostly unrelated issue reports. The only near-match is the custom-module loading pair, but the available metadata is not enough to confirm a shared root cause, so it should stay tentative rather than merged as a duplicate.", + "confidence": 0.57, + "canonical_issue_reason": "Issue 45698 is the better anchor for the cluster: it states the broader from_pretrained/save_pretrained custom-module loading failure. Issue 45632 looks related, but the packet does not firmly establish that it is the same bug rather than a specific variant.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the most suitable representative issue overall because it is broad, open, and framed around a user-visible regression that can subsume related custom-code loading problems.", + "best_issue_reason": "Most actionable issue in the set: open and centered on a concrete custom-module loading path with a clear user-facing failure.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:39290", - "right": "issue:43531", - "accept": false, - "reason": "Both mention sliding-window behavior, but they involve different model families and different failure modes; not the same bug path." - }, - { - "left": "issue:43425", - "right": "issue:45070", - "accept": false, - "reason": "One is a torch-version compatibility report, the other is a pydantic/config regression; too different to merge." - }, - { - "left": "issue:43596", - "right": "issue:45800", - "accept": false, - "reason": "Both mention incompatibility-ish symptoms, but one is a ZeRO-3 index error and the other is torch/transformers version incompatibility." - }, - { - "left": "issue:43975", - "right": "issue:45901", - "accept": false, - "reason": "Detokenization bugs and table-question-answering crashes are unrelated code paths and symptoms." - }, - { - "left": "issue:43792", - "right": "issue:45070", - "accept": false, - "reason": "Whisper runtime failure is not the same underlying issue as a PretrainedConfig/pydantic regression." - }, - { - "left": "issue:45362", - "right": "issue:45464", - "accept": false, - "reason": "Both touch Qwen3.5 chat usage, but one is a general chat crash and the other is a streaming chat/completions failure; different paths." - }, - { - "left": "issue:44292", - "right": "issue:45901", - "accept": false, - "reason": "Qwen-3 NVFP4 loading and table QA crashes are unrelated." - }, - { - "left": "issue:43404", - "right": "issue:43866", - "accept": false, - "reason": "A tied-weight bug in Mistral3 is not the same as a corrupted Ovis2 checkpoint report." - }, - { - "left": "issue:39290", - "right": "issue:45823", - "accept": false, - "reason": "Gemma3 sliding-window config and Gemma4 device-map mismatch are different model issues." - }, - { - "left": "issue:45464", - "right": "issue:45685", - "accept": false, - "reason": "Streaming inference on Qwen3.5 and an MPS histogram error on MoE models are unrelated." - }, - { - "left": "issue:43541", - "right": "issue:45685", - "accept": false, - "reason": "Grouped_mm tracing failure and an MPS Int histogram limitation are different runtime problems." - }, - { - "left": "issue:43541", - "right": "issue:43828", - "accept": false, - "reason": "Both mention dtype-ish symptoms, but one is torch dynamo tracing and the other is autocast mismatch; not the same bug." - }, - { - "left": "issue:44841", - "right": "issue:45084", - "accept": false, - "reason": "Processor failure for Voxtral and a template-node compilation error do not share a concrete code path." - }, - { - "left": "issue:36010", - "right": "issue:39290", - "accept": false, - "reason": "Importing GenerationMixin and Gemma3 sliding-window config errors are unrelated." - }, - { - "left": "issue:41093", - "right": "issue:41762", - "accept": false, - "reason": "Both are shape/index errors, but on different tensors, models, and loading scenarios." - }, - { - "left": "issue:45800", - "right": "issue:45823", - "accept": false, - "reason": "Torch version incompatibility and Gemma4 device mismatch are different failures." - }, - { - "left": "issue:43296", - "right": "issue:43366", - "accept": false, - "reason": "PaddleOCR-VL loading in vLLM and GGUF gpt-oss support are not the same bug." - }, - { - "left": "issue:43572", - "right": "issue:45070", - "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is a different config regression from the pydantic PretrainedConfig breakage." - }, - { - "left": "issue:44387", - "right": "issue:45005", - "accept": false, - "reason": "Int4 memory/OOM regression and tied-weights translation-model issues are distinct." - }, - { - "left": "issue:43541", - "right": "issue:45161", - "accept": false, - "reason": "Torch tracing failure and only-TP-not-working on GPT-OSS MoE are different implementation issues." - }, - { - "left": "issue:43828", - "right": "issue:45464", - "accept": false, - "reason": "Autocast dtype mismatch for Phi-tiny-MoE is not the same as Qwen3.5 streaming API failure." - }, - { - "left": "issue:44291", - "right": "issue:45070", - "accept": false, - "reason": "init_empty_weights argument handling and pydantic field validation are different breakages." - }, - { - "left": "issue:43366", - "right": "issue:45464", - "accept": false, - "reason": "GGUF architecture support and chat/completions streaming errors are unrelated." - }, - { - "left": "issue:45020", - "right": "issue:45800", - "accept": false, - "reason": "remote_code loading regressions and a torch/transformers version incompatibility are too broad and different to treat as one bug." - }, - { - "left": "issue:43531", - "right": "issue:45070", - "accept": false, - "reason": "Qwen3-MoE sliding_window and a pydantic config regression do not share a concrete failure path." - }, - { - "left": "issue:43541", - "right": "issue:44589", + "left": "issue:45632", + "right": "issue:45698", "accept": false, - "reason": "torch dynamo grouped_mm errors and missing Float8 storage are separate float/dtype issues." - }, - { - "left": "issue:41093", - "right": "issue:43596", - "accept": false, - "reason": "Both are index errors, but one is a mask-length mismatch and the other is a zero-sized dimension during ZeRO-3 init." - }, - { - "left": "issue:43054", - "right": "issue:43994", - "accept": false, - "reason": "Both concern SigLIP2 output quality, but one is a relative embedding-quality complaint and the other is a broader bad-results report; too imprecise to confirm same bug." - }, - { - "left": "issue:45542", - "right": "issue:45800", - "accept": false, - "reason": "TensorBoard-without-TF backend detection and torch/transformers incompatibility are unrelated." - }, - { - "left": "issue:45759", - "right": "issue:45902", - "accept": false, - "reason": "Both involve Qwen3.5/3.6 multimodal internals, but config unwrapping and uninitialized-memory materialization are different code paths." - }, - { - "left": "issue:40990", - "right": "issue:44960", - "accept": false, - "reason": "High perplexity on gpt-oss and a GLM5 issue are unrelated model-specific reports." - }, - { - "left": "issue:43716", - "right": "issue:44918", - "accept": false, - "reason": "Image-preprocessor dtype mismatch and Qwen3.5 input-embedding unpacking in TRL are different failures." - }, - { - "left": "issue:39186", - "right": "issue:44918", - "accept": false, - "reason": "FSDP weight dimensionality errors and TRL embedding unpacking are not the same bug." - }, - { - "left": "issue:45632", - "right": "issue:45698", - "accept": true, - "reason": "Both describe the same remote_code/custom-module resolution bug: cache/path collision leads to the wrong custom module being loaded after save/load." - }, - { - "left": "issue:43404", - "right": "issue:45005", - "accept": false, - "reason": "Mistral3 tied-lm_head weights and translation-model tied-weight regressions are related only at a very broad level, not the same concrete issue." - }, - { - "left": "issue:43645", - "right": "issue:45399", - "accept": false, - "reason": "Jupyter custom-model initialization and flash-attn fallback checks are unrelated." - }, - { - "left": "issue:44530", - "right": "issue:45005", - "accept": false, - "reason": "PagedAttentionCache linear_attention failures and tied-weights translation issues are different subsystems." - }, - { - "left": "issue:42915", - "right": "issue:45399", - "accept": false, - "reason": "FineGrainedFP8Config failures and flash-attn fallback gating are unrelated runtime paths." + "reason": "Both involve custom-module loading, but the evidence is too thin to prove the same underlying bug; one points to a cache-path collision, the other to wrong module selection after save/load." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The single accepted soft pair (issue:45632 / issue:45698) is plausibly the same remote_code/custom-module loading bug, and the other rejections are appropriately cautious rather than overbroad. The representative choice of issue:45020 as the open umbrella issue is also defensible from the titles and descriptions provided." + "accept": false, + "feedback": "Mostly conservative, but a bit too assertive for the evidence in the packet. The phrase \"open, clearly reproducible\" is not grounded by the supplied metadata alone, and the accepted 45632\u219445698 pairing is plausible but not strongly established beyond title similarity. Please keep the duplicate call softer unless the bodies explicitly show the same root cause." }, "evaluator_used": true, - "retried": false, - "accepted_nontrivial_soft_edge": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -905,10 +665,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36331", "issue:38175", @@ -993,241 +753,241 @@ "issue:41762|issue:42915", "issue:43782|issue:44960" ], - "prepared_review_unit_hash": "99deff697ff1a1ab3d20c37c5f1316f24a69253a2a4b37287d26cbfa9ecfce4b", + "prepared_review_unit_hash": "15c378b83f1c57bcf067669b20e229fb48e9ec7ffea7255ff33614baad816dc1", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 36584, - "estimated_input_tokens": 9146, - "estimated_eval_tokens": 18548 + "serialized_chars": 36587, + "estimated_input_tokens": 9147, + "estimated_eval_tokens": 18550 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Only one soft duplicate looks convincing: the Transformers v5 non-persistent buffer corruption regression. The other title-similar pairs appear to be different model/load-path issues and shouldn\u2019t be merged.", - "confidence": 0.81, - "canonical_issue_reason": "issue:43950 is the broadest, most concrete report of the v5 non-persistent-buffer corruption regression; issue:44534 is the same symptom restated more generally.", + "summary": "The duplicate cluster is mostly solid around the Transformers 5.x non-persistent-buffer regression: 43950, 43644, and 44534 all point to the same underlying corruption bug. Issue 45902 is related in the same area, but the packet only supports it as a narrower symptom, not a confirmed duplicate.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43950 is the best canonical representative because it describes the regression at the right level of generality\u2014`from_pretrained()` corrupting non-persistent buffers in Transformers 5.x\u2014and it is directly corroborated by 43644 and 44534. 45902 looks related, but this packet does not establish it as the same bug with enough certainty.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43950 best represents the underlying bug because it names the regression directly and covers the fix surface more clearly than the narrower duplicate.", + "best_issue_reason": "43950 is the strongest issue anchor for triage: it names the broad regression clearly, matches the shared non-persistent-buffer failure mode, and cleanly subsumes the confirmed duplicates 43644 and 44534.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "Different problems: DSA indexer ReLU discussion vs a v5 docs/run-command note." + "reason": "Unrelated topics: a DSA indexer discussion vs a docs typo about a removed command." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Both mention quantization/tied weights, but the concrete failures are different and not the same bug." + "reason": "Quantization/offloading behavior is not the same bug as tied-weights handling in translation models." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is unrelated to tied-weights behavior in translation models." + "reason": "NemotronH checkpoint loading failure is a different problem from translation-model tied weights." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A typo in cache strategies is not the same issue as stale v5 docs about a removed command." + "reason": "A cache-strategy typo is unrelated to the removed transformers run command docs issue." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "Different model/code paths: Qwen3.5 embedding unpacking vs GraniteMoEHybrid invalid method call." + "reason": "Different model/code-path failures: Qwen3.5 input embedding unpacking vs GraniteMoEHybrid invalid method calls." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "Different concrete failures: detokenization bug vs NVFP4 runtime error." + "reason": "Both are model-related, but they involve different models and concrete failures with no shared underlying bug shown." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Same underlying v5 non-persistent buffer corruption regression; 44534 is a reworded symptom of 43950." + "reason": "Same underlying non-persistent-buffer regression; both titles describe the same junk/corruption behavior in Transformers v5." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "No shared underlying bug: Qwen-3 NVFP4 execution error vs GraniteMoEHybrid method invocation problem." + "reason": "No shared bug: Qwen NVFP4 loading error vs GraniteMoEHybrid invalid method issue." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "SigLIP2 docs-example errors are not the same as a broad embedding-quality regression." + "reason": "Both mention SigLIP2, but one is a docs/example error and the other is a text-embedding quality discrepancy." }, { "left": "issue:43644", "right": "issue:43950", - "accept": false, - "reason": "Remote-code config field loss is a different failure mode than non-persistent buffer corruption." + "accept": true, + "reason": "Direct duplicate reports of the same non-persistent-buffer junk/corruption regression." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Autocast dtype mismatch and Qwen3.5 3D position_ids/SDPA issues are different code-path bugs." + "reason": "Different models and failure modes: dtype mismatch under autocast vs Qwen3.5 position_ids/SDPA behavior." }, { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "Trainer signature mismatch vs ZeRO-3 load failure; no concrete shared root cause." + "reason": "Trainer API mismatch and Gemma3 DeepSpeed loading failure are unrelated." }, { "left": "issue:41628", "right": "issue:45800", "accept": false, - "reason": "Import error for AutoImageProcessor is not the same as a torch/transformers version incompatibility." + "reason": "Importing AutoImageProcessor and torch-version incompatibility are separate issues." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Corrupted checkpoint vs generic load noise; not the same underlying bug." + "reason": "Checkpoint corruption is not the same as generic loading noise." }, { "left": "issue:43950", "right": "issue:45902", "accept": false, - "reason": "Both touch buffer initialization, but 45902 is a specific Qwen3_5Moe rotary-embedding materialization bug, not the same regression as 43950." + "reason": "The packet only shows a narrower uninitialized-memory symptom after `meta \u2192 to_empty(cuda)`; it does not clearly establish the same non-persistent-buffer regression." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "Different quantization/backing-storage failures with different symptoms and code paths." + "reason": "Bitsandbytes unexpected-kwarg failure and missing Float8 storage type are different compatibility bugs." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "SigLIP2 embedding quality issue is not the same as tokenizer behavior changing across versions." + "reason": "Both involve tokenization/model behavior, but the reported failures and likely root causes differ." }, { "left": "issue:41553", "right": "issue:43883", "accept": false, - "reason": "Bad AutoTokenizer error for Voxtral is unrelated to Molmo tied-weights metadata." + "reason": "Bad AutoTokenizer error for Voxtral is unrelated to Molmo's tied-weights attribute error." }, { "left": "issue:38175", "right": "issue:43054", "accept": false, - "reason": "Both concern SigLIP2, but zero probabilities and worse embeddings are not clearly the same concrete bug." + "reason": "Both concern SigLIP2, but unexpected zero probabilities and degraded text embeddings are different symptoms with no clear same root cause." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "FlashAttention illegal access from 3D position_ids is different from CPU-offload incompatibility in rotary embedding." + "reason": "Both are Qwen-related, but Flash Attention crash from 3D position_ids is different from CPU-offload incompatibility in rotary embedding." }, { "left": "issue:45663", "right": "issue:45902", "accept": false, - "reason": "FSDP2 shared_kv_states KeyError is unrelated to uninitialized rotary-embedding memory after materialization." + "reason": "Gemma4 FSDP2 shared_kv_states handling is a different bug from non-persistent-buffer materialization corruption." }, { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "AutoTokenizer loading error for Voxtral and glm-4v-9b loading failure are distinct issues." + "reason": "Voxtral AutoTokenizer error and glm-4v loading failure are unrelated." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "Gradient checkpointing/LoRA ineffectiveness is not the same as int4 quantization causing higher reserved memory." + "reason": "Gradient checkpointing with PEFT LoRA and int4 memory/OOM regression are different training-performance issues." }, { "left": "issue:43054", "right": "issue:43493", "accept": false, - "reason": "Poor SigLIP2 embeddings and HF-vs-JAX discrepancy are related themes but not the same concrete report." + "reason": "Both mention SigLIP2, but embedding quality and HF-vs-JAX implementation discrepancy are not the same bug." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "Generic loading noise is not the same as an inability to load a specific model." + "reason": "Generic loading noise and a specific model load failure are different issues." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "Remote-code config field loss may be part of a broader class, but 45020 is too umbrella-like to treat as the same bug." + "reason": "A missing-fields bug in AutoConfig with trust_remote_code is not the same as broad remote_code breakage." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "DeepSeek detokenization and flash_attn import errors are unrelated." + "reason": "Detokenization of a specific model and a Python 3.13 flash_attn import KeyError are unrelated." }, { "left": "issue:43975", "right": "issue:45237", "accept": false, - "reason": "Detokenization bug and AMD GPU execution failure are different problems." + "reason": "Different models and failures; no shared underlying code-path problem is evident." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Generic load noise is not the same as a specific model failing to load." + "reason": "Two separate model-loading complaints with no concrete shared bug." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "Both mention memory, but one is checkpointing/LoRA behavior and the other is MoE training memory usage." + "reason": "LoRA gradient checkpointing and Qwen3 MoE memory usage are different training-performance problems." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "Model loading failure and missing all_tied_weights_keys are different issues." + "reason": "glm-4v loading and Molmo tied-weights attribute error are unrelated." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Gemma3 ZeRO-3 loading error and Qwen3Moe FP8 failure are unrelated." + "reason": "Gemma3 ZeRO-3 loading failure and Qwen3Moe FineGrainedFP8Config failure are separate model/config issues." }, { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Qwen3VL weight_only load error is not the same as a GLM5 issue." + "reason": "Qwen3VL weight_only loading error and GLM5 are different model-loading failures." } ] }, "evaluator_result": { - "accept": true, - "feedback": "Grounded and conservative overall. The one accepted soft duplicate pair (issue:43950 / issue:44534) is well supported by the titles and clearly points to the same Transformers v5 non-persistent-buffer corruption regression. The remaining pairs are appropriately rejected based on differing bug surfaces, and the summary does not overstate the evidence." + "accept": false, + "feedback": "The 43950/43644/44534 cluster is well grounded, but the 43950\u219445902 duplicate call is too strong given the packet. 45902\u2019s title only shows an uninitialized-memory issue after meta\u2192to_empty(cuda) materialization; the packet does not clearly establish that it is the same non-persistent-buffer regression. Because soft-edge verdicts need to stay conservative, I can\u2019t accept this as written." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -1240,10 +1000,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:24643", "issue:30064", @@ -1320,29 +1080,29 @@ "issue:43257|issue:45305", "issue:42947|issue:45923", "issue:44928|issue:45588", - "issue:41093|issue:44805", "issue:43872|issue:45538", + "issue:41093|issue:44805", "issue:41553|issue:44488", - "issue:44530|issue:44863", "issue:44479|issue:44560", + "issue:44530|issue:44863", "issue:24643|issue:30064", "issue:45325|issue:45902", "issue:43366|issue:43828" ], - "prepared_review_unit_hash": "335d8be8f0c5c2f691e3e1e26decf1fc959508aa0dd29081abbce0ae0be141f0", + "prepared_review_unit_hash": "ebfd7b3d6b6706316dcf46caee9e35259dfa6eb8fddc944b4240d6d8bc325a14", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 38069, + "serialized_chars": 38071, "estimated_input_tokens": 9518, "estimated_eval_tokens": 19292 }, @@ -1351,216 +1111,216 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a collection of unrelated model-specific regressions and docs issues. Only a few soft pairs look like true duplicates: the removed-pipeline docs references, the `_is_hf_initialized` TypeError, and the repeated mask-shape IndexError.", - "confidence": 0.81, - "canonical_issue_reason": "Issue 45020 is the broadest and most representative umbrella bug in the set: recent transformers versions breaking `remote_code` models across multiple concrete failures. It is a better anchor than the narrower model-specific reports.", + "summary": "This cluster is mostly heterogeneous model-loading/training regressions, with only a few true duplicates. The clearest duplicate groups are the docs cleanup around removed v5 pipeline tasks, the bitsandbytes/_is_hf_initialized init_empty_weights TypeError, and the identical mask/tensor shape IndexError reports.", + "confidence": 0.78, + "canonical_issue_reason": "44291 is the most precise report of the bitsandbytes/_is_hf_initialized regression, naming the exact failing path and version; it best serves as the canonical issue for that duplicate pair.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45020 is the best global issue candidate because it captures the widest recurring regression pattern and is the most suitable umbrella triage target among mostly narrow one-off bugs.", + "best_issue_reason": "44291 is the strongest standalone issue in the cluster: concrete, reproducible, and root-caused, unlike the broader or more speculative reports nearby.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "Different failures: an MPS histogram dtype limitation in MoE code vs a Gemma4 PLE forward device-mismatch bug." + "reason": "Different failures: MPS Int histogram support vs Gemma4 PLE device placement mismatch." }, { "left": "issue:42491", "right": "issue:44368", "accept": false, - "reason": "Both mention Qwen3.5/Qwen3 MoE, but one is a loadability regression across hf4.x/hf5.x and the other is only a warning about `tie_word_embeddings`." + "reason": "Both mention Qwen/LoRA, but one is a hf4.x\u2192hf5.x compatibility break and the other is a tie_word_embeddings warning." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Import error for a missing Qwen2.5-VL class is unrelated to the bitsandbytes `_is_hf_initialized` constructor incompatibility." + "reason": "Unrelated bugs: missing Qwen2_5_VL import vs bitsandbytes Int8Params/_is_hf_initialized TypeError." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "`remote_code` breakage is a broad loader regression, while Gemma4 PLE device placement is a model-specific forward-path issue." + "reason": "Too broad and different: remote_code regressions vs a device_map forward mismatch." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Tokenizer-mapping edge case for `add-new-model-like` is a different code path from remote-code model loading failures." + "reason": "Different root causes: tokenizer mapping helper failure vs generic remote_code breakage." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading for `est-roberta` is unrelated to flash-attn fallback gating checks." + "reason": "Tokenizer load failure for a specific model vs flash-attn fallback gating; no shared code-path." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Autocast dtype mismatch in Phi-tiny-MoE is not the same bug as Gemma4 PLE device mismatch." + "reason": "Different runtime issues: autocast dtype mismatch vs device mismatch." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Mistral regex patch crashing in tokenizer setup is separate from flash-attn fallback being blocked by other checks." + "reason": "Tokenizer regex crash vs flash-attn fallback blocking; unrelated fixes." }, { "left": "issue:43827", "right": "issue:44509", "accept": true, - "reason": "Both report the same doc cleanup needed after v5 pipeline removals; same outdated pipeline-task references." + "reason": "Both are the same docs regression after v5 pipeline removals; one is just a narrower phrasing of the same cleanup." }, { "left": "issue:45020", "right": "issue:45356", "accept": false, - "reason": "General remote_code regressions are not the same as Kimi-K2.5 tokenizer codec-handling and warning behavior." + "reason": "Both are regressions, but one is broad remote_code breakage and the other is a specific Kimi-K2.5 tokenizer codec/warning issue." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Untied `lm_head` weights in Mistral3 are unrelated to non-persistent buffer corruption in `from_pretrained()`." + "reason": "Different model bugs: untied lm_head weights vs non-persistent buffer corruption." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "A model-specific key error while loading MobileLLM-125M is different from flash-attn fallback selection logic." + "reason": "Key error loading MobileLLM vs flash-attn fallback gating; no same underlying defect." }, { "left": "issue:42915", "right": "issue:45020", "accept": false, - "reason": "LoRA compatibility across hf4.x/hf5.x is a specific Qwen3 MoE issue, not the broader remote_code regression." + "reason": "Both are Qwen-related regressions, but one is a Qwen3_moe LoRA compatibility problem and the other is a generic remote_code breakage." }, { "left": "issue:43638", "right": "issue:45823", "accept": false, - "reason": "DeepSpeed ZeRO-3 indexing failure on a non-pretrained Bert model is unrelated to Gemma4 PLE device placement." + "reason": "Different code paths: DeepSpeed ZeRO-3/Bert IndexError vs Gemma4 device mismatch." }, { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed and a corrupted Ovis2 checkpoint are distinct load failures." + "reason": "Different model-loading failures: Qwen3 MOE weight conversion vs Ovis2 checkpoint corruption." }, { "left": "issue:43792", "right": "issue:44220", "accept": false, - "reason": "Whisper not running is too broad to merge with a specific `_torch_extract_fbank_features()` bug without clearer same-path evidence." + "reason": "Possible audio-processing relation, but the titles are not specific enough to treat as the same bug." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Both center on the same `_is_hf_initialized` TypeError during model materialization/loading, just from different entry points." + "reason": "Same bitsandbytes/_is_hf_initialized incompatibility; the second issue states the exact root cause and reproducer more clearly." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "Qwen3 MoE LoRA compatibility and the `_is_hf_initialized` constructor error are different regressions." + "reason": "Both involve model/loading regressions, but they are different bugs with different failure modes." }, { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Both are ZeRO-3 load problems on Qwen variants, but they appear to be model-specific missing-weight failures rather than one concrete duplicate bug." + "reason": "Similar DeepSpeed ZeRO-3 symptoms, but different Qwen model families and different reported failure details." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "A bad AutoTokenizer error message for Voxtral is not the same as failing to load EMBEDDIA/est-roberta." + "reason": "Different tokenizer issues for different models; not the same underlying defect." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "GLM-4.7-Flash unit-test loading failure and NemotronH checkpoint loading failure are separate model-specific loader bugs." + "reason": "Different model-specific loading failures with no shared error path." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Unexpected `num_items_in_batch` in custom trainer loss is unrelated to the mask/tensor shape mismatch IndexError." + "reason": "Unexpected compute_loss kwarg vs tensor-mask shape mismatch; unrelated bugs." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "Qwen3 MoE weight conversion with deepspeed is not the same as gradient averaging missing under GAS/model_accepts_loss_kwargs." + "reason": "Weight conversion under Accelerate/DeepSpeed vs gradient averaging under GAS; different layers of the stack." }, { "left": "issue:42947", "right": "issue:45923", "accept": false, - "reason": "LoRA gradient checkpointing being ineffective is not the same issue as a missing `supports_gradient_checkpointing` flag on a trust_remote_code model." + "reason": "Both mention checkpointing, but one is LoRA checkpointing ineffective and the other is a missing model flag on a trust_remote_code variant." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "RLHF NaN explosions from Qwen3.5 SDPA/BF16 behavior are unrelated to flash_attention.py crashing on `s_aux=None`." - }, - { - "left": "issue:41093", - "right": "issue:44805", - "accept": true, - "reason": "These are the same mask-shape mismatch IndexError, with only the reported sizes/context differing." + "reason": "Different failures: RLHF gradient explosion/SDPA fallback vs flash_attention.py handling of sink-less models." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "The `_is_hf_initialized` loading bug is unrelated to CLIPTokenizer's `model_max_length` sentinel value." + "reason": "bitsandbytes init error vs CLIPTokenizer max length constant; unrelated." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same mask/tensor shape mismatch error class with essentially identical failure message; these look like duplicate reports of the same indexing bug." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Both are tokenizer-loading complaints, but the Voxtral error message issue and the sleng-bert load failure are not the same bug." + "reason": "Both are tokenizer-related, but they concern different models and different failure modes." }, { - "left": "issue:44530", - "right": "issue:44863", + "left": "issue:44479", + "right": "issue:44560", "accept": false, - "reason": "Qwen3.5 PagedAttentionCache group-type handling and NemotronH checkpoint loading are different subsystems and failures." + "reason": "Both are video-input regressions, but the affected models and errors differ enough to keep separate." }, { - "left": "issue:44479", - "right": "issue:44560", + "left": "issue:44530", + "right": "issue:44863", "accept": false, - "reason": "Both are video-related, but one is a broad v5.3.0 regression across several Qwen models and the other is a specific StopIteration on Qwen3-vl-embedding." + "reason": "PagedAttentionCache linear_attention group crash vs NemotronH checkpoint loading failure; not the same bug." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "DeepSpeed training weight-dimension error and void segmentation-map processing are unrelated." + "reason": "Training DeepSpeed weight-shape error vs image processor segmentation-map failure; unrelated." }, { "left": "issue:45325", "right": "issue:45902", "accept": false, - "reason": "Qwen2.5-VL rope-index scaling and Qwen3.5 MoE rotary-embedding uninitialized-memory issues are distinct model internals." + "reason": "Different rotary/positioning bugs on different architectures; no shared fix path." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF gpt-oss architecture support and Phi-tiny-MoE autocast dtype mismatch are separate problems." + "reason": "GGUF gpt-oss support vs Phi-tiny-MoE autocast dtype mismatch; unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet, and the soft-edge decisions are conservative. The accepted pairs are plausible same-bug duplicates/docs-cleanup matches, while the rejected pairs avoid overclaiming broader similarity. The choice of issue 45020 as the umbrella issue is also supported by its broad \u2018remote_code\u2019 regression scope." + "feedback": "The summary is grounded in the packet and stays appropriately conservative overall. The three accepted duplicate pairs are defensible from the titles/body metadata: the docs pipeline-removal reports, the bitsandbytes/_is_hf_initialized TypeError reports, and the matching mask/tensor shape IndexError reports. No soft-edge verdict stands out as an overstatement, and the cluster-level summary matches the evidence." }, "evaluator_used": true, "retried": false, @@ -1576,10 +1336,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36010", "issue:38175", @@ -1637,9 +1397,9 @@ "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:43645|issue:43646", "issue:44560|issue:44918", "issue:42617|issue:43366", "issue:36010|issue:42915", @@ -1664,226 +1424,208 @@ "issue:43708|issue:44075", "issue:43854|issue:43931" ], - "prepared_review_unit_hash": "ef2ac56870a0ff8745e39c714ac80192bfb5c59702f7e9a3cc3030108184900d", + "prepared_review_unit_hash": "f24971b2b5c110f07a07ae8f1558b0fb5567ccbca900b5f3470c3a3788d50a86", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37193, - "estimated_input_tokens": 9299, - "estimated_eval_tokens": 18854 + "serialized_chars": 37191, + "estimated_input_tokens": 9298, + "estimated_eval_tokens": 18852 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a mixed cluster of unrelated Transformers regressions, with a few clear duplicate pairs around the same bug family. The strongest duplicate subgroup is the non-persistent buffer corruption in Transformers 5.x.", - "confidence": 0.78, - "canonical_issue_reason": "Issue 43950 is the clearest, most technical statement of the broad 5.x regression and covers the same non-persistent-buffer corruption described in nearby duplicates.", + "summary": "This cluster is mostly a grab bag of unrelated issues. Only two duplicate pairs look strong enough to merge: the two custom-model initialization regressions and the two non-persistent-buffer regression reports.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 44534 is the clearest canonical anchor for the non-persistent-buffer regression: it states the concrete Transformers v5 corruption bug directly and matches the near-verbatim duplicate 43644.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43950 is the best canonical issue because it names the exact failing behavior, has broad applicability, and matches the duplicate subgroup more precisely than the shorter title variants.", + "best_issue_reason": "Issue 44534 is the best single issue to represent the strongest duplicate pair in this set because it names the exact bug class and is more precise than the alternate duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Both are Gemma4 issues, but one is an FSDP2 shared_kv_states bug and the other is a device_map=\"auto\" PLE device-mismatch bug; different code paths." + "reason": "Same broad model family, but different failures: FSDP2 KeyError during training vs device-mismatch during forward. Not the same concrete bug." }, { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "Different models and failures: AudioFlamingo3 track leakage vs Whisper empty-transcription handling." + "reason": "Different models and unrelated symptoms (batched AudioFlamingo3 leakage vs Whisper empty-transcription generation)." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "Unrelated problems: GGUF gpt-oss support versus Qwen3-MoE sliding_window behavior." + "reason": "Unrelated topics: GGUF/gpt-oss support vs Qwen3-MoE sliding_window behavior." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "Different subsystems entirely: non-persistent buffer corruption vs Kosmos2.5 long-OCR index error." + "reason": "Both are loading/runtime issues, but one is a Transformers v5 buffer-corruption regression and the other is a long-OCR index error in Kosmos2.5." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Both touch attention/compile paths, but the model, trigger, and failure mode are different; not the same concrete bug." + "reason": "Different models and different attention paths (Bamba SDPA compile failure vs Qwen3.5 flash-attention crash)." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Import/export issue for Qwen2.5-VL class vs meta-device loading regression; not the same underlying defect." - }, - { - "left": "issue:43645", - "right": "issue:43646", - "accept": true, - "reason": "Same custom-model initialization regression in Transformers 5.0.0, with nearly identical symptoms and scope." + "reason": "Import error for a specific class vs meta-device model-loading breakage; not the same bug." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "GGUF gpt-oss support and Float8 storage lookup errors are unrelated." + "reason": "Support request vs storage-type/type-error regression; no shared underlying code-path." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3Moe FP8 failure and meta-device loading are different bugs." + "reason": "Different problems: Qwen3-MoE FP8 failure vs generic torch.device(\"meta\") loading breakage." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These describe the same Transformers v5 custom-model initialization regression; one is just a notebook-specific reproduction of the same bug." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Both involve Qwen3.5-family features, but one is video/StopIteration and the other is TRL embedding unpacking; not the same bug." + "reason": "Both mention Qwen, but one is a video embedding StopIteration and the other is an SFT-trainer unpacking failure; different code paths." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "3d_parallel.py runtime failure is unrelated to GGUF architecture support." + "reason": "No shared bug: inability to run a script vs GGUF architecture support." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "Importing GenerationMixin from transformers.generation is unrelated to Qwen3Moe FP8 behavior." + "reason": "ImportError for GenerationMixin and Qwen3-MoE FP8 failure are unrelated." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer-mapping/model-registration failure and Gemma4 device mismatch are different issues." + "reason": "Tokenizer-mapping edge case vs Gemma4 PLE device mismatch; different subsystems and failure modes." }, { "left": "issue:38175", "right": "issue:43994", - "accept": true, - "reason": "Same SigLIP2 model producing bad outputs on the same checkpoint, with closely aligned symptoms." + "accept": false, + "reason": "Same model family, but the evidence only shows similar bad outputs, not the same concrete bug or fix path." }, { "left": "issue:43632", "right": "issue:45834", "accept": false, - "reason": "_is_hf_initialized breakage is unrelated to Kosmos2.5 OCR index errors." + "reason": "Transformers v5 _is_hf_initialized regression vs Kosmos2.5 OCR index error; unrelated." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Different failure modes and model contexts; no shared concrete code path." + "reason": "Different failure modes and different model contexts; not the same bug." }, { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Both are config-validation complaints, but they affect different model families and appear to be separate regressions." + "reason": "Both involve config validation, but the model targets and likely fixes differ; too weak to merge." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "DeepSpeed ZeRO-3 Bert initialization and add-new-model-like tokenizer mapping are unrelated." + "reason": "DeepSpeed ZeRO-3/Bert indexing failure is unrelated to add-new-model-like tokenizer mapping behavior." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Zero3/BertModel index error is a different path from the tokenizer-mapping registration bug." + "reason": "Different issues: ZeRO-3/Bert index error vs tokenizer-mapping failure." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer-mapping registration and mask-shape IndexError are not the same bug." + "reason": "Tokenizer-mapping failure and a tensor mask shape mismatch are unrelated." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "Both relate to loading/memory behavior, but one is gpu+cpu offload dequantized loading and the other is Strix Halo mmap OOM; too different to merge." + "reason": "Different loading issues: gpu+cpu offload dequantization vs mmap OOM mitigation." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "These are the same Transformers v5 non-persistent-buffer corruption regression, just phrased differently." + "reason": "Near-verbatim duplicate reports of the same Transformers v5 non-persistent-buffer corruption regression." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "Same model family, but the reported problems differ: wrong probabilities vs documentation example/model-processor mismatch and quantization failures." + "reason": "Both involve SigLIP2, but one reports zero probabilities and the other a docs-example model/processor mismatch plus quantization failure; not enough evidence of one shared bug." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "GLM5 and Qwen3.5 flash-attention failures are unrelated." + "reason": "Completely different models and failures (GLM5 vs Qwen3.5 flash-attention generation)." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Qwen3-MoE LoRA compatibility on hf5.x and BitNet packed-weight loading are different bugs." + "reason": "LoRA/qwen3_moe version incompatibility and BitNet packed-weight loading are different bugs." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "Both are Qwen3.5 issues, but one is ZeRO-3 weight loading and the other is save_pretrained key serialization; distinct code paths." + "reason": "Different code paths and symptoms: ZeRO-3 weight loading vs save_pretrained key serialization." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Auto device mapping cudaErrorAssert and FineGrainedFP8Config failure are different Qwen3-family bugs." + "reason": "Different models and failures: Qwen3 device-map cuda assert vs Qwen3-MoE FP8 config issue." }, { "left": "issue:44451", "right": "issue:44488", "accept": false, - "reason": "Both are model-load failures for different BERT checkpoints, but the available evidence only shows a broad symptom match, not a concrete shared root cause." - }, - { - "left": "issue:42491", - "right": "issue:45276", - "accept": false, - "reason": "LoRA hf5.x compatibility and Gemma4 resize_token_embeddings behavior are unrelated." - }, - { - "left": "issue:42915", - "right": "issue:44756", - "accept": false, - "reason": "Qwen3Moe FP8 failure and Strix Halo mmap OOM are separate issues." - }, - { - "left": "issue:43708", - "right": "issue:44075", - "accept": false, - "reason": "Trainer resume/max_steps calculation and SGD argument handling are unrelated." + "reason": "Both are model-loading complaints, but they involve different BERT models and there is no evidence they share the same underlying bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative about the mixed cluster. The canonical issue choice is well supported by the non-persistent-buffer regression subgroup, and the accepted soft-edge pairs all look like plausible same-bug duplicates/mergeable fix targets. No obvious overstatement in the negative verdicts." + "feedback": "The summary is grounded in the packet and stays conservative on the soft edges. The two accepted pairs look reasonably mergeable for the same bugfix, and the rejected pairs are phrased cautiously rather than overstating shared causality. No obvious overclaiming." }, "evaluator_used": true, "retried": false, @@ -1899,10 +1641,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36010", "issue:39404", @@ -1970,32 +1712,32 @@ "issue:36010|issue:39404", "issue:43404|issue:43454", "issue:41720|issue:44155", + "issue:43425|issue:43957", "issue:44402|issue:44488", "issue:39692|issue:44960", - "issue:43425|issue:43957", "issue:42947|issue:45704", "issue:45663|issue:45759", "issue:43335|issue:45663", "issue:43873|issue:44387", - "issue:45663|issue:45859", "issue:44291|issue:44756", + "issue:45663|issue:45859", "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:44743|issue:44960", "issue:45276|issue:45292", "issue:45684|issue:45698" ], - "prepared_review_unit_hash": "d3e9395ca6d5a845ac94a50328fa2dd43efc974e54176c0cb319c0ce50e468cb", + "prepared_review_unit_hash": "8b6e105dd047439290cb11385c8f075ebbb2d04edf68d53cdd5ea94923fc8340", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, @@ -2010,219 +1752,219 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most pairs are unrelated by bug or code path. The only accepted duplicates are the resize_token_embeddings reports (45276/45292/45335), which all point to the same embedding-propagation regression across related model variants.", - "confidence": 0.85, - "canonical_issue_reason": "issue:45292 is the cleanest generic report for the resize_token_embeddings regression: it states the API-level symptom without extra model-specific detail.", + "summary": "This set is mostly a grab-bag of unrelated model-specific Transformer regressions. The only clear duplicate-like subgroup is the `resize_token_embeddings` propagation bug around Gemma4/T5Gemma, so that is the best canonical thread; the rest should stay separate.", + "confidence": 0.73, + "canonical_issue_reason": "issue:45292 is the broadest statement of the `resize_token_embeddings` regression, and the Gemma4/T5Gemma reports look like model-specific manifestations of the same underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45812 is the strongest overall issue candidate because it is open, has multiple inbound references, and its title describes a broad silent regression affecting Granite token IDs.", + "best_issue_reason": "issue:45292 is the cleanest representative of the only convincing duplicate cluster in this set; it generalizes the same embedding-resize failure that shows up in the related model-specific reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45488", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and different failure modes." + "reason": "Both involve tokenizer behavior, but they hit different model families and different failures: DeepSeek V3/R1 pre-tokenizer override vs Granite token-id regression." }, { "left": "issue:39692", "right": "issue:43994", "accept": false, - "reason": "Same broad area, but one is a docs/example failure and quantization issue while the other is a runtime correctness issue." + "reason": "Same SigLIP2 family, but one is a broken doc example with model/processor mismatch and quantization issues; the other is a model loading/pipeline output regression." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Different models and load paths; similar symptom class only." + "reason": "Completely different models and failure modes; Qwen3 MoE conversion under accelerate/deepspeed is not the same bug as GLM-4.7-Flash loading in tests." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Both are loading/tokenizer failures, but the titles point to different model-specific defects." + "reason": "Both are tokenizer-loading complaints, but they concern different models and likely different root causes, so this is too broad to merge." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Both involve Qwen3-family loading, but the concrete failures are different." + "reason": "These are distinct Qwen3-related load problems: one is hf4.x\u2192hf5.x LoRA compatibility, the other is a shape mismatch for Qwen3-VL-30B." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Memory-related, but the reported causes and scenarios differ." + "reason": "Both mention memory/quantization, but one is Qwen3 MoE training efficiency and the other is offloading failure with quantization; not the same concrete bug." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "Both are Transformers 5 regressions, but they describe different breakages." + "reason": "Both are Transformers 5.0 regressions, but one is junk non-persistent buffers and the other is custom model initialization in Jupyter notebooks." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Different model families and crash conditions." + "reason": "Different model-specific crashes: Qwen3.5 chat crash versus Gemma4Processor missing `_tokenizer` in serve." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both involve memory pressure, but not the same underlying bug." + "reason": "These are both memory-related, but one is training memory inefficiency and the other is int4 quantization reserved-memory/OOM behavior." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both touch flash attention, but the concrete failure modes are distinct." + "reason": "Both touch flash attention, but the root causes differ: packed-sequence misinterpretation of position_ids versus `s_aux=None` AttributeError." }, { "left": "issue:42491", "right": "issue:45292", "accept": false, - "reason": "Different problems: LoRA/version compatibility versus embedding resize propagation." + "reason": "LoRA hf4.x\u2192hf5.x incompatibility is unrelated to the generic `resize_token_embeddings` output-embedding bug." }, { "left": "issue:45276", "right": "issue:45335", "accept": true, - "reason": "Same resize_token_embeddings propagation bug, reported through related model-specific surfaces." + "reason": "Both describe the same `resize_token_embeddings` failure to update tied output/input embeddings, just surfaced in different model classes." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Both are save/load issues, but they concern different mechanisms and failures." + "reason": "One is save/from_pretrained mishandling `extra_state`; the other is `init_empty_weights` rejecting `_is_hf_initialized`." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "Different API breakages with no shared code-path evident." + "reason": "Importing `GenerationMixin` from `transformers.generation` and Whisper `return_language` pipeline behavior are unrelated." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both mention untied lm_head weights, but they are model-specific reports without clear shared fix." + "reason": "Both mention lm_head tying, but they are different multimodal model classes with no evidence of the same exact code-path bug." }, { "left": "issue:41720", "right": "issue:44155", "accept": false, - "reason": "Unrelated failures in different subsystems." + "reason": "These are unrelated: Qwen3 device-map cuda asserts versus AudioFlamingo3 batched track-state leakage." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version incompatibility is a dependency issue, while the meta-device report is a model-loading regression in Transformers 5.x." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Tokenizer vocab mismatch and tokenizer loading failure are different issues." + "reason": "Both involve tokenizer/model vocab problems, but the specific models and symptoms differ, so this is not a clear duplicate." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "Different models and different symptoms." - }, - { - "left": "issue:43425", - "right": "issue:43957", - "accept": false, - "reason": "Compatibility issues, but they are about different stack layers." + "reason": "SigLIP2 doc/model issues are unrelated to the GLM5 report." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Different subsystems entirely." + "reason": "Gradient checkpointing with PEFT LoRA is unrelated to the T5/apex RMSNorm memory leak." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "Different model families and mechanisms." + "reason": "Gemma-4 FSDP2 shared_kv_states behavior and Qwen multimodal `text_config` unwrapping are different model-integration bugs." }, { "left": "issue:43335", "right": "issue:45663", "accept": false, - "reason": "Unrelated configuration bug versus FSDP2 state handling bug." + "reason": "SwitchTransformers sparse-layer creation and Gemma-4 FSDP2 attention-state rebuilding are unrelated." }, { "left": "issue:43873", "right": "issue:44387", "accept": false, - "reason": "Both can lead to OOM, but the underlying causes differ." + "reason": "Quantization/offloading behavior and int4 reserved-memory OOM are related only at a very broad level, not as the same bug." }, { - "left": "issue:45663", - "right": "issue:45859", + "left": "issue:44291", + "right": "issue:44756", "accept": false, - "reason": "Different models and code paths." + "reason": "`init_empty_weights` argument handling and Strix Halo mmap OOM are unrelated." }, { - "left": "issue:44291", - "right": "issue:44756", + "left": "issue:45663", + "right": "issue:45859", "accept": false, - "reason": "Constructor/init error versus platform-specific mmap OOM workaround." + "reason": "Gemma-4 FSDP2 attention state handling and Qwen3_5Moe CPU-offload incompatibility are different issues." }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "Different model-specific forward bugs." + "reason": "AudioFlamingo3 batched inference state leakage is unrelated to Gemma4 device-mismatch during forward." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Quantized-loading issues, but for different formats and model families." + "reason": "Different quantization formats and failures: NVFP4 loading error versus MXFP4 fallback to bf16." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "Both can cause OOM, but the causes are unrelated." + "reason": "Both involve OOMs, but one is int4 reserved-memory growth and the other is disabling mmap on Strix Halo." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Different classes of bugs in save/load behavior." + "reason": "GLM-4.7-Flash test loading and Qwen3.5 save_pretrained regression are separate model/load paths." }, { - "left": "issue:44743", - "right": "issue:44960", + "left": "issue:43957", + "right": "issue:44756", "accept": false, - "reason": "A cache/state bug and a generic model issue are unrelated." + "reason": "Meta-device loading regressions and Strix Halo mmap OOM are not the same bug." }, { - "left": "issue:43957", - "right": "issue:44756", + "left": "issue:44743", + "right": "issue:44960", "accept": false, - "reason": "Different problems: meta-device loading regression versus Strix Halo mmap OOM workaround." + "reason": "Qwen3 recurrent-state reset with cache is unrelated to the GLM5 report." }, { "left": "issue:45276", "right": "issue:45292", "accept": true, - "reason": "Same resize_token_embeddings regression, with 45292 as the broader API-level report." + "reason": "These are the same `resize_token_embeddings` defect, with 45276 being a model-specific manifestation and 45292 the broader report." }, { "left": "issue:45684", "right": "issue:45698", "accept": false, - "reason": "Both involve save/load with custom modules, but the actual failures differ." + "reason": "`save_pretrained` permission propagation and `from_pretrained` loading the wrong custom module are different custom-model save/load problems." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster summary is mostly grounded, and the 45276/45292 duplicate call looks conservative. However, the best_issue_reason overstates the evidence by saying issue:45812 is 'clearly reproduced'\u2014the packet only shows metadata (open state, inbound refs, title), not the reproduction quality. Please tone that down to a packet-supported claim or remove it." + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only clearly supported duplicate cluster is the resize_token_embeddings trio around 45276/45292/45335, and the other soft-edge rejections avoid overclaiming sameness across different model-specific failures." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -2235,10 +1977,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36032", "issue:39404", @@ -2302,12 +2044,12 @@ "issue:43257|issue:44863", "issue:43828|issue:43957", "issue:43425|issue:43828", - "issue:44589|issue:44756", "issue:44683|issue:45823", + "issue:44589|issue:44756", "issue:39404|issue:45701", "issue:43931|issue:44863", - "issue:43906|issue:44530", "issue:43425|issue:45823", + "issue:43906|issue:44530", "issue:43611|issue:43645", "issue:43425|issue:43716", "issue:44530|issue:45084", @@ -2318,251 +2060,251 @@ "issue:43994|issue:44079", "issue:43299|issue:43931", "issue:43425|issue:44918", - "issue:39404|issue:44671", "issue:44589|issue:45084", + "issue:39404|issue:44671", "issue:44164|issue:45759", "issue:36032|issue:43452", "issue:43596|issue:44683", "issue:44671|issue:44991" ], - "prepared_review_unit_hash": "d0f3842138cdd2f3be79f405fd829a1a71bf305138a745cd48aa01b7914effe0", + "prepared_review_unit_hash": "859dd7b0156528b7b121dc0b6663950ccc58462cf636f9fe085dd04c5f7eeae3", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37972, - "estimated_input_tokens": 9493, - "estimated_eval_tokens": 19242 + "serialized_chars": 37968, + "estimated_input_tokens": 9492, + "estimated_eval_tokens": 19240 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is dominated by broad but mostly unrelated Transformers regressions (model loading, dtype/device mismatches, docs, training edge cases). Only one pair looks like a true duplicate: the resize_token_embeddings propagation bug.", - "confidence": 0.83, - "canonical_issue_reason": "issue:45292 is the broader, model-agnostic report of the resize_token_embeddings bug, while issue:45335 is the T5Gemma-specific manifestation.", + "summary": "Mostly a loose cluster of Transformers v5 regression reports, not one tight duplicate set. The only clear duplicate-like pairs are the two tokenizer-embedding resize issues and the two Qwen3-VL loading reports; the rest are related at a broad subsystem level but describe different bugs.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43611 is the broadest, most representative report of the v5 model-loading breakage theme in this cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45292 is the clearest and most general representative of the one confirmed duplicate pair.", + "best_issue_reason": "issue:43611 is the best single issue to anchor the cluster because it captures the most general loading-regression pattern rather than a narrow model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Different bugs: gradient checkpointing in eval mode vs Qwen3.5 RLHF NaN/SDPA fallback instability." + "reason": "Both involve training/gradient behavior, but the eval-mode checkpointing restriction is a different bug than the Qwen3.5 NaN/SDPA fallback issue." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "Unrelated failures: extra_state save/load handling vs mmap/OOM behavior on Strix Halo." + "reason": "Extra state handling in save/from_pretrained and disabling mmap on Strix Halo are unrelated failure modes." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Both mention gradient checkpointing, but one is LoRA inefficiency and the other is eval-mode incompatibility." + "reason": "Both mention gradient checkpointing, but one is PEFT/LoRA effectiveness and the other is an eval-mode restriction; different code paths." }, { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Different model/config regressions: Qwen VL video-input path vs strict config blocking granite_speech loading." + "reason": "Video-input regression for Qwen/VL models and strict-config loading for granite_speech are different issues." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom model init in notebooks is unrelated to Trainer resume/max_steps calculation." + "reason": "Custom model init in Jupyter notebooks and Trainer resume/max_steps calculation are separate problems." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "Different code paths and symptoms: flash_attention s_aux handling vs Gemma4 FSDP2 shared_kv_states rebuild." + "reason": "Flash-attention s_aux=None crash and Gemma4 FSDP2 shared_kv_states KeyError are not the same bug." }, { "left": "issue:45292", "right": "issue:45335", "accept": true, - "reason": "Same underlying bug: resize_token_embeddings does not propagate to the active embedding/output embedding; 45335 is the T5Gemma-specific case." + "reason": "Both report resize_token_embeddings failing to update downstream output/decoder embeddings; same underlying embedding-resize bug." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Notebook custom-model initialization is unrelated to extra_state save/from_pretrained handling." + "reason": "Notebook-defined custom model initialization and extra_state serialization are different failure modes." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "Tokenizer vocab-size issue for one model is not the same as a general load failure for another model." + "reason": "Tokenizer vocab-size mismatch and inability to load ScandiBERT are related to loading, but not the same concrete defect." }, { "left": "issue:43257", "right": "issue:44863", "accept": false, - "reason": "Both are loading problems, but they affect different architectures and failure mechanisms (Qwen3 MoE conversion vs NemotronH checkpoint loading)." + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed and NemotronH checkpoint loading are separate model-loading regressions." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Autocast dtype mismatch is a different problem from meta-device loading failures." + "reason": "Autocast dtype mismatch and meta-device loading failures are different code-path problems." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch version incompatibility is not the same as a Phi-tiny-MoE autocast dtype mismatch." + "reason": "Torch version incompatibility is too broad and not the same as the Phi-tiny-MoE autocast dtype mismatch." }, { - "left": "issue:44589", - "right": "issue:44756", + "left": "issue:44683", + "right": "issue:45823", "accept": false, - "reason": "Float8 storage lookup failure is unrelated to Strix Halo mmap/OOM behavior." + "reason": "Torch>=2.9 flex_attention compilation and Gemma4 PLE device-mapping mismatch are unrelated." }, { - "left": "issue:44683", - "right": "issue:45823", + "left": "issue:44589", + "right": "issue:44756", "accept": false, - "reason": "Different subsystems: compiled flex_attention on torch>=2.9 vs Gemma4 PLE device placement." + "reason": "Float8 storage lookup failure and mmap OOM on Strix Halo are distinct runtime issues." }, { "left": "issue:39404", "right": "issue:45701", "accept": false, - "reason": "Whisper return_language pipeline regression is not the same as general tokenization changes." + "reason": "Whisper return_language pipeline regression and tokenizer-version-dependent tokenization changes are different symptoms and code paths." }, { "left": "issue:43931", "right": "issue:44863", "accept": false, - "reason": "Different model families and symptoms: Qwen3-VL shape mismatch vs NemotronH checkpoint loading." + "reason": "Qwen3-VL weight-shape mismatch and NemotronH checkpoint loading are different model families and bugs." }, { - "left": "issue:43906", - "right": "issue:44530", + "left": "issue:43425", + "right": "issue:45823", "accept": false, - "reason": "Isolated reproduction of an earlier issue is not the same as the Qwen3.5 PagedAttentionCache crash." + "reason": "Generic Torch incompatibility and Gemma4 device mismatch are not the same bug." }, { - "left": "issue:43425", - "right": "issue:45823", + "left": "issue:43906", + "right": "issue:44530", "accept": false, - "reason": "Torch compatibility issue does not match Gemma4 forward-device mismatch." + "reason": "An isolated reproduction of a prior issue and a PagedAttentionCache linear_attention crash are unrelated." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Base_model_prefix loading regression is different from notebook-defined custom model initialization." + "reason": "Both are v5 custom-model loading regressions, but one is base_model_prefix handling and the other is notebook-defined initialization; not the same concrete bug." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch version incompatibility is unrelated to Mistral-3 image preprocessor/model dtype mismatch." + "reason": "Torch 2.10 incompatibility and Mistral-3 dtype mismatch are separate issues." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "PagedAttentionCache group-type crash is unrelated to template-node compilation errors." + "reason": "PagedAttentionCache group-type crash and template-node compilation error are different failures." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline language return regression is unrelated to MXFP4 quantization fallback." + "reason": "Whisper pipeline behavior and MXFP4 quantization fallback are unrelated." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "Both are docs issues, but they cover different obsolete pipeline/task mentions." + "reason": "Docs drift for return_all_scores and docs for removed pipeline tasks are both documentation issues, but not the same one." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "torch.export failure with torch_compilable_check is unrelated to Perceiver non-default-resolution inference." + "reason": "torch.export export failure with torch_compilable_check and Perceiver non-default-resolution failure are different bugs." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Different regressions: Qwen VL video-input path vs generic mask/index shape mismatch." + "reason": "Qwen video-input regression and a mask-shape IndexError are unrelated." }, { "left": "issue:43994", "right": "issue:44079", "accept": false, - "reason": "Nonsensical model outputs are not the same bug as incorrect ModelOutput key assignment." + "reason": "SigLIP2 nonsense predictions and ModelOutput key assignment are separate problems." }, { "left": "issue:43299", "right": "issue:43931", - "accept": false, - "reason": "Both concern Qwen3-VL loading, but one is a MoE/version regression and the other is a specific weight-shape mismatch." + "accept": true, + "reason": "Both concern Qwen3-VL / Qwen3VL model loading failing under v5, with shape-mismatch-style symptoms; same underlying loading regression is plausible." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch compatibility is unrelated to Qwen3.5 embedding unpacking with trl SFT trainer." + "reason": "Torch incompatibility and Qwen3.5 embedding unpacking are unrelated." }, { - "left": "issue:39404", - "right": "issue:44671", + "left": "issue:44589", + "right": "issue:45084", "accept": false, - "reason": "Whisper pipeline behavior and CamemBERT masked-LM predictions are different code paths." + "reason": "Float8 storage lookup failure and non-template node compilation error are different issues." }, { - "left": "issue:44589", - "right": "issue:45084", + "left": "issue:39404", + "right": "issue:44671", "accept": false, - "reason": "Float8 storage deserialization failure is unrelated to non-template-node compilation." + "reason": "Whisper pipeline regression and CamemBERT masked-LM prediction regression are different model-specific bugs." }, { "left": "issue:44164", "right": "issue:45759", "accept": false, - "reason": "extra_state handling and AutoModelForCausalLM.from_config text_config unwrapping are different loading bugs." + "reason": "Extra_state serialization and from_config text_config unwrapping are distinct loading/serialization issues." }, { "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "Tokenizer special-token conflict is unrelated to gguf_file loading behavior." + "reason": "T5 tokenizer loading conflict and gguf_file breaking from_pretrained are unrelated." }, { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "Deepspeed ZeRO3/BertModel index error is unrelated to compiled flex_attention on newer torch." + "reason": "Deepspeed ZeRO3/BertModel index error and flex_attention compilation failure are unrelated." }, { "left": "issue:44671", "right": "issue:44991", "accept": false, - "reason": "CamemBERT masked-LM predictions and tokenizer load failure for EMBEDDIA/est-roberta are different issues." + "reason": "CamemBERT prediction regression and tokenizer-loading failure for est-roberta are different bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The judgments are well grounded in the packet and stay conservative. The only accepted pair, issue:45292 / issue:45335, is supported by the titles as the same resize_token_embeddings propagation bug with a model-specific manifestation. The rest of the soft-edge rejections are cautious and not overstated, and the cluster summary matches the mostly heterogeneous issue titles." + "feedback": "The summary is grounded in the packet and stays appropriately cautious. The stated duplicate-like pairs are supported by the issue titles, and the rejected pairs are conservative rather than overstated. I don\u2019t see a soft-edge verdict that clearly stretches the evidence." }, "evaluator_used": true, "retried": false, @@ -2578,10 +2320,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:32090", "issue:34567", @@ -2636,13 +2378,13 @@ "issue:32090|issue:39404", "issue:43856|issue:44756", "issue:44991|issue:45081", - "issue:44737|issue:45859", "issue:44164|issue:44479", + "issue:44737|issue:45859", "issue:43582|issue:43632", "issue:44488|issue:45081", "issue:44661|issue:44683", - "issue:40990|issue:43421", "issue:44488|issue:44987", + "issue:40990|issue:43421", "issue:43611|issue:43644", "issue:44206|issue:44220", "issue:43716|issue:45084", @@ -2652,240 +2394,240 @@ "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:43644|issue:43646", "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:45084|issue:45507", "issue:43089|issue:45987", - "issue:45084|issue:45507" + "issue:43404|issue:44466" ], - "prepared_review_unit_hash": "1858bbbedd047516c17442ec02fb8078a7b6734e16a81c483fb3dfe96b027f0d", + "prepared_review_unit_hash": "0f1a4b7ab6d55316dcfc40cb23c10cb20d25059e5d6b52d3a3824c6347348d7a", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37267, - "estimated_input_tokens": 9317, - "estimated_eval_tokens": 18890 + "serialized_chars": 37261, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated closed issues across tokenizers, model loading, vision/audio preprocessing, training state, cache, and generation. The title/body signals do not support merging any soft pair as the same underlying bug or change.", - "confidence": 0.98, - "canonical_issue_reason": "No single issue is a reliable canonical representative: the items span unrelated regressions and subsystems rather than one duplicate family.", + "summary": "The items are mostly unrelated issue reports, with only a loose concentration around Transformers v5 loading/initialization regressions. No soft pair is a confident duplicate match.", + "confidence": 0.73, + "canonical_issue_reason": "issue:43646 is the broadest representative of the recurring v5 model-initialization breakage theme, and is the closest anchor for nearby custom-model/load regressions in this set.", "canonical_pr_reason": null, - "best_issue_reason": "No best issue stands out as a cluster anchor because the set does not converge on one bug class or code path.", + "best_issue_reason": "issue:43646 is the best single issue to represent the cluster because it captures the most general and reusable failure mode among the listed reports, even though the overall cluster is not a tight duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:32090", "right": "issue:39404", "accept": false, - "reason": "Trainer GPU broadcast NoneType error and Whisper return_language regression are unrelated code paths." + "reason": "Different subsystems and failures: GPU broadcast TypeError in Trainer vs Whisper pipeline return_language behavior." }, { "left": "issue:43856", "right": "issue:44756", "accept": false, - "reason": "Qwen3 MoE training memory usage and Strix Halo mmap OOM are different memory problems with different triggers." + "reason": "Both mention memory, but one is Qwen3 MoE training inefficiency and the other is mmap/OOM on Strix Halo; different bugs and code paths." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Separate loading failures: EMBEDDIA tokenizer regression vs Mistral regex patch/backend_tokenizer crash." + "reason": "Both are tokenizer-loading regressions, but one is a generic tokenizer load failure and the other is a Mistral regex patch crash; not the same underlying defect." }, { - "left": "issue:44737", - "right": "issue:45859", + "left": "issue:44164", + "right": "issue:44479", "accept": false, - "reason": "XLNet CPU arange bug and Qwen3.5 MoE CPU-offload incompatibility are different model-specific issues." + "reason": "Save/from_pretrained extra_state handling and a video-input regression in Qwen models are unrelated." }, { - "left": "issue:44164", - "right": "issue:44479", + "left": "issue:44737", + "right": "issue:45859", "accept": false, - "reason": "Checkpoint extra_state handling and video-input regression are unrelated serialization vs multimodal-input bugs." + "reason": "Different models and issues: XLNet CPU device placement vs Qwen3_5 MoE CPU offload compatibility." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and _is_hf_initialized flag regression are distinct initialization paths." + "reason": "Apple Silicon caching allocator TypeError and the _is_hf_initialized v5 regression are distinct problems." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Loading a specific BERT model and Mistral tokenizer regex patch failure do not share the same bug." + "reason": "Both affect loading, but one is a model-loading regression for sleng-bert and the other is a Mistral tokenizer regex patch crash." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "Model registration failure and compiled flex_attention failure are entirely different subsystems." + "reason": "Different features entirely: tokenizer mapping handling vs compiled flex_attention on torch >= 2.9." }, { - "left": "issue:40990", - "right": "issue:43421", + "left": "issue:44488", + "right": "issue:44987", "accept": false, - "reason": "High perplexity on a model and runtime post-processor updates are not the same defect." + "reason": "Both are model-load failures, but they target different models and appear to stem from different breakages." }, { - "left": "issue:44488", - "right": "issue:44987", + "left": "issue:40990", + "right": "issue:43421", "accept": false, - "reason": "Both are load failures, but they affect different models and likely different root causes." + "reason": "Perplexity on gpt-oss-20b is unrelated to TokenizersBackend not updating its post-processor." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "Base_model_prefix loading regression and junk-filled non-persistent buffers are different v5 issues." + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer serialization; different failure points." }, { "left": "issue:44206", "right": "issue:44220", "accept": false, - "reason": "Both touch audio features, but one is an unsupported center arg crash and the other is a separate fbank helper failure." + "reason": "Both are audio-feature related, but the reported failures are different enough that they do not look like the same bug." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Mistral-3 image-preprocessor dtype mismatch and a template compilation TypeError are unrelated." + "reason": "Mistral image-preprocessor dtype mismatch is unrelated to the template-node compilation TypeError." }, { "left": "issue:43883", "right": "issue:44488", "accept": false, - "reason": "Molmo tied-weights attribute error and a model loading failure are not the same bug." + "reason": "Missing all_tied_weights_keys in Molmo is unrelated to a BERT model loading failure." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "AutoConfig trust_remote_code field loss and Qwen3.5 PagedAttentionCache group-type crash are unrelated." + "reason": "AutoConfig trust_remote_code field loss and 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 model/tokenizer problems." + "reason": "T5 tokenizer special-token method conflict and Qwen3 MoE FP8 failure are unrelated." }, { "left": "issue:44811", "right": "issue:45584", "accept": false, - "reason": "Whisper batch_decode skip_special_tokens behavior and empty-transcription generation failure are distinct symptoms." + "reason": "Both are Whisper-related, but one is batch_decode skip_special_tokens behavior and the other is empty-transcription generation after align_special_tokens." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "TrainerState token counting and Qwen2.5-VL iterable-dataset finetuning failure are unrelated." + "reason": "TrainerState token counting and multi-image IterableDataset fine-tuning are unrelated." }, { "left": "issue:44464", "right": "issue:45987", "accept": false, - "reason": "Chunked generation inconsistency with compiled forward and StaticCache seq-length contract bug are different generation issues." - }, - { - "left": "issue:43644", - "right": "issue:43646", - "accept": false, - "reason": "Non-persistent buffer initialization and custom model initialization regressions are not the same underlying problem." + "reason": "Chunked generation inconsistency with compiled forward and StaticCache.get_seq_length type mismatch are different issues." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Two separate model-loading regressions on different models; no shared concrete code-path is evident." + "reason": "Different model loading regressions for different checkpoints; no clear shared bug." }, { "left": "issue:43452", "right": "issue:43482", "accept": false, - "reason": "Generic gguf_file/auto-class breakage and Qwen2.5-GGUF loading failure are related by topic only, not proven duplicates." + "reason": "Both involve GGUF loading, but one is a broad from_pretrained/gguf_file breakage and the other is a Qwen2.5-specific v5 failure; not enough evidence they are the same concrete bug." }, { "left": "issue:43541", "right": "issue:45084", "accept": false, - "reason": "Torch dynamo grouped_mm tracing error and non-template-node compile TypeError are unrelated compiler issues." + "reason": "Torch dynamo grouped_mm tracing error on Mixtral is unrelated to the non-template-node compilation TypeError." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 initialization/load regressions, but one is non-persistent buffer junk and the other is custom model initialization; they are not clearly the same bug." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "Qwen3Moe FP8 training failure and Qwen3.5 linear_attention cache crash are different MoE/cache bugs." + "reason": "Qwen3 MoE FP8 training failure and Qwen3.5 PagedAttentionCache group-type crash are different code paths." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "Device-map offload loading failure and GGUF v5 loading failure use different loading paths." + "reason": "device_map auto offload/dequantized-model loading and GGUF loading failure are different problems." }, { "left": "issue:44849", "right": "issue:45325", "accept": false, - "reason": "Qwen3.5 hidden-states bug and Qwen2.5-VL rope-index scaling bug are unrelated model-specific regressions." + "reason": "Qwen3.5 output_hidden_states bug and Qwen2.5-VL rope index scaling bug are unrelated." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Tokenizer add_special_tokens conflict and notebook custom-model init failure are different problems." + "reason": "T5 tokenizer method conflict and custom model initialization in Jupyter notebooks are different failures." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Both are version-related load failures, but they affect different artifacts and appear to stem from different regressions." + "reason": "Different failing checkpoints and different load paths; both are generic loading regressions but not the same bug." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "Molmo tied-weights attribute error and tokenizer loading failure are unrelated." + "reason": "Molmo tied-weights attribute error and tokenizer loading failure for est-roberta are unrelated." }, { - "left": "issue:43404", - "right": "issue:44466", + "left": "issue:45084", + "right": "issue:45507", "accept": false, - "reason": "Mistral3 lm_head not tied and device-dependent serialization inconsistency are related to tied weights broadly, but not the same concrete bug." + "reason": "Template-node compilation TypeError and GraniteMoEHybrid invalid method call are different issues." }, { "left": "issue:43089", "right": "issue:45987", "accept": false, - "reason": "Generation performance overhead and StaticCache return-type contract are different issues." + "reason": "Generation GPU-sync overhead and StaticCache seq-length return type are unrelated." }, { - "left": "issue:45084", - "right": "issue:45507", + "left": "issue:43404", + "right": "issue:44466", "accept": false, - "reason": "Template compilation failure and GraniteMoEHybrid invalid method call are not the same defect." + "reason": "Mistral3 lm_head tying bug and device-dependent lm_head serialization inconsistency are related only broadly, not the same concrete defect." } ] }, @@ -2904,10 +2646,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36032", "issue:40444", @@ -2930,6 +2672,7 @@ "issue:43645", "issue:43646", "issue:43742", + "issue:43792", "issue:43819", "issue:43994", "issue:44062", @@ -2971,249 +2714,253 @@ "issue:45216|issue:45357", "issue:44987|issue:45081", "issue:44220|issue:44683", - "issue:43404|issue:45127", "issue:42915|issue:44291", + "issue:43404|issue:45127", "issue:43632|issue:44756", "issue:44062|issue:44987", - "issue:44479|issue:45325", "issue:36032|issue:43742", - "issue:42915|issue:44589", + "issue:44479|issue:45325", "issue:43296|issue:43531", + "issue:42915|issue:44589", "issue:40444|issue:45325", "issue:43531|issue:44877", "issue:43611|issue:44534", "issue:36032|issue:41720", "issue:43425|issue:44403", + "issue:40990|issue:44811", "issue:41553|issue:43582", "issue:44079|issue:45663", - "issue:40990|issue:44811", "issue:43632|issue:44534", - "issue:42175|issue:45542" + "issue:42175|issue:45542", + "issue:43792|issue:44589" ], - "prepared_review_unit_hash": "e5590337e6b1dce4771794e143091280b210af4af60bf9b4cfa7ded89fab51cc", + "prepared_review_unit_hash": "8bb62c9f48b3130628f2de6138546da2786395e054524b4d4ade1aff3cf9a162", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36391, - "estimated_input_tokens": 9098, - "estimated_eval_tokens": 18452 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37221, + "estimated_input_tokens": 9306, + "estimated_eval_tokens": 18868 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab-bag of unrelated Transformers regressions, not one duplicate family. I only see two strong duplicate-like pairs: the Qwen3.5 save_pretrained regression and the Qwen video/temporal-position regression; the rest are too semantically distant to merge.", - "confidence": 0.71, - "canonical_issue_reason": "If one issue must anchor the cluster, issue 44479 is the broadest concrete regression report and best representative of the Qwen video/position-id bug subset. It is still not a good umbrella for the many unrelated loading/init/backend issues in the set.", + "summary": "This cluster is mostly a semantic grab-bag of Transformers regressions, with the strongest common thread being v5-era loading/serialization breakages. Most soft pairs are only loosely related by subsystem or model family, not by the same concrete bug.", + "confidence": 0.42, + "canonical_issue_reason": "issue:43611 is the broadest representative of the main theme in this cluster: Transformers v5 loading regressions. Its title is generic enough to cover several nearby load/init failures, without being tied to one narrow model.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44479 is the best overall issue candidate because it describes a specific regression affecting multiple Qwen variants and is a plausible duplicate target for the narrower Qwen2.5-VL position-id report.", + "best_issue_reason": "issue:43611 is the best single issue to represent the cluster because it captures the shared \u2018v5 breaks model loading\u2019 pattern more cleanly than the model-specific reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Both are audio-related, but one is a chat-template sampling-rate default bug and the other is a padding-mask/ batching correctness bug in MIMI; different code paths." + "reason": "Both are audio-related, but one is a chat-template sampling-rate default and the other is a batching/padding-mask correctness bug in MIMI." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "Different models and failures: SigLIP2 pipeline output quality vs OmDet processor image-size mismatch." + "reason": "Different models and different failures: SigLIP2 bad outputs vs OmDet-Turbo processor/model input-size mismatch." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Custom model initialization failure is not the same underlying bug as non-persistent buffers being filled with junk." + "reason": "Custom model initialization breakage is not the same bug as non-persistent buffers being filled with junk." }, { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Different multimodal model families and different symptoms: Llava Next load segfault vs Qwen3OmniMoe video ValueError." + "reason": "Both are multimodal loading/input errors, but Llava Next segfault and Qwen3OmniMoe video ValueError are distinct code paths." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Notebook/custom-model init regression is unrelated to the non-persistent buffer initialization bug." + "reason": "Notebook/custom-model init failure is unrelated to the buffer-initialization corruption described in 44534." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Generic loading noise vs a Mistral tokenizer regex crash; not the same bug." + "reason": "Generic loading noise is not the same underlying problem as a tokenizer regex patch crash." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "MIMI batching/padding-mask bug and DAC from_latents STE mismatch are unrelated." + "reason": "Different audio model families and different bugs: padding-mask batching vs DAC latent/forward mismatch." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "Qwen3MoE FP8 config failure and compile-time template-node error are different failures." + "reason": "Qwen3Moe FP8 config failure is unrelated to the template-node compilation error." }, { "left": "issue:44265", "right": "issue:44610", "accept": false, - "reason": "torch.export with torch_compilable_check and OmDet processor image sizing are unrelated." + "reason": "torch.export failure with torch_compilable_check is a different issue from OmDet-Turbo processor input sizing." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "ScandiBERT loading failure and Mistral regex patch crash are different model-specific bugs." + "reason": "A model load failure for ScandiBERT is not the same as the Mistral tokenizer regex patch crash." }, { "left": "issue:45216", "right": "issue:45357", - "accept": true, - "reason": "Same Qwen3.5 save_pretrained regression: 45357 is a later report of incorrect visual encoder keys from the same underlying bug." + "accept": false, + "reason": "These are related Qwen3.5 save_pretrained regressions, but 45357 is a narrower visual-encoder-key follow-up rather than the same concrete bug as 45216." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "Physical-intelligence/fast loading failure is not the same as the Mistral tokenizer backend_tokenizer crash." + "reason": "Different failure modes: loading a specific model repo vs crashing inside Mistral regex patching." }, { "left": "issue:44220", "right": "issue:44683", "accept": false, - "reason": "Audio feature extraction issue and compiled flex_attention failure are unrelated." + "reason": "Feature-extraction audio issue and compiled flex_attention torch-version incompatibility are unrelated." }, { - "left": "issue:43404", - "right": "issue:45127", + "left": "issue:42915", + "right": "issue:44291", "accept": false, - "reason": "Tied lm_head weights in Mistral3ForConditionalGeneration is not the same as LoRA merge collapse with extended vocab." + "reason": "Different model/setup and different root cause: Qwen3Moe FP8 config vs init_empty_weights unexpected argument." }, { - "left": "issue:42915", - "right": "issue:44291", + "left": "issue:43404", + "right": "issue:45127", "accept": false, - "reason": "Different root causes: Qwen3MoE FP8 config vs init_empty_weights/_is_hf_initialized argument handling." + "reason": "Both touch tied weights, but one is a missing lm_head tie in Mistral3 and the other is LoRA merge collapse after vocab extension." }, { "left": "issue:43632", "right": "issue:44756", "accept": false, - "reason": "_is_hf_initialized flag regression and mmap/OOM on Strix Halo are unrelated." + "reason": "_is_hf_initialized flag breakage is unrelated to the mmap/OOM issue on Strix Halo." }, { "left": "issue:44062", "right": "issue:44987", "accept": false, - "reason": "AddedToken special-argument duplication and loading physical-intelligence/fast are different bugs." - }, - { - "left": "issue:44479", - "right": "issue:45325", - "accept": true, - "reason": "45325 is a narrower manifestation of the same Qwen video/temporal-position regression described broadly in 44479." + "reason": "Duplicate AddedToken special-arg handling is not the same as loading physical-intelligence/fast failing." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "T5Tokenizer add_special_tokens conflict and MobileLLM-125M key error are unrelated loading problems." + "reason": "T5 tokenizer add_special_tokens conflict and MobileLLM key error are different loading bugs." }, { - "left": "issue:42915", - "right": "issue:44589", + "left": "issue:44479", + "right": "issue:45325", "accept": false, - "reason": "Qwen3MoE FineGrainedFP8Config failure is unrelated to missing Float8 storage support." + "reason": "Both concern Qwen vision/video behavior, but the broad video-input regression is not the same as the still-image temporal position_id scaling bug." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "PaddleOCR-VL load failure and Qwen3-MoE sliding_window issue are different model-specific regressions." + "reason": "PaddleOCR-VL loading in vLLM and Qwen3-MoE sliding_window are unrelated failures." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3Moe FP8 config failure is not the same as the missing Float8 storage type issue." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "IterableDataset multi-image fine-tuning failure is not the same as the Qwen2.5-VL temporal-position bug." + "reason": "IterableDataset multi-image finetuning failure is different from the Qwen2.5-VL rope-index scaling regression." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and granite_speech strict config loading are unrelated." + "reason": "Sliding-window handling in Qwen3-MoE and strict-config loading for granite_speech are distinct problems." }, { "left": "issue:43611", "right": "issue:44534", "accept": false, - "reason": "base_model_prefix loading breakage is a different issue from non-persistent buffer corruption." + "reason": "Generic model-loading breakage is not the same bug as junk-filled non-persistent buffers." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer add_special_tokens conflict and Qwen3 device-mapping cudaErrorAssert are unrelated." + "reason": "Tokenizer loading conflict and Qwen3 auto-device-map CUDA assert are unrelated." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch 2.10 incompatibility is not the same as generic loading noise." + "reason": "Torch version incompatibility and loading noise are not the same concrete issue." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on gpt-oss is unrelated to Whisper batch_decode skip_special_tokens handling." }, { "left": "issue:41553", "right": "issue:43582", "accept": false, - "reason": "Bad AutoTokenizer error for Voxtral and AppleSilicon caching_allocator_warmup TypeError are unrelated." + "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to the Apple Silicon warmup TypeError." }, { "left": "issue:44079", "right": "issue:45663", "accept": false, - "reason": "ModelOutput key assignment and Gemma4 FSDP2 shared_kv_states KeyError are different code paths." - }, - { - "left": "issue:40990", - "right": "issue:44811", - "accept": false, - "reason": "High perplexity on gpt-oss-20b and Whisper batch_decode skip_special_tokens are unrelated." + "reason": "ModelOutput key assignment and Gemma4 shared_kv_states/FSDP2 are different bugs." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "These are both Transformers v5 regressions, but they affect different mechanisms and are not the same underlying bug." + "reason": "_is_hf_initialized regression and non-persistent buffer corruption are distinct v5 breakages." }, { "left": "issue:42175", "right": "issue:45542", "accept": false, - "reason": "Both mention TensorFlow packaging/backend issues, but one is missing tf in the torch extra and the other is a tensorboard-only runtime backend error; too different to treat as duplicates." + "reason": "Pip extras/backend dependency omission and tensorboard-without-TensorFlow backend errors are related only loosely, not the same bug." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper model runtime failure and missing Float8 storage object are unrelated." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The chosen anchor issue 44479 is a reasonable broad representative for the Qwen video/position-id subset, and the only accepted duplicate-like pair (45216/45357) is plausibly the same save_pretrained regression. The rejections mostly rest on clearly different model families or bug mechanisms, so I don\u2019t see an overstatement." - }, - "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 }, @@ -3225,10 +2972,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:33666", "issue:35707", @@ -3249,7 +2996,6 @@ "issue:43644", "issue:43646", "issue:43749", - "issue:43792", "issue:43818", "issue:43856", "issue:43994", @@ -3281,19 +3027,18 @@ ], "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:43317|issue:43856", "issue:43381|issue:45923", + "issue:44829|issue:45479", "issue:35707|issue:40444", - "issue:44079|issue:44534", "issue:44291|issue:44589", + "issue:44079|issue:44534", "issue:43482|issue:43525", "issue:43377|issue:45491", "issue:43749|issue:44079", @@ -3303,215 +3048,209 @@ "issue:43644|issue:44079", "issue:44265|issue:45072", "issue:45325|issue:45381", + "issue:42175|issue:43296", "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": "6b5081887ac978aa05ac5a9173698c7b3d9e47d72167a66fbdfbc1726ef3d52a", + "prepared_review_unit_hash": "c21410207077f01a4dd113af1719d7eafb9936856fbcedcda2f7a5482e66726f", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36580, - "estimated_input_tokens": 9145, - "estimated_eval_tokens": 18546 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35748, + "estimated_input_tokens": 8937, + "estimated_eval_tokens": 18130 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of transformer/model-loading regression reports with only superficial overlap around Transformers v5 and tokenizer/model edge cases. I did not find any soft pair that is clearly the same underlying bug/change.", - "confidence": 0.34, - "canonical_issue_reason": "Issue 45020 is the broadest umbrella-style report in the set and the best single anchor among otherwise mixed, mostly unrelated regressions.", + "summary": "These are mostly unrelated bug reports spanning different models, loading paths, and regressions. I found no high-confidence duplicate pair among the soft edges, so the cluster should not be merged as a duplicate set.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45020 is the best umbrella anchor: it is broad, well-documented, and represents a major transformer-v5 regression class rather than a narrow model-specific symptom.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45020 has the widest scope, active discussion, and reads like the most useful representative issue for the cluster, even though the cluster is not a tight duplicate set.", + "best_issue_reason": "issue:45020 is the most representative and actionable issue in this mixed cluster, with the broadest scope and strongest discussion trail.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Different tokenizer problems: runtime post-processor sync vs add_special_tokens not inserting BOS/EOS." - }, - { - "left": "issue:43792", - "right": "issue:44589", - "accept": false, - "reason": "Whisper model loading/runtime failure is unrelated to the Float8 storage lookup TypeError." + "reason": "Both involve tokenization behavior, but one is runtime post-processor refresh and the other is add_special_tokens/BOS-EOS behavior for a specific tokenizer; not the same bug." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Video-LLaVA temporal-attention/weight-sharing bug is unrelated to Qwen3.5 save_pretrained visual-key serialization." + "reason": "Different model families and failure modes: Video-LLaVA tower architecture vs Qwen3.5 save_pretrained key serialization." }, { "left": "issue:44683", "right": "issue:45020", "accept": false, - "reason": "Torch >=2.9 compiled flex_attention failure is a different code path from remote_code model-loading regressions." + "reason": "Torch 2.9 flex_attention compilation failure is a distinct backend regression from remote_code model loading breakage." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "Generic loading noise and a specific tokenizer-load failure for EMBEDDIA/est-roberta are different issues." + "reason": "Unnecessary loading noise and tokenizer-loading failure are separate symptoms in different code paths." }, { "left": "issue:44462", "right": "issue:45812", "accept": false, - "reason": "Both involve AutoTokenizer, but ignoring tokenizer.json and producing wrong Granite token IDs are distinct bugs." + "reason": "Both are AutoTokenizer issues, but one ignores tokenizer.json while the other returns wrong Granite token IDs; not clearly the same defect." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Qwen2-VL multi-GPU training and Qwen2.5-VL multi-image IterableDataset failures are different scenarios and failure modes." + "reason": "Different Qwen2-VL/Qwen2.5-VL training workflows and distinct multi-image dataloader failure." }, { - "left": "issue:44829", - "right": "issue:45479", + "left": "issue:43482", + "right": "issue:45538", "accept": false, - "reason": "FlashAttention-3 degenerate training and the num_labels=1 zero-loss bug have different causes." + "reason": "GGUF loading under v5 and CLIPTokenizer model_max_length behavior are unrelated tokenizer/model-loading bugs." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "device_map offload load failure is unrelated to Qwen3 MoE training memory inefficiency." + "reason": "Device-map offload load failure and Qwen3 MoE training memory usage are different problems in different phases." }, { - "left": "issue:43482", - "right": "issue:45538", + "left": "issue:43381", + "right": "issue:45923", "accept": false, - "reason": "GGUF loading failure and CLIPTokenizer model_max_length sentinel handling are unrelated." + "reason": "Eval-mode gradient checkpointing restriction is not the same as a missing supports_gradient_checkpointing flag." }, { - "left": "issue:43381", - "right": "issue:45923", + "left": "issue:44829", + "right": "issue:45479", "accept": false, - "reason": "Eval-mode checkpointing restriction and a missing supports_gradient_checkpointing flag are not the same bug." + "reason": "Both end in degenerate training, but one is flash_attention_3-specific and the other is a num_labels=1 loss formulation bug." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image finetuning failures." + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image finetuning failure." }, { - "left": "issue:44079", - "right": "issue:44534", + "left": "issue:44291", + "right": "issue:44589", "accept": false, - "reason": "ModelOutput key assignment and non-persistent buffer junk are separate runtime regressions." + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different initialization path from Float8 storage resolution failures." }, { - "left": "issue:44291", - "right": "issue:44589", + "left": "issue:44079", + "right": "issue:44534", "accept": false, - "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is unrelated to Float8 storage resolution." + "reason": "ModelOutput key assignment and non-persistent buffer junk are separate internal state-management issues." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "GGUF loading failure is unrelated to missing pad_token_id on Llama4Config." + "reason": "GGUF loading regression and missing pad_token_id on Llama4Config are not the same underlying bug." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "Both are batching/padding-related, but MIMI padding masks and Gemma3 all-padding sliding-window NaNs are different model-path bugs." + "reason": "Batch-vs-single MIMI padding-mask mismatch and Gemma3 NaNs from all-padding windows are different model-specific attention/padding bugs." }, { "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP CPU RAM efficient loading and ModelOutput key handling are unrelated." + "reason": "FSDP CPU RAM-efficient loading and ModelOutput key handling are unrelated subsystems." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Multi-image finetuning failure and Qwen2.5-VL video vision_position_ids are different issues." + "reason": "Multi-image prompt finetuning failure is distinct from Qwen2.5-VL video vision_position_ids regression." }, { "left": "issue:43531", "right": "issue:44291", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to init_empty_weights argument handling." + "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights argument handling are different regressions." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "A800 device-mapping assert and Mistral tokenizer regex patch crash are different subsystems." + "reason": "Auto device mapping cudaErrorAssert on A800 is unrelated to Mistral tokenizer regex patch crashes." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Non-persistent buffer junk is unrelated to ModelOutput key assignment." + "reason": "Non-persistent buffer junk and ModelOutput key assignment bugs are different internal behaviors." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "torch.export/torch_compilable_check failure and bfloat16 dtype mismatches are different bugs." + "reason": "torch.export with torch_compilable_check and bfloat16 dtype mismatches are not the same code-path problem." }, { "left": "issue:45325", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen2.5-VL position-id regressions, but one is still-image rope scaling and the other is video vision_position_ids." + "reason": "Both are Qwen2.5-VL position-id regressions, but one is still-image temporal scaling and the other is video vision_position_ids; related, but not confidently the same bug." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Missing TensorFlow backend from pip extras and PaddleOCR-VL load failure are unrelated packaging/loading issues." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "_is_hf_initialized flag breakage is unrelated to dtype mismatch in inference." + "reason": "_is_hf_initialized breakage in v5 is unrelated to dtype mismatches in bfloat16 inference." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "SigLIP2 AutoModel/pipeline nonsense outputs and Perceiver interpolation failure are different model-specific bugs." + "reason": "SigLIP2 nonsensical outputs and Perceiver resize/interpolation failure are different model-specific vision issues." }, { "left": "issue:43611", "right": "issue:43646", "accept": false, - "reason": "Both are v5 custom-model regressions, but one is about base_model_prefix loading and the other about custom initialization; too different to merge safely." - }, - { - "left": "issue:42175", - "right": "issue:43296", - "accept": false, - "reason": "Missing tensorflow in torch extra and a PaddleOCR-VL/vLLM load failure are unrelated." + "reason": "Both mention transformers v5 breakage, but base_model_prefix loading and custom model initialization are separate failures." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "lm_head weight tying failure and device-dependent serialization inconsistency are related only at a broad topic level, not the same bug." + "reason": "AyaVision weight tying failure and lm_head.weight serialization inconsistency are related only at a high level; not the same bug." }, { "left": "issue:45325", "right": "issue:45834", "accept": false, - "reason": "Qwen2.5-VL rope-index scaling and Kosmos2.5 OCR index error are unrelated model-specific failures." + "reason": "Qwen2.5-VL temporal position-id scaling and Kosmos2.5 OCR index error are different model behaviors." } ] }, @@ -3530,10 +3269,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:34634", "issue:35707", @@ -3573,6 +3312,7 @@ "issue:44617", "issue:44877", "issue:44898", + "issue:44991", "issue:45072", "issue:45325", "issue:45584", @@ -3591,11 +3331,11 @@ "issue:43701|issue:45325", "issue:44479|issue:45823", "issue:43881|issue:44488", - "issue:43606|issue:44265", "issue:44291|issue:44877", + "issue:43606|issue:44265", "issue:43262|issue:43746", - "issue:44568|issue:45920", "issue:40990|issue:45584", + "issue:44568|issue:45920", "issue:34634|issue:35707", "issue:43873|issue:45701", "issue:44186|issue:44265", @@ -3607,208 +3347,215 @@ "issue:43317|issue:43873", "issue:39692|issue:40444", "issue:43572|issue:45759", - "issue:43454|issue:45072", "issue:43377|issue:44898", "issue:43257|issue:45923", + "issue:43454|issue:45072", "issue:43526|issue:43883", - "issue:40990|issue:42947" + "issue:40990|issue:42947", + "issue:43881|issue:44991" ], - "prepared_review_unit_hash": "694a6f61a214f066d28787eb7af6bdd617f1b86cf0e7d48f7e5d8ec531831e82", + "prepared_review_unit_hash": "db777973969792720703289d080eb2c5367d361d79033a059bfe131a5a350879", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 28, - "serialized_chars": 35603, - "estimated_input_tokens": 8901, - "estimated_eval_tokens": 18058 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36471, + "estimated_input_tokens": 9118, + "estimated_eval_tokens": 18492 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are mostly unrelated model-specific bug reports, and the soft similarity links are too coarse to merge any of them. I\u2019d keep the tokenizer-regression issues as the closest thematic subgroup, but still not as duplicates.", - "confidence": 0.69, - "canonical_issue_reason": "Issue 45701 is the broadest umbrella-style report here: it describes a generic tokenizer regression across versions and is open, making it the best cluster anchor if one is required.", + "summary": "The cluster is heterogeneous: it contains many unrelated issue reports across model loading, tokenization, quantization, audio, vision, and device-mapping paths. None of the soft pairs look like the same underlying bug/change, so they should all remain separate.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue: the items span distinct subsystems and failure modes rather than one duplicate family.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45920 is the most actionable representative of the tokenizer-regression subset because it is open, names multiple affected models, and states the failure mode clearly.", + "best_issue_reason": "No global best issue candidate; none is a clear superset or central representative of the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Different bugs: Whisper runtime failure vs meta-device loading errors on other models; no shared code path." + "reason": "Different symptoms and scope: Whisper runtime failure vs a general torch.device(\"meta\") loading regression affecting multiple models." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Different model families and failure modes: FineGrainedFP8Config on Qwen3MoE vs GGUF loading on Qwen2.5." + "reason": "Unrelated bugs: FineGrainedFP8Config failure for Qwen3Moe vs GGUF loading failure for Qwen2.5 under transformers v5." }, { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "One is a PaddleOCR-VL/vLLM load problem; the other is a broad torch/transformers version incompatibility." + "reason": "Different version stacks and failure modes: PaddleOCR-VL/vLLM load issue vs torch 2.4.1 and transformers 5.8.0 incompatibility." }, { "left": "issue:44387", "right": "issue:44617", "accept": false, - "reason": "Both mention OOM, but the causes and affected paths are different: int4 reserved-memory regression vs Sam3Video inference memory use." + "reason": "Both mention OOM, but one is an int4 quantization memory regression and the other is a model-specific Sam3Video CUDA OOM." }, { "left": "issue:43701", "right": "issue:45325", "accept": false, - "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL rope/position-id scaling." + "reason": "Different code paths: checkpoint resume key mismatch vs Qwen2.5-VL rope/position-id scaling bug." }, { "left": "issue:44479", "right": "issue:45823", "accept": false, - "reason": "Different models and subsystems: video-input regression in Qwen VL variants vs Gemma4 PLE device mismatch." + "reason": "Different models and issues: Qwen video-input regression vs Gemma4 PLE device mismatch during forward." }, { "left": "issue:43881", "right": "issue:44488", "accept": false, - "reason": "Separate model loading failures for different checkpoints; no sign of the same underlying bug." + "reason": "Separate model-loading failures for different checkpoints; no shared concrete bug is evident." }, { - "left": "issue:43606", - "right": "issue:44265", + "left": "issue:44291", + "right": "issue:44877", "accept": false, - "reason": "CPU offload device mismatch is unrelated to torch.export failing on torch_compilable_check." + "reason": "One is an init_empty_weights argument regression; the other is strict config validation blocking granite_speech config loading." }, { - "left": "issue:44291", - "right": "issue:44877", + "left": "issue:43606", + "right": "issue:44265", "accept": false, - "reason": "init_empty_weights argument handling and strict config loading are different code paths with different symptoms." + "reason": "Different subsystems: CPU offload device mismatch vs torch.export failure around torch_compilable_check." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting is unrelated to PEFT adapter checkpoint loading." + "reason": "Audio chat-template sampling-rate default bug vs GraniteSpeech PEFT checkpoint loading issue are unrelated." }, { - "left": "issue:44568", - "right": "issue:45920", + "left": "issue:40990", + "right": "issue:45584", "accept": false, - "reason": "Both are tokenizer regressions, but one is a specific add_special_tokens/BOS-EOS bug while the other is a broader wrong-token-ids issue across many models." + "reason": "Different model/workflow failures: GPT-OSS perplexity anomaly vs Whisper empty-transcription generation failure." }, { - "left": "issue:40990", - "right": "issue:45584", + "left": "issue:44568", + "right": "issue:45920", "accept": false, - "reason": "Perplexity regression on gpt-oss-20b is unrelated to Whisper empty-transcription generation after align_special_tokens." + "reason": "Both are tokenizer regressions, but they affect different tokenizers and likely different root causes." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "Bark voice_preset failure and progressive generation with inputs_embeds/past_key_values are different bugs." + "reason": "Unrelated: Bark voice_preset does not work vs progressive generation with inputs_embeds/past_key_values." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Quantization/offloading behavior is a different problem from tokenizer changes/regressions." + "reason": "Different regressions: quantization/offloading behavior vs version-dependent tokenization changes." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "Tokenizer padding/truncation crash vs torch.export/torch_compilable_check failure are not the same underlying issue." + "reason": "Tokenizer crash on NER/padding vs export failure with torch_compilable_check are different bugs." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Progressive generation with embeddings is unrelated to Qwen3 auto-device-map CUDA asserts." + "reason": "No common underlying bug: generation cache handling vs Qwen3 device-mapping cudaErrorAssert." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "Both involve audio models, but one is offload device mismatch and the other is DAC latent/STE mismatch." + "reason": "CPU offload device mismatch is unrelated to DAC.from_latents not matching forward pass." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Both are device-related, but they affect different models and likely different code paths." + "reason": "Different models and failure causes: Qwen3 auto device mapping assert vs Gemma4 PLE device mismatch." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "Weight tying bug in AyaVision is unrelated to Bamba torch.compile SDPA failure." + "reason": "AyaVision lm_head tying bug is unrelated to Bamba SDPA/torch.compile failure." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "Padding-mask batch inconsistency in MIMI and OmDet-Turbo image-size mismatch are unrelated." + "reason": "Different modalities and root causes: MIMI batching/padding-mask bug vs OmDet-Turbo processor size mismatch." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "Both touch offload/quantization, but one is dequantized-model loading with device_map=auto and the other is a broader quantization offloading complaint." + "reason": "Both involve offloading/quantization, but one is dequantized-model loading with device_map=auto and the other is a broader offloading complaint." }, { "left": "issue:39692", "right": "issue:40444", "accept": false, - "reason": "SigLIP2 doc-example issues and Qwen2.5-VL multi-image IterableDataset failures are unrelated." + "reason": "Documentation/model-processor mismatch and quantization example errors are unrelated to Qwen2.5-VL multi-image finetuning failure." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig and text_config unwrapping for Qwen multimodal configs are separate config-loading bugs." - }, - { - "left": "issue:43454", - "right": "issue:45072", - "accept": false, - "reason": "lm_head tying and bfloat16 dtype mismatches are different failure modes." + "reason": "Different config regressions: missing pad_token_idx in StableLmConfig vs not unwrapping text_config for composite multimodal configs." }, { "left": "issue:43377", "right": "issue:44898", "accept": false, - "reason": "MIMI padding-mask discrepancy is unrelated to Perceiver non-default-resolution positional interpolation." + "reason": "Different image/audio preprocessing bugs: MIMI padding-mask mismatch vs Perceiver non-default resolution failure." }, { "left": "issue:43257", "right": "issue:45923", "accept": false, - "reason": "Accelerate+DeepSpeed MoE weight conversion and missing supports_gradient_checkpointing on a trust_remote_code variant are unrelated." + "reason": "Distinct issues: Qwen3 MOE weight conversion under accelerate/deepspeed vs missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Different bugs in different models: weight tying corruption vs dtype mismatch during bfloat16 inference." }, { "left": "issue:43526", "right": "issue:43883", "accept": false, - "reason": "BEiT label reduction bug and Molmo missing all_tied_weights_keys are different issues." + "reason": "Unrelated issues: BeitImageProcessorFast reduce_labels bug vs Molmo missing all_tied_weights_keys attribute." }, { "left": "issue:40990", "right": "issue:42947", "accept": false, - "reason": "High perplexity on gpt-oss-20b is unrelated to gradient checkpointing not taking effect with PEFT LoRA." + "reason": "Different problem domains: perplexity regression on GPT-OSS vs gradient checkpointing ineffectiveness with PEFT LoRA." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer/model loading failures for different models; no evidence of a shared defect." } ] }, @@ -3827,10 +3574,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36331", "issue:40990", @@ -3883,7 +3630,6 @@ ], "soft_pairs": [ "issue:44466|issue:45357", - "issue:43881|issue:44991", "issue:43749|issue:44534", "issue:43454|issue:43720", "issue:41720|issue:43322", @@ -3891,245 +3637,251 @@ "issue:41720|issue:44977", "issue:44008|issue:45823", "issue:42617|issue:42915", - "issue:43404|issue:45357", "issue:40990|issue:45701", - "issue:44186|issue:45072", + "issue:43404|issue:45357", "issue:45632|issue:45684", + "issue:44186|issue:45072", "issue:44423|issue:45406", "issue:43577|issue:43708", "issue:44387|issue:45704", + "issue:44877|issue:44991", "issue:43873|issue:44756", "issue:36331|issue:42617", - "issue:44877|issue:44991", - "issue:43550|issue:43720", "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:43550|issue:43606", "issue:42915|issue:43317", + "issue:43316|issue:44913", "issue:43295|issue:45701", "issue:43526|issue:43881", "issue:44671|issue:44743", "issue:41720|issue:45161" ], - "prepared_review_unit_hash": "7dde2dea9dab4da0c95b0fc3caf13477864ac3fb3a357f5e112b74f8d1d59e90", + "prepared_review_unit_hash": "055bb3b15fe5c63f4e0d8b5ff9018299da87fcbac732b251cd536d1a89a09aa1", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37656, - "estimated_input_tokens": 9414, - "estimated_eval_tokens": 19084 + "soft_pair_count": 32, + "serialized_chars": 37368, + "estimated_input_tokens": 9342, + "estimated_eval_tokens": 18940 }, "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 bugs across loading, tokenization, multimodal processing, quantization, and trainer behavior. No soft pair looks like the same underlying defect, so all candidate duplicate links should be rejected.", - "confidence": 0.87, - "canonical_issue_reason": "Issue 43749 is the strongest anchor: it has the highest discussion/inbound reference signal and describes a concrete, user-facing loading/offloading regression that could plausibly attract related reports.", + "summary": "The items are a mixed set of unrelated model-, tokenizer-, loading-, and trainer-specific bugs. None of the soft pairs look like the same underlying defect closely enough to merge, so there is no single canonical issue for this cluster.", + "confidence": 0.92, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43749 is the best issue to use as the cluster representative because it is well-scoped, high-traffic, and clearly about a core broken code path rather than a narrow model-specific symptom.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44466", "right": "issue:45357", "accept": false, - "reason": "Different bugs: one is lm_head weight tying/serialization, the other is incorrect visual encoder keys on save_pretrained." - }, - { - "left": "issue:43881", - "right": "issue:44991", - "accept": false, - "reason": "Unrelated failures: model loading for glm-4v-9b versus tokenizer loading for EMBEDDIA/est-roberta." + "reason": "Both involve saving/serialization, but the bugs are different: tied lm_head serialization vs incorrect visual encoder keys for Qwen3.5." }, { "left": "issue:43749", "right": "issue:44534", "accept": false, - "reason": "One is FSDP CPU RAM efficient loading, the other is non-persistent buffers being filled with junk; different code paths." + "reason": "Both mention v5/loading regressions, but one is FSDP CPU-efficient loading and the other is non-persistent buffer initialization; different fixes." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "Different model and failure mode: AyaVision lm_head tying vs BitNet packed-weight unpacking during accelerate loading." + "reason": "Different models and code paths: AyaVision lm_head tying vs BitNet packed-weight unpacking during accelerate loading." }, { "left": "issue:41720", "right": "issue:43322", "accept": false, - "reason": "Both are crashes, but on different models and causes: Qwen3 auto device mapping cuda assert vs Llava Next segmentation fault." + "reason": "Separate failures on different models: CUDA assert with auto device mapping vs segfault loading Llava Next." }, { "left": "issue:43296", "right": "issue:44877", "accept": false, - "reason": "A model load failure and a strict-config compatibility issue are not the same underlying bug." + "reason": "One is a PaddleOCR-VL/vLLM load failure, the other is strict config blocking granite_speech; only loosely related to loading." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "Device-mapping cuda assert on Qwen3 is distinct from a flash-attention generation regression in Qwen3.5." + "reason": "Both are Qwen-related, but one is device-mapping CUDA assert and the other is flash-attention generation behavior." }, { "left": "issue:44008", "right": "issue:45823", "accept": false, - "reason": "Different model families and failures: Gemma3n variable collision vs Gemma4 PLE device mismatch." + "reason": "Both are Gemma-family, but the concrete bugs differ: variable name collision in Gemma3n vs device mismatch in Gemma4 PLE." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "Completely different problems: a script execution failure versus Qwen3Moe failing with FineGrainedFP8Config." - }, - { - "left": "issue:43404", - "right": "issue:45357", - "accept": false, - "reason": "One is tied lm_head weights in Mistral3, the other is incorrect visual encoder key serialization in Qwen3.5." + "reason": "Unrelated: a 3d_parallel.py runtime issue versus a FineGrainedFP8Config failure on Qwen3Moe." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "High perplexity on one model is not the same as a tokenizer-behavior change across versions." + "reason": "Perplexity on GPT-OSS-20B is not the same defect as a tokenization behavior change across versions." }, { - "left": "issue:44186", - "right": "issue:45072", + "left": "issue:43404", + "right": "issue:45357", "accept": false, - "reason": "Tokenizer crash in NER/padding is unrelated to dtype mismatches during bfloat16 inference." + "reason": "Different bugs: Mistral3 lm_head tying vs Qwen3.5 visual encoder key serialization." }, { "left": "issue:45632", "right": "issue:45684", "accept": false, - "reason": "Cache-path collisions for trust_remote_code are unrelated to permission propagation in save_pretrained." + "reason": "Both are save/load path issues, but one is cache path collision and the other is file permission propagation; not the same bug." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crash on NER/batched padding is unrelated to dtype mismatches in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Different multimodal serve crashes: continuous batching with Qwen3.5 versus Gemma4Processor missing _tokenizer." + "reason": "Both crash in serve, but the failing attributes and models differ: str.to on multimodal inputs vs Gemma4Processor._tokenizer." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "One is dtype loading for BLIP2, the other is resuming training and recomputing max_steps." + "reason": "One is a dtype loading bug in Blip2; the other is a Trainer max_steps resume calculation bug." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "Int4 quantization OOM and a T5 Apex RMSNorm memory leak are separate issues." + "reason": "Different regression classes: int4 CUDA memory growth vs apex.FusedRMSNorm memory leak in T5." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Both are load failures, but config strictness and tokenizer loading are different root causes." }, { "left": "issue:43873", "right": "issue:44756", "accept": false, - "reason": "Quantized offloading behavior and a Strix Halo mmap OOM workaround are not the same bug." + "reason": "Both touch memory/offload, but one is quantization offloading behavior and the other is Strix Halo mmap OOM." }, { "left": "issue:36331", "right": "issue:42617", "accept": false, - "reason": "CustomTrainer compute_loss signature mismatch is unrelated to the 3d_parallel.py execution failure." + "reason": "CustomTrainer.compute_loss signature break is unrelated to a 3d_parallel.py execution failure." }, { - "left": "issue:44877", - "right": "issue:44991", + "left": "issue:36331", + "right": "issue:42915", "accept": false, - "reason": "Strict config loading for granite_speech and tokenizer loading for est-roberta are distinct." + "reason": "Different failures: Trainer API mismatch versus Qwen3Moe FP8 loading." }, { "left": "issue:43550", "right": "issue:43720", "accept": false, - "reason": "Bamba torch.compile with SDPA and BitNet packed-weight unpacking are different failure modes." - }, - { - "left": "issue:36331", - "right": "issue:42915", - "accept": false, - "reason": "A trainer API signature regression is unrelated to Qwen3Moe FP8 loading." + "reason": "torch.compile with SDPA on Bamba is a different code path from accelerate loading of packed BitNet weights." }, { "left": "issue:43450", "right": "issue:45701", "accept": false, - "reason": "Video processor batch-shape bug does not match a version-dependent tokenization change." + "reason": "Incorrect batched video processor shapes are unrelated to version-dependent tokenization changes." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "Both are image-size related, but one is a processor/model size mismatch and the other is a non-default resolution failure in Perceiver." + "reason": "Both are vision preprocessing issues, but one is wrong processor output size and the other is non-default resolution handling in Perceiver." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "Tokenizer crashes and OmDet-Turbo image sizing issues affect different subsystems." + "reason": "Tokenizer crash on NER/padding is unrelated to OmDet-Turbo image size mismatch." }, { "left": "issue:44479", "right": "issue:44918", "accept": false, - "reason": "Qwen video-input regression and Qwen3.5 embedding unpacking with TRL are separate problems." - }, - { - "left": "issue:43550", - "right": "issue:43606", - "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to Bark-small CPU offload device mismatch." + "reason": "Both involve Qwen3.5, but one is a video-input regression and the other is input-embedding unpacking in TRL SFT training." }, { "left": "issue:41720", "right": "issue:42617", "accept": false, - "reason": "Qwen3 auto device mapping and 3d_parallel.py startup failure are not the same underlying issue." + "reason": "Qwen3 auto device mapping CUDA assert is unrelated to the 3d_parallel.py failure." }, { - "left": "issue:43316", - "right": "issue:44913", + "left": "issue:43550", + "right": "issue:43606", "accept": false, - "reason": "Gemma3TextConfig API discrepancy and GPTNeoXConfig rotary_pct reload behavior are different config bugs." + "reason": "torch.compile/SDPA failure is not the same as a CPU-offload device mismatch on suno/bark-small." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure is unrelated to dequantized model loading with device_map=auto and CPU offload." + "reason": "Different loading problems: FineGrainedFP8Config failure vs dequantized model load failure with device_map=auto." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Config API discrepancy and GPTNeoX rotary_pct reload regression are different configuration bugs." }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "Processor/tokenizer regression is not the same as a general tokenization change across versions." + "reason": "A processor.tokenizer/image-passing regression is not the same as a broad tokenization change across versions." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and glm-4v-9b loading failure are unrelated." + "reason": "BEiT Fast label reduction bug is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM prediction corruption is unrelated to Qwen3.5 recurrent-state reset behavior." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both mention Qwen/GPT-OSS family problems, but one is CUDA assert with auto mapping and the other is tensor parallelism not working for GPT-OSS MoE." } ] }, @@ -4148,10 +3900,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:30064", "issue:33357", @@ -4214,39 +3966,39 @@ "issue:45406|issue:45464", "issue:33357|issue:35707", "issue:43421|issue:45701", - "issue:43606|issue:43720", - "issue:41720|issue:43746", "issue:30064|issue:34634", "issue:44492|issue:44509", + "issue:41720|issue:43746", + "issue:43606|issue:43720", "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:44625|issue:45479", "issue:43421|issue:43927", "issue:44368|issue:45357", "issue:43782|issue:45381", - "issue:44898|issue:45072", - "issue:44451|issue:44991" + "issue:44451|issue:44991", + "issue:44898|issue:45072" ], - "prepared_review_unit_hash": "ab10fa1d657db851c495e36a45f8aeb7726bb7c1640ea9f0246e6296f70dab87", + "prepared_review_unit_hash": "0cd57974f2896455cf38930e2c6d37761d7d992c22e38e53d9b9e343e170dc44", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36656, + "serialized_chars": 36654, "estimated_input_tokens": 9164, "estimated_eval_tokens": 18584 }, @@ -4255,192 +4007,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated issue reports across different models and subsystems. Only one soft pair looks like a true duplicate: the two Qwen2_5_VLProcessor batched padding=False crash reports.", - "confidence": 0.91, - "canonical_issue_reason": "issue:44514 is the best canonical issue because it is the earlier report of the only clear duplicate pair and states the same batched padding=False crash clearly.", + "summary": "Most pairs are clearly unrelated despite surface similarity. Only issue 44514 and issue 44545 look like true duplicates of the same Qwen2_5_VLProcessor batched-padding crash.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44545 is the best canonical issue in the set because it is part of the only exact duplicate pair, has the same concrete repro as 44514, and carries slightly more discussion/inbound reference signal.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44514 is the strongest representative of the cluster\u2019s only real duplicate case and appears to be the earliest, cleaner report of that bug.", + "best_issue_reason": "Issue 44545 is the strongest issue to keep as representative: it names the exact failing code path, matches 44514 nearly verbatim, and appears to be the more established report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45081", "right": "issue:45812", "accept": false, - "reason": "Different models and failure modes: Mistral regex patching vs Granite tokenizer ID regression." + "reason": "Different bugs in different tokenizer paths: Mistral regex patch crash vs Granite token-id regression." }, { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Different configs and bugs: Qwen3-MoE sliding_window behavior vs StableLmConfig pad_token_idx missing." + "reason": "Unrelated: Qwen3-MoE sliding-window behavior vs StableLm config missing pad_token_idx." }, { "left": "issue:43540", "right": "issue:43782", "accept": false, - "reason": "Different Qwen3 multimodal codepaths: video input processing error vs from_pretrained weight_only loading error." + "reason": "Different model families and failures: Qwen3OmniMoe video ValueError vs Qwen3VL weight_only load error." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "ImportError for GenerationMixin is unrelated to a 3d_parallel.py runtime failure." + "reason": "ImportError for GenerationMixin is unrelated to a script execution problem for 3d_parallel.py." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Both involve tokenizers, but one is runtime post-processor refresh and the other is wrong token IDs for Granite models." + "reason": "Runtime special-token post-processor update bug is not the same as Granite token IDs being wrong." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "Different tokenizers and symptoms: LayoutLMv2 batching/NER crash vs MLuke AttributeError on tasks." + "reason": "Different tokenizers and failure modes: LayoutLMv2 batching crash vs MLuke AttributeError." }, { "left": "issue:42915", "right": "issue:43322", "accept": false, - "reason": "Different models and failure classes: Qwen3Moe FP8 config failure vs Llava Next segfault on load." + "reason": "Qwen3Moe FP8 config failure and Llava Next segfault are separate loading/runtime issues." }, { "left": "issue:43388", "right": "issue:45059", "accept": false, - "reason": "Metric gathering label-dropping bug is unrelated to SAM3 text/bounding-box behavior." + "reason": "Metrics label dropping and SAM3 text/bbox weirdness are different subsystems and symptoms." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Different components and models: serve-time Gemma4Processor attribute error vs Qwen3.5 streaming API failure." + "reason": "Gemma4Processor missing _tokenizer is unrelated to Qwen3.5 streaming chat/completions failure." }, { "left": "issue:33357", "right": "issue:35707", "accept": false, - "reason": "MacOS bus error with CLIP is unrelated to progressive generation with inputs_embeds and past_key_values." + "reason": "MacOS bus error on CLIP model loading is not the same as generation with inputs_embeds/past_key_values." }, { "left": "issue:43421", "right": "issue:45701", "accept": false, - "reason": "General tokenization version changes are too broad; not the same concrete bug as post-processor refresh." + "reason": "A runtime special-token update bug is not the same as a broad tokenization version-change regression." }, { - "left": "issue:43606", - "right": "issue:43720", + "left": "issue:30064", + "right": "issue:34634", "accept": false, - "reason": "Different loading/offload problems in different models: CPU offload device mismatch vs packed weights unpacking." + "reason": "Void segmentation maps and Bark voice_preset are unrelated model/data-path bugs." }, { - "left": "issue:41720", - "right": "issue:43746", + "left": "issue:44492", + "right": "issue:44509", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert is unrelated to GraniteSpeech PEFT local checkpoint loading." + "reason": "A docs typo is not the same as stale pipeline-task documentation after v5 removal." }, { - "left": "issue:30064", - "right": "issue:34634", + "left": "issue:41720", + "right": "issue:43746", "accept": false, - "reason": "Image segmentation map processing and BarkProcessor voice_preset are unrelated." + "reason": "Qwen3 auto device-mapping cuda assert and GraniteSpeech PEFT local-load failure are different code paths." }, { - "left": "issue:44492", - "right": "issue:44509", + "left": "issue:43606", + "right": "issue:43720", "accept": false, - "reason": "Both are docs/wording issues, but they are about different documentation topics and not the same bug." + "reason": "CPU offload device mismatch and BitNet packed-weight unpacking are separate loading/offload defects." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "Different subsystems: torch.compile/SDPA issue vs tokenizer special-token registration." + "reason": "torch.compile SDPA failure in Bamba is unrelated to BigBirdTokenizer special-token registration." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Quantization offloading behavior and T5 apex RMSNorm memory leak are unrelated." + "reason": "Quantization/offloading behavior and T5 apex FusedRMSNorm memory leak are not the same bug." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Same processor, same title, same batched padding=False crash; these are clearly duplicate reports of the same bug." - }, - { - "left": "issue:44625", - "right": "issue:45479", - "accept": false, - "reason": "Qwen3.5 num_labels propagation is not the same as the generic single-label zero-loss behavior across sequence-classification models." + "reason": "Near-verbatim duplicate: both report Qwen2_5_VLProcessor.apply_chat_template crashing on batched input with padding=False." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "CPU offload mismatch and BigBirdTokenizer special-token registration are different bugs." + "reason": "Device-mismatch CPU offload bug is unrelated to BigBirdTokenizer mask-token registration." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "Both touch Qwen/configuration, but one is a sliding_window bug and the other is from_config text_config unwrapping." + "reason": "Sliding-window handling in Qwen3-MoE is not the same as AutoModelForCausalLM.from_config not unwrapping text_config." }, { "left": "issue:42490", "right": "issue:43329", "accept": false, - "reason": "Trailing-slash import warning is unrelated to undefined video-branch variables in multimodal token counting." + "reason": "Trailing-slash local-model import warning and a multimodal video-token helper bug are unrelated." }, { "left": "issue:34634", "right": "issue:41720", "accept": false, - "reason": "BarkProcessor voice preset handling and Qwen3 device-mapping CUDA asserts are unrelated." + "reason": "BarkProcessor voice_preset failure and Qwen3 device-mapping cudaErrorAssert are different problems." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "Training token-count tracking and progressive generation caching are different code paths." + "reason": "TrainerState token counter not updating is unrelated to progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and degenerate zero-loss classification are different sequence-classification issues." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Runtime post-processor updates and save/load loss of custom token IDs are distinct tokenizer/config issues." + "reason": "Special-token post-processor updating and DiaConfig losing custom token IDs after save/load are distinct 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." + "reason": "tie_word_embeddings warning in Qwen3.5 LoRA training is unrelated to incorrect visual-encoder keys in save_pretrained." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Qwen3VL loading with weight_only=True and Qwen2.5-VL video position IDs are different bugs." + "reason": "Qwen3VL weight_only loading error is not the same as Qwen2.5-VL video vision_position_ids being wrong." }, { - "left": "issue:44898", - "right": "issue:45072", + "left": "issue:44451", + "right": "issue:44991", "accept": false, - "reason": "Perceiver resolution/interpolation failure is unrelated to bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + "reason": "Failed model loading for ScandiBERT and tokenizer loading regression for est-roberta are different model-specific issues." }, { - "left": "issue:44451", - "right": "issue:44991", + "left": "issue:44898", + "right": "issue:45072", "accept": false, - "reason": "Both are tokenizer-loading regressions, but for different models and likely different root causes; not the same bug." + "reason": "Perceiver image-classification interpolation bug and dtype mismatches in SwitchTransformers/TimmWrapperModel are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded overall: the packet supports one clear duplicate pair, issue:44514 and issue:44545, and the canonical choice of the earlier report is reasonable. The remaining soft-edge rejections are conservatively phrased as different models, components, or bug classes, without overstating evidence." + "feedback": "The summary is well grounded in the packet: issue 44514 and 44545 are near-verbatim duplicates with matching titles and compatible repros, and the inbound-reference counts support choosing 44545 as canonical. The soft-edge rejections stay conservative and rely on clearly different titles/failure modes. No PR-pair mergeability concerns apply here." }, "evaluator_used": true, "retried": false, @@ -4456,15 +4208,16 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:30064", "issue:36010", "issue:39692", "issue:40444", + "issue:41720", "issue:42886", "issue:42915", "issue:43381", @@ -4473,9 +4226,7 @@ "issue:43531", "issue:43540", "issue:43596", - "issue:43618", "issue:43653", - "issue:43697", "issue:43720", "issue:43746", "issue:43819", @@ -4513,15 +4264,15 @@ "soft_pairs": [ "issue:44077|issue:44625", "issue:44987|issue:45042", - "issue:45759|issue:45859", "issue:43531|issue:44589", + "issue:45759|issue:45859", "issue:44062|issue:44451", - "issue:45704|issue:45923", "issue:39692|issue:44610", - "issue:43421|issue:43653", + "issue:45704|issue:45923", "issue:44918|issue:44936", - "issue:45663|issue:45923", + "issue:43421|issue:43653", "issue:45588|issue:45759", + "issue:45663|issue:45923", "issue:42886|issue:44843", "issue:43381|issue:43844", "issue:43421|issue:44186", @@ -4529,234 +4280,227 @@ "issue:43525|issue:43531", "issue:45704|issue:45859", "issue:45081|issue:45356", - "issue:45356|issue:45907", + "issue:41720|issue:45704", + "issue:43596|issue:44220", "issue:39692|issue:43873", + "issue:45356|issue:45907", "issue:43746|issue:43873", - "issue:43596|issue:44220", "issue:40444|issue:43746", "issue:42915|issue:43746", - "issue:43720|issue:43819", "issue:43540|issue:44008", "issue:44220|issue:44661", - "issue:45183|issue:45479", + "issue:43720|issue:43819", "issue:30064|issue:36010", - "issue:43618|issue:43697", - "issue:43653|issue:43720" + "issue:45183|issue:45479" ], - "prepared_review_unit_hash": "fce444d8daf69ff3b5d28c9d2bf79c5e895cc735e6b610540967f22c19e39f48", + "prepared_review_unit_hash": "6ed42d43a328c893dc5dbd2b5d25c483d47c9ec7bc705ec92735a4db84f5cebc", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37340, - "estimated_input_tokens": 9335, - "estimated_eval_tokens": 18926 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36483, + "estimated_input_tokens": 9121, + "estimated_eval_tokens": 18498 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: it mixes unrelated tokenizer, vision, multimodal, training, and loading/offline bugs. None of the soft pairs look like the same concrete fix target, so I rejected all merges.", - "confidence": 0.93, - "canonical_issue_reason": "issue:43421 is the closest thing to a hub here because it sits in the densest tokenizer-special-token subtheme, but the cluster is too mixed to treat it as a true duplicate canonical.", + "summary": "This cluster is not a single duplicate group: the items span many unrelated bugs/features across tokenizers, multimodal models, training, quantization, and offloading. None of the soft-similarity pairs are close enough to merge as the same underlying change or bug.", + "confidence": 0.96, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:43421 is the best representative of the most coherent subcluster (runtime tokenizer/post-processor behavior), but it should not be used as a global stand-in for the whole set.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44077", "right": "issue:44625", "accept": false, - "reason": "Different problems: optional post_init on patchtsmixer vs missing num_labels propagation in Qwen3.5 config." + "reason": "Different problems: one is about PatchTSMixer post_init being optional, the other about Qwen3.5 num_labels propagation." }, { "left": "issue:44987", "right": "issue:45042", "accept": false, - "reason": "Unrelated failures: loading physical-intelligence/fast vs PIL image processors wrongly requiring torchvision." - }, - { - "left": "issue:45759", - "right": "issue:45859", - "accept": false, - "reason": "Both involve Qwen 3.5, but one is composite config unwrapping and the other is CPU-offload rotary embedding behavior; not the same bug." + "reason": "Both involve loading/models, but the failures are different: one is a loading regression for a specific repo, the other is PIL image processors incorrectly requiring torchvision." }, { "left": "issue:43531", "right": "issue:44589", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior is unrelated to the Float8 storage load error." + "reason": "Separate code paths: Qwen3-MoE sliding-window logic vs a storage-class lookup error when loading float8 tensors." }, { - "left": "issue:44062", - "right": "issue:44451", + "left": "issue:45759", + "right": "issue:45859", "accept": false, - "reason": "AddedToken keyword-collision constructor bug is not the same as ScandiBERT loading regression." + "reason": "Related to Qwen 3.5/3.6 multimodal configs, but one is about from_config not unwrapping text_config and the other is CPU-offload incompatibility in rotary embedding." }, { - "left": "issue:45704", - "right": "issue:45923", + "left": "issue:44062", + "right": "issue:44451", "accept": false, - "reason": "T5 RMSNorm memory leak and missing supports_gradient_checkpointing are different code paths." + "reason": "Both are tokenizer-related, but one is an AddedToken constructor error and the other is a model-loading failure for a specific checkpoint." }, { "left": "issue:39692", "right": "issue:44610", "accept": false, - "reason": "SigLIP2 doc/example errors and OmDet-Turbo processor size mismatch are separate vision issues." + "reason": "Both touch vision models, but one is a docs/example mismatch and quantization issue; the other is an OmDet-Turbo processor/model input-size mismatch." }, { - "left": "issue:43421", - "right": "issue:43653", + "left": "issue:45704", + "right": "issue:45923", "accept": false, - "reason": "Both are tokenizer/special-token related, but one is post-processor refresh on runtime edits and the other is BigBird mask-token registration/empty decode; not the same concrete bug." + "reason": "Unrelated model internals: apex FusedRMSNorm memory leak in T5 vs missing supports_gradient_checkpointing on a trust_remote_code model." }, { "left": "issue:44918", "right": "issue:44936", "accept": false, - "reason": "Qwen3.5 embedding unpacking in TRL SFT is unrelated to trainer.evaluate() failing after train()." + "reason": "Different training failures: Qwen3.5 embedding unpacking with TRL SFT trainer vs trainer.evaluate failing after train." }, { - "left": "issue:45663", - "right": "issue:45923", + "left": "issue:43421", + "right": "issue:43653", "accept": false, - "reason": "Gemma-4 FSDP2 shared_kv_states bug is unrelated to the missing gradient_checkpointing flag." + "reason": "Both concern tokenizers, but one is runtime special-token/post-processor updates; the other is BigBirdTokenizer special-token registration for mask decoding." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "flash_attention s_aux=None crash is not the same as Qwen 3.5 multimodal config unwrapping." + "reason": "Flash-attention crash on sink-less models is unrelated to Qwen multimodal config handling." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Different model families and failures: Gemma-4 FSDP2 shared_kv_states bug vs Nemotron-3-Nano-Omni missing gradient-checkpointing support." }, { "left": "issue:42886", "right": "issue:44843", "accept": false, - "reason": "Both touch offline/tokenizer loading, but one is cache loading with HF_HUB_OFFLINE and the other is an unconditional model_info() call in _patch_mistral_regex." + "reason": "Both involve offline/cache behavior, but one is tokenizer cache loading on HF_HUB_OFFLINE and the other is an unconditional model_info() call in _patch_mistral_regex." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Eval-mode gradient checkpointing restriction is unrelated to exploding gradients under HfDeepSpeedConfig + ZeRO-3." + "reason": "Training-mode/eval-mode checkpointing issue is not the same as the ZeRO-3 gradient growth bug." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Special-token post-processor update bug is not the same as LayoutLMv2Tokenizer crashing on NER/padding/truncation." + "reason": "Tokenizer post-processor updates are unrelated to LayoutLMv2Tokenizer crashes on NER inputs and batched padding/truncation." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different models and symptoms: SigLIP2 nonsensical outputs vs CamemBERT masked-LM prediction regression." + "reason": "Both affect model outputs, but one is a SigLIP2 loading/pipeline issue and the other is a CamemBERT masked-LM regression in v5." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "Missing pad_token_id on Llama4Config is unrelated to Qwen3-MoE sliding_window handling." + "reason": "Different model/config bugs: missing pad_token_id on Llama4Config vs sliding_window behavior in Qwen3-MoE." }, { "left": "issue:45704", "right": "issue:45859", "accept": false, - "reason": "Apex RMSNorm memory leak and Qwen3_5MoeTextRotaryEmbedding CPU offload compatibility are different defects." + "reason": "Apex/T5 RMSNorm memory leak is not the same as Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Both mention fix_mistral_regex, but one is a tokenizer crash and the other is a Kimi-K2.5 codec/regression/warning issue; not the same fix target." + "reason": "Both mention fix_mistral_regex, but one is a crash in the regex patch path and the other is a Kimi-K2.5 codec regression plus misleading warning." }, { - "left": "issue:45356", - "right": "issue:45907", + "left": "issue:41720", + "right": "issue:45704", + "accept": false, + "reason": "Qwen3 CUDA assert with auto device mapping is a different failure mode from a T5 RMSNorm memory leak." + }, + { + "left": "issue:43596", + "right": "issue:44220", "accept": false, - "reason": "Kimi tokenizer regression is unrelated to list_repo_files not forwarding revision." + "reason": "Different subsystems: deepspeed zero3 init with BertModel vs _torch_extract_fbank_features audio extraction." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "SigLIP2 example/doc issues are unrelated to quantization offloading behavior." + "reason": "Docs/example SigLIP2 errors are unrelated to the broader offloading-with-quantization behavior issue." }, { - "left": "issue:43746", - "right": "issue:43873", + "left": "issue:45356", + "right": "issue:45907", "accept": false, - "reason": "Local checkpoint PEFT loading and quantized offloading are different loading problems." + "reason": "Both touch HF Hub/tokenizer utilities, but one is a tokenizer codec/regression issue and the other is list_repo_files not forwarding revision." }, { - "left": "issue:43596", - "right": "issue:44220", + "left": "issue:43746", + "right": "issue:43873", "accept": false, - "reason": "DeepSpeed ZeRO-3/BertModel index error is unrelated to _torch_extract_fbank_features()." + "reason": "PEFT local checkpoint loading for GraniteSpeech is not the same as offloading misbehavior under quantization." }, { "left": "issue:40444", "right": "issue:43746", "accept": false, - "reason": "IterableDataset with multiple images per prompt is unrelated to GraniteSpeech PEFT local checkpoint loading." + "reason": "Multi-image IterableDataset finetuning failure is unrelated to PEFT-adapter local checkpoint loading." }, { "left": "issue:42915", "right": "issue:43746", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure is unrelated to GraniteSpeech local-checkpoint loading." - }, - { - "left": "issue:43720", - "right": "issue:43819", - "accept": false, - "reason": "BitNet packed-weight loading and DAC.from_latents/forward mismatch are unrelated model bugs." + "reason": "Qwen3Moe FineGrainedFP8Config failure and GraniteSpeech PEFT loading failure are distinct code paths." }, { "left": "issue:43540", "right": "issue:44008", "accept": false, - "reason": "Both are multimodal, but one is Qwen3OmniMoe video-input processing and the other is Gemma 3n audio tensor name collision; not the same bug." + "reason": "Both are multimodal, but one is a Qwen3OmniMoe video-processing ValueError and the other is a Gemma 3n variable-name collision causing an AttributeError." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio fbank extraction failure is unrelated to add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." + "reason": "Audio feature extraction bug is unrelated to add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." }, { - "left": "issue:45183", - "right": "issue:45479", + "left": "issue:43720", + "right": "issue:43819", "accept": false, - "reason": "Input validation XOR messaging and single-label-classification zero-loss behavior are different issues." + "reason": "Both are BitNet/DAC model issues, but one is about unpacking packed weights during accelerate loading and the other is DAC.from_latents not matching forward due to missing STE." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Image segmentation-map processing and GenerationMixin import error are unrelated." - }, - { - "left": "issue:43618", - "right": "issue:43697", - "accept": false, - "reason": "CLIPOutput attentions assignment and RTDetrV2 output differences in v5 are not the same code-path bug." + "reason": "Completely different areas: image processor void segmentation maps vs a transformers.GenerationMixin import error." }, { - "left": "issue:43653", - "right": "issue:43720", + "left": "issue:45183", + "right": "issue:45479", "accept": false, - "reason": "Tokenizer special-token registration and BitNet accelerate loading are unrelated." + "reason": "General input validation XOR messaging bug is not the same as the single-label-classification num_labels=1 zero-loss issue." } ] }, @@ -4775,15 +4519,14 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:30064", "issue:36331", "issue:39692", - "issue:41720", "issue:43295", "issue:43322", "issue:43335", @@ -4792,9 +4535,12 @@ "issue:43540", "issue:43550", "issue:43577", + "issue:43618", "issue:43643", "issue:43653", + "issue:43697", "issue:43716", + "issue:43720", "issue:43756", "issue:43782", "issue:43818", @@ -4817,7 +4563,6 @@ "issue:44877", "issue:44898", "issue:44977", - "issue:44991", "issue:45020", "issue:45072", "issue:45081", @@ -4829,6 +4574,8 @@ "issue:45987" ], "soft_pairs": [ + "issue:43618|issue:43697", + "issue:43653|issue:43720", "issue:43335|issue:43756", "issue:43295|issue:45834", "issue:43716|issue:44008", @@ -4848,198 +4595,203 @@ "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:44561|issue:45020", + "issue:44485|issue:44509", "issue:44821|issue:45084", "issue:30064|issue:36331", - "issue:44485|issue:44509", - "issue:41720|issue:44991" + "issue:43825|issue:43994" ], - "prepared_review_unit_hash": "431bcb4c571b27335462e8a10464c3ef8c7801b52cf7c54c46acfd895929d835", + "prepared_review_unit_hash": "bad9cfe50f4027d92ca536d4150bb144eb49d6a6ece6e34252dd4c153ef84463", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 26, - "serialized_chars": 35170, - "estimated_input_tokens": 8793, - "estimated_eval_tokens": 17842 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36057, + "estimated_input_tokens": 9015, + "estimated_eval_tokens": 18286 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous issue reports. A few items overlap around tokenizer/config/remote_code loading regressions, but none are close enough to treat as duplicates or to merge together.", - "confidence": 0.78, - "canonical_issue_reason": null, + "summary": "Loose cluster of Transformers regression reports and model-specific bugs. The soft pairs mostly share broad themes (v5 regressions, tokenizers, multimodal loading) but not the same concrete bug or code path, so none should be merged as duplicates.", + "confidence": 0.69, + "canonical_issue_reason": "issue:45020 is the broadest umbrella report here and best captures the cluster\u2019s general \u201crecent versions break remote_code models\u201d regression theme, even though the other issues are distinct specific bugs.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the broadest umbrella for the recurring remote_code/model-loading regressions in this set, but it is still too general to serve as a true duplicate canonical.", + "best_issue_reason": "issue:45020 has the widest scope and is the most representative single issue for this mixed regression cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Both are v5 behavioral regressions, but one is a missing CLIP attentions output and the other is RT-DETR output drift; different model paths and fixes." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration vs BitNet packed-weight loading are unrelated bugs in different subsystems." + }, { "left": "issue:43335", "right": "issue:43756", "accept": false, - "reason": "Different failures: sparse-layer creation vs RoPE layer dropping. Same broad model/config space, not the same bug." + "reason": "Different model/config issues: sparse-layer creation in SwitchTransformers vs RoPE layer count mismatch in Smollm3." }, { "left": "issue:43295", "right": "issue:45834", "accept": false, - "reason": "Both involve multimodal processor/tokenizer paths, but one is a v4.57.5 regression in custom model code and the other is a long-OCR indexing bug." + "reason": "Both concern multimodal processing, but one is processor/tokenizer API breakage and the other is long OCR input indexing in Kosmos2.5." }, { "left": "issue:43716", "right": "issue:44008", "accept": false, - "reason": "Unrelated model-specific bugs: image preprocessor dtype mismatch vs Gemma3n audio_mel_mask name collision." + "reason": "Different models and failures: dtype mismatch in Mistral-3 image preprocessing vs a Gemma 3n attribute collision." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "Different code paths and symptoms: torch.compile/SDPA on Bamba vs bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + "reason": "One is torch.compile/SDPA on Bamba-9B-v2; the other is bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "No clear underlying overlap beyond both being model runtime bugs; one is SDPA/compile, the other is DAC latent/forward mismatch." + "reason": "Different code paths: SDPA compilation failure vs DAC latent conversion not matching forward pass." }, { "left": "issue:44062", "right": "issue:44488", "accept": false, - "reason": "Both tokenizer-related, but one is an AddedToken argument error and the other is a model-specific tokenizer loading failure." + "reason": "Generic AddedToken argument conflict vs a specific model loading failure; no shared concrete bug." }, { "left": "issue:43322", "right": "issue:45685", "accept": false, - "reason": "Segfault while loading Llava Next is unrelated to an MPS histogram error in moe code." + "reason": "Segfault while loading Llava Next is unrelated to an MPS histogram kernel missing for Int tensors." }, { "left": "issue:43950", "right": "issue:45987", "accept": false, - "reason": "Both are API/regression complaints, but one concerns non-persistent buffers during from_pretrained and the other is a StaticCache return-type contract issue." + "reason": "Non-persistent buffer corruption during from_pretrained vs StaticCache returning the wrong type; different mechanisms." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "Different subsystems and failures: LayoutLMv2 tokenizer padding/NER crash vs Perceiver image classification with non-default resolution." + "reason": "LayoutLMv2 tokenizer padding/NER crash and Perceiver image classification failure are separate model-specific bugs." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Both touch `_patch_mistral_regex`, but they are distinct bugs: offline `model_info()` access vs missing `backend_tokenizer` attribute." + "reason": "Both touch _patch_mistral_regex, but one is an offline model_info call and the other is an AttributeError on backend_tokenizer; distinct failures." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior is unrelated to `trust_remote_code` config field loss." + "reason": "Sliding-window handling in Qwen3-MoE is unrelated to trust_remote_code config field loss." }, { "left": "issue:43653", "right": "issue:43819", "accept": false, - "reason": "BigBird special-token decode failure and DAC latent mismatch are unrelated bugs." + "reason": "BigBird tokenizer special-token registration and DAC latent conversion are different bugs with no shared code path." }, { "left": "issue:43643", "right": "issue:44877", "accept": false, - "reason": "Both involve config/loading behavior, but one is missing fields with `trust_remote_code` and the other is strict config rejection for `granite_speech`." + "reason": "Both involve config/loading behavior, but one is missing fields from trust_remote_code and the other is strict config blocking granite_speech." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Both mention special tokens, but one is runtime post-processor refresh and the other is Whisper `batch_decode` skipping special tokens." + "reason": "Runtime special-token post-processor updates vs Whisper batch_decode skip_special_tokens behavior are different tokenizer API issues." }, { "left": "issue:43577", "right": "issue:43818", "accept": false, - "reason": "Different models and failures: Blip2 dtype not propagating vs Video-LLaVA missing temporal attention/shared weights." + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing are unrelated multimodal model bugs." }, { "left": "issue:43540", "right": "issue:45381", "accept": false, - "reason": "Both are video-input bugs in Qwen-family models, but the concrete failures differ: processing ValueError vs wrong vision_position_ids." + "reason": "Both are video-related, but they affect different Qwen models and different failures (video input validation vs vision_position_ids)." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Different Qwen variants and different failure modes: `weight_only=True` load error vs flash-attention generation issue." + "reason": "Qwen3VL from_pretrained weight_only error and Qwen3.5 flash-attention generation failure are different issues." }, { "left": "issue:44448", "right": "issue:44671", "accept": false, - "reason": "Both are v5 output regressions, but they affect different models and likely different code paths." + "reason": "Distinct model regressions: Pegasus output drift vs CamemBERT masked-LM prediction errors." }, { "left": "issue:45584", "right": "issue:45834", "accept": false, - "reason": "Whisper empty-transcription generation and Kosmos2.5 long-OCR index errors are unrelated." + "reason": "Whisper empty-transcription generation failure is unrelated to Kosmos2.5 long OCR input indexing." }, { - "left": "issue:43825", - "right": "issue:43994", + "left": "issue:39692", + "right": "issue:45834", "accept": false, - "reason": "One is an error-message/docs mismatch about pipelines; the other is an AutoModel/pipeline quality regression for SigLIP2." + "reason": "A broken SigLIP2 docs example is not the same bug as a Kosmos2.5 OCR index error." }, { "left": "issue:44561", "right": "issue:45020", "accept": false, - "reason": "Related only at the broad 'remote_code breaks in v5' level; one is a specific removed helper, the other is a wider report." + "reason": "44561 is a specific remote_code break caused by removing is_torch_fx_available; 45020 is a broader umbrella report, not the same concrete bug." }, { - "left": "issue:39692", - "right": "issue:45834", + "left": "issue:44485", + "right": "issue:44509", "accept": false, - "reason": "SigLIP2 example/documentation errors are unrelated to Kosmos2.5 OCR indexing." + "reason": "RoPE implementation discussion for GLM-5 and stale docs about removed pipeline tasks are different concerns." }, { "left": "issue:44821", "right": "issue:45084", "accept": false, - "reason": "Both are loader/templating related, but one is AutoImageProcessor-from-URL support and the other is a template-node compilation error." + "reason": "Loading AutoImageProcessor from URL and a template-node compilation TypeError are unrelated." }, { "left": "issue:30064", "right": "issue:36331", "accept": false, - "reason": "Image segmentation-map processing and CustomTrainer loss signature mismatch are completely unrelated." - }, - { - "left": "issue:44485", - "right": "issue:44509", - "accept": false, - "reason": "GLM-5 RoPE implementation discussion is unrelated to documentation still mentioning removed v5 pipeline tasks." + "reason": "ImageProcessor void segmentation maps and CustomTrainer.compute_loss argument mismatch are completely different bugs." }, { - "left": "issue:41720", - "right": "issue:44991", + "left": "issue:43825", + "right": "issue:43994", "accept": false, - "reason": "Different regressions in different models: Qwen3 auto device mapping CUDA assert vs tokenizer loading failure for EMBEDDIA/est-roberta." + "reason": "Wrong pipeline error message about translation tasks and nonsensical SigLIP2 outputs are separate issues." } ] }, @@ -5058,14 +4810,15 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:34634", "issue:36010", "issue:36331", + "issue:41720", "issue:42175", "issue:43262", "issue:43329", @@ -5073,10 +4826,8 @@ "issue:43577", "issue:43582", "issue:43606", - "issue:43638", "issue:43644", "issue:43650", - "issue:43653", "issue:43697", "issue:43720", "issue:43742", @@ -5097,8 +4848,8 @@ "issue:44671", "issue:44805", "issue:44857", - "issue:44912", "issue:44936", + "issue:44991", "issue:45020", "issue:45072", "issue:45081", @@ -5113,15 +4864,16 @@ "issue:45834" ], "soft_pairs": [ + "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:44671|issue:45701", + "issue:43825|issue:43827", + "issue:43577|issue:43582", "issue:34634|issue:36010", + "issue:44671|issue:45701", "issue:44610|issue:45072", "issue:43782|issue:45325", "issue:43720|issue:45072", @@ -5129,222 +4881,217 @@ "issue:45081|issue:45406", "issue:43749|issue:44291", "issue:43650|issue:43906", - "issue:44060|issue:44368", "issue:43582|issue:44857", + "issue:44060|issue:44368", "issue:43262|issue:43819", "issue:43526|issue:43697", "issue:43526|issue:44554", - "issue:45459|issue:45803", "issue:34634|issue:36331", + "issue:45459|issue:45803", "issue:45084|issue:45538", "issue:43742|issue:45020", - "issue:43653|issue:44912", - "issue:43329|issue:45600", - "issue:43638|issue:44936" + "issue:43329|issue:45600" ], - "prepared_review_unit_hash": "3a95c784ed6dc7a6c761780fde3572c79ce68b114f166ca271787979b60ee35a", + "prepared_review_unit_hash": "b822be1294093627d358262f328fbe3045fb09937c3f4db57f9a94d7ee011d34", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36471, - "estimated_input_tokens": 9118, - "estimated_eval_tokens": 18492 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35509, + "estimated_input_tokens": 8878, + "estimated_eval_tokens": 18012 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose set of unrelated bug reports that only share broad themes like loading, tokenizers, multimodal models, or v5 regressions. None of the soft pairs look like the same underlying bug/change, so all soft edges should be rejected. No PRs are present; the most representative issue is the broad v5/regression report around remote_code loading.", - "confidence": 0.59, - "canonical_issue_reason": "issue:45020 is the broadest, most central issue in the set: it describes recent transformers versions breaking remote_code models, which matches the general regression-focused nature of the cluster.", + "summary": "Most candidates are broad-similarity false positives (same subsystem or release, but different concrete bugs). Only the Qwen tied-weights warning reports look like the same underlying issue.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44060 is the clearest, most concrete report of the Qwen tied-weights warning bug; issue:44368 reads like a downstream duplicate/symptom of the same warning path.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is open, broad, and impacts multiple models/paths, making it the best representative issue for the cluster even though the rest are mostly unrelated.", + "best_issue_reason": "issue:44060 best captures the root bug with a specific mis-tie (`embed_tokens.weight` vs `linear_attn.dt_bias`) and broad enough scope to serve as the canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Different failures: Qwen3 auto device-map CUDA assert vs tokenizer import/load failure for est-roberta." + }, { "left": "issue:43644", "right": "issue:43749", "accept": false, - "reason": "Both are loading/runtime regressions, but one is about non-persistent buffers and the other about FSDP CPU RAM efficient loading; different failure modes and code paths." + "reason": "Both concern v5 loading behavior, but one is non-persistent buffer corruption and the other is FSDP CPU RAM efficient loading; not the same bug." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "Both are tokenizer issues, but they affect different tokenizers and different bugs (NER/batched padding vs AutoTokenizer load failure)." + "reason": "Both are tokenizer problems, but one is LayoutLMv2 NER/padding crashes and the other is AutoTokenizer loading FastSpeech2ConformerTokenizer." }, { "left": "issue:44479", "right": "issue:45834", "accept": false, - "reason": "Both are multimodal input issues, but one is a v5.3.0 video regression in Qwen VL models and the other is a long OCR index error in Kosmos2.5." + "reason": "Both are multimodal input bugs, but on different models and code paths (video regression vs OCR long-input index error)." }, { - "left": "issue:43577", - "right": "issue:43582", + "left": "issue:43606", + "right": "issue:45072", "accept": false, - "reason": "Blip2 dtype handling and Apple Silicon allocator warmup are unrelated bugs." + "reason": "Device-mismatch CPU-offload bug for Bark vs bfloat16 dtype mismatch in different models." }, { - "left": "issue:43606", - "right": "issue:45072", + "left": "issue:44805", + "right": "issue:44936", "accept": false, - "reason": "Both mention inference/loading problems, but one is a Bark CPU offload device mismatch and the other is a dtype mismatch in different models." + "reason": "Both are runtime errors, but one is a mask/tensor shape mismatch and the other is train-then-evaluate behavior." }, { "left": "issue:43825", "right": "issue:43827", "accept": false, - "reason": "The first is an incorrect pipeline error message; the second is outdated docs. Related topic, but not the same underlying bug." + "reason": "Related to v5 pipeline removals, but one is an error message bug and the other is outdated docs; not the same concrete fix." }, { - "left": "issue:44805", - "right": "issue:44936", + "left": "issue:43577", + "right": "issue:43582", "accept": false, - "reason": "Different failures: a mask/tensor shape IndexError versus trainer.evaluate breaking after train()." + "reason": "Blip2 dtype persistence vs Apple Silicon caching allocator TypeError are unrelated." }, { - "left": "issue:44671", - "right": "issue:45701", + "left": "issue:34634", + "right": "issue:36010", "accept": false, - "reason": "One is incorrect masked LM predictions for CamemBERT; the other is a generic tokenization-change report." + "reason": "BarkProcessor voice_preset issue is unrelated to the GenerationMixin import error." }, { - "left": "issue:34634", - "right": "issue:36010", + "left": "issue:44671", + "right": "issue:45701", "accept": false, - "reason": "Bark voice_preset and GenerationMixin import failure are unrelated." + "reason": "CamemBERT masked-LM regression and generic tokenization changes are not the same bug." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "OmDet-Turbo image size mismatch and dtype mismatches in other models are different issues." + "reason": "OmDet-Turbo image-size mismatch vs dtype mismatch in other models." }, { "left": "issue:43782", "right": "issue:45325", "accept": false, - "reason": "Both are Qwen VL-related, but one is a weight_only load error and the other is a rope-index temporal scaling bug." + "reason": "Qwen VL load-time `weight_only` error vs still-image rope-index scaling bug are different paths." }, { "left": "issue:43720", "right": "issue:45072", "accept": false, - "reason": "BitNet packed-weight loading failure and bfloat16 dtype mismatches are unrelated." + "reason": "Packed-weight unpacking during accelerate loading is unrelated to dtype mismatch." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "An installation/backend packaging issue is not the same as a tokenizer regex patch crash." + "reason": "Missing TensorFlow backend in install extras is unrelated to tokenizer regex patch crash." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Both are AttributeErrors during loading, but they occur in different components and for different missing attributes." + "reason": "Both are tokenizer/processor crashes, but one is a Mistral regex patch bug and the other is a Gemma4Processor missing attribute." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "FSDP CPU RAM loading and init_empty_weights/_is_hf_initialized are separate loading bugs." + "reason": "Both touch model loading, but one is FSDP CPU RAM efficient loading and the other is init_empty_weights argument mismatch." }, { "left": "issue:43650", "right": "issue:43906", "accept": false, - "reason": "A placeholder 'ADD THE DATA' issue is unrelated to an isolated reproduction report." - }, - { - "left": "issue:44060", - "right": "issue:44368", - "accept": false, - "reason": "Both mention tied-weights warnings, but one is a concrete wrong tie in Qwen3-Next and the other is a finetuning warning about config cleanup." + "reason": "The titles are unrelated; one is a placeholder issue and the other is a reproduction of a different issue." }, { "left": "issue:43582", "right": "issue:44857", "accept": false, - "reason": "Apple Silicon allocator warmup and CUDA AMP loss crashes are unrelated." + "reason": "Apple Silicon warmup TypeError and CUDA float16 AMP crash are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": true, + "reason": "Same underlying tied-weights warning bug in Qwen3/Qwen3.5-family models; both report the incorrect warning path and should be fixed together." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Audio processor chat-template sampling-rate handling and DAC latent reconstruction are different audio bugs." + "reason": "Audio processor sampling-rate default bug vs DAC latent/forward mismatch are different issues." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "BEiT label reduction and RTDetrV2 output drift are different vision bugs." + "reason": "Beit reduce_labels bug and RTDetrV2 output drift are different model-specific regressions." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "Image label reduction and an MPS attention correctness issue do not describe the same problem." + "reason": "BeitImageProcessorFast label reduction and MPS attention correctness are unrelated." }, { - "left": "issue:45459", - "right": "issue:45803", + "left": "issue:34634", + "right": "issue:36331", "accept": false, - "reason": "Both are error-handling bugs, but they affect different code paths and different swallowed errors." + "reason": "BarkProcessor voice preset failure is unrelated to CustomTrainer.compute_loss signature breakage." }, { - "left": "issue:34634", - "right": "issue:36331", + "left": "issue:45459", + "right": "issue:45803", "accept": false, - "reason": "BarkProcessor voice preset and CustomTrainer.compute_loss signature mismatch are unrelated." + "reason": "Both involve exception handling, but in different code paths and with different root causes; too broad to merge." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "A template compilation TypeError is unrelated to CLIPTokenizer model_max_length behavior." + "reason": "Template compilation TypeError and CLIPTokenizer max_length bug are unrelated." }, { "left": "issue:43742", "right": "issue:45020", "accept": false, - "reason": "A key error loading one model is not the same underlying issue as broad remote_code breakage." - }, - { - "left": "issue:43653", - "right": "issue:44912", - "accept": false, - "reason": "BigBirdTokenizer special-token registration and MXFP4 quantization fallback are unrelated." + "reason": "Specific MobileLLM key error is not the same as broad remote_code breakage." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "A multimodal token counting bug and stale auto_mappings references are different regressions." - }, - { - "left": "issue:43638", - "right": "issue:44936", - "accept": false, - "reason": "DeepSpeed zero3 indexing failure and trainer.evaluate-after-train failure are different training bugs." + "reason": "Multimodal token counting bug and removed auto_mappings config references are unrelated." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. Most soft-edge rejections are conservative and the reasons track distinct titles/subsystems. The single accepted Qwen pair is a plausible match based on the shared tied-weights warning theme. No clear overstatement beyond the available packet evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -5356,10 +5103,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:34567", "issue:36010", @@ -5378,8 +5125,10 @@ "issue:43550", "issue:43577", "issue:43606", + "issue:43638", "issue:43643", "issue:43645", + "issue:43653", "issue:43696", "issue:43697", "issue:43720", @@ -5389,7 +5138,6 @@ "issue:43854", "issue:43927", "issue:43931", - "issue:44291", "issue:44479", "issue:44568", "issue:44589", @@ -5398,264 +5146,266 @@ "issue:44811", "issue:44849", "issue:44912", + "issue:44936", "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:43653|issue:44912", + "issue:43638|issue:44936", "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:36010|issue:43645", "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:43329|issue:44479", "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:44568|issue:45488", "issue:43257|issue:43931", "issue:43606|issue:45859", "issue:44849|issue:45701", - "issue:43697|issue:45357", - "issue:44291|issue:45042", - "issue:44987|issue:45538" + "issue:43697|issue:45357" ], - "prepared_review_unit_hash": "5408c2ba0950e719602b9b7dd32b7d2b31c54a3f9cf85a2512fdec4bda0e398d", + "prepared_review_unit_hash": "329319f65b49f5f036ae111771bbc3968d1117f6cc937d7c63ce6bc5d8536037", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36979, - "estimated_input_tokens": 9245, - "estimated_eval_tokens": 18746 + "serialized_chars": 36996, + "estimated_input_tokens": 9249, + "estimated_eval_tokens": 18754 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is very heterogeneous: most pairs are only superficially similar (often just sharing a subsystem like loading, tokenization, or multimodal/video handling) and do not look like the same underlying bug.", - "confidence": 0.71, - "canonical_issue_reason": "issue:45701 is the broadest umbrella item in the set: it is open, has multiple inbound references, and its title suggests a version-wide tokenization regression that can serve as the least-specific representative.", + "summary": "These issues are mostly unrelated and grouped by surface similarity. The 43329\u219444479 pair is only weakly related through multimodal/video vocabulary; the packet does not establish they are the same underlying bug or a mergeable shared fix.", + "confidence": 0.69, + "canonical_issue_reason": "issue:44479 is the best canonical issue because it captures the broader user-facing video-input regression across multiple Qwen VL variants. issue:43329 is narrower and may be adjacent, but the packet does not prove it is the same defect.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45701 is the most generally framed and externally referenced issue, making it the best single representative despite the cluster\u2019s mixed topics.", + "best_issue_reason": "issue:44479 is the strongest representative due to broader impact and clearer regression framing; issue:43329 is more specific and less well-supported as the root of the broader behavior.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: BigBird special-token registration vs MXFP4 quantization loading fallback." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Both are trainer failures, but the concrete breakages differ: ZeRO-3 indexing vs evaluate-after-train behavior." + }, { "left": "issue:43452", "right": "issue:44991", "accept": false, - "reason": "Both are loading/tokenizer regressions, but one is a gguf_file pathway break and the other is a specific tokenizer regression for EMBEDDIA/est-roberta; different failure modes." + "reason": "Both involve loading/tokenizer paths, but they point to different models and code paths." }, { "left": "issue:43746", "right": "issue:44811", "accept": false, - "reason": "Different subsystems entirely: PEFT/local checkpoint loading versus Whisper processor batch_decode behavior." + "reason": "PEFT local-checkpoint loading and Whisper batch_decode special-token handling are unrelated." }, { "left": "issue:44589", "right": "issue:45042", "accept": false, - "reason": "Unrelated bugs: missing Float8 storage handling versus image processors incorrectly requiring torchvision." + "reason": "Float8 storage lookup error is unrelated to PIL backend torchvision dependency checks." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "Different vision-model issues: zero probabilities in SigLIP2 versus OmDet-Turbo processor/model size mismatch." + "reason": "Different model families and failure modes: zero probabilities vs image-size mismatch." }, { "left": "issue:43854", "right": "issue:44977", "accept": false, - "reason": "Both involve model loading/runtime, but they are for different models and different code paths; not the same concrete bug." + "reason": "Generic model-load test failure vs flash-attention generation bug; no shared code-path evidence." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "Different problems: DAC forward/from_latents mismatch versus DiaConfig losing custom token IDs on save/load." + "reason": "DAC latent reconstruction mismatch and DiaConfig save/load token-ID loss are distinct bugs." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import error and Jupyter custom-model initialization breakage are different regressions." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "Doc-example/model-processor issues for SigLIP2 are unrelated to git-oss-20b MXFP4 quantization fallback." + "reason": "Documentation example errors are not the same bug as MXFP4 quantization loading fallback." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "One is accelerate/deepspeed weight conversion for Qwen3 MoE; the other is a multimodal token-counting video-branch bug." - }, - { - "left": "issue:36010", - "right": "issue:43645", - "accept": false, - "reason": "Both are import/runtime breakages, but one is GenerationMixin import resolution and the other is custom model initialization in notebooks." + "reason": "Qwen3 MoE weight conversion during accelerate+deepspeed loading is unrelated to a multimodal video-token helper bug." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "Different concrete failures: torch.compile with SDPA on Bamba versus MXFP4 quantization fallback on git-oss-20b." + "reason": "torch.compile SDPA failure on Bamba is unrelated to git-oss quantization fallback behavior." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "Packed-weight loading for BitNet is unrelated to OmDet-Turbo\u2019s processor input-size mismatch." + "reason": "Packed-weight unpacking during loading and processor image-size mismatch are different issues." }, { "left": "issue:43257", "right": "issue:43696", "accept": false, - "reason": "Accelerate/deepspeed conversion bug versus a plain CUDA OOM on GPT-oss-20b; not the same issue." + "reason": "One is a loading/conversion bug, the other is an OOM problem; not the same underlying defect." }, { "left": "issue:43454", "right": "issue:43577", "accept": false, - "reason": "AyaVision weight tying bug and BLIP2 dtype propagation bug are distinct model-loading problems." + "reason": "Weight tying/generation garbage text and dtype propagation on BLIP2 are separate model-loading issues." }, { - "left": "issue:43329", - "right": "issue:44479", + "left": "issue:43531", + "right": "issue:45042", "accept": false, - "reason": "Both touch video/VLM paths, but one is an undefined-symbol bug in token counting and the other is a broader video-input regression across models." + "reason": "Qwen3-MoE sliding-window behavior is unrelated to PIL backend torchvision requirements." }, { - "left": "issue:43531", - "right": "issue:45042", + "left": "issue:43329", + "right": "issue:44479", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to image-processor torchvision dependency regression." + "reason": "Both mention multimodal/video handling, but the packet only shows surface overlap; it does not establish the same concrete code path or a mergeable shared fix." }, { "left": "issue:43262", "right": "issue:44811", "accept": false, - "reason": "Audio chat-template sampling-rate default and Whisper batch_decode skip_special_tokens are separate audio bugs." + "reason": "Audio processor chat-template sampling-rate default and Whisper batch_decode skipping special tokens are unrelated." }, { "left": "issue:42490", "right": "issue:43257", "accept": false, - "reason": "Local-path trailing-slash import warning is unrelated to Qwen3 MoE accelerate/deepspeed weight conversion." + "reason": "Trailing-slash local model warning is unrelated to Qwen3 MoE weight conversion/loading issues." }, { "left": "issue:36010", "right": "issue:36331", "accept": false, - "reason": "Both are Transformers API breakages, but one is an import error and the other is a Trainer compute_loss signature mismatch." + "reason": "Importing GenerationMixin and custom compute_loss signature breakage are separate API regressions." }, { "left": "issue:44568", "right": "issue:45356", "accept": false, - "reason": "Tokenizer regressions, but for different models and different symptoms: missing BOS/EOS versus codec/warning behavior." + "reason": "Tokenizer BOS/EOS handling and Kimi-K2.5 codec handling are different tokenizer regressions." }, { "left": "issue:43749", "right": "issue:44756", "accept": false, - "reason": "Both concern memory/loading, but one is FSDP RAM-efficient loading and the other is disabling mmap to avoid OOM on Strix Halo." + "reason": "FSDP CPU RAM efficient loading and Strix Halo mmap/OOM are different memory/loading problems." }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "Config-field loss with trust_remote_code is not the same as failing to unwrap text_config for composite multimodal configs." - }, - { - "left": "issue:44568", - "right": "issue:45488", - "accept": false, - "reason": "Both are tokenizer-related, but one is a specific special-token bug and the other is a ByteLevel-vs-Metaspace override regression affecting DeepSeek V3/R1." + "reason": "Missing fields from trust_remote_code config loading is unrelated to composite Qwen config unwrapping." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "TrainerState token accounting and GPT-oss perplexity are unrelated issues." + "reason": "Trainer token-count tracking and GPT-oss perplexity are unrelated training issues." }, { "left": "issue:43329", "right": "issue:43450", "accept": false, - "reason": "Both involve video paths, but one is an undefined-function bug in multimodal token counting and the other is a batched video-processor shape bug." + "reason": "Video-token counting helper bug and batched video processor shape bug are different layers and not clearly the same defect." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "mdeberta special-token insertion and LlamaTokenizer pre-tokenizer override are distinct tokenizer regressions." }, { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Different Qwen model-loading problems: MoE weight conversion versus Qwen3-VL weight shape mismatch." + "reason": "Qwen3 MoE loading/conversion bug and Qwen3-VL weight-shape mismatch are not the same issue." }, { "left": "issue:43606", "right": "issue:45859", "accept": false, - "reason": "Both mention CPU offload, but they affect different models and different mechanisms; not a single concrete fix." + "reason": "CPU-offload device mismatch for bark-small is unrelated to Qwen3_MoeTextRotaryEmbedding CPU-offload compatibility." }, { "left": "issue:44849", "right": "issue:45701", "accept": false, - "reason": "Qwen3.5 output_hidden_states behavior is a model bug, while 45701 is a broad tokenization-version regression." + "reason": "Hidden-state output bug and version-dependent tokenization change are not the same code-path problem." }, { "left": "issue:43697", "right": "issue:45357", "accept": false, - "reason": "RTDetrV2 output drift in v5 and Qwen3.5 save_pretrained key mismatch are unrelated regressions." - }, - { - "left": "issue:44291", - "right": "issue:45042", - "accept": false, - "reason": "init_empty_weights/_is_hf_initialized is a model-loading API issue, not an image-processor torchvision dependency problem." - }, - { - "left": "issue:44987", - "right": "issue:45538", - "accept": false, - "reason": "Different tokenizer/loading bugs for different models; no shared underlying code-path is evident." + "reason": "RTDetr output drift in v5 and Qwen3.5 visual-encoder save_pretrained keys are unrelated regressions." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The summary is mostly grounded, but it overstates the evidence for the 43329 \u2194 44479 link. The packet only shows surface overlap in multimodal/video processing; it does not establish that 43329 is the underlying helper bug behind 44479 or that they share the same code path in a mergeable way. The canonical/best-issue choice may be reasonable, but the wording should stay more conservative." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -5668,10 +5418,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:28282", "issue:29127", @@ -5709,6 +5459,7 @@ "issue:44938", "issue:44987", "issue:44991", + "issue:45042", "issue:45072", "issue:45137", "issue:45325", @@ -5722,258 +5473,272 @@ "issue:45987" ], "soft_pairs": [ + "issue:44291|issue:45042", + "issue:44987|issue:45538", "issue:42915|issue:43742", - "issue:44479|issue:45381", + "issue:42915|issue:44821", + "issue:33357|issue:34567", "issue:43257|issue:43756", "issue:41720|issue:43540", + "issue:44479|issue:45381", "issue:43452|issue:43582", - "issue:42915|issue:44821", - "issue:33357|issue:34567", "issue:44987|issue:45907", "issue:42915|issue:45538", "issue:43927|issue:44912", - "issue:43317|issue:45538", "issue:42175|issue:43824", + "issue:43317|issue:45538", "issue:43540|issue:44479", "issue:43540|issue:44560", "issue:44062|issue:44991", - "issue:43577|issue:45072", "issue:42175|issue:44938", + "issue:43577|issue:45072", "issue:38175|issue:44898", - "issue:43404|issue:45987", "issue:42175|issue:44488", + "issue:43404|issue:45987", "issue:45137|issue:45405", - "issue:43906|issue:45381", "issue:28282|issue:34689", + "issue:43906|issue:45381", "issue:43742|issue:44291", "issue:42915|issue:43749", "issue:44737|issue:45588", "issue:43540|issue:45823", "issue:43526|issue:45479", - "issue:43582|issue:43782", + "issue:28282|issue:29127", "issue:43756|issue:45325", - "issue:28282|issue:29127" + "issue:43582|issue:43782" ], - "prepared_review_unit_hash": "b85c06198fbb1a9e61ea2dce0337802a7c778e052f1a2e18e67e276e927bbab9", + "prepared_review_unit_hash": "ce7a726130df70933c358c835abaddde8c47dfe69b84311926510a0df49db796", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36534, - "estimated_input_tokens": 9134, - "estimated_eval_tokens": 18524 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37711, + "estimated_input_tokens": 9428, + "estimated_eval_tokens": 19112 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated Transformers bug reports, with one small coherent subgroup around Qwen/Qwen-VL video-input regressions. Most soft pairs are only superficially similar and should stay separate.", + "summary": "This cluster is mostly heterogeneous: many unrelated model-loading, packaging, dtype, and video-processing bugs were grouped by superficial similarity. The only strong duplicate-like pair is the Qwen2.5-VL / Qwen3-VL video-input regression pair.", "confidence": 0.78, - "canonical_issue_reason": "issue:44479 is the broadest and most representative report in the only clearly coherent subgroup, covering a shared Qwen-VL video-input regression across multiple model variants.", + "canonical_issue_reason": "issue 44479 is the broadest, most concrete report of the shared Qwen VL video-input regression, and it can naturally subsume the narrower qwen2.5-vl-specific report in 45381.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 best captures the strongest recurring theme in the cluster and is the most useful umbrella issue for the related Qwen video-input failures.", + "best_issue_reason": "issue 44479 is the best representative because it describes the regression at the right level of abstraction and covers multiple affected Qwen VL variants.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Different failures: unexpected _is_hf_initialized argument during init_empty_weights vs PIL image processors incorrectly requiring torchvision." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "One is a model load failure for a specific repo; the other is a tokenizer max_length constant issue." + }, { "left": "issue:42915", "right": "issue:43742", "accept": false, - "reason": "Different model/load paths: Qwen3Moe FP8 loading vs MobileLLM key error." + "reason": "Both involve loading, but they are different code paths and errors: Qwen3Moe FP8 config vs MobileLLM key error." }, { - "left": "issue:44479", - "right": "issue:45381", - "accept": true, - "reason": "Same underlying Qwen-VL video-input regression; 45381 looks like a narrower instance of the broader v5.3.0 bug in 44479." + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Unrelated problems: Qwen3Moe FP8 loading vs AutoImageProcessor failing to load from URL." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Bus error on MacOS CLIP loading is unrelated to TrainerState num_input_tokens_seen not updating." }, { "left": "issue:43257", "right": "issue:43756", "accept": false, - "reason": "Different problems: Qwen3 MoE weight conversion with accelerate/deepspeed vs Smollm3 RoPE layer handling." + "reason": "Different subsystems: Qwen3 MoE weights with accelerate/deepspeed vs Smollm3 RoPE layer selection." }, { "left": "issue:41720", "right": "issue:43540", "accept": false, - "reason": "Different failure modes and code paths: device-map cudaErrorAssert vs video-input ValueError." - }, - { - "left": "issue:43452", - "right": "issue:43582", - "accept": false, - "reason": "Tokenizer/model loading with gguf_file is unrelated to Apple Silicon allocator warmup TypeError." + "reason": "Auto device map CUDA assert on A800 is not the same bug as Qwen3OmniMoe video ValueError." }, { - "left": "issue:42915", - "right": "issue:44821", - "accept": false, - "reason": "Qwen3Moe FP8 loading is unrelated to AutoImageProcessor-from-URL loading." + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "These describe the same Qwen VL video-input regression in 5.3.0; 45381 is a narrower instance of the broader bug reported in 44479." }, { - "left": "issue:33357", - "right": "issue:34567", + "left": "issue:43452", + "right": "issue:43582", "accept": false, - "reason": "MacOS bus error in CLIP loading is unrelated to TrainerState token counting." + "reason": "Different failures: gguf_file loading breaks vs an Apple Silicon caching_allocator_warmup TypeError." }, { "left": "issue:44987", "right": "issue:45907", "accept": false, - "reason": "Tokenizer/model loading regression is unrelated to list_repo_files revision forwarding in CI." + "reason": "Specific model-loading regression vs a repo-files API forwarding bug; not the same underlying issue." }, { "left": "issue:42915", "right": "issue:45538", "accept": false, - "reason": "Qwen3Moe quantization/loading issue is unrelated to CLIPTokenizer max_length behavior." + "reason": "Qwen3Moe FP8 loading failure is unrelated to CLIPTokenizer's model_max_length constant." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "Config save/load token-ID loss is unrelated to MXFP4 quantization fallback." + "reason": "DiaConfig token IDs are lost on save/load, while git-oss-20b falls back from MXFP4 quantization." }, { - "left": "issue:43317", - "right": "issue:45538", + "left": "issue:42175", + "right": "issue:43824", "accept": false, - "reason": "device_map offload failure is unrelated to CLIPTokenizer model_max_length." + "reason": "Packaging/backend dependency issue vs missing Qwen2_5_VL class import; different problems." }, { - "left": "issue:42175", - "right": "issue:43824", + "left": "issue:43317", + "right": "issue:45538", "accept": false, - "reason": "Backend packaging issue is unrelated to missing Qwen2_5_VL import symbol." + "reason": "device_map auto/offload loading failure is unrelated to tokenizer max_length behavior." }, { "left": "issue:43540", "right": "issue:44479", "accept": false, - "reason": "Both are video-related but the model families and described failures differ; not enough evidence of the same bug." + "reason": "Both are Qwen video-related, but the model families and failure modes differ; not enough evidence of the same bug." }, { "left": "issue:43540", "right": "issue:44560", "accept": false, - "reason": "Different Qwen video-input failures with different symptoms and likely different code paths." + "reason": "Different Qwen video errors (ValueError vs StopIteration) and different model variants; not a clear duplicate." }, { "left": "issue:44062", "right": "issue:44991", "accept": false, - "reason": "Tokenizer AddedToken TypeError may be adjacent, but the reports do not clearly describe the same concrete bug." + "reason": "AddedToken special-kwarg TypeError is unrelated to tokenizer loading failure for EMBEDDIA/est-roberta." }, { - "left": "issue:43577", - "right": "issue:45072", + "left": "issue:42175", + "right": "issue:44938", "accept": false, - "reason": "BLIP2 dtype propagation and SwitchTransformers/TimmWrapper dtype mismatch are different issues." + "reason": "Tensorflow backend packaging issue is not the same as Python 3.14 import/load failure." }, { - "left": "issue:42175", - "right": "issue:44938", + "left": "issue:43577", + "right": "issue:45072", "accept": false, - "reason": "Packaging/backend composition bug is unrelated to Python 3.14 import failure." + "reason": "Both mention dtype, but one is BLIP2 dtype propagation and the other is bfloat16 inference mismatches in different models." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to Perceiver interpolation failure." + "reason": "SigLIP2 zero probabilities and Perceiver non-default resolution failure are distinct model-specific bugs." }, { - "left": "issue:43404", - "right": "issue:45987", + "left": "issue:42175", + "right": "issue:44488", "accept": false, - "reason": "Mistral3 lm_head tying issue is unrelated to StaticCache return-type mismatch." + "reason": "Dependency/backend packaging issue is unrelated to the cjvt/sleng-bert loading failure." }, { - "left": "issue:42175", - "right": "issue:44488", + "left": "issue:43404", + "right": "issue:45987", "accept": false, - "reason": "TensorFlow backend packaging is unrelated to loading cjvt/sleng-bert." + "reason": "lm_head weight tying bug and StaticCache get_seq_length return type bug are unrelated." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "DeepSpeed ZeRO3 deque failure is unrelated to MIN_PEFT_VERSION metadata/versioning." + "reason": "DeepSpeed ZeRO3 deque IndexError is unrelated to the PEFT version bump problem." }, { - "left": "issue:43906", - "right": "issue:45381", + "left": "issue:28282", + "right": "issue:34689", "accept": false, - "reason": "A reproduction of a different issue is not the same as the Qwen2.5-VL video-position bug." + "reason": "Missing PyTorch ImportError and Llama 3.2 Vision model loading regression are different failures." }, { - "left": "issue:28282", - "right": "issue:34689", + "left": "issue:43906", + "right": "issue:45381", "accept": false, - "reason": "PyTorch missing ImportError is unrelated to Llama 3.2 Vision loading breakage." + "reason": "An isolated reproduction of another issue is not enough to treat it as the same bug as the qwen2.5-vl video-position-id regression." }, { "left": "issue:43742", "right": "issue:44291", "accept": false, - "reason": "MobileLLM key error is unrelated to init_empty_weights/_is_hf_initialized argument handling." + "reason": "KeyError while loading MobileLLM is unrelated to init_empty_weights passing an unexpected _is_hf_initialized argument." }, { - "left": "issue:42915", - "right": "issue:43749", + "left": "issue:43749", + "right": "issue:42915", "accept": false, - "reason": "Qwen3Moe loading is unrelated to FSDP_CPU_RAM_EFFICIENT_LOADING." + "reason": "FSDP_CPU_RAM_EFFICIENT_LOADING regression is not the same as Qwen3Moe FineGrainedFP8Config failure." }, { "left": "issue:44737", "right": "issue:45588", "accept": false, - "reason": "XLNet CPU arange bug is unrelated to flash_attention s_aux handling." + "reason": "XLNet CPU arange device bug is unrelated to flash_attention.py crashing on sink-less models." }, { "left": "issue:43540", "right": "issue:45823", "accept": false, - "reason": "Different multimodal model/device issues with no clear shared bug." + "reason": "Qwen3OmniMoe video ValueError and Gemma4 PLE device mismatch are different model-specific runtime errors." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug is unrelated to sequence-classification zero-loss behavior." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to degenerate zero-loss sequence classification." }, { - "left": "issue:43582", - "right": "issue:43782", + "left": "issue:28282", + "right": "issue:29127", "accept": false, - "reason": "Apple Silicon allocator TypeError is unrelated to Qwen3VL weight_only loading error." + "reason": "Missing PyTorch dependency error is unrelated to LayoutLMv3's box-information error message." }, { "left": "issue:43756", "right": "issue:45325", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and Qwen2.5-VL rope-index scaling are different bugs." + "reason": "Both involve RoPE/position handling, but they affect different models and different mechanics; not the same bug." }, { - "left": "issue:28282", - "right": "issue:29127", + "left": "issue:43582", + "right": "issue:43782", "accept": false, - "reason": "Missing PyTorch ImportError is unrelated to LayoutLMv3 box-content error messaging." + "reason": "AppleSilicon TypeError in warmup is unrelated to Qwen3VL from_pretrained weight_only=True failure." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis stays grounded in the packet: it identifies a single clearly related Qwen video-input subgroup, chooses a plausible umbrella issue (44479), and keeps the rest of the soft-edge verdicts conservative rather than over-merging loosely similar reports. No mergeability concerns apply here." + "feedback": "The summary is grounded in the packet, and the soft-edge judgments stay conservative: the only accepted pair, 44479/45381, is well-supported by the issue titles, while the rest are reasonably rejected as different bugs or insufficiently evidenced duplicates. The cluster-level heterogeneity summary is also consistent with the packet." }, "evaluator_used": true, "retried": false, @@ -5989,10 +5754,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:24643", "issue:29127", @@ -6046,8 +5811,8 @@ "soft_pairs": [ "issue:43493|issue:43994", "issue:34567|issue:36331", - "issue:44062|issue:45081", "issue:44291|issue:44821", + "issue:44062|issue:45081", "issue:45357|issue:45920", "issue:43643|issue:45375", "issue:43452|issue:44488", @@ -6059,33 +5824,33 @@ "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:44514|issue:45290", - "issue:43452|issue:43577", "issue:43452|issue:44843", + "issue:44514|issue:45290", "issue:44466|issue:45005", "issue:43295|issue:45356", + "issue:43452|issue:43577", "issue:43819|issue:44811", "issue:44936|issue:45823" ], - "prepared_review_unit_hash": "65bec09b74df99b97b9722ccc8d768fcab22409d6fd2eae224ab79e46a0a96e7", + "prepared_review_unit_hash": "4286c10dfb75180238aeb880b92e16b61ff6b3273d83460cfbeed60394065476", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 36186, + "serialized_chars": 36185, "estimated_input_tokens": 9047, "estimated_eval_tokens": 18350 }, @@ -6094,181 +5859,178 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of Transformers bug reports that share regression/loading/tokenizer language but not the same concrete failure. None of the soft edges look safe to merge as duplicates. The broadest current anchor is the open tokenizer regression in issue 45920.", - "confidence": 0.34, - "canonical_issue_reason": "Issue 45920 is the broadest, most current regression report in the set, spanning multiple model families and a shared tokenizer failure mode.", + "summary": "This cluster is mostly a mix of unrelated Transformers bug reports; only a couple of pairs look like true duplicates or near-duplicates. The strongest shared themes are SigLIP2 output regressions and tied-weights serialization issues.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 45920 is the broadest and most actionable representative: it is an open, current v5 regression affecting AutoTokenizer across multiple models, which makes it the best cluster anchor among otherwise heterogeneous reports.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45920 is the best global representative because it is open, high-signal, and covers a wider cross-model tokenizer regression than the more narrowly scoped reports.", + "best_issue_reason": "45920 is the best overall issue to keep: it is open, directly user-facing, and spans multiple affected models rather than a single niche symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43493", "right": "issue:43994", - "accept": false, - "reason": "Both are SigLIP2-related, but one is an HF-vs-JAX implementation discrepancy and the other is a bad-output/pipeline issue. Different symptoms and likely different code paths." + "accept": true, + "reason": "Both report SigLIP2 producing incorrect outputs; one frames it as a HF-vs-JAX discrepancy and the other as nonsensical results via AutoModel/pipeline, which looks like the same underlying model bug." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "TrainerState token counting and CustomTrainer.compute_loss API breakage are unrelated trainer bugs." + "reason": "Both are training-related regressions, but one is about TrainerState token counting and the other is a compute_loss signature change; different failures and code paths." }, { - "left": "issue:44062", - "right": "issue:45081", + "left": "issue:44291", + "right": "issue:44821", "accept": false, - "reason": "One is an AddedToken `special` argument collision; the other is a Mistral regex/backend tokenizer attribute crash. Same subsystem, different bug." + "reason": "These involve unrelated loading failures: init_empty_weights/_is_hf_initialized versus loading AutoImageProcessor from URL." }, { - "left": "issue:44291", - "right": "issue:44821", + "left": "issue:44062", + "right": "issue:45081", "accept": false, - "reason": "`init_empty_weights`/_is_hf_initialized and loading AutoImageProcessor from URL are unrelated failure modes." + "reason": "Both are tokenizer issues, but one is AddedToken construction and the other is a Mistral regex/backend_tokenizer crash; not the same bug." }, { "left": "issue:45357", "right": "issue:45920", "accept": false, - "reason": "Both involve Qwen/tokenizer regressions, but one is incorrect saved visual encoder keys and the other is wrong token IDs during tokenization. Not the same concrete bug." + "reason": "Different subsystems: Qwen3.5 save_pretrained visual key serialization versus global AutoTokenizer token-id regression." }, { "left": "issue:43643", "right": "issue:45375", "accept": false, - "reason": "Both are config-field propagation/strictness issues, but they affect different models and different missing fields." + "reason": "Both concern config handling, but the root causes differ: missing fields from trust_remote_code AutoConfig versus a specific Qwen3_5MoeVisionConfig field being dropped by strict parsing." }, { "left": "issue:43452", "right": "issue:44488", "accept": false, - "reason": "GGUF loading breakage and a model-specific load failure are not the same underlying problem." + "reason": "Both are model-loading complaints, but gguf_file breakage and a specific cjvt/sleng-bert load failure do not point to the same code-path." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "Both are multimodal load/generate issues, but they target different models and different code paths." + "reason": "Both are multimodal model failures, but they affect different models and symptoms; not enough to treat as one bug." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "Image-processor torchvision dependency regression and Mistral tokenizer regex crash are unrelated." + "reason": "PIL/torchvision backend requirements are unrelated to the Mistral tokenizer AttributeError." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "A key error on MobileLLM load and a Float8 storage lookup error are different loading failures." + "reason": "Different loading errors: a key error for MobileLLM versus missing Float8 storage object." }, { "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 behavior is unrelated to AutoImageProcessor URL loading." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "One is an unreleased dependency version bump, the other is stale auto-mapping references. No shared bug." + "reason": "These are unrelated CI/dependency/config-reference issues." }, { "left": "issue:43697", "right": "issue:45216", "accept": false, - "reason": "RTDetrV2 output drift and Qwen3.5 checkpoint serialization are separate regressions." + "reason": "Different regressions: RTDetrV2 output mismatch versus Qwen3.5 checkpoint saving correctness." }, { "left": "issue:43688", "right": "issue:43749", "accept": false, - "reason": "Auxiliary-loss normalization and FSDP CPU RAM-efficient loading are different issues." + "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are distinct problems." }, { "left": "issue:44514", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen2.5-VL/Qwen chat-template style bugs, but one is batched apply_chat_template padding and the other is video vision_position_ids. Not the same concrete failure." + "reason": "Both are Qwen2.5-VL issues, but one is chat-template batching and the other is video vision_position_ids; different code paths." }, { - "left": "issue:43720", - "right": "issue:44898", + "left": "issue:44484", + "right": "issue:44704", "accept": false, - "reason": "BitNet packed-weight unpacking and Perceiver resolution handling are unrelated." + "reason": "A save_pretrained sharding-size question is unrelated to AutoProcessor kwargs forwarding." }, { - "left": "issue:44484", - "right": "issue:44704", + "left": "issue:43720", + "right": "issue:44898", "accept": false, - "reason": "save_pretrained shard size behavior and AutoProcessor kwarg forwarding are separate API issues." + "reason": "BitNet packed-weight loading and Perceiver image classification failures are unrelated." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "DeepSpeed ZeRO-3 load failure and trainer.evaluate-after-train behavior are unrelated." + "reason": "DeepSpeed ZeRO-3 Gemma3 loading and trainer.evaluate-after-train failures are separate issues." }, { "left": "issue:24643", "right": "issue:29127", "accept": false, - "reason": "DeepSpeed training weight-shape error and LayoutLMv3 box validation messaging are not duplicates." + "reason": "One is a DeepSpeed training RuntimeError; the other is a LayoutLMv3 error-message clarity issue." }, { "left": "issue:44625", "right": "issue:44877", "accept": false, - "reason": "Qwen3.5 num_labels propagation and strict config loading for granite_speech are different config bugs." - }, - { - "left": "issue:44514", - "right": "issue:45290", - "accept": false, - "reason": "Both hit apply_chat_template, but one is batched padding=False and the other is assistant tool-call messages with no content. Different edge cases." + "reason": "num_labels propagation in Qwen3.5 and strict config blocking granite_speech are different configuration bugs." }, { "left": "issue:43452", - "right": "issue:43577", + "right": "issue:44843", "accept": false, - "reason": "GGUF loading breakage and BLIP2 dtype propagation are unrelated." + "reason": "gguf_file loading breakage and offline mistral-regex model_info calls are unrelated tokenizer/loading bugs." }, { - "left": "issue:43452", - "right": "issue:44843", + "left": "issue:44514", + "right": "issue:45290", "accept": false, - "reason": "GGUF-from_pretrained failure and offline mistral regex patch behavior are different tokenizer/loading problems." + "reason": "Both are apply_chat_template crashes, but the triggers differ substantially: batched padding=False versus assistant tool-call messages with no content." }, { "left": "issue:44466", "right": "issue:45005", - "accept": false, - "reason": "Both mention tied weights in v5, but one is device-dependent serialization of lm_head.weight and the other is translation-model tied-weight issues. Similar area, not clearly the same bug." + "accept": true, + "reason": "Both point to tied-weights serialization problems in v5; the device-dependent lm_head.weight behavior and translation-model tied-weight breakage are plausibly the same save_pretrained bug." }, { "left": "issue:43295", "right": "issue:45356", "accept": false, - "reason": "Processor/tokenizer regression and Kimi-K2.5 codec/mistral-regex regression are different tokenizer issues." + "reason": "Processor/tokenizer access regressions and Kimi-K2.5 codec/fix_mistral_regex issues are different tokenizer bugs." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "DAC latent reconstruction mismatch and Whisper batch_decode special-token handling are unrelated." + "reason": "DAC from_latents/STE mismatch and Whisper batch_decode skip_special_tokens handling are unrelated." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "trainer.evaluate failure and Gemma4 device-map forward mismatch are separate runtime problems." + "reason": "Trainer evaluate failure and Gemma4 device mismatch during forward are separate runtime issues." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The canonical issue choice is supported by the packet: 45920 is open, user-facing, and spans multiple models under a single AutoTokenizer v5 regression. The two accepted soft pairs are plausible duplicates/near-duplicates based on titles alone, and the rejected pairs are mostly appropriately cautious. I don\u2019t see material overstatement." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -6280,10 +6042,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:28282", "issue:30064", @@ -6292,7 +6054,6 @@ "issue:33666", "issue:34567", "issue:35141", - "issue:36010", "issue:38175", "issue:41720", "issue:43122", @@ -6329,286 +6090,282 @@ "issue:44977", "issue:44991", "issue:45440", + "issue:45491", "issue:45588", "issue:45701", - "issue:45704" + "issue:45704", + "issue:46002" ], "soft_pairs": [ "issue:38175|issue:43295", - "issue:43653|issue:44568", + "issue:30064|issue:33666", + "issue:44464|issue:44743", "issue:43653|issue:44361", "issue:44361|issue:44442", - "issue:30064|issue:33666", "issue:43643|issue:44561", - "issue:44464|issue:44743", + "issue:43653|issue:44568", "issue:41720|issue:43906", "issue:43688|issue:45440", "issue:43688|issue:45704", "issue:28282|issue:32090", "issue:28282|issue:33357", + "issue:45491|issue:46002", "issue:43577|issue:43697", "issue:28282|issue:35141", "issue:44843|issue:44991", - "issue:43646|issue:43749", "issue:43688|issue:45701", + "issue:43646|issue:43749", "issue:43653|issue:43927", "issue:43531|issue:43742", "issue:43550|issue:43927", "issue:44464|issue:44977", - "issue:43550|issue:44361", "issue:44479|issue:44625", - "issue:43122|issue:43906", + "issue:43550|issue:44361", "issue:43577|issue:44554", + "issue:43122|issue:43906", "issue:43577|issue:45588", - "issue:43504|issue:43720", "issue:43504|issue:43550", "issue:32090|issue:34567", "issue:41720|issue:44464", + "issue:43504|issue:43720", "issue:43504|issue:44610", "issue:32090|issue:33666", "issue:43452|issue:44451", "issue:43742|issue:44821", - "issue:43278|issue:43688", - "issue:33666|issue:36010" + "issue:43278|issue:43688" ], - "prepared_review_unit_hash": "3fd1233f82948697ab3814f1d84c4efa37218912a27db3db22e0b14b02110161", + "prepared_review_unit_hash": "de34865d7e6df05cc33f45c023f0045a527f78b8661131f50d118943e5d080b1", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 36, - "serialized_chars": 37895, - "estimated_input_tokens": 9474, - "estimated_eval_tokens": 19204 + "serialized_chars": 38481, + "estimated_input_tokens": 9621, + "estimated_eval_tokens": 19498 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated Transformers bug reports, with a few loose tokenizer/model-loading regressions but no true duplicate pair among the soft edges. I would keep one concrete tokenizer regression as the representative issue, and there are no PRs to consider.", - "confidence": 0.84, - "canonical_issue_reason": "issue:43122 is a concrete, user-visible tokenizer regression with version-specific repro and inbound references, making it the cleanest representative issue in this set.", + "summary": "The cluster is largely heterogeneous. A few items share a broad tokenizer/regression theme, but none of the soft pairs appear to be the same underlying bug or change, so all soft edges are rejected.", + "confidence": 0.86, + "canonical_issue_reason": "Issue #45701 is the broadest, most umbrella-like report in the set: it explicitly centers on version-dependent tokenization changes, which is the only recurring theme spanning multiple nearby issues.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43122 is the strongest issue candidate because it is specific, already closed, and describes a reproducible version-to-version behavior change rather than a vague umbrella symptom.", + "best_issue_reason": "Issue #45701 is the best representative issue for this cluster because it is the most general tokenization-regression report and has inbound attention, even though the cluster is too mixed to collapse into one duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:38175", "right": "issue:43295", "accept": false, - "reason": "Different failures: zero probabilities in SigLIP2 vs processor/tokenizer access regression in custom model code." + "reason": "Unrelated failures: SigLIP2 zero probabilities vs custom model init/processor.tokenizer regression." }, { - "left": "issue:43653", - "right": "issue:44568", + "left": "issue:30064", + "right": "issue:33666", "accept": false, - "reason": "Both are tokenizer-special-token bugs, but they affect different models and different symptoms/code paths." + "reason": "Different domains and bugs: void segmentation maps vs Qwen2-VL multi-GPU training." }, { - "left": "issue:43653", - "right": "issue:44361", + "left": "issue:44464", + "right": "issue:44743", "accept": false, - "reason": "BigBird special-token decode issue vs MLukeTokenizer AttributeError; not the same bug." + "reason": "Both are Qwen-related, but one is compiled-forward chunked generation inconsistency and the other is recurrent-state reset in modular code; different code paths." }, { - "left": "issue:44361", - "right": "issue:44442", + "left": "issue:43653", + "right": "issue:44361", "accept": false, - "reason": "Tokenizer AttributeError on tasks vs AutoTokenizer failing to load a specific tokenizer class; different root causes." + "reason": "Tokenizer issues, but different models and symptoms: BigBird special-token registration vs MLuke task AttributeError." }, { - "left": "issue:30064", - "right": "issue:33666", + "left": "issue:44361", + "right": "issue:44442", "accept": false, - "reason": "Image processor segmentation-map handling and Qwen2-VL multi-GPU training are unrelated." + "reason": "Different tokenizer loaders and different exceptions; no clear shared underlying bug." }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "Both touch trust_remote_code/v5 behavior, but one is missing config fields and the other is a removed utility breaking models." + "reason": "One is missing fields from trust_remote_code config loading; the other is a v5.0 API removal breaking trust_remote_code models." }, { - "left": "issue:44464", - "right": "issue:44743", + "left": "issue:43653", + "right": "issue:44568", "accept": false, - "reason": "Chunked generation with compiled forward is a different code path from recurrent-state reset in modular Qwen3.5." + "reason": "Both involve special tokens, but they affect different tokenizers and different behaviors (decode output vs BOS/EOS addition)." }, { "left": "issue:41720", "right": "issue:43906", "accept": false, - "reason": "Different CUDA/Qwen3 device-mapping crash versus an isolated reproduction of another issue; no concrete same defect." + "reason": "No concrete overlap: Qwen3 A800 cudaErrorAssert vs an isolated reproduction of a different issue." }, { "left": "issue:43688", "right": "issue:45440", "accept": false, - "reason": "Both involve MoE models, but one is auxiliary-loss normalization and the other is a remote/native implementation divergence." + "reason": "MoE-related but different defects: auxiliary-loss normalization vs divergence from the remote DeepSeekV3 implementation." }, { "left": "issue:43688", "right": "issue:45704", "accept": false, - "reason": "Auxiliary-loss normalization and an apex RMSNorm memory leak are unrelated bugs." + "reason": "Completely different bugs: MoE loss normalization vs T5/apex RMSNorm memory leak." }, { "left": "issue:28282", "right": "issue:32090", "accept": false, - "reason": "Missing PyTorch import vs NoneType passed to gpu broadcast are distinct runtime errors." + "reason": "ImportError for missing PyTorch vs Trainer NoneType broadcast error; unrelated." }, { "left": "issue:28282", "right": "issue:33357", "accept": false, - "reason": "PyTorch-not-found import error and MacOS bus error on CLIP are different failures." + "reason": "Missing PyTorch ImportError vs MacOS bus error in CLIP loading; unrelated." }, { - "left": "issue:43577", - "right": "issue:43697", + "left": "issue:45491", + "right": "issue:46002", "accept": false, - "reason": "BLIP-2 dtype propagation and RTDetrV2 output drift are different model-specific issues." + "reason": "Both mention NaNs, but the trigger and code path differ: sliding-window/all-padding embeddings vs classification-head NaNs after checkout/init." }, { - "left": "issue:28282", - "right": "issue:35141", + "left": "issue:43577", + "right": "issue:43697", "accept": false, - "reason": "ImportError from missing torch and embedding reinitialization after resize are unrelated." + "reason": "Different model families and failures: BLIP2 dtype propagation vs RTDetrV2 output divergence." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Offline hub lookup bug and tokenizer load failure for a specific model are different problems." + "reason": "Both are tokenizer-loading regressions, but one is an offline model_info call in _patch_mistral_regex and the other is a specific tokenizer load failure." }, { - "left": "issue:43646", - "right": "issue:43749", + "left": "issue:43688", + "right": "issue:45701", "accept": false, - "reason": "Custom model initialization breakage is not the same as FSDP RAM-efficient loading failure." + "reason": "Different defect types: auxiliary-loss normalization vs broad tokenization version-change report." }, { - "left": "issue:43688", - "right": "issue:45701", + "left": "issue:43646", + "right": "issue:43749", "accept": false, - "reason": "Auxiliary-loss normalization and broad tokenization changes are not the same underlying bug." + "reason": "Custom model initialization breakage vs FSDP CPU RAM efficient loading; different subsystems and bugs." }, { "left": "issue:43653", "right": "issue:43927", "accept": false, - "reason": "BigBird special-token registration and DiaConfig custom token-ID loss are both tokenizer/config issues, but they are separate code paths." + "reason": "Both are token-related, but one is special-token registration and the other is config loss of custom token IDs; not the same bug." }, { "left": "issue:43531", "right": "issue:43742", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and MobileLLM loading key error are unrelated." + "reason": "Qwen3-MoE sliding-window issue vs MobileLLM pretrained load KeyError; unrelated." }, { "left": "issue:43550", "right": "issue:43927", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to DiaConfig token-ID persistence." + "reason": "torch.compile + SDPA failure vs token-ID persistence/config bug; unrelated." }, { "left": "issue:44464", "right": "issue:44977", "accept": false, - "reason": "Compiled-forward chunked generation and flash-attention generation regression are different execution paths." + "reason": "Both affect generation, but one is compiled-forward chunked generation inconsistency and the other is a flash-attention regression in Qwen3.5." }, { "left": "issue:43550", "right": "issue:44361", "accept": false, - "reason": "Model compile/SDPA failure and tokenizer AttributeError are unrelated." + "reason": "torch.compile/SDPA bug vs tokenizer AttributeError; unrelated." }, { - "left": "issue:44479", - "right": "issue:44625", + "left": "issue:43577", + "right": "issue:44554", "accept": false, - "reason": "Video-input regression in Qwen VL models and num_labels propagation are different bugs." + "reason": "BLIP2 dtype propagation vs an MPS attention correctness issue; different models and failure modes." }, { "left": "issue:43122", "right": "issue:43906", "accept": false, - "reason": "Tokenizer behavior change across versions is not the same as an isolated reproduction of another issue." - }, - { - "left": "issue:43577", - "right": "issue:44554", - "accept": false, - "reason": "BLIP-2 dtype mismatch and MPS attention correctness are different issues." + "reason": "Version-dependent tokenization change vs isolated reproduction of a different issue; no shared underlying bug." }, { "left": "issue:43577", "right": "issue:45588", "accept": false, - "reason": "BLIP-2 dtype propagation and flash_attention crashing on s_aux=None are unrelated." + "reason": "Dtype propagation bug vs flash_attention crash on s_aux=None; unrelated." }, { "left": "issue:43504", - "right": "issue:43720", + "right": "issue:43550", "accept": false, - "reason": "BEiT legacy-field loading and BitNet packed-weight loading are different loaders and bugs." + "reason": "Pretrained load legacy-field issue vs Bamba torch.compile/SDPA failure; unrelated." }, { "left": "issue:32090", "right": "issue:34567", "accept": false, - "reason": "gpu_broadcast NoneType failure and TrainerState token counter not updating are unrelated trainer issues." + "reason": "Trainer broadcast TypeError vs TrainerState counter not updating; different training bugs." }, { "left": "issue:41720", "right": "issue:44464", "accept": false, - "reason": "Qwen3 auto device-mapping CUDA assert and compiled-forward generation inconsistency are different failures." + "reason": "Qwen3 auto device mapping assert vs chunked generation inconsistency under compile; different problems." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Legacy-field model loading bug vs BitNet packed-weight unpacking issue; different code paths." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "BEiT preset loading bug and OmDet processor size mismatch are unrelated." + "reason": "Pretrained-load legacy field vs processor/model input-size mismatch; unrelated." }, { "left": "issue:32090", "right": "issue:33666", "accept": false, - "reason": "NoneType broadcast crash and Qwen2-VL multi-GPU training are not the same bug." + "reason": "Trainer broadcast NoneType error vs Qwen2-VL multi-GPU training request; unrelated." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "gguf_file loading breakage and ScandiBERT tokenizer loading failure are different model-loading problems." + "reason": "Both are load failures, but one is gguf_file breaking AutoTokenizer/AutoModel loading and the other is a specific tokenizer load regression for ScandiBERT." }, { "left": "issue:43742", "right": "issue:44821", "accept": false, - "reason": "MobileLLM key error and AutoImageProcessor URL loading failure are unrelated." + "reason": "Different loading failures: MobileLLM KeyError vs AutoImageProcessor-from-URL problem." }, { "left": "issue:43278", "right": "issue:43688", "accept": false, - "reason": "Embedding dtype drift during evaluate and auxiliary-loss normalization in MoE models are different bugs." - }, - { - "left": "issue:33666", - "right": "issue:36010", - "accept": false, - "reason": "Qwen2-VL multi-GPU training and GenerationMixin import failure are unrelated." + "reason": "Embedding dtype drift in evaluate vs MoE auxiliary-loss normalization; unrelated." } ] }, @@ -6627,14 +6384,15 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:28218", "issue:33357", "issue:33666", + "issue:36010", "issue:36331", "issue:39692", "issue:43257", @@ -6673,281 +6431,267 @@ "issue:45229", "issue:45357", "issue:45405", - "issue:45520", - "issue:45584", "issue:45759", "issue:45803", "issue:45812", "issue:45823", - "issue:45987" + "issue:45987", + "issue:46002" ], "soft_pairs": [ - "issue:43493|issue:43825", + "issue:33666|issue:36010", "issue:44849|issue:45357", - "issue:43606|issue:43927", - "issue:43720|issue:43927", - "issue:44568|issue:45812", "issue:43525|issue:43572", + "issue:43606|issue:43927", + "issue:43493|issue:43825", "issue:43262|issue:43295", + "issue:43720|issue:43927", "issue:43756|issue:44913", - "issue:43720|issue:44361", + "issue:44568|issue:45812", + "issue:44625|issue:46002", "issue:28218|issue:33357", + "issue:43720|issue:44361", "issue:33666|issue:36331", "issue:39692|issue:43493", "issue:43540|issue:44977", - "issue:43493|issue:43844", "issue:44964|issue:45405", "issue:43334|issue:43572", + "issue:43493|issue:43844", "issue:45803|issue:45987", "issue:43278|issue:43844", - "issue:44625|issue:45584", "issue:43756|issue:45083", - "issue:43257|issue:43299", "issue:43334|issue:45759", + "issue:43257|issue:43299", "issue:45200|issue:45229", "issue:44488|issue:44843", - "issue:43824|issue:44589", "issue:39692|issue:43295", + "issue:43824|issue:44589", "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" + "issue:33357|issue:33666" ], - "prepared_review_unit_hash": "cc25bde8a33c12270186dcebb87ba6c7702eb5bf14f281675d87420cddb2cc12", + "prepared_review_unit_hash": "5b61a481dadd4dd1b07afc58f09abcd9d5c741e48a2836f9f23212ba73a7f6bf", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37873, - "estimated_input_tokens": 9469, - "estimated_eval_tokens": 19194 + "soft_pair_count": 32, + "serialized_chars": 37566, + "estimated_input_tokens": 9392, + "estimated_eval_tokens": 19040 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly a collection of unrelated Transformers issues, with only loose thematic overlap around v5/model-loading regressions. I found no soft pair that is clearly the same underlying bug or change, so all candidate duplicate edges are rejected.", - "confidence": 0.36, - "canonical_issue_reason": "issue:45812 is the broadest open, user-facing regression here with multiple inbound references and a concrete tokenizer failure; it is the best anchor if one issue must represent the set.", + "summary": "Most items are unrelated standalone bug reports. None of the soft pairs look like the same concrete underlying defect, so I would not merge any of them as duplicates. The strongest canonical issue candidate is the Granite tokenizer regression because it is broad, clearly framed, and has the most evidence of reuse.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45812 is the broadest and most central report here: it describes a silent tokenizer regression across all Granite models and already has inbound references, making it the best candidate to anchor related reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45812 has the clearest repro-oriented bug report, the widest apparent impact, and active community signal, making it the strongest standalone issue in this batch.", + "best_issue_reason": "issue:45812 is the best global issue representative because it is specific enough to reproduce, broad enough to absorb nearby tokenizer reports, and appears to be the highest-signal open regression in the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43493", - "right": "issue:43825", + "left": "issue:33666", + "right": "issue:36010", "accept": false, - "reason": "Different subsystems: SigLIP2 implementation discrepancy vs pipeline translation-task error messaging." + "reason": "Both are ML import/training problems, but one is Qwen2-VL multi-GPU training and the other is a GenerationMixin import error; different failure modes and code paths." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Same model family but different bugs: output_hidden_states behavior vs save_pretrained visual-key serialization." + "reason": "Both mention Qwen3.5, but one is an output_hidden_states bug and the other is incorrect save_pretrained visual encoder keys; not the same fix." }, { - "left": "issue:43606", - "right": "issue:43927", + "left": "issue:43525", + "right": "issue:43572", "accept": false, - "reason": "CPU offload device mismatch is unrelated to DiaConfig custom token ID persistence." + "reason": "Both are missing pad token config fields, but for different models and different attributes (pad_token_id vs pad_token_idx); too model-specific to be one bug." }, { - "left": "issue:43720", + "left": "issue:43606", "right": "issue:43927", "accept": false, - "reason": "Packed-weight unpacking during accelerate loading is a different code path from config token-ID loss." + "reason": "One is a device mismatch with CPU offload, the other is a config/token-ID loss causing generation IndexError; unrelated underlying defects." }, { - "left": "issue:44568", - "right": "issue:45812", + "left": "issue:43493", + "right": "issue:43825", "accept": false, - "reason": "Both are tokenizer regressions, but on different models and symptoms; not the same concrete bug." + "reason": "SigLIP2 implementation mismatch vs. a pipeline error-message regression; different subsystems and fixes." }, { - "left": "issue:43525", - "right": "issue:43572", + "left": "issue:43262", + "right": "issue:43295", "accept": false, - "reason": "Both mention missing pad-token fields after v5, but they affect different config classes and attributes." + "reason": "Audio chat template sampling-rate default and processor.tokenizer regression are both multimodal API issues, but they affect different paths and are not the same bug." }, { - "left": "issue:43262", - "right": "issue:43295", + "left": "issue:43720", + "right": "issue:43927", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting is unrelated to processor.tokenizer / image-passing regression." + "reason": "Packed-weight unpacking during accelerate loading is unrelated to DiaConfig custom token ID persistence." }, { "left": "issue:43756", "right": "issue:44913", "accept": false, - "reason": "RoPE-layer count mismatch and rotary_pct reload persistence are different bugs in different model families." + "reason": "Smollm3 RoPE layer count bug and GPTNeoX rotary_pct reload regression involve different config fields and models." }, { - "left": "issue:43720", - "right": "issue:44361", + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both concern tokenization behavior, but one is BOS/EOS not being added for mdeberta-v3-base while the other is Granite token IDs being wrong across models; not the same defect." + }, + { + "left": "issue:44625", + "right": "issue:46002", "accept": false, - "reason": "Accelerate packed-weight loading bug is unrelated to MLukeTokenizer task AttributeError." + "reason": "Qwen3.5 num_labels propagation and NaNs in classification heads are different symptoms with different root causes." }, { "left": "issue:28218", "right": "issue:33357", "accept": false, - "reason": "Tokenizer spacing bug and Mac bus error on CLIP are clearly unrelated." + "reason": "Tokenizer spacing after added tokens is unrelated to a MacOS bus error loading a CLIP model." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight loading for BitNet AutoBitLinear is unrelated to MLukeTokenizer task AttributeError." }, { "left": "issue:33666", "right": "issue:36331", "accept": false, - "reason": "Multi-GPU training discussion vs CustomTrainer signature mismatch; different problem areas." + "reason": "Multi-GPU training for Qwen2-VL and a CustomTrainer.compute_loss signature break are separate training issues with different fixes." }, { "left": "issue:39692", "right": "issue:43493", "accept": false, - "reason": "Docs/example errors are not the same as a model implementation discrepancy." + "reason": "SigLIP2 docs example errors are documentation/example problems; the other is a model implementation discrepancy." }, { "left": "issue:43540", "right": "issue:44977", "accept": false, - "reason": "Video input processing failure and flash-attention generation bug are different code paths." - }, - { - "left": "issue:43493", - "right": "issue:43844", - "accept": false, - "reason": "SigLIP2 JAX-vs-HF discrepancy is unrelated to ZeRO-3 gradient growth." + "reason": "Qwen3OmniMoe video input processing and Qwen3.5 flash-attention generation issues are different code paths." }, { "left": "issue:44964", "right": "issue:45405", "accept": false, - "reason": "Model loading failure vs unreleased dependency version bump; not duplicate bugs." + "reason": "Model loading failure for Phi-4 multimodal and an unreleased PEFT version pin are unrelated." }, { "left": "issue:43334", "right": "issue:43572", "accept": false, - "reason": "Both are pad-token related, but different model/config regressions and not one concrete issue." + "reason": "Both are pad-token related, but one is Qwen3-VL missing pad_token_id on config and the other is StableLmConfig missing pad_token_idx after v5; not one shared bug." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient growth are distinct numerical/training issues." }, { "left": "issue:45803", "right": "issue:45987", "accept": false, - "reason": "Bare except swallowing errors in Fuyu is unrelated to StaticCache returning the wrong type." + "reason": "Bare except in Fuyu tensor conversion and StaticCache.get_seq_length return-type bug are unrelated API/safety issues." }, { "left": "issue:43278", "right": "issue:43844", "accept": false, - "reason": "Embedding dtype drift during eval is unrelated to gradient explosion with ZeRO-3." - }, - { - "left": "issue:44625", - "right": "issue:45584", - "accept": false, - "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription handling are unrelated." + "reason": "Embedding dtype drift during evaluate and abnormal gradient growth under ZeRO-3 are different symptoms and fixes." }, { "left": "issue:43756", "right": "issue:45083", "accept": false, - "reason": "Different RoPE/length-calculation problems in different models; not the same bug." + "reason": "RoPE-layer dropping in Smollm3 and qwen3_omni_moe feature-extract length behavior are unrelated model internals." }, { - "left": "issue:43257", - "right": "issue:43299", + "left": "issue:43334", + "right": "issue:45759", "accept": false, - "reason": "Both involve Qwen MoE loading, but one is accelerate/deepspeed weight conversion and the other is a different Qwen3VL loading regression." + "reason": "Qwen3-VL pad_token_id absence and AutoModelForCausalLM.from_config not unwrapping text_config are different multimodal config problems." }, { - "left": "issue:43334", - "right": "issue:45759", + "left": "issue:43257", + "right": "issue:43299", "accept": false, - "reason": "Missing pad_token_id in Qwen3-VL config is unrelated to AutoModelForCausalLM.from_config not unwrapping text_config." + "reason": "Qwen3 MOE weight conversion during accelerate/deepspeed loading and Qwen3VL Moe loading breakage are similar only at a family level, but not the same concrete bug." }, { "left": "issue:45200", "right": "issue:45229", "accept": false, - "reason": "Text-only mm_token_type_ids defaulting is unrelated to multi-GPU inference OOM." + "reason": "Gemma4 mm_token_type_ids defaulting and Gemma4 multi-GPU CUDA OOM are not the same underlying issue." }, { "left": "issue:44488", "right": "issue:44843", "accept": false, - "reason": "Model load failure and offline model_info() behavior are different bugs; same broad area only." + "reason": "A model failing to load and an offline-mode failure in _patch_mistral_regex stem from different causes." }, { - "left": "issue:44589", - "right": "issue:45520", + "left": "issue:39692", + "right": "issue:43295", "accept": false, - "reason": "Float8 storage lookup failure is unrelated to flash_attn import KeyError on Python 3.13." + "reason": "SigLIP2 docs errors and processor.tokenizer regression are both multimodal, but one is an example mismatch/quantization issue and the other is a runtime API regression." }, { "left": "issue:43824", "right": "issue:44589", "accept": false, - "reason": "Importing a missing class and storage-object lookup failures are unrelated." - }, - { - "left": "issue:39692", - "right": "issue:43295", - "accept": false, - "reason": "Documentation example problems are unrelated to the processor.tokenizer regression." + "reason": "Importing a missing Qwen2.5-VL class and missing Float8 storage support are unrelated import/type issues." }, { "left": "issue:43646", "right": "issue:44466", "accept": false, - "reason": "Custom model initialization breakage is a different issue from device-dependent lm_head serialization." + "reason": "Custom model initialization breakage and inconsistent lm_head.weight serialization are different model lifecycle bugs." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "CUDA OOM during inference and device mismatch in forward are different failure modes." + "reason": "Gemma4 multi-GPU OOM and PLE device mismatch during forward are different runtime resource problems." }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Legacy-field pretrained load failure is unrelated to CPU offload device mismatch." + "reason": "BEiT legacy-field loading failure and bark-small CPU-offload device mismatch are unrelated model-loading bugs." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "Missing pad_token_idx is unrelated to init_empty_weights receiving an unexpected argument." - }, - { - "left": "issue:44589", - "right": "issue:45520", - "accept": false, - "reason": "Unrelated failures: float8 storage lookup vs missing flash_attn import key." + "reason": "StableLmConfig missing pad_token_idx and init_empty_weights rejecting _is_hf_initialized are separate compatibility regressions." }, { "left": "issue:33357", "right": "issue:33666", "accept": false, - "reason": "MacOS bus error on a CLIP model and Qwen2-VL multi-GPU training are unrelated." - }, - { - "left": "issue:43927", - "right": "issue:44361", - "accept": false, - "reason": "DiaConfig token-ID loss and MLukeTokenizer task AttributeError are separate bugs." + "reason": "A MacOS bus error loading CLIP and Qwen2-VL multi-GPU training are wholly different failures." } ] }, @@ -6966,10 +6710,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:15354", "issue:28218", @@ -6981,7 +6725,6 @@ "issue:42490", "issue:43232", "issue:43278", - "issue:43295", "issue:43493", "issue:43504", "issue:43540", @@ -6992,16 +6735,18 @@ "issue:43696", "issue:43701", "issue:43844", + "issue:43927", "issue:43957", "issue:43994", "issue:44112", "issue:44315", + "issue:44361", "issue:44423", "issue:44464", "issue:44493", "issue:44521", "issue:44554", - "issue:44610", + "issue:44589", "issue:44734", "issue:44792", "issue:44849", @@ -7012,7 +6757,6 @@ "issue:45198", "issue:45200", "issue:45290", - "issue:45356", "issue:45405", "issue:45446", "issue:45520", @@ -7020,6 +6764,8 @@ "issue:45823" ], "soft_pairs": [ + "issue:44589|issue:45520", + "issue:43927|issue:44361", "issue:44423|issue:44734", "issue:43504|issue:43653", "issue:44464|issue:45584", @@ -7028,9 +6774,9 @@ "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:44521|issue:45290", "issue:43844|issue:44964", "issue:28218|issue:34567", "issue:44554|issue:45446", @@ -7039,198 +6785,196 @@ "issue:43540|issue:45200", "issue:15354|issue:38175", "issue:43232|issue:44849", - "issue:45072|issue:45198", "issue:37428|issue:43957", + "issue:45072|issue:45198", "issue:45200|issue:45823", "issue:44315|issue:44849", - "issue:43493|issue:43701", - "issue:43295|issue:44610", - "issue:44554|issue:45356" + "issue:43493|issue:43701" ], - "prepared_review_unit_hash": "d06800b383e02227a032c9c1c493ff61edc5f94c3d92becc84103a06ba8228c0", + "prepared_review_unit_hash": "fd6be3534eeb26b48acf08a7a4c17a3e56164cf8e5002c49071a5bb07744888d", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 26, - "serialized_chars": 34964, - "estimated_input_tokens": 8741, - "estimated_eval_tokens": 17738 + "serialized_chars": 34877, + "estimated_input_tokens": 8720, + "estimated_eval_tokens": 17696 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is heterogeneous: the soft pairs mostly share only broad subsystem vocabulary (generation, loading, tokenizers, CI, multimodal), but not the same concrete bug or change. I would not merge any of the proposed soft edges, and there is no single canonical issue/PR for the whole set.", - "confidence": 0.91, + "summary": "The cluster is heterogeneous: most items are unrelated bug reports that only share broad subsystem words (tokenization, generation, flash-attn, device/dtype, serving). None of the soft pairs look like the same underlying bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Both are import/runtime failures, but they affect different symbols and failure modes; not the same bug." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "One is config save/load causing generation index errors; the other is a tokenizer AttributeError in tasks." + }, { "left": "issue:44423", "right": "issue:44734", "accept": false, - "reason": "Both are serving-related crashes, but one is a multimodal `'str'.to` error and the other is KV-cache continuation indexing; different failure modes and code paths." + "reason": "Both involve serve, but one crashes on multimodal input conversion and the other on KV-cache continuation indexing." }, { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "Both mention loading/token handling, but BEiT legacy-field loading and BigBirdTokenizer mask-token registration are unrelated bugs." + "reason": "Different components and symptoms: BEiT legacy-field loading vs BigBirdTokenizer special-token registration." }, { "left": "issue:44464", "right": "issue:45584", "accept": false, - "reason": "Both involve generation, but chunked generation with compiled forward and empty-transcription whisper failure after token alignment are different issues." + "reason": "Both are generation-related, but one is compiled forward inconsistency and the other is empty-transcription/chat-template behavior." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "Both are CI failures, but CPU offload device mismatch in bark-small and a stale GraniteSpeech device-override test are not the same bug." + "reason": "Different models and code paths; one is CPU offload device mismatch, the other is a stale CI test override." }, { "left": "issue:43994", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 nonsensical outputs and generic 'unexpected key with position id' regressions are too different in symptom and likely root cause." + "reason": "Different bugs: SigLIP2 wrong outputs vs a broad position-id key warning across many models." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "Qwen2 TP OOM and a PEFT version bump/release issue are unrelated; one is memory pressure, the other dependency metadata." + "reason": "OOM during tensor-parallel model load is unrelated to a PEFT version requirement issue." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "One is embedding dtype changing between train/eval, the other is a resume_from_checkpoint key mismatch; no shared underlying defect." + "reason": "Embedding dtype drift and checkpoint key mismatch are unrelated training/eval issues." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "A Janus image-generation test failure and a missing released PEFT version are unrelated." - }, - { - "left": "issue:44521", - "right": "issue:45290", - "accept": false, - "reason": "Both concern chat/template processing, but all-zero assistant masks for multimodal inputs and tool-call assistant messages with no content are distinct edge cases." + "reason": "A janus image-generation test failure is unrelated to the PEFT version bump." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Flash Attention 2 test failures and MLflow not being reported after job failure are different CI/training issues with different surfaces." + "reason": "FlashAttention test failures and MLFlow reporting on failed jobs are different subsystems and failures." }, { "left": "issue:42490", "right": "issue:43696", "accept": false, - "reason": "Local-path import warnings and GPT-oss CUDA OOM are unrelated; one is path handling, the other memory exhaustion." + "reason": "Import warning on trailing-slash paths is unrelated to a GPT-oss OOM." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both are apply_chat_template issues, but one is multimodal assistant masks and the other is tool-call content handling." }, { "left": "issue:43844", "right": "issue:44964", "accept": false, - "reason": "Gradient growth with HfDeepSpeedConfig/ZeRO-3 and inability to load Phi-4 multimodal are different model/runtime problems." + "reason": "ZeRO-3 gradient growth and Phi-4 multimodal loading are unrelated problems." }, { "left": "issue:28218", "right": "issue:34567", "accept": false, - "reason": "Tokenizer added-space behavior and TrainerState token counting are both token-related but not the same bug." + "reason": "Tokenizer spacing after added tokens is unrelated to TrainerState token-count tracking." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "MPS attention correctness when head dims differ and a PyTorch version check for AuxRequest import are unrelated." + "reason": "Different flex-attention/MPS correctness and version-check issues; no shared code-path bug." }, { "left": "issue:45084", "right": "issue:45520", "accept": false, - "reason": "Non-template node compilation error and flash_attn import key error on Python 3.13 are different failure modes." + "reason": "Compile-time node handling and flash-attn import lookup are unrelated." }, { "left": "issue:43582", "right": "issue:44977", "accept": false, - "reason": "Apple Silicon warmup TypeError and Qwen3.5 flash-attention generation bugs are separate platform/model-specific issues." + "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention output issues are different failures." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Qwen3OmniMoe video-processing ValueError and Gemma 4 mm_token_type_ids defaulting are different multimodal input problems." + "reason": "Video-input processing in Qwen3OmniMoe is not the same as Gemma 4 token-type defaults for text-only fine-tuning." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "TorchScript export GeneratorExp limitation and SigLIP2 zero probabilities are unrelated model/runtime bugs." + "reason": "TorchScript GeneratorExp export failure and SigLIP2 zero-probability outputs are unrelated." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs update after sync_gpus and Qwen3.5 hidden_states output bug are distinct generation path issues." + "reason": "Generation kwargs update after sync_gpus is a different bug from Qwen3.5 hidden-states behavior." }, { - "left": "issue:45072", - "right": "issue:45198", + "left": "issue:37428", + "right": "issue:43957", "accept": false, - "reason": "bfloat16 dtype mismatches in inference and Wav2Vec2 save/tokenization failures do not look like one underlying bug." + "reason": "Missing flash-attention helper import and meta-device model-loading breakage are distinct issues." }, { - "left": "issue:37428", - "right": "issue:43957", + "left": "issue:45072", + "right": "issue:45198", "accept": false, - "reason": "Missing flash_supports_window_size import and meta-device loading regressions are both loading-related but clearly different problems." + "reason": "Bfloat16 dtype mismatches and Wav2Vec2 save/tokenization failures do not share the same underlying bug." }, { "left": "issue:45200", "right": "issue:45823", "accept": false, - "reason": "Gemma 4 token type ids defaulting and Gemma4 PLE device mismatch are separate issues in the same model family, not the same code-path defect." + "reason": "Token-type-id defaults and Gemma4 PLE device mismatch are different problems." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger Kernel not applied with model_init and Qwen3.5 hidden_states output bug are unrelated training/model behavior issues." + "reason": "Liger Kernel not applied with model_init is unrelated to Qwen3.5 output_hidden_states behavior." }, { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "SigLIP2 implementation discrepancy and resume checkpoint key mismatch are different classes of bug with no clear shared root cause." - }, - { - "left": "issue:43295", - "right": "issue:44610", - "accept": false, - "reason": "processor.tokenizer regression with images and OmDet-Turbo input-size mismatch are both multimodal, but not the same defect." - }, - { - "left": "issue:44554", - "right": "issue:45356", - "accept": false, - "reason": "MPS attention correctness and Kimi-K2.5 tokenizer regression are unrelated subsystems." + "reason": "SigLIP2 JAX/HF discrepancy and resume-from-checkpoint key mismatch are unrelated." } ] }, @@ -7249,10 +6993,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:28218", "issue:35141", @@ -7260,7 +7004,6 @@ "issue:38175", "issue:42490", "issue:42915", - "issue:43262", "issue:43278", "issue:43295", "issue:43334", @@ -7287,9 +7030,9 @@ "issue:44466", "issue:44514", "issue:44521", + "issue:44554", "issue:44610", "issue:44792", - "issue:44857", "issue:44898", "issue:44936", "issue:44987", @@ -7299,250 +7042,244 @@ "issue:45200", "issue:45245", "issue:45325", + "issue:45356", "issue:45412", "issue:45563", "issue:45584" ], "soft_pairs": [ + "issue:43295|issue:44610", + "issue:44554|issue:45356", "issue:44898|issue:45412", "issue:44466|issue:45127", - "issue:44792|issue:45563", "issue:43572|issue:44987", + "issue:44792|issue:45563", "issue:37428|issue:43824", "issue:43572|issue:43957", "issue:45200|issue:45325", - "issue:43844|issue:44936", "issue:43295|issue:43450", + "issue:43844|issue:44936", "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:38175|issue:45412", "issue:38175|issue:43493", "issue:44514|issue:44521", "issue:44442|issue:45198", "issue:28218|issue:35141", - "issue:43278|issue:43856", "issue:42490|issue:43493", + "issue:43278|issue:43856", "issue:43653|issue:44112", - "issue:43827|issue:43901", "issue:43450|issue:43575", + "issue:43827|issue:43901", "issue:44206|issue:45584", "issue:45127|issue:45245", - "issue:43819|issue:45083", - "issue:43819|issue:44112", - "issue:43262|issue:43450", - "issue:44610|issue:44857" + "issue:43819|issue:45083" ], - "prepared_review_unit_hash": "b1a9777f9f32995f9da20c3e439b814cbffbc68b1237895b0de7bd0bf24a934b", + "prepared_review_unit_hash": "9cb2039c1dd20c5ddd9fb136ad8c12400b4491ed915f9e424b458496ef22e61d", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36950, - "estimated_input_tokens": 9238, - "estimated_eval_tokens": 18732 + "soft_pair_count": 29, + "serialized_chars": 36673, + "estimated_input_tokens": 9169, + "estimated_eval_tokens": 18594 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the soft pairs share only broad subsystem similarity, not the same underlying bug or change, so I would not merge any of them as duplicates.", + "summary": "These soft edges are mostly false positives: they share broad subsystem or model-family overlap, but not the same concrete bug. No PRs are present. The set is heterogeneous overall, with no strong duplicate cluster.", "confidence": 0.94, - "canonical_issue_reason": null, + "canonical_issue_reason": "Issue 44521 is the closest thing to a cluster anchor because it is open, recent, and has the highest user-facing activity among the remaining items, but the surrounding issues are too heterogeneous to treat it as a true canonical duplicate target.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the most central/active report in the set, but the overall cluster is too diverse for it to serve as a true duplicate canonical.", + "best_issue_reason": "44521 is the best overall representative only in the loose sense of being the most active, general multimodal regression here; it is not a valid dedup target for the other items.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Both are multimodal processor regressions, but one is a processor.tokenizer/image-handling regression and the other is a video/input-size mismatch; different code paths and fixes." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "One is an MPS attention correctness bug; the other is a tokenizer codec/warning regression. No shared underlying defect." + }, { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Different bugs: one is a Perceiver positional-encoding failure, the other is an RT-DETR memory release problem." + "reason": "Perceiver interpolation failure and RT-DETR memory release are unrelated bugs in different models/subsystems." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "Both involve weight serialization/collapse, but the failures are on different code paths and model behaviors." + "reason": "Both involve tied/serialization semantics, but one is inconsistent lm_head serialization by device and the other is LoRA merge collapse after vocab extension; not the same fix." }, { - "left": "issue:44792", - "right": "issue:45563", + "left": "issue:43572", + "right": "issue:44987", "accept": false, - "reason": "A failed Janus image-generation test and a stale paged-generate warning are unrelated symptoms." + "reason": "Both are model-loading regressions, but the reported symptoms and likely causes differ; too little evidence they are the same bug." }, { - "left": "issue:43572", - "right": "issue:44987", + "left": "issue:44792", + "right": "issue:45563", "accept": false, - "reason": "Both are load-time regressions, but one is about missing pad token metadata and the other about a specific model load failure." + "reason": "Janus image-generation test failure and a stale paged-generate warning are distinct generation issues." }, { "left": "issue:37428", "right": "issue:43824", "accept": false, - "reason": "Importing a missing flash-attention helper is unrelated to a missing Qwen2.5-VL class export." + "reason": "Both are ImportErrors, but for different missing symbols in different modules; not the same underlying import breakage." }, { "left": "issue:43572", "right": "issue:43957", "accept": false, - "reason": "Missing pad token metadata and meta-device loading failures are different model-loading bugs." + "reason": "One is a missing pad_token_idx config regression; the other is a meta-device model-loading failure affecting some models. Not the same bug." }, { "left": "issue:45200", "right": "issue:45325", "accept": false, - "reason": "Gemma mm_token_type_ids defaults and Qwen2.5-VL rope-index scaling are separate multimodal issues." + "reason": "Gemma 4 mm_token_type_ids defaulting and Qwen2.5-VL rope-index scaling are separate model-specific correctness issues." }, { - "left": "issue:43844", - "right": "issue:44936", + "left": "issue:43295", + "right": "issue:43450", "accept": false, - "reason": "Training gradient instability with ZeRO-3 is unrelated to trainer.evaluate() failing after train()." + "reason": "Both touch processors, but one is about processor.tokenizer/image routing and the other is batched video output shape; different defects." }, { - "left": "issue:43295", - "right": "issue:43450", + "left": "issue:43844", + "right": "issue:44936", "accept": false, - "reason": "Both concern processor behavior, but one is a regression around processor.tokenizer/images and the other is batched video output shape." + "reason": "Gradient explosion under ZeRO-3 and evaluate() failing after train() are not the same training-state problem." }, { "left": "issue:43334", "right": "issue:43525", "accept": false, - "reason": "Different configs with the same missing-field symptom; the underlying model code paths are not the same." + "reason": "Same symptom class (missing pad_token_id), but different config classes/models and no evidence of a shared root cause." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "An import/export regression and a detokenization bug are not the same underlying issue." + "reason": "An import error for Qwen2.5-VL and a detokenization regression in DeepSeek Coder are unrelated." }, { "left": "issue:43295", "right": "issue:43873", "accept": false, - "reason": "A regression in custom processor usage is unrelated to quantized offloading behavior." + "reason": "Processor-tokenizer regression vs quantization offloading behavior; too different to merge." }, { "left": "issue:43388", "right": "issue:43526", "accept": false, - "reason": "Both affect labels, but one is metric gathering and the other is BeitImageProcessorFast label reduction." + "reason": "Both concern labels, but one drops tuple label elements in gather_for_metrics while the other reduces labels incorrectly in an image processor; not the same path." }, { - "left": "issue:38175", - "right": "issue:45412", + "left": "issue:42915", + "right": "issue:43824", "accept": false, - "reason": "SigLIP2 zero-probabilities and RT-DETR memory cleanup are unrelated model bugs." + "reason": "FP8-config failure in Qwen3MoE and a Qwen2.5-VL import error are unrelated." }, { - "left": "issue:42915", - "right": "issue:43824", + "left": "issue:38175", + "right": "issue:45412", "accept": false, - "reason": "Qwen3Moe FP8 failures and a missing VL class import are different issues." + "reason": "SigLIP2 zero-probability behavior and RT-DETR memory cleanup are entirely different bugs." }, { "left": "issue:38175", "right": "issue:43493", "accept": false, - "reason": "SigLIP2 implementation discrepancy and a different model's JAX/HF discrepancy are not the same bug." + "reason": "Both are SigLIP2-related, but one reports zero probabilities and the other a broader HF-vs-JAX discrepancy; not enough to treat as the same concrete bug." }, { "left": "issue:44514", "right": "issue:44521", "accept": false, - "reason": "Both touch Qwen2_5_VLProcessor.apply_chat_template, but one is a batched padding crash and the other is incorrect assistant masks." + "reason": "Same processor family and similar API surface, but one is a batched padding=False crash and the other is zero assistant masks for multimodal inputs; different failure modes." }, { "left": "issue:44442", "right": "issue:45198", "accept": false, - "reason": "Different tokenizer failures in different models; no shared concrete code-path bug is evident." + "reason": "Different tokenizer/model families and different failure modes: loading FastSpeech2ConformerTokenizer vs save_pretrained/tokenization failures in Wav2Vec2." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing after added tokens and embedding reinitialization on resize are unrelated." + "reason": "Tokenizer spacing after added tokens and embedding reinitialization after resize are separate tokenizer/model-weight bugs." }, { - "left": "issue:43278", - "right": "issue:43856", + "left": "issue:42490", + "right": "issue:43493", "accept": false, - "reason": "A dtype change in evaluation and Qwen3 MoE memory usage are separate training-time problems." + "reason": "Path-with-trailing-slash import warning and SigLIP2 implementation discrepancy are unrelated." }, { - "left": "issue:42490", - "right": "issue:43493", + "left": "issue:43278", + "right": "issue:43856", "accept": false, - "reason": "Local-path trailing-slash import warnings and SigLIP2 implementation discrepancies are unrelated." + "reason": "Training/eval dtype drift and Qwen3 MoE memory inefficiency are different problems." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "A tokenizer special-token registration bug and a stale CI device-override test are not the same issue." + "reason": "BigBirdTokenizer special-token registration and a GraniteSpeech CI device-override test failure do not share the same bug." }, { - "left": "issue:43827", - "right": "issue:43901", + "left": "issue:43450", + "right": "issue:43575", "accept": false, - "reason": "Both are docs-related, but they refer to different pipeline deprecations and different API behavior." + "reason": "Batched video processor shape bug and tensor-parallel OOM while loading a large model are unrelated." }, { - "left": "issue:43450", - "right": "issue:43575", + "left": "issue:43827", + "right": "issue:43901", "accept": false, - "reason": "Batched video processor shape bugs and Qwen2-57B TP OOM are unrelated." + "reason": "Both are docs regressions about pipelines, but they refer to different pipeline APIs and deprecations; not duplicates." }, { "left": "issue:44206", "right": "issue:45584", "accept": false, - "reason": "An unsupported feature-extractor argument and a Whisper empty-transcription regression are different bugs." + "reason": "Unsupported center argument in a feature extractor and Whisper empty-transcription failure after align_special_tokens are different audio bugs." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA merging with extended vocab and a categorical limit runtime error have no common underlying code path." + "reason": "LoRA/tied-weights collapse after vocab extension is unrelated to the 2^24 category limit runtime error." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "Two different helper functions in qwen3_omni_moe are involved, so these are not the same defect." - }, - { - "left": "issue:43819", - "right": "issue:44112", - "accept": false, - "reason": "A DAC latent/STE mismatch and a GraniteSpeech CI test issue are unrelated." - }, - { - "left": "issue:43262", - "right": "issue:43450", - "accept": false, - "reason": "Audio apply_chat_template sampling-rate defaults and batched video shape outputs are separate processor bugs." - }, - { - "left": "issue:44610", - "right": "issue:44857", - "accept": false, - "reason": "OmDet-Turbo image-size mismatch and LwDetrImageLoss AMP/CUDA failure are different model-specific problems." + "reason": "DAC latent/STE mismatch and qwen3_omni_moe feature-length helper behavior are unrelated code paths." } ] }, @@ -7561,10 +7298,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:29127", "issue:29942", @@ -7572,10 +7309,11 @@ "issue:37428", "issue:38175", "issue:39692", - "issue:42490", + "issue:43262", "issue:43278", "issue:43335", "issue:43425", + "issue:43450", "issue:43504", "issue:43526", "issue:43550", @@ -7585,7 +7323,6 @@ "issue:43720", "issue:43819", "issue:43825", - "issue:43854", "issue:43931", "issue:44112", "issue:44206", @@ -7596,15 +7333,14 @@ "issue:44462", "issue:44493", "issue:44561", + "issue:44610", "issue:44743", "issue:44779", "issue:44855", "issue:44857", - "issue:44977", "issue:45072", "issue:45083", "issue:45200", - "issue:45229", "issue:45290", "issue:45310", "issue:45381", @@ -7616,6 +7352,9 @@ "issue:45859" ], "soft_pairs": [ + "issue:43262|issue:43450", + "issue:43819|issue:44112", + "issue:44610|issue:44857", "issue:37428|issue:43425", "issue:43335|issue:43550", "issue:43606|issue:45083", @@ -7623,12 +7362,12 @@ "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:44360|issue:44561", "issue:29942|issue:32090", - "issue:43611|issue:43931", "issue:44206|issue:45823", + "issue:43611|issue:43931", "issue:39692|issue:43526", "issue:43335|issue:43653", "issue:43819|issue:44493", @@ -7644,254 +7383,258 @@ "issue:44448|issue:44779", "issue:38175|issue:44493", "issue:43335|issue:45072", + "issue:43335|issue:44112", "issue:44462|issue:44561", - "issue:43720|issue:44112", "issue:44561|issue:44779", - "issue:43335|issue:44112", - "issue:44977|issue:45229", - "issue:42490|issue:43854" + "issue:43720|issue:44112" ], - "prepared_review_unit_hash": "f82bb94aa980ddac020333cb79f8fa90141d7603f2ea2d472a11c38b12ea8eb4", + "prepared_review_unit_hash": "6fd9d30c8f8c0aeffc2e20a26b81b7d0f1cead8db6e9f43239e1f0011357da02", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 34, - "serialized_chars": 37857, - "estimated_input_tokens": 9465, - "estimated_eval_tokens": 19186 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37677, + "estimated_input_tokens": 9420, + "estimated_eval_tokens": 19096 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is still mostly heterogeneous. The only clear duplicate pair is the Qwen3.5 MoE `from_pretrained` report: issue:45310 and issue:45478 share the same title and underlying failure mode, with 45310 being the earlier, more detailed report and 45478 a later repost.", - "confidence": 0.94, - "canonical_issue_reason": "issue:45310 is the better canonical issue because it is earlier and has the longer, more detailed report for the same Qwen3.5 MoE `from_pretrained` error; issue:45478 appears to be a later repost with the same title.", + "summary": "This set is mostly unrelated issue reports; there is one clear duplicate pair: the Qwen3.5 MoE `from_pretrained` regression in issue:45310 and issue:45478. The rest share broad subsystem keywords but describe different bugs/code paths.", + "confidence": 0.95, + "canonical_issue_reason": "issue:45310 is the earlier, fuller report of the same Qwen3.5 MoE `from_pretrained` regression; issue:45478 is a near-identical follow-up.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the strongest issue candidate overall for the duplicate cluster because it most clearly captures the underlying bug and predates issue:45478, which looks like a shorter follow-up repost.", + "best_issue_reason": "issue:45310 is the best canonical anchor because it captures the duplicated bug clearly and predates the later duplicate report.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Different processors and failures: audio chat template sampling-rate default vs batched video shape bug." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "Different models and code paths: DAC latent/STE mismatch vs GraniteSpeech CI device override test." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Different components and symptoms: processor input size mismatch vs LwDetr loss AMP crash." + }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "Both are runtime/compatibility failures, but they point to different missing-symbol vs. torch-version problems." + "reason": "One is an import error for a flash-attn helper; the other is broad Torch 2.10 compatibility." }, { "left": "issue:43335", "right": "issue:43550", "accept": false, - "reason": "SwitchTransformers sparse-layer initialization and Bamba torch.compile/SDPA failures are different code paths." + "reason": "Different model families and bugs: SwitchTransformers config layer creation vs Bamba torch.compile/SDPA failure." }, { "left": "issue:43606", "right": "issue:45083", "accept": false, - "reason": "Bark CPU-offload device mismatch is unrelated to the qwen3_omni_moe feature-length helper bug." + "reason": "CPU offload device mismatch for Bark vs a helper length-calculation bug in qwen3_omni_moe." }, { "left": "issue:45290", "right": "issue:45381", "accept": false, - "reason": "Chat-template tool-call handling and Qwen2.5-VL video position IDs are distinct issues." + "reason": "Different failures: chat template with tool calls vs Qwen2.5-VL video position IDs." }, { "left": "issue:44448", "right": "issue:44743", "accept": false, - "reason": "Pegasus output drift and Qwen3.5 recurrent-state reset are separate model regressions." + "reason": "Pegasus v4/v5 output regression is unrelated to Qwen recurrent-state reset logic." }, { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "LwDetr AMP/CUDA crash is not the same as D-FINE's missing auxiliary losses when denoising is off." + "reason": "Different training-time failures: float16 AMP crash in LwDetrImageLoss vs missing auxiliary losses in D-FINE." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma 4 token-type defaults and flash_attention `s_aux=None` crashes are different failures." - }, - { - "left": "issue:44360", - "right": "issue:44561", - "accept": false, - "reason": "DSA indexer activation behavior and removal of `is_torch_fx_available` breaking remote-code models are unrelated." + "reason": "Gemma4 `mm_token_type_ids` defaulting issue is unrelated to flash_attention `s_aux=None` crash." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "Embedding dtype regression in evaluate is not the same as a pipeline error-message issue." + "reason": "Embedding dtype drift during evaluate is not the same as the v5 pipeline translation-task error message bug." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different compatibility breaks." + "reason": "Both are import errors, but for different symbols and causes (`_flash_supports_window_size` vs `HybridCache`)." }, { - "left": "issue:29942", - "right": "issue:32090", + "left": "issue:44360", + "right": "issue:44561", "accept": false, - "reason": "Flash Attention 2 test failures and `_gpu_broadcast_one` NoneType handling are separate problems." + "reason": "DSA indexer ReLU discussion is unrelated to removal of `is_torch_fx_available` breaking trust_remote_code models." }, { - "left": "issue:43611", - "right": "issue:43931", + "left": "issue:29942", + "right": "issue:32090", "accept": false, - "reason": "Base-model-prefix loading breakage and Qwen3-VL weight-shape mismatch are not the same bug." + "reason": "Flash Attention 2 test failures and Trainer `_gpu_broadcast_one` NoneType errors are different issues." }, { "left": "issue:44206", "right": "issue:45823", "accept": false, - "reason": "Unsupported `center` argument in a feature extractor is unrelated to Gemma4 device mismatch during forward." + "reason": "Unsupported `center` arg in LasrFeatureExtractor is unrelated to Gemma4 PLE device mismatch under `device_map=\"auto\"`." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Generic `base_model_prefix` loading breakage is not the same as Qwen3-VL weight-shape mismatch." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "SigLIP2 docs example errors and BeitImageProcessorFast `reduce_labels` behavior are different artifacts." + "reason": "SigLIP2 docs/model mismatch and quantization failure is unrelated to BeitImageProcessorFast `reduce_labels` truncation." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "SwitchTransformers sparse-layer creation and BigBirdTokenizer special-token registration are unrelated." + "reason": "SwitchTransformers sparse-layer config bug is unrelated to BigBirdTokenizer mask-token decode behavior." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "DAC latent-forward mismatch and unexpected position-id keys are different regressions." + "reason": "DAC forward/latent mismatch is unrelated to the position-id key issue affecting many models." }, { "left": "issue:43550", "right": "issue:44112", "accept": false, - "reason": "Bamba SDPA/torch.compile behavior and GraniteSpeech CI stale-device testing are not the same bug." + "reason": "Bamba torch.compile SDPA failure is unrelated to the GraniteSpeech CI stale device override test." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "SwitchTransformers sparse-layer initialization and Beit legacy-field loading failure are unrelated." + "reason": "SwitchTransformers layer-count config bug is unrelated to Beit pretrained preset loading with legacy fields." }, { "left": "issue:44855", "right": "issue:45083", "accept": false, - "reason": "Python 3.13 `IndentationError` from scripted code is unrelated to the qwen3_omni_moe helper issue." + "reason": "Python 3.13 `IndentationError` in DebertaV2 import is unrelated to qwen3_omni_moe feature-length helper behavior." }, { "left": "issue:45310", "right": "issue:45478", "accept": true, - "reason": "Same title, same model family, and same `from_pretrained` error; 45478 looks like a later repost of 45310." + "reason": "Same Qwen3.5 MoE `from_pretrained` regression, with matching title and failure mode." }, { "left": "issue:43335", - "right": "issue:45083", + "right": "issue:45072", "accept": false, - "reason": "SwitchTransformers sparse-layer creation and qwen3_omni_moe helper behavior are different issues." + "reason": "SwitchTransformers sparse-layer creation is unrelated to the bfloat16 dtype mismatch in inference." }, { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "LayoutLMv3 message clarity and Trainer `_gpu_broadcast_one` NoneType failure are unrelated." + "reason": "LayoutLMv3 box-clarity error message and Trainer `_gpu_broadcast_one` TypeError are unrelated." }, { "left": "issue:45588", "right": "issue:45859", "accept": false, - "reason": "Both touch Qwen3.5/MoE/offload, but they describe different failure modes and code paths." + "reason": "Both involve Qwen3_5/MoE/offload, but one is a flash_attention `s_aux=None` crash and the other is a rotary-embedding CPU-offload incompatibility." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "Docs example failures are not the same as runtime unexpected key/position-id behavior." + "reason": "SigLIP2 docs/quantization issue is unrelated to the position-id key regression." }, { "left": "issue:44292", "right": "issue:45520", "accept": false, - "reason": "Qwen-3-8B-NVFP4 runtime failure and Python 3.13 flash-attn import KeyError are unrelated." + "reason": "Qwen-3-8B-NVFP4 runtime failure is not the same as the Python 3.13 `flash_attn` import KeyError." }, { "left": "issue:44448", "right": "issue:44779", "accept": false, - "reason": "Pegasus output differences and Deepseek tokenizer regressions are different bugs." + "reason": "Pegasus output differences and DeepSeek tokenizer regressions are different bugs." }, { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 and unexpected position-id keys are different symptoms and subsystems." + "reason": "SigLIP2 zero-probabilities bug is unrelated to the position-id key regression." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "SwitchTransformers sparse-layer creation and bfloat16 dtype mismatches are unrelated." + "reason": "Same as the other SwitchTransformers/dtype pair: unrelated bugs in the same broad area." }, { - "left": "issue:44462", - "right": "issue:44561", + "left": "issue:43335", + "right": "issue:44112", "accept": false, - "reason": "Tokenizer repository-file selection and removal of a helper function are different problems." + "reason": "SwitchTransformers config bug and GraniteSpeech CI device override test are unrelated." }, { - "left": "issue:43720", - "right": "issue:44112", + "left": "issue:44462", + "right": "issue:44561", "accept": false, - "reason": "BitNet packed-weight loading and a GraniteSpeech CI device-override test do not describe the same bug." + "reason": "Tokenizer.json loading behavior and `is_torch_fx_available` removal are unrelated regressions." }, { "left": "issue:44561", "right": "issue:44779", "accept": false, - "reason": "A removed helper breaking remote-code models and a Deepseek tokenizer regression are unrelated." + "reason": "Trust-remote-code breakage from helper removal is unrelated to DeepSeek tokenizer output changes." }, { - "left": "issue:43335", + "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "SwitchTransformers sparse-layer creation and GraniteSpeech CI device-override failure are different issues." - }, - { - "left": "issue:44977", - "right": "issue:45229", - "accept": false, - "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU OOM are not the same underlying problem." - }, - { - "left": "issue:42490", - "right": "issue:43854", - "accept": false, - "reason": "Trailing-slash import warning and GLM-4.7-Flash unit-test load failure are different loading issues." + "reason": "BitNet accelerate unpacking bug is unrelated to the GraniteSpeech stale device override test." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The duplicate call on issue:45310/45478 is plausible, but the justification overstates the evidence: 45478 actually has more discussion activity than 45310, so it is not grounded to say 45310 has 'slightly more discussion/context.' A safer statement would be that 45310 is earlier and slightly longer, while 45478 appears to be a later repost with the same title. The rest of the soft-edge rejections look conservative." + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The one accepted duplicate pair (issue:45310 / issue:45478) is well-supported by matching titles and the same Qwen3.5 MoE from_pretrained regression, and the rest of the soft-edge rejections are phrased cautiously without overstating evidence." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -7904,15 +7647,14 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:10000", "issue:15354", "issue:28218", - "issue:29127", "issue:29942", "issue:32090", "issue:33357", @@ -7931,6 +7673,7 @@ "issue:43606", "issue:43701", "issue:43723", + "issue:43854", "issue:43873", "issue:43927", "issue:43976", @@ -7958,226 +7701,245 @@ "issue:45803" ], "soft_pairs": [ + "issue:44977|issue:45229", + "issue:42490|issue:43854", "issue:40444|issue:43526", "issue:34689|issue:35141", "issue:44448|issue:44977", "issue:43606|issue:44857", "issue:43723|issue:44554", "issue:44857|issue:45072", - "issue:44977|issue:45563", "issue:28218|issue:32090", + "issue:44977|issue:45563", "issue:43927|issue:45698", - "issue:44568|issue:45491", "issue:43701|issue:45083", + "issue:44568|issue:45491", "issue:43550|issue:45083", - "issue:45198|issue:45803", "issue:37428|issue:44987", + "issue:45198|issue:45803", "issue:29942|issue:35141", "issue:45372|issue:45588", - "issue:45459|issue:45712", "issue:43873|issue:44493", "issue:32090|issue:33357", + "issue:45459|issue:45712", "issue:43873|issue:45229", "issue:45245|issue:45563", "issue:43412|issue:45588", - "issue:41720|issue:45229", "issue:43278|issue:43329", + "issue:41720|issue:45229", "issue:10000|issue:15354", "issue:43976|issue:45440", - "issue:45372|issue:45406", "issue:42490|issue:43575", - "issue:28218|issue:29127" + "issue:45372|issue:45406" ], - "prepared_review_unit_hash": "520a581f8117e9e5129cd400c489b7d0c44e16462206dc8a13ed6c861c941775", + "prepared_review_unit_hash": "6c1dda20d1cfded88b308eefeb07a2750a3a65dde9cac36b07ff6983183be230", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 36076, - "estimated_input_tokens": 9019, - "estimated_eval_tokens": 18294 + "soft_pair_count": 30, + "serialized_chars": 36341, + "estimated_input_tokens": 9086, + "estimated_eval_tokens": 18428 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a set of unrelated Transformer bugs that only share broad subsystem similarity (tokenizers, multimodal, loading, attention, offload). I did not find any soft pair that looks like the same underlying defect closely enough to merge.", - "confidence": 0.9, - "canonical_issue_reason": "issue:43873 has the highest engagement and inbound references, making it the most defensible representative issue if a single canonical item is needed.", + "summary": "This cluster is very heterogeneous: most items are unrelated issues spanning tokenization, model loading, precision/device-mismatch, attention kernels, and multimodal processor bugs. None of the soft-edge pairs look like true duplicates of the same underlying bug/change.", + "confidence": 0.95, + "canonical_issue_reason": "Issue #42490 is the clearest generic loading-path bug in the set, with a reproducible and narrowly scoped root cause (local model path normalization trailing slash).", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the strongest standalone issue in the set: high discussion activity, multiple inbound references, and a broad runtime/infrastructure impact.", + "best_issue_reason": "Issue #42490 is a good representative because it is a concrete, user-facing loading regression with a clear failure mode and likely straightforward fixability.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Different failure modes and subsystems: flash-attention generation behavior vs multi-GPU CUDA OOM." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Both are loading-related, but one is a path-trailing-slash warning and the other is a specific model-load failure for a named checkpoint." + }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "Both are multimodal/processor-related, but one is an IterableDataset multi-image failure and the other is a BeitImageProcessorFast label-reduction bug; different code paths and symptoms." + "reason": "Unrelated areas: multimodal iterable dataset finetuning vs BeitImageProcessorFast label reduction." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Model-loading failure for Llama 3.2 vision is not the same defect as token embedding reinitialization after resize when tie_word_embeddings is false." + "reason": "Model loading regression vs token-embedding resize/post-init reinitialization; not the same bug." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Different models and failure modes: Pegasus output drift across versions versus Qwen3.5 flash-attention generation problems." + "reason": "Different models and errors; Pegasus output drift across versions is not the same as Qwen3.5 flash-attention generation failure." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "CPU offload device mismatch for bark-small is unrelated to the float16 AMP crash in LwDetrImageLoss." + "reason": "CPU offload device mismatch is a different concrete bug than float16 AMP crashes in LWDETR loss." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are separate code paths and bugs." + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are unrelated code paths." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Both mention dtype/precision, but one is a loss crash under AMP and the other is a bfloat16 inference mismatch in different models." + "reason": "Both mention dtype/precision, but they affect different models and different execution paths; not one bug." }, { - "left": "issue:44977", - "right": "issue:45563", + "left": "issue:28218", + "right": "issue:32090", "accept": false, - "reason": "Flash-attention generation failure and a stale warning about num_return_sequences are unrelated." + "reason": "Tokenizer spacing after added token is unrelated to Trainer broadcast TypeError." }, { - "left": "issue:28218", - "right": "issue:32090", + "left": "issue:44977", + "right": "issue:45563", "accept": false, - "reason": "Tokenizer spacing behavior and Trainer GPU broadcast NoneType errors are not the same underlying issue." + "reason": "Flash-attention generation failure vs a stale warning in paged generate(); different underlying issues." }, { "left": "issue:43927", "right": "issue:45698", "accept": false, - "reason": "Both involve save/load behavior, but one loses custom token IDs in config while the other loads the wrong custom module after save_pretrained." + "reason": "Both involve save/load flows, but one loses custom token IDs in config and the other loads the wrong custom module; distinct defects." }, { - "left": "issue:44568", - "right": "issue:45491", + "left": "issue:43701", + "right": "issue:45083", "accept": false, - "reason": "Missing BOS/EOS insertion in a tokenizer is unrelated to Gemma3 NaN embeddings from sliding-window attention." + "reason": "Checkpoint key mismatch is unrelated to the qwen3_omni_moe feature-length helper behavior." }, { - "left": "issue:43701", - "right": "issue:45083", + "left": "issue:44568", + "right": "issue:45491", "accept": false, - "reason": "Checkpoint key mismatch and a qwen3_omni_moe helper-function bug are different defects." + "reason": "Tokenizer special-token handling and Gemma3 NaN embeddings are different bugs." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba-9B-v2 does not match the qwen3_omni_moe length helper issue." + "reason": "torch.compile/SDPA failure for Bamba is unrelated to qwen3_omni_moe feature-length computation." }, { - "left": "issue:45198", - "right": "issue:45803", + "left": "issue:37428", + "right": "issue:44987", "accept": false, - "reason": "Wav2Vec2 save/tokenization failure and FuyuBatchFeature's bare except swallowing errors are related to tokenization but not the same concrete bug." + "reason": "Both are load-time issues around flash attention, but the concrete failures and target code paths differ." }, { - "left": "issue:37428", - "right": "issue:44987", + "left": "issue:45198", + "right": "issue:45803", "accept": false, - "reason": "Both involve loading/import issues, but there is no evidence they share the same failing code path or root cause." + "reason": "Wav2Vec2 save/tokenization failure and a bare-except swallowing errors in Fuyu are not the same defect." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Failing Flash Attention 2 tests are not the same defect as embedding reinitialization after resize." + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization after resize." }, { "left": "issue:45372", "right": "issue:45588", "accept": false, - "reason": "Gemma4 processor loading breaks because of a missing mistral_common symbol; flash_attention.py crashes on s_aux=None in sink-less models. Different dependency and runtime bugs." - }, - { - "left": "issue:45459", - "right": "issue:45712", - "accept": false, - "reason": "Tokenizer exception masking from protobuf handling is unrelated to leftover dummy class cleanup and dir(transformers) leakage." + "reason": "Gemma4 processor loading fails due to a missing dependency import, while the other is a flash-attention AttributeError on sink-less models." }, { "left": "issue:43873", "right": "issue:44493", "accept": false, - "reason": "Quantization/offloading behavior and unexpected position-id key warnings are different problems." + "reason": "Quantization/offloading behavior and unexpected position-id keys are distinct problems." }, { "left": "issue:32090", "right": "issue:33357", "accept": false, - "reason": "Trainer _gpu_broadcast_one NoneType errors and MacOS bus errors on a CLIP model are separate runtime failures." + "reason": "Trainer broadcast NoneType error is unrelated to a MacOS bus error with a CLIP model." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer protobuf error handling and leftover dummy classes are unrelated repository hygiene/runtime issues." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "Both touch memory/offload concerns, but one is a quantization offloading bug and the other is a Gemma4 multi-GPU OOM; not the same concrete issue." + "reason": "Quantization offloading behavior is not the same as a multi-GPU OOM during Gemma4 inference." }, { - "left": "issue:41720", - "right": "issue:45229", + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-cardinality limit error and stale generate warning are unrelated." + }, + { + "left": "issue:43412", + "right": "issue:45588", "accept": false, - "reason": "CUDA assert with auto device mapping on Qwen3 is a different failure mode from multi-GPU OOM on Gemma4 31B." + "reason": "Executorch export failures and flash-attention sinkless-model AttributeError are different code paths." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Embedding dtype regression in eval is unrelated to an undefined-variable bug in the video multimodal token counting path." + "reason": "Embedding dtype drift in evaluation is unrelated to the undefined video-branch helper issue." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Auto device mapping cudaErrorAssert and CUDA OOM are different failure classes." }, { "left": "issue:10000", "right": "issue:15354", "accept": false, - "reason": "German DistilBertModel issue and GeneratorExp unsupported by torch.jit.script are unrelated legacy bugs." + "reason": "German DistilBert issue and torch.jit generator-expression export issue are unrelated and very old." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "Python version compatibility and DeepseekV3MoE divergence are not the same issue." - }, - { - "left": "issue:45372", - "right": "issue:45406", - "accept": false, - "reason": "Both concern Gemma4 processor loading, but one fails on an import from mistral_common and the other crashes in serve due to a missing _tokenizer attribute; insufficient evidence of a shared root cause." + "reason": "Python version compatibility issue is unrelated to DeepSeekV3MoE divergence from remote implementation." }, { "left": "issue:42490", "right": "issue:43575", "accept": false, - "reason": "Local-path import warning and Qwen2-57B-A14B-Instruct tensor-parallel OOM are unrelated." + "reason": "Local-path loading warning is unrelated to tensor-parallel OOM on a large Qwen model." }, { - "left": "issue:28218", - "right": "issue:29127", + "left": "issue:45372", + "right": "issue:45406", "accept": false, - "reason": "Tokenizer spacing behavior and LayoutLMv3 box validation error messages are different bugs." + "reason": "Gemma4 processor import failure and Gemma4Processor missing _tokenizer in serve are different concrete failures." } ] }, @@ -8196,12 +7958,13 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:25251", + "issue:28218", "issue:29127", "issue:29942", "issue:30064", @@ -8221,13 +7984,11 @@ "issue:43421", "issue:43653", "issue:43756", - "issue:43824", "issue:43873", "issue:43994", "issue:44186", "issue:44206", "issue:44265", - "issue:44279", "issue:44361", "issue:44448", "issue:44451", @@ -8252,6 +8013,7 @@ ], "soft_pairs": [ "issue:43065|issue:43994", + "issue:28218|issue:29127", "issue:43065|issue:45412", "issue:45372|issue:45459", "issue:44857|issue:45588", @@ -8259,52 +8021,51 @@ "issue:43653|issue:44743", "issue:45588|issue:45823", "issue:43278|issue:43381", - "issue:44206|issue:44479", "issue:25251|issue:32090", + "issue:44206|issue:44479", "issue:43994|issue:45412", "issue:44186|issue:45198", "issue:43066|issue:44462", - "issue:44451|issue:45520", "issue:44361|issue:45198", + "issue:44451|issue:45520", "issue:42915|issue:42994", "issue:44871|issue:44977", "issue:44265|issue:45198", "issue:43756|issue:45440", "issue:29942|issue:30064", "issue:43421|issue:45491", - "issue:43257|issue:43278", "issue:33357|issue:39692", + "issue:43257|issue:43278", "issue:29127|issue:34567", - "issue:44610|issue:45412", "issue:32090|issue:33290", "issue:42490|issue:43873", - "issue:45440|issue:45593", - "issue:43824|issue:44279" + "issue:44610|issue:45412", + "issue:45440|issue:45593" ], - "prepared_review_unit_hash": "bf0336af5cac260dd17f286c01e3f8ff8114fbf089afae3580a04245d3d85107", + "prepared_review_unit_hash": "8f232ed4bae1f726392dbc8e96089e6056012ec297a05f53016c5f5789bc8f1b", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 36354, - "estimated_input_tokens": 9089, - "estimated_eval_tokens": 18434 + "serialized_chars": 35789, + "estimated_input_tokens": 8948, + "estimated_eval_tokens": 18152 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the soft pairs are all false positives across unrelated tokenizer, model, trainer, quantization, and documentation bugs.", - "confidence": 0.97, + "summary": "The items are a broad mix of unrelated tokenizer, loading, training, quantization, and vision bugs. The soft pairs mostly share only broad subsystem overlap, so none look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.96, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -8314,175 +8075,175 @@ "left": "issue:43065", "right": "issue:43994", "accept": false, - "reason": "Different model bugs: a dummy Conv2d in Sam3PixelDecoder vs SigLIP2 producing bad outputs through AutoModel/pipeline." + "reason": "Different models and failure modes: Sam3PixelDecoder dummy Conv2d vs SigLIP2 bad AutoModel/pipeline output." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Tokenizer spacing bug vs LayoutLMv3 error-message clarity issue; unrelated root causes." }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "Unrelated failures: Sam3PixelDecoder dummy layer vs RT-DETR model memory not being released." + "reason": "Sam3PixelDecoder placeholder layer is unrelated to RT-DETR memory not being released." }, { "left": "issue:45372", "right": "issue:45459", "accept": false, - "reason": "Different import paths and causes: Gemma 4 processor loading breaks on ReasoningEffort import, while this is a protobuf-related tokenizer error." + "reason": "Gemma 4 processor import failure and protobuf error masking are separate tokenizer-loading problems." }, { "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "Different code paths: LwDetrImageLoss AMP/CUDA crash vs flash_attention integration failing on s_aux=None." + "reason": "LwDetr float16 AMP crash is unrelated to flash-attention s_aux=None handling." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Both are version-regression reports, but one is generation output drift for Pegasus and the other is lm_head serialization/tied-weights behavior." + "reason": "Both are v5 regressions, but one is generation-output drift and the other is tied-weight serialization inconsistency." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "Tokenizer special-token decode bug vs Qwen3.5 recurrent-state reset in cache handling; not the same defect." + "reason": "BigBirdTokenizer special-token decode bug is unrelated to Qwen recurrent-state reset logic." }, { "left": "issue:45588", "right": "issue:45823", "accept": false, - "reason": "Different models and bugs: flash_attention crashes on sink-less models, while Gemma4 has a device-mapping mismatch." + "reason": "Both involve Gemma-related code, but one is a flash-attention AttributeError and the other is a device-map forward mismatch." }, { "left": "issue:43278", "right": "issue:43381", "accept": false, - "reason": "One is a dtype regression in eval, the other is a gradient-checkpointing restriction in eval mode." + "reason": "Eval-mode dtype change and gradient-checkpointing-in-eval are distinct issues." }, { - "left": "issue:44206", - "right": "issue:44479", + "left": "issue:25251", + "right": "issue:32090", "accept": false, - "reason": "Unsupported center argument in a feature extractor is unrelated to a video-input regression in Qwen VL models." + "reason": "Pipeline top_k nesting regression is unrelated to Trainer NoneType broadcast failure." }, { - "left": "issue:25251", - "right": "issue:32090", + "left": "issue:44206", + "right": "issue:44479", "accept": false, - "reason": "Pipeline top_k nesting change and Trainer _gpu_broadcast_one NoneType error are unrelated subsystems and failures." + "reason": "Unsupported feature arg in LasrFeatureExtractor does not match the Qwen video-input regression." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 bad outputs and RT-DETR memory leak are different model bugs with no shared code path." + "reason": "SigLIP2 inference regression is unrelated to RT-DETR memory cleanup." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "LayoutLMv2 tokenizer crashes on NER/padding inputs, while Wav2Vec2 has save_pretrained/tokenization failure." + "reason": "LayoutLMv2 tokenizer NER/padding crash and Wav2Vec2 save/tokenization failure are different code paths." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Both involve tokenizer loading/serialization, but one is decoder-type mismatch in v5 and the other is AutoTokenizer ignoring tokenizer.json." + "reason": "Wrong tokenizer decoder type and ignoring tokenizer.json are separate tokenizer-loading behaviors." }, { - "left": "issue:44451", - "right": "issue:45520", + "left": "issue:44361", + "right": "issue:45198", "accept": false, - "reason": "ScandiBERT loading failure is unrelated to the Python 3.13 flash_attn import_utils KeyError." + "reason": "MLuke tokenizer AttributeError is unrelated to Wav2Vec2 save_pretrained/tokenization failure." }, { - "left": "issue:44361", - "right": "issue:45198", + "left": "issue:44451", + "right": "issue:45520", "accept": false, - "reason": "MLukeTokenizer task AttributeError and Wav2Vec2 tokenization/save_pretrained failure are different bugs." + "reason": "Model load failure for ScandiBERT and flash_attn KeyError on Python 3.13 are unrelated." }, { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "Quantization load failure for Qwen3 MoE with FineGrainedFP8Config is distinct from quantized model saving failure." + "reason": "Qwen3Moe FP8 config failure and quantized-model saving failure are both quantization-related but different bugs." }, { "left": "issue:44871", "right": "issue:44977", "accept": false, - "reason": "Gemma-3 eos_token_id config inconsistency is unrelated to Qwen3.5 flash-attention generation problems." + "reason": "EOS config mismatch and flash-attention generation regression are unrelated." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "torch.export failure with torch_compilable_check is unrelated to Wav2Vec2 tokenizer/save_pretrained issues." + "reason": "torch.export failure with torch_compilable_check is unrelated to Wav2Vec2 save/tokenization problems." }, { "left": "issue:43756", "right": "issue:45440", "accept": false, - "reason": "Different model implementations: Smollm3 RoPE-layer mismatch vs DeepseekV3MoE divergence from remote implementation." + "reason": "Different model implementations and defects: RoPE-layer drop vs DeepseekV3MoE divergence." }, { "left": "issue:29942", "right": "issue:30064", "accept": false, - "reason": "Flash Attention 2 test failures and void segmentation map processing are unrelated." + "reason": "Flash Attention 2 test failures are unrelated to void segmentation map processing." }, { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime special-token post-processor update bug vs Gemma3 NaN embeddings on mixed-length GPU batches are different issues." - }, - { - "left": "issue:43257", - "right": "issue:43278", - "accept": false, - "reason": "Qwen3 MoE conversion with accelerate/deepspeed and embedding dtype drift in eval are unrelated." + "reason": "Runtime post-processor update bug and Gemma3 NaN embeddings are unrelated." }, { "left": "issue:33357", "right": "issue:39692", "accept": false, - "reason": "MacOS CLIP bus error and SigLIP2 doc-example errors/quantization failure do not describe the same underlying bug." + "reason": "MacOS bus error on CLIP model load is unrelated to SigLIP2 documentation-example mistakes." }, { - "left": "issue:29127", - "right": "issue:34567", + "left": "issue:43257", + "right": "issue:43278", "accept": false, - "reason": "LayoutLMv3 error-message clarity and TrainerState token counter not updating are unrelated." + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed is unrelated to BF16-to-FP32 eval dtype drift." }, { - "left": "issue:44610", - "right": "issue:45412", + "left": "issue:29127", + "right": "issue:34567", "accept": false, - "reason": "OmDet-Turbo processor size mismatch and RT-DETR memory release problems are distinct." + "reason": "LayoutLMv3 error-message clarity and TrainerState token counter updates are unrelated." }, { "left": "issue:32090", "right": "issue:33290", "accept": false, - "reason": "Trainer NoneType broadcast error and DeepSpeed/Adafactor OOM are different failure modes." + "reason": "Trainer broadcast TypeError and Adafactor+deepspeed OOM are distinct training issues." }, { "left": "issue:42490", "right": "issue:43873", "accept": false, - "reason": "Local-path trailing-slash import warning is unrelated to quantization offloading behavior." + "reason": "Trailing-slash local model import warning is unrelated to quantization offloading behavior." }, { - "left": "issue:45440", - "right": "issue:45593", + "left": "issue:44610", + "right": "issue:45412", "accept": false, - "reason": "DeepseekV3MoE implementation divergence and D-FINE auxiliary-loss omission are different model bugs." + "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR memory retention." }, { - "left": "issue:43824", - "right": "issue:44279", + "left": "issue:45440", + "right": "issue:45593", "accept": false, - "reason": "Qwen2.5 VL import error is not the same concrete bug as a generic transformers dependency issue." + "reason": "DeepseekV3MoE implementation divergence and D-FINE auxiliary-loss omission are different model bugs." } ] }, @@ -8501,10 +8262,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:29127", "issue:29942", @@ -8525,18 +8286,19 @@ "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:44625", "issue:44743", "issue:44811", "issue:44857", @@ -8547,15 +8309,15 @@ "issue:45245", "issue:45372", "issue:45440", - "issue:45479", "issue:45491", + "issue:45584", "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", @@ -8565,229 +8327,221 @@ "issue:43526|issue:44186", "issue:29127|issue:33357", "issue:43334|issue:43531", + "issue:44625|issue:45584", "issue:44977|issue:45245", "issue:29127|issue:35141", "issue:44464|issue:45491", - "issue:44442|issue:45072", "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:43575|issue:43701", "issue:44743|issue:44811", + "issue:43441|issue:45588", "issue:43232|issue:43388", - "issue:43575|issue:43701", "issue:43646|issue:44077", "issue:43761|issue:44079", "issue:43575|issue:44387", - "issue:45003|issue:45440", - "issue:43723|issue:45479", - "issue:44442|issue:45803", - "issue:43761|issue:44188" + "issue:45003|issue:45440" ], - "prepared_review_unit_hash": "c045f41cb130e5f3765fff2ec841f8f08dfa8aaef1c59f226f3200b926418f7e", + "prepared_review_unit_hash": "cd69876bda4584e3eae62d9a3a1df6bfda0eb8b70d8926057462ec7ad151d05b", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36586, - "estimated_input_tokens": 9147, - "estimated_eval_tokens": 18550 + "soft_pair_count": 28, + "serialized_chars": 36134, + "estimated_input_tokens": 9034, + "estimated_eval_tokens": 18324 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is heterogeneous: these are not duplicate reports, but unrelated regressions and edge cases across tokenizers, generation, model loading, attention kernels, and multimodal processors. No soft pair looks safe to merge as the same underlying bug.", - "confidence": 0.96, - "canonical_issue_reason": "Issue 43761 is the best anchor if one is needed: it is a clear, self-contained regression with a precise API, expected behavior, and reproducible symptom.", + "summary": "This cluster is a heterogeneous mix of unrelated Transformers issues (imports, generation, tokenizer/image processor bugs, flash-attention, model-specific regressions). I don\u2019t see a single underlying bug or change that ties them together strongly enough to pick one canonical representative or merge any soft-edge pair.", + "confidence": 0.91, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "43761 is the most actionable and well-scoped issue in the set; the bug is concrete and isolated enough to serve as a representative anchor.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "One is a specific missing export for `Qwen2_5_VLForConditionalGeneration`; the other is a vague dependency/loading problem with no shared code-path evidence." + }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "Both involve tokenizers, but one is a special-token decode bug and the other is an AutoTokenizer loading failure; different code paths." + "reason": "Both are tokenizer-related, but they affect different models and different failure modes (`BigBirdTokenizer` special-token registration vs `AutoTokenizer` loading `FastSpeech2ConformerTokenizer`)." }, { "left": "issue:43761", "right": "issue:45859", "accept": false, - "reason": "A CLIPVision hidden-state regression and a Qwen3 MoE rotary/cpu-offload issue are unrelated model-specific bugs." + "reason": "Different model families and bugs: CLIPVision hidden-states regression vs Qwen3_5 MoE rotary embedding CPU-offload incompatibility." }, { "left": "issue:43526", "right": "issue:45834", "accept": false, - "reason": "One is a BEiT Fast image label reduction bug; the other is a Kosmos2.5 long-OCR index error. No same underlying failure." + "reason": "BEiT image processor label reduction bug is unrelated to Kosmos2.5 OCR long-input index errors." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Gradient checkpointing in eval mode and checkpoint resume key mismatch are distinct training-state issues." + "reason": "Gradient checkpointing in eval mode and checkpoint resume key mismatch are distinct training/runtime issues." }, { "left": "issue:45103", "right": "issue:45372", "accept": false, - "reason": "Auto-docstring annotation parsing and Gemma processor loading/import dependency issues are different subsystems." + "reason": "Auto-docstring annotation handling is unrelated to the `ReasoningEffort` import failure in Gemma 4 processor loading." }, { "left": "issue:29942", "right": "issue:36010", "accept": false, - "reason": "Flash Attention 2 test failures and GenerationMixin import errors are unrelated regression classes." + "reason": "Flash Attention 2 test failures are not the same as a `GenerationMixin` import removal/visibility issue." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "Both touch layout/image tokenization, but the BEiT label reduction bug and LayoutLMv2 NER/padding crash are not the same defect." + "reason": "Different processor/tokenizer code paths and symptoms: label reduction in BEiT vs NER/padding crashes in LayoutLMv2Tokenizer." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 box-content validation and a macOS bus error loading CLIP are completely different failures." + "reason": "LayoutLMv3 error messaging and a MacOS bus error on community CLIP loading are unrelated." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Missing pad_token_id in Qwen3-VL text config and sliding_window behavior in Qwen3-MoE are separate model bugs." + "reason": "Qwen3-VL `pad_token_id` loading failure and Qwen3-MoE sliding-window behavior are different bugs." + }, + { + "left": "issue:44625", + "right": "issue:45584", + "accept": false, + "reason": "`num_labels` propagation in Qwen3.5 config is unrelated to Whisper empty-transcription generation after token alignment." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Flash-attention generation corruption and category-count overflow are unrelated; no shared code path." + "reason": "Qwen3.5 flash-attention generation regression is unrelated to the 2^24 category limit runtime error." }, { "left": "issue:29127", "right": "issue:35141", "accept": false, - "reason": "One is an error-message clarity issue for LayoutLMv3; the other is embedding reinitialization during post_init. Different bugs." + "reason": "LayoutLMv3 error messaging issue and embedding reinitialization in `post_init` are different model behaviors." }, { "left": "issue:44464", "right": "issue:45491", "accept": false, - "reason": "Compiled chunked generation inconsistency and Gemma3 mixed-length NaNs stem from different attention/generation paths." + "reason": "Chunked generation with compiled forward and Gemma3 NaN embeddings under mixed-length sliding-window batching are not the same problem." }, { - "left": "issue:44442", - "right": "issue:45072", + "left": "issue:42915", + "right": "issue:43931", "accept": false, - "reason": "Tokenizer loading failure and bfloat16 dtype mismatch in inference are different classes of problems." + "reason": "FineGrainedFP8Config failure for Qwen3Moe and Qwen3-VL weight-shape mismatch are separate model-loading bugs." }, { - "left": "issue:42915", - "right": "issue:43931", + "left": "issue:44442", + "right": "issue:45072", "accept": false, - "reason": "Fine-grained FP8 config failure for Qwen3Moe and Qwen3-VL weight-shape mismatch are separate model-loading bugs." + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch in unrelated models are different subsystems and code paths." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Audio chat-template sampling-rate handling and feature-extractor unsupported-arg crash are unrelated processor issues." + "reason": "Audio chat-template sampling-rate defaulting and LasrFeatureExtractor unsupported-arg crashes are unrelated processor bugs." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "A label-reduction bug in BEiT fast processing does not match an AMP/CUDA image-loss crash." + "reason": "BEiT label reduction and LwDetrImageLoss float16/CUDA crash affect different components and do not share an underlying change." }, { "left": "issue:42490", "right": "issue:43381", "accept": false, - "reason": "Local-path trailing-slash import warning and gradient-checkpointing eval-mode restriction are unrelated." + "reason": "Local-path slash import warning and gradient-checkpointing-in-eval are unrelated." }, { "left": "issue:44062", "right": "issue:45907", "accept": false, - "reason": "AddedToken constructor argument duplication and list_repo_files revision forwarding are different API bugs." + "reason": "`AddedToken` duplicate `special` argument is unrelated to `list_repo_files` not forwarding `revision`." }, { - "left": "issue:43441", - "right": "issue:45588", + "left": "issue:43575", + "right": "issue:43701", "accept": false, - "reason": "Ministral FlashAttention failure and sink-less flash_attention.py s_aux=None crash are distinct attention implementations/fixes." + "reason": "Tensor-parallel OOM for Qwen2-57B and resume-from-checkpoint key mismatch are distinct issues." }, { "left": "issue:44743", "right": "issue:44811", "accept": false, - "reason": "Qwen3.5 recurrent-state reset and Whisper batch_decode skip_special_tokens handling are not the same underlying issue." + "reason": "Qwen3.5 recurrent-state reset bug and Whisper `batch_decode` skip_special_tokens handling are unrelated generation/decoder issues." }, { - "left": "issue:43232", - "right": "issue:43388", + "left": "issue:43441", + "right": "issue:45588", "accept": false, - "reason": "Generation kwargs synchronization after sync_gpus and metric-gather label truncation are different training/generation paths." + "reason": "Ministral-3 flash-attention failure and sink-less flash_attention.py `s_aux=None` crash are both attention-related but not the same concrete bug." }, { - "left": "issue:43575", - "right": "issue:43701", + "left": "issue:43232", + "right": "issue:43388", "accept": false, - "reason": "Tensor-parallel OOM on model load and resume_from_checkpoint key mismatch are unrelated." + "reason": "Generation kwargs update after `sync_gpus` and `gather_for_metrics` dropping tuple labels are unrelated distributed-training bugs." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "Transformers 5 custom initialization breakage and patchtsmixer post_init allowance are not the same code-path problem." + "reason": "Custom model initialization breakage in Transformers 5.0.0 and `patchtsmixer` post_init contract change are not the same underlying change." }, { "left": "issue:43761", "right": "issue:44079", "accept": false, - "reason": "Hidden_states missing from CLIPVision forward and ModelOutput key assignment when a value was previously None are separate bugs." + "reason": "CLIPVision hidden_states regression and `ModelOutput` None-key assignment are separate model-output bugs." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "Qwen2-57B tp OOM on load and increased reserved memory under int4 quantization are different memory-pressure issues." + "reason": "Both can OOM, but one is TP loading of a specific Qwen model while 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 unrelated." - }, - { - "left": "issue:43723", - "right": "issue:45479", - "accept": false, - "reason": "Tokenizer loading in v5 and degenerate zero-loss sequence classification are different APIs and symptoms." - }, - { - "left": "issue:44442", - "right": "issue:45803", - "accept": false, - "reason": "AutoTokenizer loading failure and FuyuBatchFeature exception swallowing are unrelated tokenizer/feature-processing bugs." - }, - { - "left": "issue:43761", - "right": "issue:44188", - "accept": false, - "reason": "CLIPVision hidden_states regression and attention-kernel divergence under torch.compile are separate model execution issues." + "reason": "Unsafe `sys.modules` access in `modeling_utils` is unrelated to DeepSeekV3MoE divergence from the remote implementation." } ] }, @@ -8806,20 +8560,17 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ - "issue:25251", - "issue:28282", "issue:33290", "issue:34567", "issue:34689", "issue:35141", "issue:36010", "issue:36331", - "issue:39692", "issue:41628", "issue:42175", "issue:42490", @@ -8827,19 +8578,20 @@ "issue:43065", "issue:43316", "issue:43381", - "issue:43404", - "issue:43441", "issue:43493", "issue:43525", "issue:43540", "issue:43611", "issue:43643", "issue:43720", + "issue:43723", "issue:43749", + "issue:43761", "issue:43827", "issue:43873", "issue:43931", "issue:44077", + "issue:44188", "issue:44190", "issue:44442", "issue:44479", @@ -8856,26 +8608,29 @@ "issue:45216", "issue:45290", "issue:45372", - "issue:45491", + "issue:45479", "issue:45698", - "issue:45759" + "issue:45759", + "issue:45803" ], "soft_pairs": [ - "issue:44479|issue:45290", + "issue:43723|issue:45479", + "issue:44442|issue:45803", + "issue:43761|issue:44188", "issue:43316|issue:43525", - "issue:44442|issue:44898", + "issue:44479|issue:45290", "issue:42907|issue:45698", - "issue:42490|issue:44743", + "issue:44442|issue:44898", "issue:33290|issue:34567", + "issue:42490|issue:44743", "issue:34689|issue:43611", "issue:33290|issue:35141", "issue:33290|issue:34689", - "issue:39692|issue:45491", "issue:43381|issue:43873", "issue:43931|issue:45216", "issue:43493|issue:43827", - "issue:44077|issue:44479", "issue:43316|issue:45759", + "issue:44077|issue:44479", "issue:43720|issue:44442", "issue:41628|issue:45372", "issue:43643|issue:44913", @@ -8888,218 +8643,216 @@ "issue:43540|issue:44514", "issue:43316|issue:44877", "issue:42175|issue:43316", - "issue:43065|issue:44617", - "issue:43404|issue:43441", - "issue:25251|issue:28282" + "issue:43065|issue:44617" ], - "prepared_review_unit_hash": "3fc865d5a30c3dee3013d22b6a262ec7c7df624f6f4817c4603faf4b29296f50", + "prepared_review_unit_hash": "cd0c2215d24199ab904202b2c39e1bea1c174085af4b9bc89a72f227948b149a", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36864, - "estimated_input_tokens": 9216, - "estimated_eval_tokens": 18688 + "serialized_chars": 36328, + "estimated_input_tokens": 9082, + "estimated_eval_tokens": 18420 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are not duplicates as a cluster: the items cover many unrelated issues across loading, config, training, docs, quantization, and multimodal/video paths. All soft-similarity pairs are superficial and should be rejected.", - "confidence": 0.95, - "canonical_issue_reason": "No canonical issue: the set is heterogeneous and does not represent one underlying bug or change.", - "canonical_pr_reason": "No PRs are present in this cluster, so no canonical PR can be selected.", - "best_issue_reason": "No single best issue for deduping; none of the issues is clearly central enough to serve as a representative for the others.", - "best_pr_reason": "No PRs are present in this cluster, so no best PR exists.", + "summary": "The set is highly heterogeneous: the soft pairs mostly connect unrelated loading, config, tokenizer, vision, training, and docs bugs. No pair looks like the same underlying change or defect, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: these items are not duplicates of one bug, but a grab bag of unrelated regressions and API mismatches.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative because there is no one underlying problem to centralize.", + "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44479", - "right": "issue:45290", + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Different failures: tokenizer loading in v5 vs degenerate loss in sequence classification." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Unrelated code paths: AutoTokenizer loading vs Fuyu tensor conversion error handling." + }, + { + "left": "issue:43761", + "right": "issue:44188", "accept": false, - "reason": "Both involve video/chat-related failures, but one is a video-input regression and the other is a chat-template crash on tool-call messages; different code paths and symptoms." + "reason": "Different subsystems: CLIPVision hidden_states regression vs attention-kernel divergence under torch.compile." }, { "left": "issue:43316", "right": "issue:43525", "accept": false, - "reason": "Both are config/API discrepancies, but they concern different models and different missing fields; not the same bug." + "reason": "Both are config-related, but they affect different models and bugs: Gemma3TextConfig API mismatch vs Llama4Config missing pad_token_id." }, { - "left": "issue:44442", - "right": "issue:44898", + "left": "issue:44479", + "right": "issue:45290", "accept": false, - "reason": "Tokenizer loading failure vs image-classification interpolation bug; no shared underlying code path." + "reason": "Different Qwen chat/video issues: video-input regression vs tool-call chat-template crash." }, { "left": "issue:42907", "right": "issue:45698", "accept": false, - "reason": "Both touch save/load behavior, but one is about saving dequantized weights and the other about loading the wrong custom module after save_pretrained; distinct failures." + "reason": "Both involve save/load, but one is dequantized model saving and the other is wrong custom-module loading after save_pretrained; not the same bug." }, { - "left": "issue:42490", - "right": "issue:44743", + "left": "issue:44442", + "right": "issue:44898", "accept": false, - "reason": "Local-path import warning and recurrent-state reset in Qwen3.5 are unrelated." + "reason": "Completely different models and paths: tokenizer loading vs Perceiver image resizing/interpolation." }, { "left": "issue:33290", "right": "issue:34567", "accept": false, - "reason": "DeepSpeed/Adafactor OOM and TrainerState token-count tracking are unrelated training issues." + "reason": "Different training problems: DeepSpeed/Adafactor OOM vs TrainerState token counter not updating." + }, + { + "left": "issue:42490", + "right": "issue:44743", + "accept": false, + "reason": "Local-path import warning is unrelated to recurrent-state caching behavior in Qwen3.5." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are model-loading regressions, but they involve different loading mechanisms and different root causes." + "reason": "Both concern model loading, but they are distinct regressions with different root causes and model families." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "OOM in optimizer setup vs embedding reinitialization during post_init; not the same defect." + "reason": "OOM with Adafactor is unrelated to embedding reinitialization in post_init." }, { "left": "issue:33290", "right": "issue:34689", "accept": false, - "reason": "Different failures: optimizer memory usage versus specific model-loading breakage." - }, - { - "left": "issue:39692", - "right": "issue:45491", - "accept": false, - "reason": "Docs example errors for SigLIP2 versus Gemma3 NaN embeddings; unrelated surfaces and code paths." + "reason": "Different bugs: optimizer memory blowup vs Llama 3.2 Vision model loading failure." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Gradient checkpointing in eval mode and quantization/offloading behavior are different bugs." + "reason": "Gradient checkpointing in eval mode and quantization offloading are separate execution paths." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Weight-shape mismatch on load versus incorrect checkpoint saving; related to persistence broadly but not the same concrete issue." + "reason": "Weight-shape mismatch on Qwen3-VL loading is unrelated to a save_pretrained checkpoint regression in Qwen3.5." }, { "left": "issue:43493", "right": "issue:43827", "accept": false, - "reason": "SigLIP2 implementation discrepancy and pipeline-doc removal are unrelated." + "reason": "SigLIP2 implementation discrepancy is unrelated to docs still referencing pipeline()." }, { - "left": "issue:44077", - "right": "issue:44479", + "left": "issue:43316", + "right": "issue:45759", "accept": false, - "reason": "Optional post_init enforcement for patchtsmixer and a video-input regression are unrelated." + "reason": "Different config-loading problems: Gemma3TextConfig API mismatch vs not unwrapping text_config in AutoModelForCausalLM.from_config." }, { - "left": "issue:43316", - "right": "issue:45759", + "left": "issue:44077", + "right": "issue:44479", "accept": false, - "reason": "Both mention config handling, but one is an API discrepancy in Gemma3TextConfig and the other is unwrapping text_config for composite Qwen configs; different fixes." + "reason": "PatchTST post_init validation and Qwen video-input regression are unrelated bugs." }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "Accelerate loading of packed BitNet weights versus tokenizer loading failure; no overlap beyond generic model loading." + "reason": "BitNet packed-weight loading and tokenizer loading are unrelated." }, { "left": "issue:41628", "right": "issue:45372", "accept": false, - "reason": "Different import errors for different components and dependencies; not the same underlying bug." + "reason": "Different import failures: AutoImageProcessor export vs mistral_common ReasoningEffort dependency." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "Remote-code config missing fields on load versus a specific GPTNeoX config value not persisting; distinct serialization issues." + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct reload behavior do not share the same code path." }, { "left": "issue:43749", "right": "issue:43931", "accept": false, - "reason": "FSDP CPU RAM-efficient loading breakage and a Qwen3-VL weight mismatch are different loading problems." + "reason": "FSDP CPU RAM efficient loading and Qwen3-VL weight mismatch are separate loading failures." }, { "left": "issue:34689", "right": "issue:36010", "accept": false, - "reason": "Both are import/load regressions, but they affect different symbols and code paths." + "reason": "Llama model-loading regression and GenerationMixin import error are different issues." }, { "left": "issue:43873", "right": "issue:44871", "accept": false, - "reason": "Quantization/offloading behavior and Gemma-3 eos_token_id inconsistency are unrelated." + "reason": "Quantization/offloading behavior is unrelated to Gemma-3 eos_token_id config inconsistency." }, { "left": "issue:33290", "right": "issue:36331", "accept": false, - "reason": "OOM with Adafactor/DeepSpeed is unrelated to the CustomTrainer compute_loss signature break." + "reason": "DeepSpeed OOM and CustomTrainer compute_loss signature mismatch are distinct trainer bugs." }, { "left": "issue:44190", "right": "issue:44496", "accept": false, - "reason": "Dataset-loading issue in an example script versus unrecognized model type in config.json; different layers entirely." + "reason": "Local dataset loading in an example script is unrelated to unrecognized model config loading." }, { "left": "issue:44855", "right": "issue:45137", "accept": false, - "reason": "Python 3.13 import parsing error and DeepSpeed deque underflow are unrelated." + "reason": "Python 3.13 IndentationError in Deberta import is unrelated to ZeRO3 deque underflow." }, { "left": "issue:43540", "right": "issue:44514", "accept": false, - "reason": "Both are multimodal/chat-related, but one is video-input validation in Qwen3OmniMoe and the other is apply_chat_template crashing on tool-call messages; not the same bug." + "reason": "Video processing in Qwen3OmniMoe and batched chat-template tool-call handling are different failures." }, { "left": "issue:43316", "right": "issue:44877", "accept": false, - "reason": "Both involve config handling, but the specific models and failure modes differ completely." + "reason": "Gemma3TextConfig API discrepancy and granite_speech strict-config loading are different model/config issues." }, { "left": "issue:42175", "right": "issue:43316", "accept": false, - "reason": "Packaging/backend dependency omission and Gemma3 config API mismatch are unrelated." + "reason": "Backend packaging for TensorFlow is unrelated to Gemma3TextConfig API behavior." }, { "left": "issue:43065", "right": "issue:44617", "accept": false, - "reason": "Same model family, but dummy Conv2d in Sam3PixelDecoder and Sam3Video CUDA OOM are different issues." - }, - { - "left": "issue:43404", - "right": "issue:43441", - "accept": false, - "reason": "Related to Mistral/Ministral, but one is a missing lm_head tie and the other is a FlashAttention failure; not the same code-path problem." - }, - { - "left": "issue:25251", - "right": "issue:28282", - "accept": false, - "reason": "Pipeline top_k nesting bug and AutoModel PyTorch import error are entirely unrelated." + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video CUDA OOM are not the same defect." } ] }, @@ -9118,13 +8871,15 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:16998", "issue:22355", + "issue:25251", + "issue:28282", "issue:32090", "issue:35141", "issue:41950", @@ -9132,6 +8887,8 @@ "issue:43065", "issue:43295", "issue:43388", + "issue:43404", + "issue:43441", "issue:43452", "issue:43475", "issue:43504", @@ -9153,7 +8910,6 @@ "issue:44464", "issue:44479", "issue:44496", - "issue:44521", "issue:44534", "issue:44610", "issue:44617", @@ -9162,29 +8918,29 @@ "issue:44792", "issue:44871", "issue:44913", - "issue:44977", "issue:45127", "issue:45200", - "issue:45381", "issue:45406", "issue:45563", "issue:45584", "issue:45698" ], "soft_pairs": [ - "issue:43673|issue:44743", + "issue:25251|issue:28282", "issue:43295|issue:43825", + "issue:43404|issue:43441", + "issue:43673|issue:44743", "issue:44162|issue:44792", + "issue:16998|issue:22355", "issue:43388|issue:43688", "issue:41950|issue:43475", "issue:44077|issue:44534", - "issue:16998|issue:22355", "issue:43550|issue:43701", "issue:43606|issue:43701", "issue:44871|issue:45584", "issue:43761|issue:44479", - "issue:45127|issue:45200", "issue:43295|issue:44871", + "issue:45127|issue:45200", "issue:42617|issue:43575", "issue:43452|issue:44496", "issue:43575|issue:43742", @@ -9192,218 +8948,209 @@ "issue:43646|issue:44913", "issue:43504|issue:45698", "issue:44617|issue:45584", - "issue:43931|issue:44060", "issue:43761|issue:44242", + "issue:43931|issue:44060", "issue:32090|issue:35141", "issue:45563|issue:45584", "issue:44464|issue:44871", - "issue:43065|issue:44610", - "issue:44792|issue:44977", - "issue:44479|issue:44734", - "issue:44521|issue:45381" + "issue:43065|issue:44610" ], - "prepared_review_unit_hash": "868263f649e9596f951ca7a658eb90481e95275a28881f017c3c9a6c851ce861", + "prepared_review_unit_hash": "1c4a8bc4ef0772382cba602527de0897b316460d693c4df8fdc0e99e5aad97ac", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35779, - "estimated_input_tokens": 8945, - "estimated_eval_tokens": 18146 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36103, + "estimated_input_tokens": 9026, + "estimated_eval_tokens": 18308 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the soft pairs mostly share only broad terminology (generation, loading, multimodal, training) but not the same concrete bug or code path. I would not merge any of the proposed soft edges as duplicates. If a representative issue is needed, issue:44521 is the strongest activity-wise, but it is not a true canonical for the whole set.", - "confidence": 0.96, - "canonical_issue_reason": "No single canonical issue fits this cluster; the items span unrelated bugs across loading, generation, multimodal processing, serving, and training.", + "summary": "The items are mostly unrelated model/loading/training regressions, so I found no convincing duplicate cluster beyond loose subsystem similarity. The strongest representative issue is the custom-module loading regression.", + "confidence": 0.27, + "canonical_issue_reason": "issue:45698 is the clearest broad, user-facing loader regression in the set, with a concrete save/load repro and active discussion.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the most active/open item and has the strongest discussion footprint, but it is only representative of one narrow multimodal bug, not the cluster as a whole.", + "best_issue_reason": "issue:45698 best represents a high-impact core `from_pretrained` failure and is the most actionable issue in the group.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43673", - "right": "issue:44743", + "left": "issue:25251", + "right": "issue:28282", "accept": false, - "reason": "Both involve cache-related generation behavior, but one is about chunked_prefill cache availability and the other about recurrent states resetting with seq_len>1; different symptoms and code paths." + "reason": "Different failures: pipeline output shape vs missing PyTorch import path." }, { "left": "issue:43295", "right": "issue:43825", "accept": false, - "reason": "One is a regression in processor/tokenizer access and image passing; the other is an error-message mismatch about supported translation tasks. Different bug types." + "reason": "Both touch processors/tokenizers, but one is a v5 regression in custom code handling while the other is just an incorrect error message for unsupported translation tasks." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Same model family, but different bugs: weight tying vs FlashAttention failure." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both are cache-related, but they affect different mechanisms and code paths (chunked prefill cache vs recurrent state reset)." }, { "left": "issue:44162", "right": "issue:44792", "accept": false, - "reason": "ESM2 workflow breakage and a Janus image-generation test failure are unrelated models and failures." + "reason": "Completely different domains: ESM2 model breakage vs Janus image generation test failure." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Unrelated: max length handling for DeBERTa vs missing `transformers.onnx` module." }, { "left": "issue:43388", "right": "issue:43688", "accept": false, - "reason": "Dropping label elements in gather_for_metrics is unrelated to auxiliary-loss normalization in expert models." + "reason": "Training-related, but one is metric gathering on last batch and the other is auxiliary-loss normalization." }, { "left": "issue:41950", "right": "issue:43475", "accept": false, - "reason": "A pipeline selecting the wrong processor type is not the same as a Sam3VisionEncoderOutput missing fpn_position_embeddings." + "reason": "Both involve vision/video models, but the bugs are different: processor selection vs missing attribute in SAM3 video output." }, { "left": "issue:44077", "right": "issue:44534", "accept": false, - "reason": "Optional post_init handling for patchtsmixer and junk-filled non-persistent buffers are different initialization bugs." - }, - { - "left": "issue:16998", - "right": "issue:22355", - "accept": false, - "reason": "Model max length behavior for DeBERTa-V3 is unrelated to a missing transformers.onnx module import." + "reason": "One is a model class API constraint; the other is a v5 buffer-initialization regression." }, { "left": "issue:43550", "right": "issue:43701", "accept": false, - "reason": "torch.compile/SDPA failure for Bamba and a resume_from_checkpoint key mismatch are different problems." + "reason": "Unrelated: torch.compile SDPA OOM vs checkpoint key mismatch." }, { "left": "issue:43606", "right": "issue:43701", "accept": false, - "reason": "CPU offload device mismatch in bark-small is not the same as the checkpoint key mismatch bug." + "reason": "Different issues: CPU offload device mismatch vs resume checkpoint key mismatch." }, { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "EOS token config inconsistency in Gemma-3 and Whisper empty-transcription failure after align_special_tokens are different model-specific issues." + "reason": "Both mention tokenization/generation, but one is an eos_token_id config mismatch and the other is an empty-transcription generation crash." }, { "left": "issue:43761", "right": "issue:44479", "accept": false, - "reason": "CLIPVisionModel hidden_states regression and Qwen VL video-input regression are separate model families and failure modes." + "reason": "Different model families and failure modes: CLIP hidden_states regression vs Qwen video-input regression." }, { - "left": "issue:45127", - "right": "issue:45200", + "left": "issue:43295", + "right": "issue:44871", "accept": false, - "reason": "LoRA merging with extended vocabulary and Gemma 4 mm_token_type_ids defaults are unrelated training/configuration bugs." + "reason": "Processor/tokenizer regression vs eos_token_id inconsistency; not the same underlying bug." }, { - "left": "issue:43295", - "right": "issue:44871", + "left": "issue:45127", + "right": "issue:45200", "accept": false, - "reason": "Both mention processor/tokenizer behavior, but one is a custom model regression and the other is an EOS-token config mismatch; not the same bug." + "reason": "Both are model config/training issues, but one is LoRA/embedding collapse after merge and the other is a missing default for `mm_token_type_ids`." }, { "left": "issue:42617", "right": "issue:43575", "accept": false, - "reason": "Running 3d_parallel.py and OOM when loading Qwen2-57B with tensor parallelism are different issues." + "reason": "Different symptoms and paths: running a 3D script vs OOM when loading a specific model with tensor parallelism." }, { "left": "issue:43452", "right": "issue:44496", "accept": false, - "reason": "A gguf_file path breaking tokenizer/model loading is not the same as failing because a config.json lacks model_type." + "reason": "Both involve loading, but one is a `gguf_file` path bug and the other is an unrecognized custom model/config issue." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "OOM on a very large Qwen model with tp and a key error loading MobileLLM-125M are unrelated load-time failures." + "reason": "Different model-loading problems: OOM on large Qwen with tp vs key error for MobileLLM-125M." }, { "left": "issue:44734", "right": "issue:45406", "accept": false, - "reason": "KV-cache indexing in transformers serve and Gemma4Processor missing _tokenizer are different serving bugs." + "reason": "Both are service/runtime crashes, but they stem from different serve code paths and different root causes." }, { "left": "issue:43646", "right": "issue:44913", "accept": false, - "reason": "Breaking custom model initialization in v5 and GPTNeoXConfig rotary_pct not persisting are distinct configuration/init issues." + "reason": "Custom model init breakage is unrelated to GPTNeoX config reload losing `rotary_pct`." }, { "left": "issue:43504", "right": "issue:45698", "accept": false, - "reason": "Legacy-field loading failure in BeitForSemanticSegmentation and wrong custom module selection after save_pretrained are different pretrained-loading bugs." + "reason": "Both concern loading/saving, but one is a legacy field in BEiT preset loading and the other is wrong custom-module resolution after save/load." }, { "left": "issue:44617", "right": "issue:45584", "accept": false, - "reason": "Sam3Video CUDA OOM and Whisper empty transcription failure are unrelated." + "reason": "Unrelated: CUDA OOM in SAM3 video vs Whisper empty-transcription generation failure." }, { - "left": "issue:43931", - "right": "issue:44060", + "left": "issue:43761", + "right": "issue:44242", "accept": false, - "reason": "A weight-shape mismatch when loading Qwen3-VL is not the same as an incorrect tied-weights warning in Qwen3-Next." + "reason": "Different training/inference bugs: CLIP hidden_states regression vs missing load-balancing loss." }, { - "left": "issue:43761", - "right": "issue:44242", + "left": "issue:43931", + "right": "issue:44060", "accept": false, - "reason": "Hidden_states=None in CLIPVisionModel and missing load-balancing loss when output_router_logits=False are unrelated." + "reason": "Related to Qwen3-VL/Next, but one is a shape mismatch on load and the other is a tied-weights warning bug." }, { "left": "issue:32090", "right": "issue:35141", "accept": false, - "reason": "GPU broadcast TypeError in Trainer and embedding reinitialization after resize are separate bugs." + "reason": "Different failures: distributed broadcast NoneType vs output embedding reinitialization after resizing token embeddings." }, { "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "A stale warning in paged generate and Whisper generation failing on empty transcription are not the same underlying issue." + "reason": "Paged generation warning bug vs Whisper align_special_tokens crash; not the same issue." }, { "left": "issue:44464", "right": "issue:44871", "accept": false, - "reason": "Compiled chunked generation inconsistency and Gemma-3 EOS configuration mismatch are unrelated." + "reason": "Chunked generation inconsistency with compiled forward is unrelated to eos_token_id config mismatch." }, { "left": "issue:43065", "right": "issue:44610", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and OmDet-Turbo processor/model size mismatch are both vision-related but clearly different bugs." - }, - { - "left": "issue:44792", - "right": "issue:44977", - "accept": false, - "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation failure are different models and code paths." - }, - { - "left": "issue:44479", - "right": "issue:44734", - "accept": false, - "reason": "A multimodal video-input regression and a serve KV-cache continuation indexing crash are unrelated." - }, - { - "left": "issue:44521", - "right": "issue:45381", - "accept": false, - "reason": "Both are multimodal, but one is assistant mask construction in apply_chat_template and the other is vision_position_ids for Qwen2.5-VL video input; not the same bug." + "reason": "Both are vision model issues, but one is a dummy Conv2d in SAM3 pixel decoder and the other is a processor/model image-size mismatch." } ] }, @@ -9422,15 +9169,13 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:35141", - "issue:39692", "issue:41720", - "issue:41950", "issue:42490", "issue:43335", "issue:43388", @@ -9443,7 +9188,6 @@ "issue:43906", "issue:43976", "issue:43994", - "issue:44016", "issue:44077", "issue:44079", "issue:44112", @@ -9451,7 +9195,9 @@ "issue:44220", "issue:44462", "issue:44464", + "issue:44479", "issue:44496", + "issue:44521", "issue:44534", "issue:44734", "issue:44737", @@ -9461,12 +9207,14 @@ "issue:44933", "issue:44938", "issue:44964", + "issue:44977", "issue:45127", "issue:45245", "issue:45276", "issue:45290", "issue:45357", "issue:45362", + "issue:45381", "issue:45542", "issue:45563", "issue:45584", @@ -9476,232 +9224,238 @@ "issue:45907" ], "soft_pairs": [ - "issue:43906|issue:45290", + "issue:44792|issue:44977", + "issue:44479|issue:44734", + "issue:44521|issue:45381", "issue:43827|issue:43994", "issue:44464|issue:45563", "issue:44534|issue:44913", + "issue:43906|issue:45290", "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:43388|issue:43582", + "issue:45127|issue:45357", + "issue:44737|issue:45803", "issue:44462|issue:45907", - "issue:44077|issue:44079", "issue:43335|issue:44855", + "issue:44077|issue:44079", "issue:44938|issue:45542", + "issue:43644|issue:44913", "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:43335|issue:44190", - "issue:45276|issue:45584", - "issue:39692|issue:44190", - "issue:45245|issue:45584", - "issue:41950|issue:44016" + "issue:43650|issue:44220", + "issue:45276|issue:45584" ], - "prepared_review_unit_hash": "76fb2c28234ac7c80fb3cba196541da178f6ebf7ae23bee59945582b892e8af5", + "prepared_review_unit_hash": "691a63f3334cc7339cda6012cef477e06f4f82a59d60f039980072dc8263cea5", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 35902, - "estimated_input_tokens": 8976, - "estimated_eval_tokens": 18208 + "serialized_chars": 36467, + "estimated_input_tokens": 9117, + "estimated_eval_tokens": 18490 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous and does not look like a tight duplicate cluster. The only clear thematic overlap is around token-embedding resizing, but the listed soft pairs are otherwise separate bugs or unrelated regressions.", - "confidence": 0.92, - "canonical_issue_reason": "issue:35141 is the clearest, most general concrete bug report in the set: it names the exact code path (`post_init` after `resize_token_embeddings`) and the failure mode (`output embedding` reinitialized when `tie_word_embedding=False`).", + "summary": "All proposed soft edges look like loose topic/keyword similarity, not the same underlying bug or change. I would reject every candidate pair; the set is heterogeneous and there is no clear canonical issue/PR for the whole group.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:35141 is the best anchor for the only plausible duplicate family here because it is specific, actionable, and directly describes the underlying embedding-resize bug more cleanly than the other items.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43906", - "right": "issue:45290", + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Different failures in different models: Janus image generation test vs Qwen3.5 flash-attention behavior." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation/runtime bugs, but one is a Qwen VL video regression and the other is KV-cache indexing in serve; not the same code path." + }, + { + "left": "issue:44521", + "right": "issue:45381", "accept": false, - "reason": "Both mention chat/template-style behavior, but one is just an isolated reproduction of another issue while the other is a concrete crash on assistant tool-call messages; not enough evidence of the same bug." + "reason": "Both are multimodal/chat-template issues, but one is assistant masks for multimodal inputs and the other is Qwen2.5-VL vision \u0564\u056b\u0580 ids; distinct bugs." }, { "left": "issue:43827", "right": "issue:43994", "accept": false, - "reason": "Documentation still referencing `pipeline()` after v5 removals is unrelated to SigLIP2 producing bad outputs with AutoModel/pipeline." + "reason": "Docs referencing removed pipeline() APIs is unrelated to a bad AutoModel/pipeline inference result." }, { "left": "issue:44464", "right": "issue:45563", "accept": false, - "reason": "Chunked generation inconsistency under compiled forward and a stale `num_return_sequences` warning in paged generate are different problems." + "reason": "Chunked compiled generation inconsistency is unrelated to a stale warning in paged generate()." }, { "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "One is about non-persistent buffers being filled with junk; the other is about a config value reverting on reload." + "reason": "Non-persistent buffer initialization and GPTNeoX config reload defaults are different problems." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "Insufficient evidence that the isolated reproduction matches the tool-call crash; only a generic chat-template similarity is visible." }, { "left": "issue:44190", "right": "issue:44964", "accept": false, - "reason": "Local dataset loading in an example script and model loading for Phi-4 multimodal are separate failures." + "reason": "A local dataset loading issue is unrelated to loading a multimodal model." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "A bad import from `image_utils` is unrelated to Qwen3.5 chat crashes." + "reason": "Missing/nonexistent import from image_utils is unrelated to a Qwen3.5 chat crash." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "CUDA assert in Qwen3 auto device mapping and a category-limit runtime error are different failure modes." + "reason": "CUDA assert with auto device mapping has nothing to do with the category-count limit error." }, { "left": "issue:44792", "right": "issue:45600", "accept": false, - "reason": "A janus image-generation test failure and broken `auto_mappings.py` references are not the same underlying bug." + "reason": "Janus test failure and stale auto_mappings references are unrelated." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Python 3.13 import parsing/`torch.jit.script` issue is unrelated to flash-attention crashing on `s_aux=None`." + "reason": "Python 3.13 import/torch.jit parsing issue is unrelated to flash_attention crashing on s_aux=None." }, { - "left": "issue:44737", - "right": "issue:45803", + "left": "issue:35141", + "right": "issue:42490", "accept": false, - "reason": "Missing `device=` in `torch.arange` causing CPU work is unrelated to the bare `except:` swallowing errors." + "reason": "Embedding resize/post_init reinit bug is unrelated to loading local model paths with trailing slashes." }, { - "left": "issue:45127", - "right": "issue:45357", + "left": "issue:43388", + "right": "issue:43582", "accept": false, - "reason": "LoRA/extended-vocab collapse with tied embeddings and incorrect visual-encoder keys in save_pretrained are different bugs." + "reason": "Metric label handling bug is unrelated to an Apple Silicon allocator warmup TypeError." }, { - "left": "issue:43388", - "right": "issue:43582", + "left": "issue:45127", + "right": "issue:45357", "accept": false, - "reason": "A metrics label-truncation bug and an Apple Silicon `caching_allocator_warmup` TypeError do not match." + "reason": "LoRA merge with extended vocabulary on tied embeddings is unrelated to incorrect visual encoder keys during save_pretrained." }, { - "left": "issue:35141", - "right": "issue:42490", + "left": "issue:44737", + "right": "issue:45803", "accept": false, - "reason": "Embedding reinitialization after resize and a trailing-slash local-path import warning are unrelated." + "reason": "CPU device placement bug in XLNet is unrelated to a bare-except error swallowing interrupts in Fuyu conversion." }, { "left": "issue:44462", "right": "issue:45907", "accept": false, - "reason": "Ignoring `tokenizer.json` and failing to forward `revision` in `list_repo_files` are different repository-loading issues." + "reason": "Tokenizer resolution from repository files is unrelated to list_repo_files failing to forward revision." }, { - "left": "issue:44077", - "right": "issue:44079", + "left": "issue:43335", + "right": "issue:44855", "accept": false, - "reason": "These are separate core-library bugs: `post_init` policy for patchtsmixer versus `ModelOutput` key assignment." + "reason": "Sparse layer creation in SwitchTransformers is unrelated to DebertaV2 import parsing on Python 3.13." }, { - "left": "issue:43335", - "right": "issue:44855", + "left": "issue:44077", + "right": "issue:44079", "accept": false, - "reason": "SwitchTransformers sparse-layer construction and a Python 3.13 import parsing error are unrelated." + "reason": "These are both model-output/config related, but they describe different bugs: optional post_init handling vs key assignment when previously None." }, { "left": "issue:44938", "right": "issue:45542", "accept": false, - "reason": "Python 3.14 import/load failure and the TensorBoard-without-TensorFlow backend error are different compatibility problems." + "reason": "Python 3.14 import failure is unrelated to the TensorFlow-backend warning from tensorboard-only installs." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Junk non-persistent buffers and GPTNeoX rotary_pct reload regression are not the same issue." }, { "left": "issue:43550", "right": "issue:44190", "accept": false, - "reason": "Bamba torch.compile/SDPA failure is unrelated to local dataset loading in an example script." + "reason": "torch.compile/SDPA failure in Bamba is unrelated to loading a local dataset script." }, { "left": "issue:43976", "right": "issue:44855", "accept": false, - "reason": "General Python-version compatibility and a specific DebertaV2 import indentation/parsing bug are not the same issue." - }, - { - "left": "issue:43644", - "right": "issue:44913", - "accept": false, - "reason": "Non-persistent buffer initialization junk and `rotary_pct` not persisting on reload are separate state-handling bugs." + "reason": "Python version compatibility issue is unrelated to a specific DebertaV2 import parser error." }, { "left": "issue:43540", "right": "issue:44734", "accept": false, - "reason": "Qwen3OmniMoe video input processing and serve-side KV-cache tensor indexing are different code paths." + "reason": "Qwen3OmniMoe video-input ValueError is unrelated to serve KV-cache continuation tensor indexing." }, { "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "A stale CI test and broken auto-mapping references are both CI-related but not the same underlying change." + "reason": "GraniteSpeech CI test flake is unrelated to stale Sam3LiteText auto-mapping references." }, { "left": "issue:44496", "right": "issue:45803", "accept": false, - "reason": "Model-type resolution failure when loading a repo and a bare exception swallowing errors are unrelated." - }, - { - "left": "issue:43650", - "right": "issue:44220", - "accept": false, - "reason": "`ADD THE DATA` is too vague to tie to the audio feature extraction bug." - }, - { - "left": "issue:45276", - "right": "issue:45584", - "accept": false, - "reason": "Gemma4 resize-token-embedding behavior and Whisper empty-transcription failure are unrelated." + "reason": "Model config missing model_type is unrelated to Fuyu's broad exception handling." }, { - "left": "issue:39692", + "left": "issue:43335", "right": "issue:44190", "accept": false, - "reason": "SigLIP2 docs/model-processor mismatch and local dataset loading are different documentation/example issues." + "reason": "Sparse-layer config bug is unrelated to local dataset loading." }, { - "left": "issue:45245", - "right": "issue:45584", + "left": "issue:43650", + "right": "issue:44220", "accept": false, - "reason": "Category-count runtime error and Whisper empty-transcription crash are unrelated." + "reason": "Placeholder issue title is unrelated to _torch_extract_fbank_features()." }, { - "left": "issue:41950", - "right": "issue:44016", + "left": "issue:45276", + "right": "issue:45584", "accept": false, - "reason": "Video-classification pipeline processor selection and a notebook syntax error do not share the same bug." + "reason": "Gemma4 resize_token_embeddings behavior and Whisper empty-transcription failure are different code paths and symptoms." } ] }, @@ -9720,36 +9474,36 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36246", "issue:38175", "issue:38617", + "issue:39692", "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:44190", "issue:44220", "issue:44246", "issue:44279", @@ -9764,248 +9518,249 @@ "issue:44964", "issue:44987", "issue:45003", - "issue:45042", "issue:45216", + "issue:45245", "issue:45276", "issue:45335", "issue:45375", "issue:45446", + "issue:45584", "issue:45600", "issue:45632" ], "soft_pairs": [ - "issue:43479|issue:45375", + "issue:39692|issue:44190", + "issue:45245|issue:45584", + "issue:41950|issue:44016", "issue:43295|issue:45276", + "issue:43479|issue:45375", "issue:36246|issue:41628", "issue:36246|issue:38617", - "issue:44186|issue:44734", "issue:38175|issue:43065", + "issue:44186|issue:44734", "issue:42175|issue:44279", "issue:44683|issue:45446", "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:44734|issue:45632", + "issue:44561|issue:45632", "issue:42490|issue:45632", "issue:43643|issue:44496", "issue:44964|issue:45600", "issue:44112|issue:44964", "issue:43854|issue:44964", "issue:42907|issue:43441", - "issue:44016|issue:44062", "issue:43976|issue:44987", + "issue:44016|issue:44062", "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" + "issue:43824|issue:44933" ], - "prepared_review_unit_hash": "21a6295b2542464e886e796dc5b61e86b9f5b8dd4cfa068152c89ad033495881", + "prepared_review_unit_hash": "6b7c6a00d477b5a48013c4fc9b2d8b1f0049a99d4cea74e0b9297402eceed074", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 35884, - "estimated_input_tokens": 8971, - "estimated_eval_tokens": 18198 + "serialized_chars": 36414, + "estimated_input_tokens": 9104, + "estimated_eval_tokens": 18464 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is not a true duplicate cluster: it mixes unrelated issues across imports, model loading, configs, attention, tokenizers, docs, and CI. All soft-edge pairs should be rejected.", + "summary": "This cluster is a loose collection of Transformers issues, mostly import/load regressions, model/config mismatches, and a few unrelated tokenizer, docs, and serving bugs. The soft-similarity pairs are not strong duplicates; they usually share a subsystem or theme, not the same underlying defect.", "confidence": 0.89, - "canonical_issue_reason": null, + "canonical_issue_reason": "issue:44964 is the clearest, most reproducible bug report in the set: a specific model load failure against latest Transformers with a concrete target and narrow scope.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44964 is the broadest user-facing regression report here (a concrete model-loading failure with recent transformers) and has relatively strong discussion activity, but it still only loosely represents this heterogeneous set.", + "best_issue_reason": "issue:44964 is the best representative issue for this cluster because it is concrete, actionable, and centered on a single user-visible regression rather than a broad or ambiguous symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43479", - "right": "issue:45375", + "left": "issue:39692", + "right": "issue:44190", + "accept": false, + "reason": "Different problems: notebook/example errors vs local dataset loading failure in a training script." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Unrelated bugs: category-count limit vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:41950", + "right": "issue:44016", "accept": false, - "reason": "Both are multimodal-config bugs, but they affect different models and different fields/code paths; not the same underlying defect." + "reason": "Different artifacts and failures: pipeline processor lookup vs notebook syntax error." }, { "left": "issue:43295", "right": "issue:45276", "accept": false, - "reason": "Both mention resize/token embedding behavior, but the regressions are on different models and symptoms; not mergeable as one fix." + "reason": "Both involve model APIs, but one is a processor/tokenizer regression and the other is embedding resize not propagating." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different config bugs affecting different multimodal models and different fields." }, { "left": "issue:36246", "right": "issue:41628", "accept": false, - "reason": "Different missing imports for different symbols and modules; same broad theme, not the same bug." + "reason": "Both are import errors, but they involve different missing symbols and different code paths." }, { "left": "issue:36246", "right": "issue:38617", "accept": false, - "reason": "Separate import errors in unrelated modules/symbols, so they are not the same underlying issue." + "reason": "Distinct missing-import failures in unrelated modules." }, { - "left": "issue:44186", - "right": "issue:44734", + "left": "issue:38175", + "right": "issue:43065", "accept": false, - "reason": "Tokenizer NER/padding crash vs server KV-cache continuation indexing bug; different code paths and failures." + "reason": "Unrelated model behavior bug vs pixel decoder implementation issue." }, { - "left": "issue:38175", - "right": "issue:43065", + "left": "issue:44186", + "right": "issue:44734", "accept": false, - "reason": "Unrelated model behavior bug vs dummy Conv2d implementation issue; no shared defect." + "reason": "Different tokenizer/NER crash vs serving KV-cache tensor indexing crash." }, { "left": "issue:42175", "right": "issue:44279", "accept": false, - "reason": "Both are dependency-related, but one is about optional backend installation and the other is a vague dependency problem; too different to deduplicate." + "reason": "Generic dependency/install complaint is not the same as a missing TensorFlow backend in the torch extra." }, { "left": "issue:44683", "right": "issue:45446", "accept": false, - "reason": "Both touch flex_attention, but they are distinct torch/version-check problems in different code paths." + "reason": "Related area, but different concrete failures: compiled flex_attention on new torch vs an incorrect version check for AuxRequest import." }, { "left": "issue:44016", "right": "issue:44220", "accept": false, - "reason": "Notebook syntax error and fbank feature extraction bug are unrelated." + "reason": "Notebook syntax error and audio feature extraction bug are unrelated." }, { "left": "issue:44466", "right": "issue:44913", "accept": false, - "reason": "Tied-weight serialization/device behavior vs rotary_pct persistence in GPTNeoXConfig; different components and fixes." + "reason": "Weight-serialization/tieing regression is separate from GPTNeoX rotary_pct reload behavior." }, { "left": "issue:43404", "right": "issue:45216", "accept": false, - "reason": "Both involve saving/tied weights, but they concern different models and different save-pretrained regressions." + "reason": "Different models and different save/tie semantics; not the same underlying bug." }, { - "left": "issue:44561", - "right": "issue:45632", + "left": "issue:44246", + "right": "issue:45003", "accept": false, - "reason": "Removal of is_torch_fx_available breaking remote-code models is unrelated to local cache-path collisions." + "reason": "Import slowness and unsafe sys.modules access are not the same defect." }, { "left": "issue:44734", "right": "issue:45632", "accept": false, - "reason": "Server request crash and trust_remote_code cache collision are separate bugs with no shared code path." + "reason": "Serving KV-cache crash and trust_remote_code cache-path collision are unrelated." }, { - "left": "issue:44246", - "right": "issue:45003", + "left": "issue:44561", + "right": "issue:45632", "accept": false, - "reason": "Import-time slowdown and unsafe sys.modules access are related only loosely; they are not the same bug." + "reason": "Both mention trust_remote_code, but one is a missing helper removal breakage and the other is a cache-path collision." }, { "left": "issue:42490", "right": "issue:45632", "accept": false, - "reason": "Import-warning behavior for paths ending in slash is unrelated to cache collisions between local model paths." + "reason": "Both concern local-path handling, but one is a warning on trailing slashes and the other is a leaf-directory cache collision." }, { "left": "issue:43643", "right": "issue:44496", "accept": false, - "reason": "Missing fields from trust_remote_code config loading vs unrecognized model/config.json issue; different failure modes." + "reason": "Missing fields from trust_remote_code config loading is different from an unrecognized model/config error." }, { "left": "issue:44964", "right": "issue:45600", "accept": false, - "reason": "Model-loading failure for one checkpoint vs CI break from removed Sam3LiteText configs; different underlying problems." + "reason": "Model load failure for Phi-4-multimodal-instruct is not the same as stale auto_mappings references breaking CI." }, { "left": "issue:44112", "right": "issue:44964", "accept": false, - "reason": "A stale CI test failure is not the same as a real model-loading regression." + "reason": "CI test flake in GraniteSpeech is unrelated to model loading for Phi-4-multimodal-instruct." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "Both are load-related, but one is a specific test/model loading issue and the other is a different checkpoint load failure." + "reason": "Both are model load reports, but they concern different models and likely different root causes." }, { "left": "issue:42907", "right": "issue:43441", "accept": false, - "reason": "Saving dequantized models and FlashAttention failures are unrelated." + "reason": "Dequantized save failure and FlashAttention failure in Ministral are distinct issues." }, { - "left": "issue:44016", - "right": "issue:44062", + "left": "issue:43976", + "right": "issue:44987", "accept": false, - "reason": "Notebook syntax error vs AddedToken keyword conflict; unrelated bugs." + "reason": "Version/platform compatibility issue is not the same as failing to load a specific model." }, { - "left": "issue:43976", - "right": "issue:44987", + "left": "issue:44016", + "right": "issue:44062", "accept": false, - "reason": "Python-version compatibility and a specific model-loading failure are not the same defect." + "reason": "Notebook syntax error and tokenization API TypeError are unrelated." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "Both mention resize_token_embeddings, but on different model families and different affected embeddings; not a single code-path bug." + "reason": "Different regression targets: processor/tokenizer behavior vs decoder embedding resize propagation." }, { "left": "issue:43673", "right": "issue:44336", "accept": false, - "reason": "Generation cache absence during chunked prefill vs ANSI logging behavior; unrelated." + "reason": "Generation cache regression and ANSI formatting in loading_report are unrelated." }, { "left": "issue:43531", "right": "issue:45600", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and removed auto_mapping configs are separate regressions." + "reason": "Sliding-window model bug and stale auto_mappings references are different code paths." }, { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "Different import errors from different modules/symbols; same class of problem, not the same bug." - }, - { - "left": "issue:44496", - "right": "issue:45042", - "accept": false, - "reason": "Unrecognized-model loading error vs unnecessary torchvision dependency in PIL image processors; different issues." - }, - { - "left": "issue:43526", - "right": "issue:43901", - "accept": false, - "reason": "Image-processor label reduction bug vs documentation mismatch in TextClassificationPipeline; unrelated." - }, - { - "left": "issue:43299", - "right": "issue:45216", - "accept": false, - "reason": "Qwen3-MoE loading regression and Qwen3.5 save_pretrained serialization bug are different model-specific failures." + "reason": "Both are import-related, but one is a missing top-level export and the other is a nonexistent image_utils import." } ] }, @@ -10024,12 +9779,11 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ - "issue:33290", "issue:38175", "issue:39692", "issue:41950", @@ -10037,9 +9791,10 @@ "issue:43299", "issue:43335", "issue:43381", - "issue:43441", + "issue:43450", "issue:43479", "issue:43525", + "issue:43526", "issue:43577", "issue:43650", "issue:43854", @@ -10060,6 +9815,7 @@ "issue:44683", "issue:44779", "issue:45020", + "issue:45042", "issue:45081", "issue:45200", "issue:45216", @@ -10071,157 +9827,175 @@ "issue:45542", "issue:45584", "issue:45593", - "issue:45656", "issue:45759", "issue:45812", "issue:45823", - "issue:45834", "issue:45907" ], "soft_pairs": [ + "issue:44496|issue:45042", + "issue:43526|issue:43901", + "issue:43299|issue:45216", "issue:43335|issue:45593", "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:43299|issue:45357", "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:43976|issue:45405", "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:43577|issue:45216", "issue:39692|issue:43901", - "issue:43299|issue:43854", "issue:44279|issue:45405", + "issue:43299|issue:43854", "issue:43295|issue:44779", "issue:41950|issue:43650", "issue:44462|issue:45081", - "issue:44297|issue:44462", "issue:45081|issue:45907", + "issue:44297|issue:44462", "issue:44016|issue:44291", - "issue:33290|issue:45656", - "issue:43441|issue:45834" + "issue:43450|issue:44279" ], - "prepared_review_unit_hash": "7d9e743bcb22acd3ccaf54dca4d678a314a353705375a47b9f27926b5eaf45ef", + "prepared_review_unit_hash": "ebb1fbfbaded5448d5f51f4780313240f3907517830fc4ed4be167d727ab072f", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36740, - "estimated_input_tokens": 9185, - "estimated_eval_tokens": 18626 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36853, + "estimated_input_tokens": 9214, + "estimated_eval_tokens": 18684 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the soft pairs mostly share broad themes like tokenizers, multimodal models, or deepspeed, but they describe different concrete bugs and code paths. I would not merge any of the soft pairs as duplicates.", - "confidence": 0.98, - "canonical_issue_reason": "No single canonical issue fits this cluster because the items span unrelated regressions and feature bugs. If a representative must be picked, issue:44521 is the best candidate because it is concrete, currently open, and has the strongest inbound discussion signal among the multimodal-related issues.", + "summary": "This cluster is heterogeneous: most items are separate bugs across tokenizers, processors, configs, and model-loading paths. I don\u2019t see any soft pair that clearly describes the same underlying defect, so I rejected them all. The closest umbrella issue is the broad AutoTokenizer/tokenizer-loading regression, but even that is not a true duplicate anchor for the rest.", + "confidence": 0.67, + "canonical_issue_reason": "issue:44462 is the broadest tokenizer-loading regression in the set and has the most obvious overlap with the other tokenizer-related reports, but the cluster is still not a single duplicate bug.", "canonical_pr_reason": null, - "best_issue_reason": "Issue:44521 is the most representative issue in this set: it is specific, actionable, and has the highest visible reuse/reference signal. It is a better cluster anchor than the other items, which are either narrower, stale, or more ambiguous.", + "best_issue_reason": "issue:44462 is the best representative issue because it is broad, user-facing, and sits near several tokenizer-related reports, making it the most plausible triage anchor despite the lack of true duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Different bugs: model config recognition vs PIL image processor torchvision dependency." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast label handling is unrelated to a docs/behavior mismatch for TextClassificationPipeline." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3VL loading regression and Qwen3.5 save_pretrained regression are different code paths." + }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "Different bugs: SwitchTransformers config layer construction vs D-FINE auxiliary-loss behavior." + "reason": "Sparse-layer initialization and D-FINE auxiliary-loss logic are unrelated." }, { "left": "issue:44075", "right": "issue:44368", "accept": false, - "reason": "Unrelated: SGD optimizer args not used vs a Qwen fine-tuning warning about tie_word_embeddings." + "reason": "SGD argument handling is unrelated to a tie_word_embeddings warning." }, { "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "Different code paths: t5gemma embedding resize propagation vs Whisper empty-transcription generation failure." + "reason": "Embedding resize propagation and Whisper empty-transcription handling are different problems." }, { "left": "issue:43976", "right": "issue:44279", "accept": false, - "reason": "One is a Python-version compatibility break; the other is a generic dependency issue without the same failure mode." + "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 denoising/aux-loss handling." + "reason": "Gradient checkpointing in eval mode is unrelated to D-FINE denoising/aux-loss behavior." }, { - "left": "issue:43299", - "right": "issue:45357", + "left": "issue:43901", + "right": "issue:44496", "accept": false, - "reason": "Both involve Qwen multimodal models, but one is a load-time failure and the other is a save_pretrained key regression." + "reason": "Docs drift for return_all_scores does not match AutoTokenizer ignoring tokenizer.json." }, { - "left": "issue:43901", - "right": "issue:44496", + "left": "issue:43299", + "right": "issue:45357", "accept": false, - "reason": "Docs drift for return_all_scores is unrelated to an unrecognized-model/config missing model_type error." + "reason": "Both mention Qwen3.5, but one is model loading and the other is incorrect visual-encoder checkpoint keys." }, { "left": "issue:44496", "right": "issue:45759", "accept": false, - "reason": "Different problems: missing model_type on load vs AutoModelForCausalLM not unwrapping text_config for composite configs." + "reason": "AutoTokenizer repository-file handling and composite config unwrapping are different bugs." }, { "left": "issue:44521", "right": "issue:45325", "accept": false, - "reason": "Both are multimodal, but one is assistant mask generation and the other is Qwen2.5-VL rope index scaling." + "reason": "Multimodal assistant masks and Qwen2.5-VL rope indexing are distinct code paths." }, { "left": "issue:41950", "right": "issue:45020", "accept": false, - "reason": "Video-classification processor lookup bug is not the same as remote_code model-loading regressions." + "reason": "Video-classification processor lookup is unrelated to remote_code model breakage." }, { "left": "issue:44351", "right": "issue:45278", "accept": false, - "reason": "Missing HybridCache import is a specific symbol regression, not the broad import-error cluster from upgrading versions." + "reason": "A specific HybridCache import error is not the same as a broad import-errors-after-upgrade report." }, { - "left": "issue:43976", - "right": "issue:45405", + "left": "issue:44242", + "right": "issue:45200", "accept": false, - "reason": "Python compatibility and an unreleased PEFT minimum-version bump are different dependency issues." + "reason": "Load-balancing loss routing and Gemma 4 mm_token_type_ids defaults are unrelated." }, { - "left": "issue:44242", - "right": "issue:45200", + "left": "issue:43976", + "right": "issue:45405", "accept": false, - "reason": "Load-balancing loss omission and mm_token_type_ids defaulting are separate model-training bugs." + "reason": "Python support regression and a PEFT minimum-version bump are different issues." }, { "left": "issue:43479", "right": "issue:43525", "accept": false, - "reason": "Phi4 multimodal default config initialization is unrelated to Llama4Config missing pad_token_id." + "reason": "Multimodal config default initialization and missing pad_token_id are not the same bug." }, { "left": "issue:44779", @@ -10233,85 +10007,85 @@ "left": "issue:41950", "right": "issue:45823", "accept": false, - "reason": "Video pipeline processor selection is unrelated to Gemma4 PLE device placement during forward." + "reason": "Video processor lookup and Gemma4 PLE device placement are unrelated." }, { "left": "issue:38175", "right": "issue:44617", "accept": false, - "reason": "SigLIP2 zero-probabilities and Sam3Video CUDA OOM are unrelated failure modes." + "reason": "Zero probabilities for SigLIP2 and a Sam3Video OOM are clearly different failures." }, { - "left": "issue:43577", - "right": "issue:45216", + "left": "issue:44683", + "right": "issue:45542", "accept": false, - "reason": "Blip2 dtype propagation is not the same as Qwen3.5 save_pretrained checkpoint corruption." + "reason": "flex_attention compilation on torch 2.9 is unrelated to TensorBoard/TensorFlow backend installation." }, { - "left": "issue:44683", - "right": "issue:45542", + "left": "issue:43577", + "right": "issue:45216", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and tensorboard-without-TF backend errors are unrelated." + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint serialization are different model-loading bugs." }, { "left": "issue:39692", "right": "issue:43901", "accept": false, - "reason": "SigLIP2 documentation example errors are not the same as stale TextClassificationPipeline docs." + "reason": "SigLIP2 doc example errors are not the same as a TextClassificationPipeline docs mismatch." }, { - "left": "issue:43299", - "right": "issue:43854", + "left": "issue:44279", + "right": "issue:45405", "accept": false, - "reason": "Qwen3VL loading regression and GLM-4.7-Flash unit-test loading failure are different model-specific issues." + "reason": "A dependency problem is not the same as bumping MIN_PEFT_VERSION too early." }, { - "left": "issue:44279", - "right": "issue:45405", + "left": "issue:43299", + "right": "issue:43854", "accept": false, - "reason": "A generic dependency issue does not match a specific unreleased MIN_PEFT_VERSION bump." + "reason": "Qwen3VL loading regression and GLM-4.7-Flash test loading are unrelated model-specific issues." }, { "left": "issue:43295", "right": "issue:44779", "accept": false, - "reason": "Custom processor.tokenizer regression is not the same as Deepseek tokenizer producing wrong outputs." + "reason": "Custom processor.tokenizer breakage is not the same as Deepseek tokenizer output regressions." }, { - "left": "issue:44462", - "right": "issue:45081", + "left": "issue:41950", + "right": "issue:43650", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json and a Mistral regex patch crash are different tokenizer code paths." + "reason": "Video pipeline processor lookup and a placeholder issue title are unrelated." }, { - "left": "issue:44297", - "right": "issue:44462", + "left": "issue:44462", + "right": "issue:45081", "accept": false, - "reason": "Tokenizer-class mismatch on save_pretrained is a different bug from AutoTokenizer ignoring repository tokenizer.json." + "reason": "Ignoring tokenizer.json and a Mistral regex patch crash are different tokenizer bugs." }, { "left": "issue:45081", "right": "issue:45907", "accept": false, - "reason": "Mistral regex patching crashes in tokenizer loading; list_repo_files revision forwarding is unrelated repository API plumbing." + "reason": "Tokenizer regex patch failure is unrelated to list_repo_files revision forwarding." }, { - "left": "issue:44016", - "right": "issue:44291", + "left": "issue:44297", + "right": "issue:44462", "accept": false, - "reason": "Notebook syntax error and init_empty_weights argument handling are unrelated." + "reason": "Tokenizer_class metadata mismatch and ignoring tokenizer.json are distinct save/load issues." }, { - "left": "issue:33290", - "right": "issue:45656", + "left": "issue:44016", + "right": "issue:44291", "accept": false, - "reason": "OOM with deepspeed + Adafactor and optimizer.step being called twice are different deepspeed optimizer bugs." + "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated." }, { - "left": "issue:43441", - "right": "issue:45834", + "left": "issue:43450", + "right": "issue:44279", "accept": false, - "reason": "Ministral FlashAttention failure and Kosmos2.5 long-OCR index errors are unrelated model-specific issues." + "reason": "Video processor batching shape is unrelated to a dependency issue." } ] }, @@ -10330,11 +10104,12 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ + "issue:33290", "issue:42175", "issue:42994", "issue:43065", @@ -10342,7 +10117,6 @@ "issue:43262", "issue:43317", "issue:43441", - "issue:43450", "issue:43525", "issue:43643", "issue:43650", @@ -10361,13 +10135,11 @@ "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", @@ -10381,20 +10153,23 @@ "issue:45542", "issue:45593", "issue:45600", + "issue:45656", "issue:45712", - "issue:45823" + "issue:45823", + "issue:45834" ], "soft_pairs": [ - "issue:43450|issue:44279", + "issue:33290|issue:45656", + "issue:43441|issue:45834", "issue:45600|issue:45712", "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:43650|issue:45290", "issue:44623|issue:44749", + "issue:43441|issue:44683", "issue:43653|issue:45593", "issue:43262|issue:44521", "issue:43723|issue:44162", @@ -10411,215 +10186,211 @@ "issue:43824|issue:43976", "issue:44188|issue:44336", "issue:43525|issue:43881", - "issue:43525|issue:43643", - "issue:43450|issue:44617" + "issue:43525|issue:43643" ], - "prepared_review_unit_hash": "395336265ca2c1e82e5d499715cca80fd8d7d76f37f7d39c192c1679a2079774", + "prepared_review_unit_hash": "e4edceb586338d007116c60bb541d9de33c8eeebe712c9c4195fd7ff3f24e42c", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 35943, - "estimated_input_tokens": 8986, - "estimated_eval_tokens": 18228 + "serialized_chars": 35964, + "estimated_input_tokens": 8991, + "estimated_eval_tokens": 18238 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Only one soft edge looks like a true duplicate pair; the rest are distinct issues across separate subsystems or different failure modes.", - "confidence": 0.72, - "canonical_issue_reason": "43643 is the broader root-cause report: `trust_remote_code=True` returns config objects with missing fields; 43525 looks like a specific `pad_token_id` symptom of that bug.", + "summary": "These items are largely unrelated Transformers issues. The soft-pair candidates mostly share broad vocabulary (e.g. deepspeed, apply_chat_template, loading, tokenizer) but do not appear to be the same concrete bug or change, so I reject all soft edges.", + "confidence": 0.89, + "canonical_issue_reason": "issue:44521 is the broadest and most referenced issue in the set, so it is the best available anchor if one must be chosen, though the collection is not a true duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "43643 has the clearest general reproduction of the config-field-loss bug and is the best anchor for deduping the pair.", + "best_issue_reason": "issue:44521 has the widest scope and strongest discussion/inbound-reference signal, making it the most representative issue among otherwise unrelated reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43450", - "right": "issue:44279", + "left": "issue:33290", + "right": "issue:45656", "accept": false, - "reason": "Different bugs: batched video processor shape vs a generic quantized-model save failure." + "reason": "Both involve deepspeed/optimizer behavior, but one is OOM during Adafactor use and the other is double optimizer stepping; different concrete failures." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "Unrelated bugs: FlashAttention failure for Ministral-3 vs long OCR index error in Kosmos2.5." }, { "left": "issue:45600", "right": "issue:45712", "accept": false, - "reason": "Both are cleanup/CI-related, but they target different stale artifacts and different breakages." + "reason": "Both touch generated/dummy mappings, but one is stale Sam3LiteText references and the other is leftover dummy classes; different fixes." }, { "left": "issue:43065", "right": "issue:44898", "accept": false, - "reason": "Unrelated model issues: dummy Conv2d in Sam3PixelDecoder vs Perceiver resolution handling." + "reason": "Different models and symptoms: dummy Conv2d in Sam3PixelDecoder vs Perceiver resolution/interpolation failure." }, { "left": "issue:42994", "right": "issue:43317", "accept": false, - "reason": "Save-failure for quantized models vs load/offload failure for dequantized models; different code paths." + "reason": "Quantized model saving failure and dequantized-model offload loading failure are separate code paths." }, { "left": "issue:44466", "right": "issue:45276", "accept": false, - "reason": "Both involve Gemma4 weights, but one is serialization inconsistency and the other is resize_token_embeddings behavior." + "reason": "One is device-dependent lm_head serialization, the other is resize_token_embeddings not updating Gemma4 embedding/output layers." }, { "left": "issue:44261", "right": "issue:44263", "accept": false, - "reason": "Different GLM/MoE bugs: missing rms_norm_eps precision issue vs torch.split return handling." + "reason": "Different model internals: MLA layernorm epsilon precision issue vs torch.split return handling in GlmMoeDsaIndexer." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing files on processor.save_pretrained is not the same as ZeRO3 from_pretrained failure for gemma-4." }, { "left": "issue:43650", "right": "issue:45290", "accept": false, - "reason": "Generic low-signal issue vs a specific chat_template crash on tool-call messages; not the same bug." + "reason": "The first is a vague data request; the second is a specific apply_chat_template crash with tool-call assistant messages." }, { "left": "issue:44623", - "right": "issue:45397", + "right": "issue:44749", "accept": false, - "reason": "processor.save_pretrained missing files is separate from gemma-4 zero3 from_pretrained loading failures." + "reason": "processor.save_pretrained file omission and Chinese performance regression after upgrade are unrelated." }, { "left": "issue:43441", "right": "issue:44683", "accept": false, - "reason": "Different attention-backend failures: FlashAttention on Ministral-3 vs compiled flex_attention on torch>=2.9." - }, - { - "left": "issue:44623", - "right": "issue:44749", - "accept": false, - "reason": "Missing processor save files vs a tokenizer/filtering performance regression; unrelated symptoms." + "reason": "Both mention attention/flash, but the failures are on different models and different triggers." }, { "left": "issue:43653", "right": "issue:45593", "accept": false, - "reason": "Tokenizer special-token registration vs D-FINE auxiliary-loss logic; different components." + "reason": "Tokenizer special-token registration bug and D-FINE auxiliary-loss logic are unrelated." }, { "left": "issue:43262", "right": "issue:44521", "accept": false, - "reason": "Both touch apply_chat_template, but one is audio sampling-rate defaults and the other is multimodal assistant masks." + "reason": "Both concern apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant_mask generation." }, { "left": "issue:43723", "right": "issue:44162", "accept": false, - "reason": "Tokenizer loading regression vs ESM2 model breakage; no shared underlying defect." + "reason": "Tokenizer loading regression and ESM2 model breakage are different issues." }, { "left": "issue:44016", "right": "issue:45823", "accept": false, - "reason": "Notebook syntax error is unrelated to Gemma4 device-mismatch runtime behavior." + "reason": "Notebook syntax error is unrelated to Gemma4 device-mismatch during forward." }, { "left": "issue:43673", "right": "issue:43761", "accept": false, - "reason": "Generation cache regression and CLIP hidden_states regression are separate model-path bugs." + "reason": "Generation cache missing in chunked_prefill and CLIPVisionModel hidden_states regression are separate bugs." }, { "left": "issue:42175", "right": "issue:43976", "accept": false, - "reason": "TF backend packaging issue vs Python version compatibility regression; different root causes." + "reason": "Packaging/backend omission is not the same as a Python-version compatibility failure." }, { "left": "issue:44361", "right": "issue:45593", "accept": false, - "reason": "MLukeTokenizer task AttributeError is unrelated to D-FINE auxiliary-loss behavior." + "reason": "MLukeTokenizer AttributeError and D-FINE auxiliary-loss behavior are unrelated." }, { "left": "issue:44671", "right": "issue:44779", "accept": false, - "reason": "Different failures: CamemBERT masked-LM predictions vs Deepseek tokenizer correctness." + "reason": "Both are model/tokenizer regressions in v5, but the affected models and failure modes differ." }, { "left": "issue:43784", "right": "issue:45542", "accept": false, - "reason": "Sentence-transformers import NameError and TF backend packaging error are separate import/dependency issues." + "reason": "Importing sentence-transformers fails due to missing nn; the other is a TensorFlow backend packaging issue." }, { "left": "issue:43901", "right": "issue:43994", "accept": false, - "reason": "Docs mismatch for return_all_scores vs a model/pipeline output quality issue; not duplicate bugs." + "reason": "Docs mismatch for return_all_scores is unrelated to incorrect SigLIP2 inference results." }, { "left": "issue:44987", "right": "issue:45542", "accept": false, - "reason": "Loading a specific model failing in v5.1.0 is not the same as the TensorFlow backend dependency problem." + "reason": "Loading a specific model on transformers>=5.1.0 and tensorboard-only TensorFlow backend issues are different." }, { "left": "issue:43122", "right": "issue:43650", "accept": false, - "reason": "Tokenizer output changed across versions vs an unrelated low-signal issue." + "reason": "Tokenization behavior change and a vague 'ADD THE DATA' request do not describe the same bug." }, { "left": "issue:44297", "right": "issue:45397", "accept": false, - "reason": "Tokenizer metadata saved incorrectly vs gemma-4 zero3 loading; separate save/load issues." + "reason": "Tokenizer save_pretrained metadata mismatch is unrelated to gemma-4 ZeRO3 loading." }, { "left": "issue:43824", "right": "issue:43976", "accept": false, - "reason": "ImportError for a missing model class vs Python 3.9 support regression; different failure modes." + "reason": "Missing Qwen2.5-VL export and Python 3.9/3.10 compatibility are unrelated." }, { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "Attention kernel branching under torch.compile is unrelated to ANSI code emission in loading_report." + "reason": "Attention-kernel divergence under torch.compile is unrelated to ANSI code emission in loading_report." }, { "left": "issue:43525", "right": "issue:43881", "accept": false, - "reason": "Llama4Config missing pad_token_id is not the same as GLM-4V loading failure." + "reason": "Llama4Config missing pad_token_id and glm-4v-9b load failure are different model-specific issues." }, { "left": "issue:43525", "right": "issue:43643", - "accept": true, - "reason": "Both describe missing fields on configs returned by AutoConfig/trust_remote_code; 43525 is a concrete missing-pad_token_id instance of the broader bug." - }, - { - "left": "issue:43450", - "right": "issue:44617", "accept": false, - "reason": "Batched video processor shape bug is unrelated to Sam3Video CUDA OOM." + "reason": "A missing config attribute in Llama4Config is not the same as trust_remote_code dropping fields from AutoConfig." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The analysis is grounded in the packet and stays conservative overall. The single accepted soft edge, issue:43525 with issue:43643, is a plausible duplicate based on the shared missing-config-field failure mode, and the other rejections are framed as distinct failure modes or subsystems without overstating the 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 }, @@ -10631,21 +10402,20 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36246", "issue:41628", "issue:41950", "issue:42491", "issue:42757", - "issue:43065", "issue:43232", "issue:43299", "issue:43352", - "issue:43408", + "issue:43450", "issue:43526", "issue:43531", "issue:43596", @@ -10664,6 +10434,7 @@ "issue:44496", "issue:44561", "issue:44589", + "issue:44617", "issue:44749", "issue:44779", "issue:44857", @@ -10682,15 +10453,15 @@ "issue:45563", "issue:45584", "issue:45593", - "issue:45701", - "issue:45759" + "issue:45701" ], "soft_pairs": [ + "issue:43450|issue:44617", "issue:44589|issue:45362", "issue:41628|issue:43976", "issue:43901|issue:44246", - "issue:45561|issue:45563", "issue:44336|issue:44373", + "issue:45561|issue:45563", "issue:42491|issue:43299", "issue:44242|issue:45593", "issue:44295|issue:45397", @@ -10698,261 +10469,256 @@ "issue:44246|issue:44496", "issue:43531|issue:45362", "issue:43352|issue:45250", - "issue:36246|issue:42757", "issue:44336|issue:44485", + "issue:36246|issue:42757", "issue:43526|issue:45003", "issue:36246|issue:44351", "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:44162|issue:45200", "issue:36246|issue:43596", - "issue:44877|issue:45375", "issue:44779|issue:45292", + "issue:44877|issue:45375", "issue:45292|issue:45584", "issue:43901|issue:45003", "issue:45292|issue:45701", "issue:43232|issue:44336", - "issue:44987|issue:45459", "issue:44496|issue:45003", - "issue:43065|issue:43408", - "issue:45375|issue:45759" + "issue:44987|issue:45459" ], - "prepared_review_unit_hash": "2576f80e9e2645550051fc4e979259e8b8e963f483c9f9b342950b5e116c298c", + "prepared_review_unit_hash": "0f1dc857b05fe3a4cf5f0842988a3941516c9115db91c2dbcc3e317afb77295e", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37279, - "estimated_input_tokens": 9320, - "estimated_eval_tokens": 18896 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36335, + "estimated_input_tokens": 9084, + "estimated_eval_tokens": 18424 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly heterogeneous regression reports around Transformers v5, model/config loading, and unrelated utility bugs; I did not find any pair that clearly describes the same underlying fix target.", - "confidence": 0.31, - "canonical_issue_reason": "issue:44561 is the broadest, clearest compatibility regression report in the set: a concrete v5 removal breaking trust_remote_code model loading, which makes it the best umbrella issue among otherwise unrelated model-specific failures.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers regressions (imports, model-specific loading, generation, docs, testing, and performance). Only one soft pair looks like a plausible duplicate; the rest are too different in code path or failure mode to merge.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44877 is the clearest concrete bug in the cluster and the best representative of the only strong overlap: strict config handling dropping required model fields during loading.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44561 is the strongest representative issue because it has a specific failure mode, clear upgrade context, and broad downstream impact compared with the more narrow or ambiguous reports.", + "best_issue_reason": "44877 is the most suitable single issue to anchor the cluster because it matches the same strict-config code path as the only plausible duplicate candidate and is more specific than the broader version-breakage reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Different bugs: pipeline processor selection vs CUDA OOM in Sam3Video." + }, { "left": "issue:44589", "right": "issue:45362", "accept": false, - "reason": "Different failures: a missing Float8 storage class versus a Qwen chat crash; no shared code path is evident." + "reason": "One is a storage/type import failure; the other is a Qwen chat/runtime crash." }, { "left": "issue:41628", "right": "issue:43976", "accept": false, - "reason": "ImportError vs Python-version compatibility; same package area, but not the same bug." + "reason": "Import export regression vs Python-version compatibility issue; not the same bug." }, { "left": "issue:43901", "right": "issue:44246", "accept": false, - "reason": "Docstring mismatch for text classification is unrelated to intermittent import slowness." + "reason": "Docs mismatch vs a MoE load-balancing loss bug in training." }, { - "left": "issue:45561", - "right": "issue:45563", + "left": "issue:44336", + "right": "issue:44373", "accept": false, - "reason": "Pytest-xdist file race and a stale generation warning are unrelated behaviors." + "reason": "Different scopes: terminal ANSI output vs a wrong docstring." }, { - "left": "issue:44336", - "right": "issue:44373", + "left": "issue:45561", + "right": "issue:45563", "accept": false, - "reason": "ANSI output leakage and a wrong docstring are separate documentation/runtime issues." + "reason": "Test race condition vs a stale generation warning; unrelated code paths." }, { "left": "issue:42491", "right": "issue:43299", "accept": false, - "reason": "Both involve Qwen3 MoE, but one is LoRA loading on hf4.x/hf5.x and the other is multimodal model loading; too different to merge." + "reason": "Both involve Qwen/MoE, but one is LoRA compatibility across versions and the other is a model-loading failure." }, { "left": "issue:44242", "right": "issue:45593", "accept": false, - "reason": "Missing load-balancing loss and missing auxiliary losses in D-FINE are different training-loss bugs." + "reason": "Similar symptom shape, but different models and loss mechanisms." }, { "left": "issue:44295", "right": "issue:45397", "accept": false, - "reason": "Buffer access on position_ids and a Gemma-4 ZeRO-3 loading problem are unrelated." + "reason": "Buffer registration error vs ZeRO-3 from_pretrained loading problem." }, { "left": "issue:41950", "right": "issue:44220", "accept": false, - "reason": "Video-classification pipeline processor lookup and fbank feature extraction are different pipeline/audio issues." + "reason": "Video pipeline processor lookup vs audio feature extraction; unrelated." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import performance and unrecognized model config are not the same underlying bug." + "reason": "Import performance issue vs unrecognized model/config loading failure." }, { "left": "issue:43531", "right": "issue:45362", "accept": false, - "reason": "Both mention Qwen models, but one is sliding-window behavior and the other is a chat crash; different code paths." + "reason": "Both Qwen-related, but sliding_window handling and chat crashes are different problems." }, { "left": "issue:43352", "right": "issue:45250", "accept": false, - "reason": "A model-specific Flash Attention support gap is not the same as the generic Flash Attention 2.0 issue." + "reason": "Specific model/Flash-Attn incompatibility vs a generic Flash Attention topic." }, { - "left": "issue:36246", - "right": "issue:42757", + "left": "issue:44336", + "right": "issue:44485", "accept": false, - "reason": "Different missing symbols from different libraries; both are import errors but not one duplicate bug." + "reason": "ANSI-report formatting vs GLM-5 RoPE implementation; no overlap." }, { - "left": "issue:44336", - "right": "issue:44485", + "left": "issue:36246", + "right": "issue:42757", "accept": false, - "reason": "ANSI-code output and GLM-5 RoPE implementation are unrelated." + "reason": "Both are import errors, but for different symbols and modules." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "Image label reduction logic and unsafe sys.modules access are distinct bugs." + "reason": "Image-processor label reduction bug vs unsafe sys.modules access; unrelated." }, { "left": "issue:36246", "right": "issue:44351", "accept": false, - "reason": "Missing Qwen2.5 VL export and missing HybridCache export are separate symbol-export regressions." + "reason": "Different missing exports from different parts of the package." }, { "left": "issue:45003", "right": "issue:45561", "accept": false, - "reason": "sys.modules access safety and captured-info file races do not share a fix target." + "reason": "Import/module safety bug vs a test file race condition." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Both are v5 regressions, but one is generation cache/chunked prefill and the other is trust_remote_code import behavior; too broad to merge." + "reason": "Both are v5 regressions, but generation cache and trust_remote_code import removal are different code paths." }, { "left": "issue:44246", "right": "issue:44871", "accept": false, - "reason": "Import slowdown and Gemma EOS-token config inconsistency are unrelated." + "reason": "Import slowdown vs Gemma eos_token_id config mismatch." }, { "left": "issue:44242", "right": "issue:44857", "accept": false, - "reason": "Load-balancing loss omission and float16 CUDA crash are different loss/runtime failures." - }, - { - "left": "issue:44162", - "right": "issue:45200", - "accept": false, - "reason": "ESM2 breakage and Gemma-4 mm_token_type_ids defaulting are separate model issues." + "reason": "Different failures: missing auxiliary loss vs AMP/CUDA crash." }, { "left": "issue:44295", "right": "issue:44749", "accept": false, - "reason": "Position_ids buffer access and post-upgrade data-filter slowness are unrelated." + "reason": "Position_ids buffer error vs a data-filtering performance regression." }, { - "left": "issue:36246", - "right": "issue:43596", + "left": "issue:44162", + "right": "issue:45200", "accept": false, - "reason": "ImportError for a missing processor class and a zero-sized tensor IndexError are unrelated." + "reason": "Different models and different bugs; not mergeable." }, { - "left": "issue:44877", - "right": "issue:45375", + "left": "issue:36246", + "right": "issue:43596", "accept": false, - "reason": "Both involve strict config handling, but they are different model configs and different symptoms; too broad to treat as one duplicate." + "reason": "Import symbol issue vs DeepSpeed zero3/BertModel indexing error." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "Tokenizer output regression and resize_token_embeddings/output_embeddings mismatch are separate tokenization/model-editing bugs." + "reason": "Tokenizer output regression vs embedding-resize synchronization bug." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": true, + "reason": "Both point to the same strict-config code path dropping required fields from model configs." }, { "left": "issue:45292", "right": "issue:45584", "accept": false, - "reason": "Embedding resize behavior and Whisper empty-transcription generation failure are unrelated." + "reason": "Embedding resize bug vs Whisper empty-transcription generation failure." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "TextClassificationPipeline docs and unsafe sys.modules access are unrelated." + "reason": "Docs issue vs unsafe module lookup; no common underlying bug." }, { "left": "issue:45292", "right": "issue:45701", "accept": false, - "reason": "Output-embedding resize bug and version-dependent tokenization changes are not the same issue." + "reason": "Resize-embeddings behavior vs version-dependent tokenization changes." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs after sync_gpus and ANSI-code emission are unrelated." - }, - { - "left": "issue:44987", - "right": "issue:45459", - "accept": false, - "reason": "A model-loading failure on transformers>=5.1.0 and hidden tokenizer errors from protobuf handling are different bugs." + "reason": "Generation kwargs bug vs terminal ANSI output bug." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Model config recognition and sys.modules access safety are different parts of the loading stack." - }, - { - "left": "issue:43065", - "right": "issue:43408", - "accept": false, - "reason": "SAM3 pixel-decoder implementation and SAM3 tracker/model-type warning are different issues." + "reason": "Config/model recognition vs sys.modules access safety." }, { - "left": "issue:45375", - "right": "issue:45759", + "left": "issue:44987", + "right": "issue:45459", "accept": false, - "reason": "A strict-config field omission and AutoModelForCausalLM text_config unwrapping are separate composite-config bugs." + "reason": "Model loading failure vs tokenizer exception masking; different layers." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The summary matches the packet\u2019s titles and the one accepted soft pair (44877/45375) is the only clearly defensible overlap: both are strict-config omissions in model config loading. The other rejections stay appropriately cautious and do not overclaim duplicate evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -10964,28 +10730,27 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:28282", "issue:30990", - "issue:42371", "issue:42886", "issue:42994", + "issue:43065", "issue:43232", "issue:43257", "issue:43262", + "issue:43408", "issue:43475", "issue:43482", "issue:43540", - "issue:43643", "issue:43646", "issue:43653", "issue:43673", "issue:43931", - "issue:44038", "issue:44060", "issue:44077", "issue:44162", @@ -11001,7 +10766,6 @@ "issue:44933", "issue:44977", "issue:44995", - "issue:45092", "issue:45137", "issue:45200", "issue:45229", @@ -11010,24 +10774,27 @@ "issue:45310", "issue:45335", "issue:45356", - "issue:45381", + "issue:45375", "issue:45397", "issue:45459", "issue:45563", "issue:45588", "issue:45600", - "issue:45656" + "issue:45656", + "issue:45759" ], "soft_pairs": [ + "issue:43065|issue:43408", + "issue:45375|issue:45759", "issue:42886|issue:45229", "issue:43262|issue:44246", "issue:43257|issue:45137", "issue:44995|issue:45200", - "issue:44060|issue:44077", "issue:43475|issue:43540", - "issue:44466|issue:45335", + "issue:44060|issue:44077", "issue:45397|issue:45656", "issue:43653|issue:44162", + "issue:44466|issue:45335", "issue:44995|issue:45588", "issue:44368|issue:45563", "issue:44368|issue:44977", @@ -11045,227 +10812,217 @@ "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" + "issue:28282|issue:30990" ], - "prepared_review_unit_hash": "a3b5e6c0b97ba765baaeade95f6f6192787dd2fe77833838d6eb66f5bfc010b7", + "prepared_review_unit_hash": "809bad2185657622bcbcf4e78bac2cf52e89f42376d6bf7ee7ef8e005a9f1a7a", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37147, - "estimated_input_tokens": 9287, - "estimated_eval_tokens": 18830 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36006, + "estimated_input_tokens": 9002, + "estimated_eval_tokens": 18260 }, "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 regression reports, many centered on v5-era model loading/generation/tokenizer issues. I don\u2019t see any pair that clearly describes the same concrete bug or a mergeable PR-sized fix.", - "confidence": 0.82, - "canonical_issue_reason": "issue:43646 is the broadest representative regression report: it frames a general v5.0 breakage in custom model initialization, which fits the overall upgrade-regression theme better than the more model-specific tickets.", + "summary": "This cluster is very heterogeneous: it mixes unrelated tokenizer, generation, model-loading, DeepSpeed, SAM3, Gemma, Qwen, and save/load bugs. I do not see any soft pair that is clearly the same underlying issue; all should stay separate. The broadest representative is the generic v5 regression/import report, but it still does not meaningfully cover the rest.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45278 is the most umbrella-like report (\u201cmany import errors after update\u2026\u201d), so it is the closest thing to a cluster representative, even though the cluster itself is too mixed to have a truly good canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the best single issue to anchor the cluster because it is general, user-visible, and closest to the shared theme of Transformers v5 compatibility breakages.", + "best_issue_reason": "issue:45278 is the broadest issue in the set and the closest fit for a representative cluster label.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Both are SAM3-related, but one is about a dummy Conv2d in the pixel decoder and the other is a model-type warning for sam3_video vs sam3_tracker; different bugs." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal config handling, but one is about a missing config field being dropped and the other is about AutoModelForCausalLM.from_config not unwrapping text_config; not the same fix." + }, { "left": "issue:42886", "right": "issue:45229", "accept": false, - "reason": "Offline tokenizer cache loading and Gemma4 multi-GPU OOM are unrelated failures in different code paths." + "reason": "Offline tokenizer cache loading and Gemma4 multi-GPU CUDA OOM are unrelated problems." }, { "left": "issue:43262", "right": "issue:44246", "accept": false, - "reason": "Audio processor sampling-rate defaults and import slowdown are not the same bug." + "reason": "Audio chat-template sample-rate defaulting and slow import behavior are unrelated." }, { "left": "issue:43257", "right": "issue:45137", "accept": false, - "reason": "Both involve DeepSpeed, but one is Qwen3 MOE weight conversion and the other is a ZeRO3 deque error." + "reason": "Both mention DeepSpeed, but one is Qwen3 MoE weight conversion during loading and the other is a ZeRO3 deque error; different code paths." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "A stale second-forward cache crash is unrelated to the mm_token_type_ids defaulting issue." - }, - { - "left": "issue:44060", - "right": "issue:44077", - "accept": false, - "reason": "Incorrect tied-weights warnings and patchtsmixer post_init allowance are different model/config behaviors." + "reason": "GlmMoeDsa stale indexer cache on second forward pass is unrelated to Gemma4 mm_token_type_ids defaults." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "SAM3 video encoder missing attribute and Qwen3OmniMoe video processing ValueError are different bugs." + "reason": "Different model families and failures: SAM3 video output attribute error vs Qwen3OmniMoe video-processing ValueError." }, { - "left": "issue:44466", - "right": "issue:45335", + "left": "issue:44060", + "right": "issue:44077", "accept": false, - "reason": "Serialization of tied lm_head weights is not the same as resize_token_embeddings failing to update decoder embeddings." + "reason": "Qwen3-Next tied-weights warning and patchtsmixer post_init allowance are unrelated." }, { "left": "issue:45397", "right": "issue:45656", "accept": false, - "reason": "Gemma4 from_pretrained with ZeRO3 and duplicated optimizer steps are different DeepSpeed problems." + "reason": "Gemma-4 Zero3 from_pretrained failure and a duplicated optimizer step under DeepSpeed are different bugs." }, { "left": "issue:43653", "right": "issue:44162", "accept": false, - "reason": "BigBirdTokenizer special-token registration and ESM2 breakage are unrelated tokenizer/model issues." + "reason": "BigBirdTokenizer special-token registration and ESM2 being broken are not the same underlying issue." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both concern tied-embedding behavior, but one is serialization of lm_head.weight and the other is resize_token_embeddings not updating decoder.embed_tokens; different concrete failures." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "A model cache crash and a flash-attention sinkless AttributeError are different failure modes." + "reason": "Stale indexer cache crash in GlmMoeDsa and flash-attention s_aux=None AttributeError are unrelated." }, { "left": "issue:44368", "right": "issue:45563", "accept": false, - "reason": "A tie_word_embeddings warning and a stale num_return_sequences warning are not the same underlying issue." + "reason": "A tied-word-embeddings warning for Qwen3.5 fine-tuning is unrelated to a stale num_return_sequences warning in paged generate()." }, { "left": "issue:44368", "right": "issue:44977", "accept": false, - "reason": "A config warning is not the same as Qwen3.5 flash-attention generation failure." + "reason": "Both involve Qwen3.5, but one is a configuration warning and the other is a flash-attention generation failure; not the same bug." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Generation cache missing and KV-cache continuation indexing are both generation-related, but they are distinct code-path bugs." + "reason": "Chunked-prefill cache missing and /v1/responses KV-cache continuation indexing are different generation bugs." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "A ZeRO3 deque error and stale auto_mappings references are unrelated." + "reason": "DeepSpeed ZeRO3 deque error and removed Sam3LiteText config references are unrelated." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch is not the same as a tied-embeddings warning." + "reason": "Qwen3-VL weight-shape mismatch and a tied-embeddings warning are unrelated." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "A missing import from image_utils and suppressed tokenizer decode errors are different import/error-handling bugs." + "reason": "Missing image_utils import and hidden tokenizer decode errors when protobuf is absent are different import-path issues." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Whisper word-timestamp decode crash and Kimi-K2.5 codec regression are both tokenizer-adjacent, but not the same defect." + "reason": "Whisper timestamp decode crash and Kimi-K2.5 tokenizer regression are distinct tokenizer/decoding problems." }, { "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "Tokenizer save_pretrained config mismatch and processor save_pretrained missing files are separate serialization issues." + "reason": "Tokenizer save_pretrained writing the wrong tokenizer_class and processor.save_pretrained missing files are related to saving, but not the same concrete bug." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "sync_gpus generation kwargs handling and chunked_prefill cache missing are different generation regressions." + "reason": "Both are generation/cache-related, but one is sync_gpus kwarg updating and the other is chunked_prefill cache availability; different fixes." }, { "left": "issue:44361", "right": "issue:44749", "accept": false, - "reason": "MLukeTokenizer task AttributeError and slowdown after upgrade are unrelated symptoms." + "reason": "MLukeTokenizer task AttributeError and a slowdown after upgrading transformers are unrelated." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Custom model initialization breakage and ESM2 breakage are both broad regressions, but not the same concrete bug." + "reason": "Generic custom model initialization breakage and ESM2-specific failure are not the same issue." }, { "left": "issue:43673", "right": "issue:45278", "accept": false, - "reason": "Missing GenerationMixin cache in chunked_prefill is not the same as many import errors after upgrade." + "reason": "Generation cache missing during chunked_prefill is unrelated to broad import errors after upgrading." }, { "left": "issue:44623", "right": "issue:45656", "accept": false, - "reason": "Processor serialization missing files and duplicated optimizer steps do not share a code path." + "reason": "Processor save_pretrained missing files and duplicated DeepSpeed optimizer steps are unrelated." }, { "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "Performance slowdown after upgrade and repeated optimizer stepping are unrelated." + "reason": "A performance regression after upgrading transformers and a duplicated optimizer step under DeepSpeed are different problems." }, { "left": "issue:44749", "right": "issue:45310", "accept": false, - "reason": "Data filtering slowdown and Qwen3.5 MOE from_pretrained failure are different bugs." + "reason": "Both mention Qwen3.5, but one is a slowdown report and the other is a from_pretrained error with newer transformers; not the same bug." }, { "left": "issue:42994", "right": "issue:43482", "accept": false, - "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are different directions of the serialization/load pipeline." - }, - { - "left": "issue:28282", - "right": "issue:30990", - "accept": false, - "reason": "PyTorch-missing ImportError and Sentence Transformers hanging on load are unrelated issues." + "reason": "Quantized model saving failure and GGUF loading failure are opposite-direction serialization/loading issues, not one bug." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "The generic bug report provides no concrete overlap with Gemma4 Zero3 from_pretrained." - }, - { - "left": "issue:42371", - "right": "issue:45092", - "accept": false, - "reason": "TF32 settings guidance and InternVL2 meta-initialization incompatibility are unrelated." - }, - { - "left": "issue:43475", - "right": "issue:43643", - "accept": false, - "reason": "SAM3 video encoder attribute loss and trust_remote_code AutoConfig field loss are different failures." + "reason": "'Bug report' is too vague to match concretely, and the Gemma-4 Zero3 from_pretrained issue is specific; no evidence they are the same." }, { - "left": "issue:44038", - "right": "issue:44623", + "left": "issue:28282", + "right": "issue:30990", "accept": false, - "reason": "Qwen3-VL-Moe v5 issue and processor save_pretrained missing files are not the same bug." + "reason": "PyTorch missing ImportError for AutoModel and Sentence Transformers hanging on load are unrelated." } ] }, @@ -11284,10 +11041,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:30990", "issue:35141", @@ -11295,6 +11052,7 @@ "issue:41628", "issue:42175", "issue:42222", + "issue:42371", "issue:42673", "issue:42831", "issue:42898", @@ -11302,18 +11060,16 @@ "issue:43232", "issue:43377", "issue:43475", - "issue:43479", "issue:43504", "issue:43525", "issue:43526", + "issue:43643", "issue:43673", "issue:43704", - "issue:43784", "issue:43824", "issue:43873", "issue:43976", "issue:44038", - "issue:44079", "issue:44188", "issue:44222", "issue:44242", @@ -11323,276 +11079,283 @@ "issue:44623", "issue:44661", "issue:44792", - "issue:44869", "issue:44933", "issue:44945", "issue:44964", "issue:45081", + "issue:45092", "issue:45103", "issue:45137", "issue:45200", "issue:45310", "issue:45375", + "issue:45381", "issue:45478", "issue:45561", "issue:45712", "issue:45753" ], "soft_pairs": [ + "issue:42371|issue:45092", + "issue:44038|issue:44623", + "issue:43475|issue:43643", + "issue:43475|issue:45381", "issue:41628|issue:44933", "issue:45081|issue:45103", - "issue:43475|issue:44661", "issue:42994|issue:43525", + "issue:43475|issue:44661", "issue:45375|issue:45478", "issue:43232|issue:44188", - "issue:42673|issue:43704", "issue:45310|issue:45375", "issue:43873|issue:44945", + "issue:42673|issue:43704", "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:43824", - "issue:42222|issue:45200", + "issue:36010|issue:41628", "issue:42175|issue:45712", + "issue:42222|issue:45200", "issue:43232|issue:44792", "issue:44038|issue:45310", - "issue:43526|issue:45561", "issue:43377|issue:44242", "issue:44496|issue:45561", - "issue:43504|issue:45561", + "issue:43526|issue:45561", "issue:44964|issue:45137", + "issue:43504|issue:45561", "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", - "issue:43784|issue:43824" + "issue:43976|issue:44933" ], - "prepared_review_unit_hash": "aae2b7f7a365c5119c8a224012c96782590731b73970ca4049d28b676ffa7711", + "prepared_review_unit_hash": "069a14d0d03fd11cd4a0f31762d92f43af48b6837343bc15128f0edd45c31a96", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37509, - "estimated_input_tokens": 9378, - "estimated_eval_tokens": 19012 + "serialized_chars": 37473, + "estimated_input_tokens": 9369, + "estimated_eval_tokens": 18994 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most pairs are only loosely similar and should stay separate. The only accepted soft-edge duplicate is issue:42673 / issue:43704, which share the same title and appear to describe the same Qwen3ForCausalLM VRAM leak, with 42673 showing more discussion. No PR cluster is present.", - "confidence": 0.88, - "canonical_issue_reason": "issue:42673 is the better canonical issue because it is the earlier report and has substantially more discussion than issue:43704, while the titles indicate the same Qwen3ForCausalLM VRAM leak scenario.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers issues. Among the provided soft pairs, only issue:42673 / issue:43704 is a clear duplicate; the rest are conservative non-matches. No PR pairings are present.", + "confidence": 0.97, + "canonical_issue_reason": "There is no single canonical issue for the whole cluster because the items cover many unrelated bugs. The only true duplicate subcluster in the provided soft pairs is the Qwen3ForCausalLM VRAM leak report, where issue:42673 is the best representative and issue:43704 is its duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42673 is the best issue overall because it is the clearest anchor for the duplicate pair and the later issue:43704 looks like a repeat report of the same bug.", + "best_issue_reason": "issue:42673 is the best canonical issue candidate because it is the earlier, fuller report for the exact Qwen3ForCausalLM multi-dataloader-thread VRAM leak, and issue:43704 repeats the same bug.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "Different bugs: TF32 API guidance versus a meta-initialization incompatibility in old InternVL2 remote code." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Different code paths and symptoms: Qwen3-VL-Moe loading error versus processor.save_pretrained missing files." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "Different failures: missing Sam3VisionEncoderOutput attribute versus AutoConfig losing fields under trust_remote_code." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Related vision models, but not the same bug: SAM 3 attribute error versus qwen2.5-vl position-id issue." + }, { "left": "issue:41628", "right": "issue:44933", "accept": false, - "reason": "Both are import-related, but they name different missing symbols and do not show the same concrete bug." + "reason": "Both are import-related, but they involve different missing symbols and different modules." }, { "left": "issue:45081", "right": "issue:45103", "accept": false, - "reason": "Tokenizer regex crash vs auto-docstring AttributeError are different code paths and different failures." + "reason": "Different crash sites: Mistral tokenizer regex patching versus auto-docstring kwargs processing." }, { - "left": "issue:43475", - "right": "issue:44661", + "left": "issue:42994", + "right": "issue:43525", "accept": false, - "reason": "SAM 3 vision encoder attribute error and tokenizer-mapping model-addition failure are unrelated." + "reason": "Unrelated problems: quantized model saving failure versus Llama4Config missing pad_token_id." }, { - "left": "issue:42994", - "right": "issue:43525", + "left": "issue:43475", + "right": "issue:44661", "accept": false, - "reason": "Quantized model saving failure and missing pad_token_id on Llama4Config are different bugs." + "reason": "Different bugs: SAM output attribute issue versus add-new-model-like failing in TOKENIZER_MAPPING_NAMES." }, { "left": "issue:45375", "right": "issue:45478", "accept": false, - "reason": "Same model family, but the visible reports describe different failure modes and not one shared root cause." + "reason": "Same model family, but different concrete issues: missing deepstack_visual_indexes versus a from_pretrained error." }, { "left": "issue:43232", "right": "issue:44188", "accept": false, - "reason": "Generation kwargs handling after sync_gpus and attention-kernel divergence under torch.compile are different problems." - }, - { - "left": "issue:42673", - "right": "issue:43704", - "accept": true, - "reason": "Identical title and closely matching symptom indicate the same Qwen3ForCausalLM VRAM leak bug." + "reason": "Different generation bugs: sync_gpus update behavior versus attention-kernel divergence under torch.compile." }, { "left": "issue:45310", "right": "issue:45375", "accept": false, - "reason": "Both involve Qwen3.5 MoE, but one is a from_pretrained error and the other is a missing config field; not enough to treat as the same bug." + "reason": "Both involve Qwen3.5-related models, but one is a from_pretrained error and the other is a missing vision config field." }, { "left": "issue:43873", "right": "issue:44945", "accept": false, - "reason": "Quantization/offloading behavior and pipeline-parallel output correctness are different issues." + "reason": "Different problem areas: quantization/offloading behavior versus incorrect pipeline-parallel LLM output." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact same reported bug and symptom: Qwen3ForCausalLM VRAM leak when used across multiple dataloader threads." }, { "left": "issue:41628", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but they refer to different missing exports and likely different fixes." + "reason": "Different missing imports: AutoImageProcessor versus HybridCache." }, { "left": "issue:42831", "right": "issue:44222", "accept": false, - "reason": "FP8 accuracy issue versus FP8 save_pretrained bug are related thematically but not the same concrete change." + "reason": "Different FP8 issues: accuracy regression versus save_pretrained failure for MoE." }, { "left": "issue:44945", "right": "issue:45753", "accept": false, - "reason": "Pipeline-parallel output mismatch and an infinite loop on a specific image are distinct bugs." + "reason": "Both are generation-related, but they concern different models and different failure modes." }, { "left": "issue:44222", "right": "issue:45310", "accept": false, - "reason": "FP8 save/pretrained issue and Qwen3.5 MoE from_pretrained error do not point to one shared code-path problem." + "reason": "Different concrete bugs: FP8 MoE save_pretrained versus Qwen3.5 MoE from_pretrained error." }, { "left": "issue:43673", "right": "issue:44188", "accept": false, - "reason": "Generation cache missing in chunked prefill and attention-kernel branching under torch.compile are different code paths." - }, - { - "left": "issue:36010", - "right": "issue:41628", - "accept": false, - "reason": "Both are import failures, but for different symbols and different breakages." + "reason": "Unrelated generation/cache bug versus a compile-time attention branching issue." }, { "left": "issue:42994", "right": "issue:43824", "accept": false, - "reason": "Quantized model saving and missing Qwen2_5_VL import are unrelated." + "reason": "Saving quantized models and importing Qwen2_5_VLForConditionalGeneration are unrelated." }, { - "left": "issue:42222", - "right": "issue:45200", + "left": "issue:36010", + "right": "issue:41628", "accept": false, - "reason": "Broken vitpose models and Gemma 4 token-type-id defaults are separate model-specific bugs." + "reason": "Both are import errors, but for different symbols and different API surfaces." }, { "left": "issue:42175", "right": "issue:45712", "accept": false, - "reason": "Packaging/backend dependency issue and leftover dummy classes leaking into dir(transformers) are not the same bug." + "reason": "Packaging/backend dependency behavior is not the same as leftover dummy classes leaking into dir(transformers)." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Different model/component breakages: VitPose models versus Gemma 4 mm_token_type_ids defaults." }, { "left": "issue:43232", "right": "issue:44792", "accept": false, - "reason": "Generation kwargs update after sync_gpus and a janus test failure do not share a concrete root cause." + "reason": "Different bugs: generation kwargs update versus a Janus image-generation test failure." }, { "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Different Qwen model variants with different failure modes; too broad to merge." - }, - { - "left": "issue:43526", - "right": "issue:45561", - "accept": false, - "reason": "Processor label-reduction bug and pytest-xdist file-race bug are unrelated." + "reason": "Different model variants and failures: Qwen3-VL-Moe loading bug versus Qwen3.5 MoE from_pretrained error." }, { "left": "issue:43377", "right": "issue:44242", "accept": false, - "reason": "Missing padding-mask support in MIMI encoder and missing load balancing loss are different bugs." + "reason": "Different sub-systems: MIMI padding-mask batching bug versus MoE load-balancing loss logic." }, { "left": "issue:44496", "right": "issue:45561", "accept": false, - "reason": "Unrecognized model load failure and test-worker file race are unrelated." + "reason": "Model config loading failure is unrelated to the pytest-xdist file race." }, { - "left": "issue:43504", + "left": "issue:43526", "right": "issue:45561", "accept": false, - "reason": "Beit legacy-field loading issue and xdist race on captured_info.txt are unrelated." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to the xdist race on captured_info.txt." }, { "left": "issue:44964", "right": "issue:45137", "accept": false, - "reason": "Phi-4 multimodal load failure and DeepSpeed ZeRO3 deque underflow are different problems." + "reason": "Different failures: Phi-4 multimodal loading versus a DeepSpeed ZeRO3 deque error." + }, + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "Beit pretrained preset legacy-field issue is unrelated to the testing-utils race." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "Missing TensorFlow backend dependency and nonexistent image_utils import are different issues." + "reason": "Dependency/backend install issue is unrelated to the missing image_utils import." }, { "left": "issue:42898", "right": "issue:44568", "accept": false, - "reason": "clean_up_tokenization_spaces behavior change and missing BOS/EOS with add_special_tokens are distinct tokenizer regressions." - }, - { - "left": "issue:30990", - "right": "issue:35141", - "accept": false, - "reason": "Sentence-Transformers loading hang and embedding reinitialization after resize are unrelated." + "reason": "Different tokenizer regressions: cleanup-space behavior change versus add_special_tokens BOS/EOS behavior." }, { "left": "issue:43976", "right": "issue:44933", "accept": false, - "reason": "Python version compatibility breakage and image_utils import error are not the same bug." - }, - { - "left": "issue:43479", - "right": "issue:44869", - "accept": false, - "reason": "Multimodal config default initialization bug and Whisper timestamp decoding crash are unrelated." - }, - { - "left": "issue:43479", - "right": "issue:44079", - "accept": false, - "reason": "Config defaulting bug and ModelOutput key assignment bug are different code paths." + "reason": "Python version compatibility issue is unrelated to the missing image_utils import." } ] }, "evaluator_result": { "accept": false, - "feedback": "The core duplicate call on issue:42673 / issue:43704 looks plausible from the identical title, but the writeup overstates the evidence in a few places. The packet does not show their full descriptions, so phrases like \u201cexact same \u2026 in title and description\u201d are too strong. Also, the justification about having \u201cmore discussion/inbound references\u201d is only partly grounded: 42673 clearly has more discussion, but both items show 0 inbound references in the packet. The soft-edge verdicts themselves are mostly conservative, but the overall summary should be tightened to stay within the visible evidence." + "feedback": "Mostly grounded, but the summary is slightly overclaimed: among the listed soft pairs, only issue:42673/issue:43704 is an accepted duplicate. The second Qwen3.5 MoE from_pretrained pair is not one of the provided soft pairs, so calling it a true 'soft pair' duplicate is imprecise. The rest of the verdicts look conservative." }, "evaluator_used": true, "retried": true, @@ -11608,17 +11371,16 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:22355", "issue:28282", "issue:30333", "issue:33290", "issue:34689", - "issue:35141", "issue:36331", "issue:41628", "issue:42757", @@ -11630,23 +11392,25 @@ "issue:43479", "issue:43644", "issue:43723", + "issue:43784", + "issue:43824", "issue:43874", "issue:44060", + "issue:44079", "issue:44188", "issue:44190", "issue:44206", "issue:44222", - "issue:44263", "issue:44295", "issue:44297", "issue:44373", "issue:44448", - "issue:44483", "issue:44484", "issue:44568", "issue:44623", "issue:44734", "issue:44779", + "issue:44869", "issue:44933", "issue:44977", "issue:45092", @@ -11656,26 +11420,29 @@ "issue:45310", "issue:45356", "issue:45405", - "issue:45406", "issue:45656", "issue:45712", "issue:45812", "issue:45834" ], "soft_pairs": [ + "issue:43479|issue:44869", + "issue:43479|issue:44079", + "issue:44623|issue:45310", + "issue:43784|issue:43824", "issue:44188|issue:44373", - "issue:42898|issue:45812", "issue:43278|issue:45137", + "issue:42898|issue:45812", "issue:44734|issue:45103", "issue:30333|issue:33290", - "issue:43874|issue:45092", "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:42898|issue:44448", "issue:44933|issue:45712", "issue:44222|issue:44297", "issue:44297|issue:45656", @@ -11692,201 +11459,240 @@ "issue:44222|issue:44484", "issue:43232|issue:45834", "issue:43723|issue:44977", - "issue:28282|issue:30333", - "issue:44263|issue:45092", - "issue:30333|issue:35141", - "issue:44483|issue:45406" + "issue:28282|issue:30333" ], - "prepared_review_unit_hash": "c9edff0655d02f829e62f71bb6152f01daa9df32c32302d5802cf0d14f6f3bf2", + "prepared_review_unit_hash": "0addc67cd4e93fdd756b4568460ebded52120856c34163c07488f1581a2545f0", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37555, - "estimated_input_tokens": 9389, - "estimated_eval_tokens": 19034 + "soft_pair_count": 34, + "serialized_chars": 37872, + "estimated_input_tokens": 9468, + "estimated_eval_tokens": 19192 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous; the soft-similarity pairs do not look like true duplicates. The strongest standalone issue is the open Granite tokenizer regression, but it is not the same bug as the others.", - "confidence": 0.88, - "canonical_issue_reason": "issue:45812 is the best representative target because it is an open, detailed regression report with inbound references; among these otherwise unrelated issues, it has the highest signal as a duplicate anchor.", + "summary": "The soft pairs are mostly false positives: they connect unrelated import errors, tokenizer regressions, training issues, and config/model bugs that do not share the same concrete fix. No PRs are present in the cluster. The closest hub is the v5 tokenizer regression issue, but it is still only a loose representative, not a true duplicate anchor.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 42898 is the broadest hub among the soft edges and best matches the recurring v5 tokenizer-regression theme, even though most neighboring pairs are not true duplicates.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45812 is the most suitable global issue target: active, concrete, user-impacting, and well-scoped enough to serve as a duplicate destination, even though it does not match the other items.", + "best_issue_reason": "42898 is the least narrow representative of the cluster because it sits at the center of several tokenizer-related soft links and has the strongest chance of being the intended anchor issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44188", - "right": "issue:44373", + "left": "issue:43479", + "right": "issue:44869", "accept": false, - "reason": "Different bugs: attention-kernel divergence under torch.compile vs a docstring typo for position_ids." + "reason": "Different subsystems: multimodal config initialization vs Whisper timestamp decoding crash." }, { - "left": "issue:42898", - "right": "issue:45812", + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "One is config default handling; the other is ModelOutput key assignment logic." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Both involve saving/loading, but the concrete bugs are different processor files vs Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import failures in different packages and code paths." + }, + { + "left": "issue:44188", + "right": "issue:44373", "accept": false, - "reason": "Both are tokenizer-related, but one is a v5 cleanup-space behavior change and the other is wrong token IDs for Granite models; different root causes." + "reason": "Attention-kernel divergence under torch.compile is unrelated to a docstring typo." }, { "left": "issue:43278", "right": "issue:45137", "accept": false, - "reason": "Embedding dtype drift in evaluation is unrelated to a DeepSpeed ZeRO3 deque IndexError." + "reason": "Different runtime problems: dtype drift during eval vs DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they describe different concrete failures and likely different fixes." }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "Serve KV-cache continuation crash and auto-docstring annotation crash are different code paths and failure modes." + "reason": "Serve KV-cache indexing bug is unrelated to auto-docstring annotation parsing." }, { "left": "issue:30333", "right": "issue:33290", "accept": false, - "reason": "MLflow reporting on failed jobs is unrelated to an OOM in Adafactor with DeepSpeed." + "reason": "MLflow reporting on failed jobs and an Adafactor+DeepSpeed OOM are unrelated bugs." }, { - "left": "issue:43874", - "right": "issue:45092", + "left": "issue:43723", + "right": "issue:44568", "accept": false, - "reason": "Missing image-processor method vs remote-code/meta-initialization incompatibility; not the same bug." + "reason": "General tokenizer loading regression is not the same as mdeberta special-token behavior." }, { - "left": "issue:43723", - "right": "issue:44568", + "left": "issue:43874", + "right": "issue:45092", "accept": false, - "reason": "Tokenizer loading failure and add_special_tokens/BOS-EOS regression are distinct issues." + "reason": "Different multimodal loading failures with different root causes." }, { "left": "issue:42898", "right": "issue:45356", "accept": false, - "reason": "Both mention tokenizer regressions, but the model-specific symptoms and likely fixes differ." + "reason": "Both are tokenizer regressions, but they affect different models and behaviors." }, { "left": "issue:44060", "right": "issue:45125", "accept": false, - "reason": "Incorrect tied-weights warning is unrelated to a missing tensor-parallel plan." + "reason": "Tied-weights warning bug is unrelated to missing tensor-parallel plan support." }, { "left": "issue:42898", "right": "issue:44779", "accept": false, - "reason": "General tokenizer cleanup behavior change is not the same as DeepSeek producing incorrect tokenization results." + "reason": "Different tokenizer regressions affecting different models and failure modes." }, { "left": "issue:45405", "right": "issue:45712", "accept": false, - "reason": "A dependency version bump and leftover dummy-class cleanup are unrelated maintenance issues." + "reason": "Unreleased PEFT version bump is unrelated to dummy class cleanup." }, { - "left": "issue:42898", - "right": "issue:44448", + "left": "issue:44295", + "right": "issue:45656", "accept": false, - "reason": "Tokenizer whitespace cleanup behavior and Pegasus output mismatch are different regressions." + "reason": "Position_ids buffer access bug is unrelated to double optimizer stepping under DeepSpeed." }, { - "left": "issue:44295", - "right": "issue:45656", + "left": "issue:42898", + "right": "issue:44448", "accept": false, - "reason": "Position_ids buffer handling is unrelated to optimizer.step being called twice with DeepSpeed." + "reason": "Both mention v4/v5 output changes, but they do not point to the same concrete defect." }, { "left": "issue:44933", "right": "issue:45712", "accept": false, - "reason": "Missing import from image_utils and dummy-class leakage are different cleanup/import problems." + "reason": "Missing image_utils import and dummy-class leakage are separate API-surface issues." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "FP8 save_pretrained behavior and tokenizer_config metadata mismatch do not share the same code path." + "reason": "Different save_pretrained bugs: FP8 MoE serialization vs tokenizer config mismatch." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch is unrelated to DeepSpeed optimizer stepping." }, { "left": "issue:43116", "right": "issue:44190", "accept": false, - "reason": "Multi-label classification example output and local image dataset loading are unrelated example-script issues." + "reason": "Different example scripts and different failures." }, { "left": "issue:43479", "right": "issue:43644", "accept": false, - "reason": "Default config initialization and non-persistent buffer junk are distinct model state bugs." + "reason": "Config None-handling is unrelated to non-persistent buffer initialization." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "Both involve save_pretrained, but FP8/MoE saving and processor file omission are not the same fix." + "reason": "Both are save_pretrained-related, but on different objects and different bugs." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "FineGrainedFP8 accuracy regression is unrelated to processor.save_pretrained missing files." + "reason": "FP8 accuracy drift is unrelated to missing processor save files." }, { "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Unsupported center argument in a feature extractor is unrelated to the auto-docstring annotation crash." + "reason": "Feature extractor argument regression is unrelated to auto-docstring annotation handling." }, { "left": "issue:41628", "right": "issue:42757", "accept": false, - "reason": "Two separate import errors for different missing symbols; they do not point to one underlying defect." + "reason": "Two separate import errors from different modules and different missing symbols." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "Missing transformers.onnx and missing PyTorch are different dependency/import failures." + "reason": "Different import errors caused by different missing dependencies/modules." }, { "left": "issue:30333", "right": "issue:36331", "accept": false, - "reason": "MLflow reporting on failed training jobs is unrelated to a CustomTrainer compute_loss signature change." + "reason": "MLflow reporting on failure is unrelated to CustomTrainer.compute_loss signature mismatch." }, { "left": "issue:30333", "right": "issue:34689", "accept": false, - "reason": "Training-job reporting and Llama model-loading regression are different problems." + "reason": "Training-job reporting and Llama model loading regression are unrelated." }, { "left": "issue:44297", "right": "issue:45310", "accept": false, - "reason": "Tokenizer save metadata mismatch and Qwen3.5 MoE from_pretrained failure are not the same underlying bug." + "reason": "Tokenizer save_pretrained metadata bug is unrelated to Qwen3.5 MoE loading failure." }, { - "left": "issue:44263", - "right": "issue:45092", + "left": "issue:44222", + "right": "issue:44484", "accept": false, - "reason": "GlmMoeDsaIndexer torch.split behavior and InternVL2 meta-init incompatibility are unrelated." + "reason": "FP8 MoE serialization bug is unrelated to max_shard_size default behavior." }, { "left": "issue:43232", "right": "issue:45834", "accept": false, - "reason": "Generation kwarg update logic and long OCR input indexing are different failure modes." + "reason": "Generation KV-cache update bug is unrelated to long-ocr indexing in Kosmos2.5." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression is unrelated to flash-attention generation failure." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "AutoModel missing PyTorch and MLflow job reporting are unrelated." } ] }, @@ -11905,15 +11711,14 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ - "issue:22355", - "issue:28218", + "issue:30333", "issue:30990", - "issue:33357", + "issue:35141", "issue:38175", "issue:39401", "issue:41628", @@ -11933,21 +11738,19 @@ "issue:43824", "issue:44038", "issue:44060", - "issue:44117", "issue:44261", "issue:44263", "issue:44295", - "issue:44297", "issue:44360", "issue:44373", "issue:44442", + "issue:44483", "issue:44485", "issue:44514", "issue:44521", "issue:44568", "issue:44623", - "issue:44704", - "issue:44743", + "issue:44829", "issue:44871", "issue:44913", "issue:44991", @@ -11956,19 +11759,25 @@ "issue:45278", "issue:45310", "issue:45357", + "issue:45406", "issue:45593", - "issue:45753" + "issue:45753", + "issue:46002" ], "soft_pairs": [ - "issue:44263|issue:44360", + "issue:30333|issue:35141", + "issue:44263|issue:45092", "issue:44373|issue:44485", + "issue:44263|issue:44360", "issue:44295|issue:44623", "issue:44514|issue:45103", + "issue:44483|issue:45406", "issue:44261|issue:45092", - "issue:45092|issue:45357", "issue:43723|issue:44871", + "issue:45092|issue:45357", "issue:43723|issue:44991", "issue:30990|issue:38175", + "issue:44829|issue:46002", "issue:43723|issue:44442", "issue:41628|issue:43824", "issue:43479|issue:44913", @@ -11984,221 +11793,210 @@ "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", - "issue:44295|issue:44297", - "issue:43232|issue:44743" + "issue:42371|issue:44263" ], - "prepared_review_unit_hash": "17ae752da0a7d4660a9a1a654bea36c8a277f1e0b1d11f2941c8f61ca2994646", + "prepared_review_unit_hash": "4bf002b9695d4cdc9486247621a88f7c6f630b34ed35c765c7f8fbca9cf42ac5", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36309, - "estimated_input_tokens": 9078, - "estimated_eval_tokens": 18412 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35590, + "estimated_input_tokens": 8898, + "estimated_eval_tokens": 18052 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is a mixed bag of tokenizer, import, config, and model-specific regression reports rather than a single duplicate thread. None of the soft pairs look like the same underlying bug or change; the broad tokenizer-loading regression issue is the best umbrella node.", - "confidence": 0.88, - "canonical_issue_reason": "issue:43723 is the broadest, most umbrella-like tokenizer regression here and best represents the tokenizer-loading side of this heterogeneous cluster.", - "canonical_pr_reason": null, - "best_issue_reason": "issue:43723 is the most general issue in the set and can anchor the cluster better than the highly specific model/config tickets.", - "best_pr_reason": null, + "summary": "This cluster is heterogeneous: most items are unrelated bug reports spanning tokenizer loading, model config, generation, serving, and training. I do not see a single duplicate family that safely unifies the whole set.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out; the items are mostly distinct defects in different code paths and models, so forcing one duplicate target would be misleading.", + "canonical_pr_reason": "No PRs are present in the provided items.", + "best_issue_reason": "Issue 43723 is the closest thing to a hub only because it is a broad tokenizer-loading regression in v5, but it is still too general to serve as a true canonical for this mixed set.", + "best_pr_reason": "No PRs are present in the provided items.", "soft_edge_verdicts": [ + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Training-job MLflow reporting and embedding reinitialization are unrelated bugs." + }, { "left": "issue:44263", - "right": "issue:44360", + "right": "issue:45092", "accept": false, - "reason": "Both mention DSA/indexer internals, but one is about torch.split return handling and the other about a missing ReLU; different bugs." + "reason": "DSA torch.split behavior and InternVL2 meta-init incompatibility affect different code paths." }, { "left": "issue:44373", "right": "issue:44485", "accept": false, - "reason": "A docstring mismatch is not the same as a RoPE implementation discussion; no shared concrete failure." + "reason": "A wrong docstring and a RoPE implementation bug are not the same underlying issue." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA/indexer, but one is a torch.split bug and the other is a missing ReLU; different defects." }, { "left": "issue:44295", "right": "issue:44623", "accept": false, - "reason": "Reading a buffer-backed position_ids tensor and missing processor save files are unrelated save/load problems." + "reason": "Reading registered position_ids buffers and processor.save_pretrained file omission are unrelated." }, { "left": "issue:44514", "right": "issue:45103", "accept": false, - "reason": "One is a Qwen2_5_VL chat-template batching crash; the other is an auto-docstring annotation crash. Different subsystems." + "reason": "Multimodal chat-template batching and auto_docstring future-annotations crashes are separate problems." }, { - "left": "issue:44261", - "right": "issue:45092", + "left": "issue:44483", + "right": "issue:45406", "accept": false, - "reason": "MLA layernorm epsilon handling and InternVL2 meta-init compatibility are distinct multimodal issues." + "reason": "API request validation failure and Gemma4Processor missing _tokenizer are different failures." }, { - "left": "issue:45092", - "right": "issue:45357", + "left": "issue:44261", + "right": "issue:45092", "accept": false, - "reason": "Both are multimodal-model regressions, but one is meta initialization for remote-code checkpoints and the other is incorrect visual encoder keys on save." + "reason": "Layernorm epsilon precision mismatch and remote-code meta-init incompatibility are unrelated." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "Both involve tokenizer/model loading, but one is a generic AutoTokenizer load regression and the other is an eos_token_id config mismatch." + "reason": "Generic tokenizer-loading regression and Gemma eos_token_id mismatch are different bugs." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "InternVL2 meta-init incompatibility and Qwen3.5 save_pretrained key corruption do not share the same code path." }, { "left": "issue:43723", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer load failures, but the affected model and likely root cause are different; too broad to merge as duplicates." + "reason": "Both concern tokenizers in v5, but they describe different model-specific loading failures; not enough to merge." }, { "left": "issue:30990", "right": "issue:38175", "accept": false, - "reason": "Sentence-Transformers loading hang and zero-probability outputs are unrelated symptoms and code paths." + "reason": "Sentence-transformers loading stalls and SigLIP2 zero probabilities are unrelated." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "Flash-attention training degeneration and NaNs after checkout/init are different training-path defects." }, { "left": "issue:43723", "right": "issue:44442", "accept": false, - "reason": "FastSpeech2ConformerTokenizer load failure is a model-specific tokenizer registration problem, not the same as the v5 AutoTokenizer regression." + "reason": "AutoTokenizer generic loading regression and FastSpeech2ConformerTokenizer failure are not clearly the same root cause." }, { "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but they concern different missing symbols from different model families." + "reason": "Missing AutoImageProcessor and missing Qwen2_5_VLForConditionalGeneration are distinct import errors." }, { "left": "issue:43479", "right": "issue:44913", "accept": false, - "reason": "Default multimodal config initialization and GPTNeoX rotary_pct reload behavior are separate config bugs." + "reason": "Default vision/audio config initialization and rotary_pct reload behavior are unrelated config bugs." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "FineGrainedFP8 accuracy and Qwen3.5 Moe from_pretrained errors are unrelated regressions." + "reason": "FineGrainedFP8 accuracy and Qwen3.5 from_pretrained errors are different issues." }, { "left": "issue:44263", "right": "issue:44373", "accept": false, - "reason": "Indexer split-return behavior and a docstring issue are not the same functional bug." + "reason": "A runtime torch.split bug and a docstring mistake are not duplicates." }, { "left": "issue:39401", "right": "issue:44568", "accept": false, - "reason": "Offset mapping correctness and add_special_tokens BOS/EOS behavior are different tokenizer behaviors." + "reason": "Wrong offset_mapping and missing BOS/EOS insertion are different tokenizer behaviors." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "An FP8 accuracy issue and a Qwen3-VL-Moe bug are unrelated." + "reason": "FP8 accuracy regression and Qwen3-VL-Moe bug reports are unrelated." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "A specific missing import from huggingface_hub is not the same as a broad set of import errors after upgrade." + "reason": "A specific missing import from huggingface_hub and a broad 'many import errors' report are not the same concrete bug." }, { "left": "issue:42886", "right": "issue:42994", "accept": false, - "reason": "Offline cache loading for tokenizers and quantized model saving are different storage-path failures." + "reason": "Offline cache tokenizer loading and quantized model saving are unrelated." }, { "left": "issue:43232", "right": "issue:45593", "accept": false, - "reason": "Generation-state handling after sync_gpus and D-FINE auxiliary-loss logic are unrelated model behaviors." + "reason": "Generation kwargs update and D-FINE auxiliary-loss behavior are separate code paths." }, { "left": "issue:43756", "right": "issue:44060", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and Qwen3-Next tied-weights warnings are different architecture-specific issues." + "reason": "Smollm3 RoPE layer count and Qwen3-Next tied-weights warning are different model-definition bugs." }, { "left": "issue:43576", "right": "issue:43784", "accept": false, - "reason": "Broken transformers env CLI and a sentence-transformers import NameError are separate failures." + "reason": "Broken env command and sentence-transformers import NameError are unrelated." }, { "left": "issue:42831", "right": "issue:45753", "accept": false, - "reason": "FP8 accuracy regression and Qwen3_5 infinite-loop behavior are unrelated." + "reason": "FP8 accuracy regression and Qwen3_5 infinite-loop behavior are different failures." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Offline tokenizer cache loading and wrong decoder type in v5 are different tokenizer/config problems." + "reason": "Offline tokenizer cache loading and wrong tokenizer decoder type are different tokenizer issues." }, { "left": "issue:43122", "right": "issue:44521", "accept": false, - "reason": "Tokenization changes across versions and multimodal assistant_mask handling are different bugs." + "reason": "Tokenization drift across versions and multimodal assistant_mask output are unrelated." }, { "left": "issue:42371", "right": "issue:44263", "accept": false, - "reason": "TF32 API guidance and DSA indexer split behavior do not share a concrete code-path problem." - }, - { - "left": "issue:22355", - "right": "issue:28218", - "accept": false, - "reason": "Missing transformers.onnx module and an extra-space tokenizer bug are unrelated." - }, - { - "left": "issue:44117", - "right": "issue:44704", - "accept": false, - "reason": "A tokenizer-mapping None bug and passing kwargs to cached_file in AutoProcessor are separate load-path issues." - }, - { - "left": "issue:30990", - "right": "issue:33357", - "accept": false, - "reason": "A loading hang and a MacOS bus error are different runtime failures." - }, - { - "left": "issue:44295", - "right": "issue:44297", - "accept": false, - "reason": "Buffer access for position_ids and tokenizer_config class mismatch are unrelated serialization bugs." - }, - { - "left": "issue:43232", - "right": "issue:44743", - "accept": false, - "reason": "Both involve generation/cache behavior, but one resets recurrent states and the other is a separate modular_qwen3_5 cache bug." + "reason": "TF32 settings API guidance and a torch.split return-value bug are not duplicates." } ] }, @@ -12217,33 +12015,34 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ + "issue:22355", + "issue:28218", "issue:29127", "issue:30990", + "issue:33357", "issue:36296", - "issue:38617", "issue:39401", "issue:41628", "issue:42757", "issue:42907", - "issue:43066", "issue:43116", "issue:43122", - "issue:43278", + "issue:43232", "issue:43408", "issue:43452", "issue:43475", - "issue:43493", + "issue:43646", "issue:43784", "issue:43824", "issue:43937", "issue:43976", - "issue:43992", "issue:44038", + "issue:44117", "issue:44222", "issue:44261", "issue:44295", @@ -12257,38 +12056,43 @@ "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" + "issue:46002" ], "soft_pairs": [ + "issue:44117|issue:44704", + "issue:22355|issue:28218", + "issue:43646|issue:46002", + "issue:30990|issue:33357", + "issue:44295|issue:44297", + "issue:43232|issue:44743", "issue:44704|issue:45290", "issue:42907|issue:44945", "issue:43122|issue:44514", "issue:41628|issue:45278", "issue:43976|issue:44945", + "issue:44261|issue:44373", "issue:43784|issue:45600", "issue:39401|issue:44488", - "issue:44261|issue:44373", - "issue:43408|issue:43475", "issue:42907|issue:43937", + "issue:43408|issue:43475", "issue:44360|issue:44485", - "issue:44625|issue:44829", "issue:39401|issue:44521", "issue:43116|issue:45200", + "issue:44625|issue:44829", "issue:44038|issue:44297", - "issue:29127|issue:30990", "issue:42907|issue:44964", + "issue:29127|issue:30990", "issue:43122|issue:44779", "issue:44038|issue:44295", "issue:36296|issue:43116", @@ -12296,242 +12100,222 @@ "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", - "issue:43066|issue:44779", - "issue:38617|issue:45278" + "issue:42757|issue:44351" ], - "prepared_review_unit_hash": "2552135a8a8c9ea209aa57914601d3c7c03b1a822959f2133beb4abd25a3c167", + "prepared_review_unit_hash": "5dec8af14112048f5fd271ee1c5b94f6279cf3b4a6be1b9a9563bca6c315a449", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37179, - "estimated_input_tokens": 9295, - "estimated_eval_tokens": 18846 + "soft_pair_count": 31, + "serialized_chars": 36572, + "estimated_input_tokens": 9143, + "estimated_eval_tokens": 18542 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is highly heterogeneous: most items are distinct model-, tokenizer-, import-, or training-path bugs, not duplicates. I did not find any soft pair that looks like the same underlying issue or change.", - "confidence": 0.94, - "canonical_issue_reason": "issue:44779 is the most self-contained, actionable regression report in the set, with a clear version boundary and concrete tokenizer misbehavior.", + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues across tokenization, imports, generation, multimodal models, and training/runtime regressions. The soft links are largely lexical/topic similarity rather than the same concrete bug, so I reject all soft edges.", + "confidence": 0.9, + "canonical_issue_reason": "45278 is the broadest umbrella regression in the set (multiple import errors after upgrading), so it is the best representative issue for this heterogeneous cluster, though the cluster is not a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44779 is the best representative issue for triage because it is specific, reproducible, and clearly scoped.", + "best_issue_reason": "45278 is the most generic and representative issue here; it best summarizes the cluster\u2019s broad \u201cimport breakage after upgrade\u201d theme even if it does not match the other issues exactly.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Different failure modes: tokenizer mapping fallback vs AutoProcessor kwargs not reaching cached_file. Same API surface, but not the same bug." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "One is a missing module import, the other is tokenization spacing after added tokens. No shared underlying code-path." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Custom model initialization breakage and NaNs in classification heads are distinct training/runtime problems." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Both are loading-related, but one is a hang and the other is a Mac bus error with CLIP; different root causes." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Position_ids buffer access and tokenizer_class metadata mismatch are unrelated save/load behaviors." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/cache, but one is sync_gpus bookkeeping and the other is recurrent state reset with seq_len>1." + }, { "left": "issue:44704", "right": "issue:45290", "accept": false, - "reason": "Different code paths: cached_file kwarg forwarding vs chat-template tokenization crash with tool-call messages." + "reason": "cached_file argument forwarding is unrelated to chat template crashes on tool-call assistant messages." }, { "left": "issue:42907", "right": "issue:44945", "accept": false, - "reason": "Unrelated failures: dequantized model saving vs incorrect outputs under pipeline parallelism." + "reason": "Saving dequantized Ministral/Devstral models and incorrect output under pipeline parallelism are different bugs." }, { "left": "issue:43122", "right": "issue:44514", "accept": false, - "reason": "Both are tokenizer/chat-template complaints, but one is a tokenization regression and the other is a batched processor padding crash." + "reason": "Tokenizer-version drift and apply_chat_template batching/padding failure are different tokenization paths." }, { "left": "issue:41628", "right": "issue:45278", "accept": false, - "reason": "One is a single missing export; the other is a broad upgrade-time import breakage across many symbols." + "reason": "Both are import errors, but 41628 is a specific missing symbol while 45278 is a broad upgrade breakage report; not the same concrete issue." }, { "left": "issue:43976", "right": "issue:44945", "accept": false, - "reason": "Python-version compatibility problem vs pipeline-parallel inference correctness are not the same bug." + "reason": "Python-version compatibility and pipeline-parallel wrong output are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A model config precision bug and a wrong docstring are not the same underlying problem." }, { "left": "issue:43784", "right": "issue:45600", "accept": false, - "reason": "Import NameError in sentence-transformers integration vs stale auto_mappings references to removed configs." + "reason": "Sentence-transformers import failure and broken auto_mappings references in CI are separate breakages." }, { "left": "issue:39401", "right": "issue:44488", "accept": false, - "reason": "Tokenizer offset-mapping bug for Qwen3 is unrelated to loading a specific model repository." + "reason": "Qwen3 offset_mapping errors and loading cjvt/sleng-bert are different tokenizer/model-loading issues." }, { - "left": "issue:44261", - "right": "issue:44373", + "left": "issue:42907", + "right": "issue:43937", "accept": false, - "reason": "Runtime precision/config issue vs a docstring mismatch; not the same underlying defect." + "reason": "Save_pretrained failure for dequantized models and invalid GenerationConfig for GLM-5 are unrelated." }, { "left": "issue:43408", "right": "issue:43475", "accept": false, - "reason": "A warning about mismatched model types is different from an attribute error in SAM3 vision encoder output." - }, - { - "left": "issue:42907", - "right": "issue:43937", - "accept": false, - "reason": "Different subsystems: save/dequantization failure vs invalid generation config handling." + "reason": "Both are SAM3-related, but a model-type warning and a missing output attribute are distinct bugs." }, { "left": "issue:44360", "right": "issue:44485", "accept": false, - "reason": "Unrelated ML internals: DSA indexer activation vs GLM-5 RoPE implementation." - }, - { - "left": "issue:44625", - "right": "issue:44829", - "accept": false, - "reason": "Config propagation bug in Qwen3.5 is unrelated to flash_attention_3 causing degenerate training." + "reason": "DSA indexer activation and GLM-5 RoPE implementation are unrelated subsystems." }, { "left": "issue:39401", "right": "issue:44521", "accept": false, - "reason": "Both involve tokenization-like behavior, but offset mapping and assistant mask generation are different defects." + "reason": "Wrong offset mappings and all-zero assistant masks are different tokenizer/chat-template bugs." }, { "left": "issue:43116", "right": "issue:45200", "accept": false, - "reason": "Example-script multi-label output bug vs Gemma 4 multimodal token-type defaulting are not the same path." + "reason": "Multi-label classification returning empty results and mm_token_type_ids defaults are not the same issue." }, { - "left": "issue:44038", - "right": "issue:44297", + "left": "issue:44625", + "right": "issue:44829", "accept": false, - "reason": "Qwen3-VL-Moe loading bug vs tokenizer save metadata mismatch; different operations and symptoms." + "reason": "Qwen3.5 num_labels propagation and flash_attention_3 degenerate training are unrelated classification/modeling problems." }, { - "left": "issue:29127", - "right": "issue:30990", + "left": "issue:44038", + "right": "issue:44297", "accept": false, - "reason": "LayoutLMv3 error-message clarity vs Sentence Transformers loading hang are unrelated." + "reason": "Qwen3-VL-Moe loading and tokenizer_class metadata mismatch do not share a concrete code-path." }, { "left": "issue:42907", "right": "issue:44964", "accept": false, - "reason": "Dequantized save failure vs loading Phi-4 multimodal instruct are separate model-loading/saving issues." + "reason": "Dequantized save_pretrained issues and failing to load Phi-4 multimodal instruct are separate model lifecycle bugs." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang are not the same bug." }, { "left": "issue:43122", "right": "issue:44779", "accept": false, - "reason": "Both are tokenization regressions, but they affect different models and different tokenization behaviors." + "reason": "Tokenizer behavior drift in v5 and Deepseek tokenizer incorrect results are different tokenizer regressions." }, { "left": "issue:44038", "right": "issue:44295", "accept": false, - "reason": "Qwen3-VL-Moe bug vs position_ids buffer read error; no shared code path is evident." + "reason": "Qwen3-VL-Moe bug and position_ids buffer read error are unrelated." }, { "left": "issue:36296", "right": "issue:43116", "accept": false, - "reason": "Tensor-parallel training bug is unrelated to the multi-label classification example script returning empty results." + "reason": "Tensor parallel training bug and example-script multi-label classification empty outputs are different problems." }, { "left": "issue:42907", "right": "issue:43452", "accept": false, - "reason": "Saving a dequantized model and gguf_file loading failures are different serialization/loading problems." + "reason": "Saving dequantized models and gguf_file breaking from_pretrained are unrelated load/save bugs." }, { "left": "issue:43824", "right": "issue:44351", "accept": false, - "reason": "Two import errors, but for different symbols and likely different missing-export causes." + "reason": "Missing Qwen2.5-VL export and missing HybridCache export are both import errors but not the same symbol or fix." }, { "left": "issue:44038", "right": "issue:44222", "accept": false, - "reason": "Qwen3-VL-Moe loading issue vs FP8 save_pretrained failure are distinct save/load paths." + "reason": "Qwen3-VL-Moe loading and FP8 moe save_pretrained are distinct model-format issues." }, { "left": "issue:45216", "right": "issue:45478", "accept": false, - "reason": "Both mention Qwen3.5 and newer versions, but one is save_pretrained checkpoint corruption and the other is from_pretrained loading failure." + "reason": "Qwen3.5 save_pretrained regression and Qwen3.5 Moe from_pretrained error may be adjacent, but the titles point to different concrete failures and code-paths." }, { "left": "issue:42757", "right": "issue:44351", "accept": false, - "reason": "Different packages and symbols: huggingface_hub import failure vs transformers import failure." - }, - { - "left": "issue:43278", - "right": "issue:44945", - "accept": false, - "reason": "Training/evaluate dtype drift is unrelated to incorrect outputs under pipeline parallelism." - }, - { - "left": "issue:43493", - "right": "issue:45753", - "accept": false, - "reason": "SigLIP2 implementation discrepancy and Qwen3_5 image-specific infinite loop are different model-specific bugs." - }, - { - "left": "issue:42907", - "right": "issue:44222", - "accept": false, - "reason": "Saving dequantized models vs FP8 moe save_pretrained are similar only at a very broad level, not the same bug." - }, - { - "left": "issue:43122", - "right": "issue:44977", - "accept": false, - "reason": "Both are tokenizer regressions in v5, but they concern different models and likely different fixes." - }, - { - "left": "issue:43992", - "right": "issue:44704", - "accept": false, - "reason": "Missing embed_tokens.weight in UMT5Encoder loading is unrelated to AutoProcessor kwarg forwarding." - }, - { - "left": "issue:43784", - "right": "issue:45446", - "accept": false, - "reason": "Import NameError from latest transformers vs a PyTorch version check bug in flex_attention are unrelated." - }, - { - "left": "issue:43066", - "right": "issue:44779", - "accept": false, - "reason": "Wrong tokenizer decoder type and incorrect Deepseek tokenization are both tokenizer-related, but not the same concrete defect." - }, - { - "left": "issue:38617", - "right": "issue:45278", - "accept": false, - "reason": "A single missing import symbol and a broad post-upgrade import breakage are not sufficiently the same root cause." + "reason": "Different missing imports from different packages; only the surface symptom matches." } ] }, @@ -12550,300 +12334,299 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:22355", "issue:29127", "issue:33453", "issue:38617", "issue:39401", - "issue:41628", "issue:42222", "issue:42371", "issue:42673", + "issue:42907", "issue:43064", + "issue:43066", "issue:43116", - "issue:43421", + "issue:43122", + "issue:43278", "issue:43441", - "issue:43450", "issue:43493", + "issue:43611", "issue:43673", + "issue:43784", "issue:43825", "issue:43827", "issue:43874", "issue:43906", "issue:43937", "issue:43976", - "issue:43986", + "issue:43992", "issue:44038", "issue:44075", "issue:44117", - "issue:44291", - "issue:44410", - "issue:44484", + "issue:44222", + "issue:44466", "issue:44485", + "issue:44704", "issue:44779", - "issue:44829", "issue:44936", + "issue:44945", "issue:44977", - "issue:45071", "issue:45072", - "issue:45081", "issue:45083", - "issue:45216", - "issue:45310", - "issue:45341", + "issue:45278", "issue:45357", - "issue:45405", "issue:45446", "issue:45478", - "issue:45561", "issue:45563", - "issue:45588" + "issue:45588", + "issue:45753", + "issue:46002" ], "soft_pairs": [ + "issue:43278|issue:44945", + "issue:43493|issue:45753", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43784|issue:45446", + "issue:43992|issue:44704", + "issue:43066|issue:44779", + "issue:38617|issue:45278", "issue:42673|issue:45072", "issue:43937|issue:44485", "issue:22355|issue:29127", + "issue:43611|issue:46002", "issue:42371|issue:43874", "issue:43976|issue:45446", + "issue:42222|issue:43441", "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:43116|issue:43825", "issue:45083|issue:45446", "issue:43937|issue:45563", "issue:44117|issue:45588", "issue:33453|issue:39401", "issue:39401|issue:44779", "issue:43827|issue:45446", + "issue:44466|issue:46002", "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:44829|issue:45216", - "issue:44484|issue:45310" + "issue:42673|issue:43906" ], - "prepared_review_unit_hash": "8328568362319c77935459c38a2f7d7aadf6c1159643df8afd754179cd15a817", + "prepared_review_unit_hash": "b01498f2c2861769f30faffbbdc8b8e00a88a128deb1a56cd5229d5665be984b", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36606, - "estimated_input_tokens": 9152, - "estimated_eval_tokens": 18560 + "serialized_chars": 35734, + "estimated_input_tokens": 8934, + "estimated_eval_tokens": 18124 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous; the only noticeable subtheme is a small set of Qwen3.5 save/load regressions, but the listed soft pairs are not strong duplicates. I would not merge any of the soft-edge candidates.", - "confidence": 0.71, - "canonical_issue_reason": "issue:45310 is the closest representative of the small Qwen3.5 serialization/from_pretrained subtheme, but the cluster overall is too mixed to treat it as a true duplicate bucket.", + "summary": "This cluster is thematically similar but not duplicate-level: most items are distinct v5-era regressions or compatibility issues across tokenization, loading, training, serialization, and model-specific code paths. No soft pair looks safe to merge; 45278 is only a broad umbrella, not a true canonical duplicate.", + "confidence": 0.67, + "canonical_issue_reason": "Issue 45278 is the broadest representative of the cluster\u2019s shared v5 compatibility breakage theme (import failures after upgrade), but the rest are not the same underlying bug, so this is only a loose umbrella choice.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the best single representative by breadth and relevance to the only recurring model-specific regression theme in the set.", + "best_issue_reason": "45278 is the best single issue to stand in for the cluster because it is the most general and cross-cutting regression report, even though the cluster should not be collapsed into one duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:42673", - "right": "issue:45072", + "left": "issue:43278", + "right": "issue:44945", "accept": false, - "reason": "Different failures: VRAM leak in dataloader-threaded generation vs dtype mismatch in bfloat16 inference." + "reason": "Different failures: dtype drift between train/eval vs incorrect outputs under pipeline parallelism. No shared code-path." }, { - "left": "issue:43937", - "right": "issue:44485", + "left": "issue:43493", + "right": "issue:45753", "accept": false, - "reason": "Both touch GLM-5, but one is a GenerationConfig validation error and the other is a RoPE implementation discussion." + "reason": "Different models and symptoms: SigLIP2 implementation mismatch vs Qwen3_5 image-specific infinite loop." }, { - "left": "issue:22355", - "right": "issue:29127", + "left": "issue:42907", + "right": "issue:44222", "accept": false, - "reason": "Unrelated issues: missing transformers.onnx module vs clearer layoutlmv3 box error messaging." + "reason": "Both concern save_pretrained, but one is dequantized Ministral/Devstrals and the other FP8 MoE; not the same bug." }, { - "left": "issue:42371", - "right": "issue:43874", + "left": "issue:43122", + "right": "issue:44977", "accept": false, - "reason": "TF32 API warning and missing image-patch method are different code paths and different bugs." + "reason": "Both are tokenization-related regressions, but one is version-to-version tokenization drift and the other is a flash-attention generation failure." }, { - "left": "issue:43976", + "left": "issue:43784", "right": "issue:45446", "accept": false, - "reason": "Python-version compatibility regression is unrelated to the flex_attention AuxRequest version check." + "reason": "Import error in sentence-transformers vs a PyTorch version check bug in flex_attention; unrelated code paths." }, { - "left": "issue:43064", - "right": "issue:43673", + "left": "issue:43992", + "right": "issue:44704", "accept": false, - "reason": "Wrong optimizer state assignment in FSDP2/PEFT is not the same as a missing GenerationMixin cache in chunked prefill." + "reason": "Missing embedding weights in UMT5 loading vs AutoProcessor kwargs forwarding; different loader layers and symptoms." }, { - "left": "issue:43116", - "right": "issue:43493", + "left": "issue:43066", + "right": "issue:44779", "accept": false, - "reason": "Example-script multi-label output bug and SigLIP2 implementation discrepancy are separate model/task issues." + "reason": "Both involve tokenizers, but one is decoder type selection and the other is Deepseek tokenization correctness; not the same concrete defect." }, { - "left": "issue:42222", - "right": "issue:43441", + "left": "issue:38617", + "right": "issue:45278", "accept": false, - "reason": "VitPose model breakage is unrelated to Ministral FlashAttention failures." + "reason": "45278 is a broad import-regression report, but 38617 is a specific missing symbol import; too general to treat as the same bug." }, { - "left": "issue:44075", - "right": "issue:44936", + "left": "issue:42673", + "right": "issue:45072", "accept": false, - "reason": "SGD argument handling and trainer evaluate-after-train failure are different trainer bugs." + "reason": "VRAM leak in Qwen3ForCausalLM threaded dataloaders vs dtype mismatch CI issue; different problems." }, { - "left": "issue:43116", - "right": "issue:43825", + "left": "issue:43937", + "right": "issue:44485", "accept": false, - "reason": "Empty multi-label results in an example script is not the same as a pipeline() error-message/doc-support issue." + "reason": "GenerationConfig validation error vs RoPE implementation discussion; not the same failure mode." }, { - "left": "issue:45357", - "right": "issue:45478", + "left": "issue:22355", + "right": "issue:29127", "accept": false, - "reason": "Same model family, but one is a save_pretrained key regression and the other is a from_pretrained load error; too different to treat as one bug." + "reason": "Module import failure vs LayoutLMv3 error-message clarity; unrelated." }, { - "left": "issue:44038", - "right": "issue:45478", - "accept": false, - "reason": "Qwen3-VL-Moe/Transformers 5.0 issue and Qwen3.5 MoE from_pretrained error are distinct regressions." - }, - { - "left": "issue:45083", - "right": "issue:45446", + "left": "issue:43611", + "right": "issue:46002", "accept": false, - "reason": "Unexpected output-length helper behavior is unrelated to the PyTorch version check in flex_attention." + "reason": "Model loading with base_model_prefix vs NaNs in classification heads after checkout/init; different code paths." }, { - "left": "issue:43937", - "right": "issue:45563", + "left": "issue:42371", + "right": "issue:43874", "accept": false, - "reason": "GenerationConfig invalidity and a stale num_return_sequences warning are different symptoms and different fixes." + "reason": "TF32 behavior API message vs missing image-patch helper on GLM46V; unrelated." }, { - "left": "issue:44117", - "right": "issue:45588", + "left": "issue:43976", + "right": "issue:45446", "accept": false, - "reason": "Tokenizer mapping None and flash_attention s_aux handling are unrelated subsystems." + "reason": "Python version compatibility bug vs flex_attention version-check bug; different issues." }, { - "left": "issue:33453", - "right": "issue:39401", + "left": "issue:42222", + "right": "issue:43441", "accept": false, - "reason": "Tokenizer-loading regression and Qwen3 offset_mapping bug are not the same concrete failure." + "reason": "VitPose model breakage vs Ministral FlashAttention failure; different model families and causes." }, { - "left": "issue:39401", - "right": "issue:44779", + "left": "issue:43064", + "right": "issue:43673", "accept": false, - "reason": "Different models and different tokenizer bugs: offset_mapping vs incorrect Deepseek results in v5." + "reason": "Wrong optimizer states under FSDP2/PEFT loading vs missing generation cache in chunked prefill; not the same bug." }, { - "left": "issue:43827", - "right": "issue:45446", + "left": "issue:43116", + "right": "issue:43493", "accept": false, - "reason": "Docs still referencing pipeline() is unrelated to the AuxRequest version check." + "reason": "Example script multi-label output issue vs SigLIP2 implementation discrepancy; different domains." }, { - "left": "issue:43937", - "right": "issue:44977", + "left": "issue:44075", + "right": "issue:44936", "accept": false, - "reason": "GLM-5 generation config validation and Qwen3.5 flash-attention generation breakage are different bugs." + "reason": "SGD argument handling vs trainer.evaluate after train; unrelated trainer behaviors." }, { - "left": "issue:42673", - "right": "issue:43906", + "left": "issue:45357", + "right": "issue:45478", "accept": false, - "reason": "VRAM leak in threaded dataloader use is unrelated to an isolated reproduction of another issue." + "reason": "Both are Qwen3.5-related, but one is save_pretrained key serialization and the other is from_pretrained loading failure; distinct defects." }, { - "left": "issue:44291", - "right": "issue:45071", + "left": "issue:44038", + "right": "issue:45478", "accept": false, - "reason": "Unexpected _is_hf_initialized argument and PretrainedConfig type-checking breakage are different initialization/type issues." + "reason": "Both mention Qwen3.5/MoE, but one is a broader v5/Qwen3-VL-Moe bug and the other is a specific from_pretrained error; not enough to merge." }, { - "left": "issue:43450", - "right": "issue:43986", + "left": "issue:43116", + "right": "issue:43825", "accept": false, - "reason": "Batched video-processor shape bug is different from missing-torchvision crash on AutoProcessor load." + "reason": "Classification example empty results vs stale pipeline translation error message; unrelated." }, { - "left": "issue:45405", + "left": "issue:45083", "right": "issue:45446", "accept": false, - "reason": "PEFT minimum-version bump and PyTorch version check are unrelated release/compatibility issues." + "reason": "qwen3_omni_moe feature-length helper behavior vs flex_attention import/version check; different components." }, { - "left": "issue:45341", - "right": "issue:45561", + "left": "issue:43937", + "right": "issue:45563", "accept": false, - "reason": "A vague testing_utils bug and a specific xdist race on captured_info.txt are not clearly the same defect." + "reason": "GenerationConfig invalid vs stale warning for num_return_sequences; different generation issues." }, { "left": "issue:44117", - "right": "issue:45081", + "right": "issue:45588", "accept": false, - "reason": "Tokenizer mapping fallback and Mistral regex patch crashing on backend_tokenizer are separate tokenizer-load failures." + "reason": "Tokenizer mapping fallback bug vs flash_attention crash on s_aux=None; unrelated." }, { - "left": "issue:38617", - "right": "issue:41628", + "left": "issue:33453", + "right": "issue:39401", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different code paths." + "reason": "General tokenizer loading regression vs Qwen3 offset_mapping bug; overlapping area but not the same underlying defect." }, { "left": "issue:39401", - "right": "issue:43421", + "right": "issue:44779", "accept": false, - "reason": "Wrong offset_mapping and runtime post-processor updates are distinct tokenizer behaviors." + "reason": "Both are tokenizer correctness issues, but they affect different models and behaviors (offset mapping vs generation tokenization)." }, { - "left": "issue:44410", - "right": "issue:45310", + "left": "issue:43827", + "right": "issue:45446", "accept": false, - "reason": "Missing qwen3next projections and Qwen3.5 from_pretrained errors are unrelated bugs." + "reason": "Docs still referencing removed pipeline API vs flex_attention import/version check; documentation vs runtime bug." }, { - "left": "issue:44829", - "right": "issue:45216", + "left": "issue:44466", + "right": "issue:46002", "accept": false, - "reason": "Degenerate training with flash_attention_3 is unrelated to incorrect Qwen3.5 save_pretrained checkpoints." + "reason": "Serialization of tied lm_head weights vs NaNs on init/checkout; different symptoms and code paths." }, { - "left": "issue:44484", - "right": "issue:45310", + "left": "issue:43937", + "right": "issue:44977", "accept": false, - "reason": "save_pretrained shard-size question and Qwen3.5 from_pretrained failure are unrelated." + "reason": "GenerationConfig validation error vs Qwen3.5 flash-attention generation failure; not the same bug." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "VRAM leak in multi-threaded Qwen3ForCausalLM use vs isolated reproduction of another issue; no concrete shared bug." } ] }, @@ -12862,12 +12645,13 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:38617", + "issue:39401", "issue:41628", "issue:42175", "issue:42222", @@ -12878,297 +12662,275 @@ "issue:42831", "issue:43012", "issue:43066", - "issue:43097", "issue:43122", - "issue:43335", "issue:43408", - "issue:43441", - "issue:43452", + "issue:43421", + "issue:43450", "issue:43577", "issue:43582", "issue:43673", "issue:43742", "issue:43874", - "issue:43931", "issue:43937", "issue:43986", - "issue:44038", "issue:44075", + "issue:44117", "issue:44220", "issue:44261", - "issue:44263", + "issue:44291", "issue:44410", "issue:44483", "issue:44484", - "issue:44485", - "issue:44493", "issue:44496", "issue:44829", "issue:44933", - "issue:45003", "issue:45071", + "issue:45081", + "issue:45216", "issue:45278", + "issue:45310", "issue:45341", - "issue:45459", + "issue:45405", + "issue:45446", "issue:45464", "issue:45478", "issue:45542", + "issue:45561", "issue:45656" ], "soft_pairs": [ + "issue:43450|issue:43986", + "issue:44291|issue:45071", + "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:44829|issue:45216", + "issue:44484|issue:45310", "issue:42371|issue:44261", - "issue:42673|issue:43582", "issue:43408|issue:43742", + "issue:42673|issue:43582", "issue:42617|issue:45341", - "issue:44933|issue:45278", "issue:42222|issue:45542", + "issue:44933|issue:45278", "issue:42490|issue:42673", - "issue:43937|issue:44496", "issue:42175|issue:42222", + "issue:43937|issue:44496", "issue:38617|issue:44220", - "issue:44483|issue:45464", "issue:42371|issue:42831", "issue:43066|issue:43122", + "issue:44483|issue:45464", "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:41628|issue:45071", - "issue:43012|issue:43408", - "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" + "issue:44410|issue:45478" ], - "prepared_review_unit_hash": "51d59883150a9aeae12a1b118910608d697f7ab75456d02927eadb72d2aac40f", + "prepared_review_unit_hash": "6c4da4618f6640e8e4de47ed70e777ed40d417aa61b07524db031227d629cf31", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 32, - "serialized_chars": 36315, - "estimated_input_tokens": 9079, - "estimated_eval_tokens": 18414 + "soft_pair_count": 29, + "serialized_chars": 35629, + "estimated_input_tokens": 8908, + "estimated_eval_tokens": 18072 }, "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, with only weak thematic overlap around v5 import/API regressions. None of the soft-pair candidates look like the same concrete bug, so I would not merge any of them as duplicates.", - "confidence": 0.44, - "canonical_issue_reason": "issue:45278 is the broadest umbrella for the import-regression subset and best represents the recurring v5 breakage reports in this set.", + "summary": "The set is largely heterogeneous: several tokenizer/import/version-regression reports overlap superficially, but they do not appear to be the same underlying bug. No soft pair looks mergeable into a single issue or PR.", + "confidence": 0.86, + "canonical_issue_reason": "Issue 45278 is the closest umbrella candidate because it broadly covers import regressions after upgrading to 5.5.0, but the cluster is too mixed for a strong true canonical duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the most general, user-facing report here and the best anchor for duplicate triage among the issue candidates.", + "best_issue_reason": "Issue 45278 is the most representative broad regression report in the set, but only as a loose umbrella; it is not a true duplicate of the other items.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:42371", - "right": "issue:44261", - "accept": false, - "reason": "TF32 API guidance vs MLA layernorm precision bug; different subsystems and failure modes." - }, - { - "left": "issue:42673", - "right": "issue:43582", + "left": "issue:43450", + "right": "issue:43986", "accept": false, - "reason": "VRAM leak in multi-threaded Qwen3 loading vs Apple Silicon warmup TypeError; unrelated causes." + "reason": "Both touch video-processing flows, but one is a shape bug and the other is a crash from missing torchvision; different failure modes and code paths." }, { - "left": "issue:43408", - "right": "issue:43742", + "left": "issue:44291", + "right": "issue:45071", "accept": false, - "reason": "SAM3 tracker config warning vs MobileLLM key error; not the same code path." + "reason": "Both are v5 loading/type-related regressions, but one is an init_empty_weights argument issue and the other is a PreTrainedConfig type-checking break." }, { - "left": "issue:42617", - "right": "issue:45341", + "left": "issue:45405", + "right": "issue:45446", "accept": false, - "reason": "3d_parallel.py runtime issue vs a testing_utils bug; no overlap in concrete failure." + "reason": "Unrelated problems: a released-version dependency pin vs a PyTorch version check for flex_attention import." }, { - "left": "issue:44933", - "right": "issue:45278", + "left": "issue:45341", + "right": "issue:45561", "accept": false, - "reason": "Both are import-related, but one is a missing symbol and the other is a broad upgrade regression; not the same bug." + "reason": "Both mention testing utils, but one is a small bug and the other is an xdist race on captured_info.txt; not the same defect." }, { - "left": "issue:42222", - "right": "issue:45542", + "left": "issue:44117", + "right": "issue:45081", "accept": false, - "reason": "vitpose model breakage vs TensorFlow backend/package-selection error; different areas." + "reason": "Both involve tokenizer internals, but one is a mapping lookup returning None and the other is a Mistral regex patch crash." }, { - "left": "issue:42490", - "right": "issue:42673", + "left": "issue:38617", + "right": "issue:41628", "accept": false, - "reason": "Local-path import warning vs VRAM leak under dataloader threads; unrelated." + "reason": "Both are import errors, but they concern different missing symbols and likely different API breakages." }, { - "left": "issue:43937", - "right": "issue:44496", + "left": "issue:39401", + "right": "issue:43421", "accept": false, - "reason": "GenerationConfig validation failure vs unknown-model loading error; distinct config/loading problems." + "reason": "Both are tokenizer behavior issues, but one is wrong offset mappings and the other is runtime special-token/post-processor sync." }, { - "left": "issue:42175", - "right": "issue:42222", + "left": "issue:44410", + "right": "issue:45310", "accept": false, - "reason": "Backend packaging issue vs vitpose model failure; not the same underlying defect." + "reason": "Different Qwen-family issues: missing projections in qwen3next vs a from_pretrained error in Qwen3.5 MoE." }, { - "left": "issue:38617", - "right": "issue:44220", + "left": "issue:44829", + "right": "issue:45216", "accept": false, - "reason": "Missing import symbol vs audio feature extraction issue; different code paths." + "reason": "One is a training degradation with flash_attention_3, the other is a save_pretrained checkpoint regression; different code paths." }, { - "left": "issue:44483", - "right": "issue:45464", + "left": "issue:44484", + "right": "issue:45310", "accept": false, - "reason": "Both touch chat APIs, but one is request acceptance and the other streaming inference; not a single concrete bug." + "reason": "A max_shard_size question is unrelated to a Qwen3.5 MoE from_pretrained failure." }, { "left": "issue:42371", - "right": "issue:42831", + "right": "issue:44261", "accept": false, - "reason": "TF32 settings warning vs FineGrainedFP8 accuracy regression; unrelated precision features." + "reason": "TF32 API guidance and an rms_norm_eps precision bug are unrelated." }, { - "left": "issue:43066", - "right": "issue:43122", + "left": "issue:43408", + "right": "issue:43742", "accept": false, - "reason": "Tokenizer decoder type mismatch vs tokenization change across versions; related domain, but not the same bug." + "reason": "Different model-loading failures: a model-type mismatch warning vs a key error for a specific model." }, { - "left": "issue:44075", - "right": "issue:45656", + "left": "issue:42673", + "right": "issue:43582", "accept": false, - "reason": "SGD args ignored vs deepspeed stepping twice; different optimizer bugs." + "reason": "A VRAM leak in multithreaded Qwen3 inference and an Apple Silicon TypeError in caching_allocator_warmup are distinct issues." }, { - "left": "issue:43673", + "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "Generation cache regression vs testing utility bug; no shared failure path." + "reason": "A 3d_parallel.py execution problem and a testing_utils bug are unrelated." }, { - "left": "issue:43012", - "right": "issue:43577", - "accept": false, - "reason": "PyTorch bfloat16 compile warning vs Blip2 dtype staying float32; different symptoms and causes." - }, - { - "left": "issue:43874", - "right": "issue:44261", - "accept": false, - "reason": "Missing multimodal patch-count method vs q_a_layernorm epsilon precision bug; unrelated." - }, - { - "left": "issue:44484", - "right": "issue:45478", + "left": "issue:42222", + "right": "issue:45542", "accept": false, - "reason": "save_pretrained shard-size question vs Qwen3.5-Moe loading error; not the same issue." + "reason": "A broken VitPose model family and a backend detection issue with tensorboard-only installs do not share the same root cause." }, { - "left": "issue:44410", - "right": "issue:45478", + "left": "issue:44933", + "right": "issue:45278", "accept": false, - "reason": "Missing projections in qwen3next vs Qwen3.5-Moe from_pretrained error; different model families and failures." + "reason": "Both are import-related, but 45278 is a broad upgrade regression while 44933 is a specific missing image_utils export." }, { - "left": "issue:43097", - "right": "issue:44493", + "left": "issue:42490", + "right": "issue:42673", "accept": false, - "reason": "Removed config option vs unexpected key warnings in many models; both version-related, but not the same concrete regression." + "reason": "A trailing-slash local-path import warning and a VRAM leak in Qwen3 multithreaded use are unrelated." }, { - "left": "issue:44263", - "right": "issue:44485", + "left": "issue:42175", + "right": "issue:42222", "accept": false, - "reason": "torch.split return handling bug vs GLM-5 RoPE implementation discussion; not the same path." + "reason": "Package/backend installation coverage and a broken VitPose model are different problems." }, { - "left": "issue:41628", - "right": "issue:45071", + "left": "issue:43937", + "right": "issue:44496", "accept": false, - "reason": "AutoImageProcessor import error vs PreTrainedConfig type checking regression; different API surfaces." + "reason": "One is a missing method on a vision processor fast class; the other is an unrecognized model/config issue." }, { - "left": "issue:43012", - "right": "issue:43408", + "left": "issue:38617", + "right": "issue:44220", "accept": false, - "reason": "bfloat16 compile warning vs SAM3 model-type warning; unrelated." + "reason": "Both are generic framework bugs, but one is an import error and the other is an audio feature-extraction failure." }, { - "left": "issue:42222", - "right": "issue:45459", + "left": "issue:42371", + "right": "issue:42831", "accept": false, - "reason": "vitpose model breakage vs protobuf-related tokenizer error handling; different layers." + "reason": "TF32 configuration messaging and FineGrainedFP8 accuracy are not the same bug." }, { - "left": "issue:43441", - "right": "issue:44829", + "left": "issue:43066", + "right": "issue:43122", "accept": false, - "reason": "FlashAttention inference failure vs FlashAttention-3 training degeneration; same broad feature, but not one concrete bug." + "reason": "Both are tokenizer/version regressions, but one is a wrong decoder type and the other is changed tokenization output." }, { - "left": "issue:45071", - "right": "issue:45542", + "left": "issue:44483", + "right": "issue:45464", "accept": false, - "reason": "Type-checking regression vs undefined TensorFlow backend error; unrelated." + "reason": "Both involve chat/completions, but one is a general request rejection and the other is a streaming inference failure on a specific model." }, { - "left": "issue:43931", - "right": "issue:44410", + "left": "issue:44075", + "right": "issue:45656", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch vs qwen3next missing projections; distinct model-loading defects." + "reason": "Both involve optimizers, but one says SGD args are ignored while the other says optimizer.step is called twice under deepspeed." }, { - "left": "issue:43335", - "right": "issue:45071", + "left": "issue:43673", + "right": "issue:45341", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug vs config type-checking regression; unrelated." + "reason": "A generation cache regression and a testing_utils bug are unrelated." }, { - "left": "issue:43931", - "right": "issue:44038", + "left": "issue:43012", + "right": "issue:43577", "accept": false, - "reason": "Both involve Qwen3-VL/Transformers 5.0, but one is a specific checkpoint shape mismatch and the other is a generic bug report." + "reason": "Both mention dtype/precision, but one is a compile-time warning and the other is incorrect model dtype propagation on load." }, { - "left": "issue:45003", - "right": "issue:45341", + "left": "issue:43874", + "right": "issue:44261", "accept": false, - "reason": "sys.modules access bug vs testing_utils bug; no shared underlying code path." + "reason": "One is a missing image-patch-count method in a GLM vision processor, the other is an rms_norm_eps precision issue." }, { - "left": "issue:43097", - "right": "issue:43452", + "left": "issue:44484", + "right": "issue:45478", "accept": false, - "reason": "Removed tie_embeddings option vs gguf_file from_pretrained breakage; different APIs." + "reason": "A save_pretrained shard-size question is unrelated to a Qwen3.5 MoE from_pretrained failure." }, { - "left": "issue:43986", - "right": "issue:45341", + "left": "issue:44410", + "right": "issue:45478", "accept": false, - "reason": "AutoProcessor video-model crash vs testing_utils bug; unrelated." + "reason": "Different Qwen-family failures: missing layer projections vs a from_pretrained error." } ] }, @@ -13187,32 +12949,31 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:38617", + "issue:41628", + "issue:42222", "issue:42757", - "issue:42886", - "issue:42907", "issue:43012", "issue:43064", "issue:43066", "issue:43097", - "issue:43208", - "issue:43352", - "issue:43381", + "issue:43335", "issue:43408", + "issue:43441", + "issue:43452", "issue:43502", "issue:43531", - "issue:43550", "issue:43824", - "issue:43825", "issue:43873", "issue:43874", "issue:43901", "issue:43906", + "issue:43931", "issue:43976", "issue:43986", "issue:43992", @@ -13224,38 +12985,50 @@ "issue:44315", "issue:44351", "issue:44368", - "issue:44380", "issue:44410", "issue:44484", "issue:44485", - "issue:44655", + "issue:44493", "issue:44704", "issue:44829", "issue:44987", + "issue:45003", "issue:45071", "issue:45103", - "issue:45245", "issue:45341", "issue:45372", "issue:45375", - "issue:45588", - "issue:45753" + "issue:45459", + "issue:45542", + "issue:45588" ], "soft_pairs": [ - "issue:44117|issue:44987", + "issue:44263|issue:44485", + "issue:43097|issue:44493", + "issue:42222|issue:45459", + "issue:41628|issue:45071", + "issue:43012|issue:43408", + "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", "issue:43986|issue:44484", - "issue:43408|issue:44368", + "issue:44117|issue:44987", "issue:43874|issue:44263", + "issue:43408|issue:44368", "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:38617|issue:44351", - "issue:44410|issue:45375", "issue:44062|issue:44117", + "issue:44410|issue:45375", + "issue:38617|issue:44351", "issue:43097|issue:45588", "issue:44038|issue:44410", "issue:44704|issue:45103", @@ -13264,231 +13037,240 @@ "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" + "issue:43097|issue:43901" ], - "prepared_review_unit_hash": "f53b3a577ca6ffaf1b094da4a506afbd44ae2159029b07cbc6c0e4cfe942f66f", + "prepared_review_unit_hash": "d1e3d1b36efb4acdc062cacd6d6adeec10755af6fbf94bb94ba4e6edcf70d78b", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37187, - "estimated_input_tokens": 9297, - "estimated_eval_tokens": 18850 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37683, + "estimated_input_tokens": 9421, + "estimated_eval_tokens": 19098 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are mostly unrelated Transformers bug reports spanning imports, model configs, training, and docs. None of the soft pairs look like the same underlying bug/change, so all should be rejected. The most suitable anchor issue is the active quantization/offloading report.", - "confidence": 0.93, - "canonical_issue_reason": "issue:43873 is the most active and broadly scoped report in the set, with the highest discussion/inbound reference signal, so it is the best canonical anchor.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers regressions: import errors, model-specific loading failures, config/warning regressions, and a few training/runtime bugs. None of the soft pairs look like the same underlying issue, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43097 is the broadest v5 compatibility regression in the set and the closest thing to a cluster hub; it has cross-references and reflects a general API break rather than a model-specific symptom.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 stands out as the most representative and triage-worthy issue here because it is open, has substantial discussion, and concerns a broadly impactful runtime behavior.", + "best_issue_reason": "Issue 43097 is the best representative issue here because it captures generic Transformers v5 breakage with broader impact, while the others are narrower model- or dependency-specific reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44117", - "right": "issue:44987", + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "Both are GLM-related, but one is a torch.split indexing bug and the other is a RoPE implementation issue; different code paths." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Both are v5 regressions, but one is a missing config flag warning and the other is an unexpected position_id key; not the same bug." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "Completely different symbols and dependencies: vitpose model breakage vs tokenizer protobuf error handling." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Top-level import/type issues, but AutoImageProcessor import failure and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Both mention warnings, but a bfloat16 precision warning and a sam3_video/sam3_tracker type mismatch are distinct." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "FlashAttention is common, but one is a load-time failure and the other is a training-quality regression; not mergeable as one fix." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "No concrete overlap beyond being runtime regressions." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Same broad Qwen/VL family, but weight-shape mismatch and missing projection layers are different model bugs." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "Different scope: SwitchTransformers sparse-layer construction vs config type checking." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Both concern Qwen3-VL, but a load mismatch and a Qwen3-VL-Moe issue are different concrete failures." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated internals: sys.modules access vs a testing utility bug." + }, + { + "left": "issue:43097", + "right": "issue:43452", "accept": false, - "reason": "Both are tokenizer/loading failures, but one is a tokenizer mapping assumption and the other is a specific model-loading regression; not the same bug." + "reason": "Both affect v5 loading, but gguf_file handling and a removed config option are distinct paths." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Video-model processor crash and testing_utils bug have no shared code path." }, { "left": "issue:43986", "right": "issue:44484", "accept": false, - "reason": "Video AutoProcessor/torchvision crash vs save_pretrained shard-size question; unrelated code paths." + "reason": "Different features: torchvision-dependent processor loading vs shard-size documentation/behavior." }, { - "left": "issue:43408", - "right": "issue:44368", + "left": "issue:44117", + "right": "issue:44987", "accept": false, - "reason": "A model-type mismatch warning and a tie_word_embeddings warning are different config-validation issues." + "reason": "Tokenizer mapping None and physical-intelligence/fast loading failure are not the same underlying bug." }, { "left": "issue:43874", "right": "issue:44263", "accept": false, - "reason": "Missing image-patch helper in GLM46V and torch.split return handling in GlmMoeDsaIndexer are separate model bugs." + "reason": "Both GLM-related, but one is an image patch counter method missing and the other is torch.split return handling." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Different model families and warnings." }, { "left": "issue:43976", "right": "issue:45071", "accept": false, - "reason": "Both mention version breakage, but one is Python compatibility and the other is PretrainedConfig type checking; different failures." + "reason": "Python-version compatibility vs config type checking; unrelated." }, { "left": "issue:43986", "right": "issue:45372", "accept": false, - "reason": "Different crashes in different loading stacks: missing torchvision vs missing ReasoningEffort import from mistral_common." - }, - { - "left": "issue:44829", - "right": "issue:45245", - "accept": false, - "reason": "FlashAttention-3 degenerate training and category-count overflow are unrelated problems." + "reason": "Processor-loading crash due to missing torchvision vs mistral_common import error; different dependencies and failures." }, { "left": "issue:43531", "right": "issue:45341", "accept": false, - "reason": "A Qwen3-MoE sliding_window bug and a testing_utils bug do not share the same underlying cause." + "reason": "Sliding-window MoE behavior vs testing_utils bug; unrelated." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Two separate ImportErrors from different symbols/modules; same symptom type, but not the same bug." + "reason": "Both are ImportErrors from internal symbols, but they refer to different missing names/modules and likely different release breakages." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "RMS norm epsilon precision/config issue vs GLM-5 RoPE implementation issue; different model internals." + "reason": "Both touch GLM-5-ish internals, but RMS epsilon config and RoPE implementation are separate numeric issues." }, { "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "Optimizer-state corruption under FSDP2/PEFT is unrelated to Liger Kernel application with model_init." + "reason": "Training/FSDP optimizer-state bug vs Liger-kernel application bug; different integration paths." }, { - "left": "issue:38617", - "right": "issue:44351", + "left": "issue:44062", + "right": "issue:44117", "accept": false, - "reason": "Different missing imports: configuration_utils.layer_type_validation vs transformers.HybridCache." + "reason": "AddedToken argument duplication and tokenizer mapping None are separate tokenizer loader issues." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "One is missing attention projections in qwen3next; the other is a vision config field being dropped by @strict." - }, - { - "left": "issue:44062", - "right": "issue:44117", - "accept": false, - "reason": "AddedToken keyword duplication and TOKENIZER_MAPPING_NAMES returning None are different tokenizer-path failures." + "reason": "Both are Qwen config/model problems, but missing projections and a dropped vision-index config field are different concrete bugs." }, { - "left": "issue:43097", - "right": "issue:45588", + "left": "issue:38617", + "right": "issue:44351", "accept": false, - "reason": "A removed config flag and a flash-attention sink-less crash are unrelated issues." + "reason": "Both are import failures, but layer_type_validation and HybridCache are unrelated symbols." }, { "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Both concern Qwen variants, but one is a broad v5 compatibility issue and the other is a specific missing-projection bug." + "reason": "Both are Qwen3-VL/MoE related, but the reported failures are different model defects." }, { "left": "issue:44704", "right": "issue:45103", "accept": false, - "reason": "Passing kwargs to cached_file and auto_docstring crashing on future annotations are separate utility-layer bugs." + "reason": "Processor kwargs forwarding and auto_docstring annotation handling are unrelated." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "local_files_only still making API requests is unrelated to UMT5Encoder missing embed_tokens.weight." + "reason": "local_files_only networking bug vs missing embed_tokens weight loading are different issues." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Video model loading without torchvision is unrelated to tokenizer mapping returning None." + "reason": "Processor/vision dependency crash vs tokenizer mapping bug; unrelated." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "A removed embedding-tie config flag and quantization offloading behavior are different problems." + "reason": "Offloading/quantization behavior and tie_embeddings removal are different regressions." }, { "left": "issue:43824", "right": "issue:43986", "accept": false, - "reason": "Different loading failures: missing Qwen2_5_VL export vs missing torchvision for a video model." + "reason": "Qwen2.5-VL import error and video processor torchvision failure are different model/dependency paths." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Wrong tokenizer decoder type and an isolated reproduction of another issue are not enough to establish the same bug." + "reason": "A tokenizer decoder-type regression and an isolated reproduction of another issue are not enough to treat as the same bug." }, { "left": "issue:43097", "right": "issue:43901", "accept": false, - "reason": "Config flag removal and outdated pipeline docs about return_all_scores are unrelated." - }, - { - "left": "issue:43825", - "right": "issue:44655", - "accept": false, - "reason": "Pipeline task-support messaging and save_pretrained on Pipeline objects are different features and failure modes." - }, - { - "left": "issue:43992", - "right": "issue:44484", - "accept": false, - "reason": "Missing UMT5Encoder weights and the max_shard_size default question do not share an underlying code-path issue." - }, - { - "left": "issue:43208", - "right": "issue:43550", - "accept": false, - "reason": "xLSTM training blockers and Bamba torch.compile/SDPA failure are unrelated model-specific bugs." - }, - { - "left": "issue:43012", - "right": "issue:44368", - "accept": false, - "reason": "A bfloat16 compile warning and a tie_word_embeddings warning are different warning sources and behaviors." - }, - { - "left": "issue:42886", - "right": "issue:43381", - "accept": false, - "reason": "Offline cache loading failure and eval-mode gradient checkpointing incompatibility are separate runtime issues." - }, - { - "left": "issue:43352", - "right": "issue:44380", - "accept": false, - "reason": "Unsupported Flash Attention 2 for Nemotron and GPT2 attention-scaling being ignored are distinct backend/model bugs." - }, - { - "left": "issue:42907", - "right": "issue:45753", - "accept": false, - "reason": "Saving dequantized models and Qwen3_5 infinite-image-loop behavior are unrelated." - }, - { - "left": "issue:42907", - "right": "issue:44655", - "accept": false, - "reason": "Both mention saving, but one is dequantized model persistence and the other is Pipeline.save_pretrained; different artifacts and code paths." + "reason": "Config warning removal and docs behavior mismatch are unrelated." } ] }, @@ -13507,67 +13289,75 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:36010", "issue:36683", "issue:38617", "issue:42490", "issue:42757", - "issue:42898", + "issue:42886", + "issue:42907", "issue:42994", "issue:43012", "issue:43064", - "issue:43066", "issue:43208", "issue:43299", "issue:43352", + "issue:43381", "issue:43475", "issue:43502", - "issue:43525", "issue:43526", + "issue:43550", "issue:43582", - "issue:43611", "issue:43618", "issue:43756", "issue:43761", "issue:43824", + "issue:43825", "issue:43867", "issue:43901", "issue:43937", "issue:43976", + "issue:43992", "issue:44038", "issue:44077", "issue:44222", "issue:44230", - "issue:44242", - "issue:44263", + "issue:44368", "issue:44380", "issue:44483", + "issue:44484", "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:43825|issue:44655", + "issue:43992|issue:44484", + "issue:43208|issue:43550", + "issue:43012|issue:44368", + "issue:43352|issue:44380", + "issue:42886|issue:43381", + "issue:43012|issue:43550", + "issue:42907|issue:45753", + "issue:42907|issue:44655", "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:36683|issue:43582", + "issue:44483|issue:44514", "issue:44222|issue:45478", "issue:42490|issue:43012", "issue:43012|issue:44683", @@ -13575,10 +13365,10 @@ "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:45290", "issue:43756|issue:44485", + "issue:43299|issue:43867", "issue:44483|issue:45381", "issue:43901|issue:44655", "issue:43299|issue:45753", @@ -13587,255 +13377,306 @@ "issue:43352|issue:43937", "issue:44077|issue:44380", "issue:43867|issue:45216", - "issue:36010|issue:42757", - "issue:42898|issue:43066", - "issue:36683|issue:44077", - "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:36010|issue:42757" ], - "prepared_review_unit_hash": "9cb4dc6e8e88f0eba9c6a4ddc7da89b95297253b4625bbed65bc727b9c6871ec", + "prepared_review_unit_hash": "1616aab27087dc3e2747f880a093122185c0e7150b8fa6936ccd816f8c849dc2", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 35, - "serialized_chars": 37832, - "estimated_input_tokens": 9458, - "estimated_eval_tokens": 19172 + "serialized_chars": 37361, + "estimated_input_tokens": 9341, + "estimated_eval_tokens": 18938 }, "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 and regressions. I did not find any soft pair that convincingly describes the same underlying issue or code change, so no merges are warranted from the provided evidence.", - "confidence": 0.34, - "canonical_issue_reason": "issue:43611 is the broadest, most central regression report in the set: a Transformers 5.0 loading breakage affecting models with `base_model_prefix`, which is more representative of the cluster\u2019s general v5-regression theme than the narrower model-specific reports.", + "summary": "The cluster is very heterogeneous: it mixes unrelated import errors, model-specific regressions, saving/loading bugs, and backend-specific behavior changes. None of the soft pairs look like true duplicates or mergeable into a single fix.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 43825 is the least ambiguous, self-contained user-facing regression in the set, but the cluster is too mixed for a strong canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 is the best single issue to represent this cluster because it is a clear, high-impact version-regression report with wide applicability and strong triage value.", + "best_issue_reason": "43825 is the best available representative, but only because no other issue meaningfully spans the cluster; this is not a strong duplicate hub.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Different failures: a v5 pipeline error-message regression vs saving Pipeline objects." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Unrelated bugs: missing embed_tokens.weight in UMT5 loading vs save_pretrained shard-size behavior." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different models and paths: xLSTM training blockers vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both are warnings, but about different causes and models; not the same code-path problem." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Different concrete issues: unsupported Flash Attention in Nemotron vs GPT2 attention scaling ignored under SDPA/FA." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading bug vs gradient checkpointing in eval mode; unrelated behaviors." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "Precision warning during compile is unrelated to Bamba SDPA compilation failure." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized models is unrelated to a Qwen3.5 image-generation infinite-loop report." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Model dequantization save bug vs saving Pipeline objects are different save paths." + }, { "left": "issue:44380", "right": "issue:45479", "accept": false, - "reason": "Different failures: GPT-2 attention scaling under SDPA/FlashAttention vs. degenerate zero loss in sequence classification with `num_labels=1`." + "reason": "Attention-scaling backend bug is unrelated to the zero-loss classification bug." }, { "left": "issue:43352", "right": "issue:43976", "accept": false, - "reason": "One is a model/backend support limitation, the other is a Python version compatibility failure; no shared code-path bug." + "reason": "Flash-Attention support error vs Python version support regression; different problems." }, { "left": "issue:43064", "right": "issue:44380", "accept": false, - "reason": "Trainer/FSDP2/PEFT optimizer-state corruption is unrelated to GPT-2 attention scaling behavior." + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to GPT2 attention scaling under SDPA/FlashAttention." }, { - "left": "issue:44483", - "right": "issue:44514", + "left": "issue:43208", + "right": "issue:43526", "accept": false, - "reason": "An API request validation issue is unrelated to a batched `apply_chat_template` crash in a VL processor." + "reason": "xLSTM training blockers vs BeitImageProcessorFast reduce_labels returning one label; different components." }, { "left": "issue:36683", "right": "issue:43582", "accept": false, - "reason": "Gemma3Config missing `vocab_size` and Apple Silicon allocator warmup TypeError are distinct bugs in different areas." + "reason": "Gemma3Config missing vocab_size is unrelated to Apple Silicon caching_allocator_warmup TypeError." }, { - "left": "issue:43208", - "right": "issue:43526", + "left": "issue:44483", + "right": "issue:44514", "accept": false, - "reason": "xLSTM training blockers and BeitImageProcessorFast label reduction are unrelated model/processor bugs." + "reason": "Chat-completions request rejection vs batched apply_chat_template crash are different API paths." }, { "left": "issue:44222", "right": "issue:45478", "accept": false, - "reason": "FP8 `save_pretrained` on MoE and Qwen3.5 MoE `from_pretrained` load failure are different directions of failure and not the same concrete bug." + "reason": "Both involve Qwen3.5 MoE/FP8, but one is save_pretrained and the other from_pretrained; not the same concrete bug." }, { "left": "issue:42490", "right": "issue:43012", "accept": false, - "reason": "Local-path import warning and a bfloat16 compilation precision warning are unrelated." + "reason": "Local-path trailing-slash warning is unrelated to a bfloat16 compile warning." }, { "left": "issue:43012", "right": "issue:44683", "accept": false, - "reason": "A PyTorch warning during bfloat16 compilation is not the same as flex_attention failing on torch >= 2.9." + "reason": "PyTorch precision warning is unrelated to compiled flex_attention failure on torch>=2.9." }, { "left": "issue:43618", "right": "issue:43761", "accept": false, - "reason": "Both involve CLIP, but one is missing attentions and the other missing hidden_states; these look like separate output-field regressions." + "reason": "Both are CLIP regressions, but one loses attentions and the other loses hidden_states; not the same fix." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Importing `is_offline_mode` from huggingface_hub and importing `Qwen2_5_VLForConditionalGeneration` from transformers are different import-path issues." + "reason": "Different import errors from different modules: huggingface_hub vs transformers Qwen2.5-VL class." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "CLIP output field assignment and GPT-2 attention scaling under specific backends are unrelated." + "reason": "CLIP output regression is unrelated to GPT2 attention scaling backend behavior." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "A missing internal import and unwanted network requests despite `local_files_only=True` are different failure modes." - }, - { - "left": "issue:44483", - "right": "issue:45290", - "accept": false, - "reason": "A chat-completions API rejection is unrelated to tool-call assistant message handling in `apply_chat_template`." + "reason": "Importing layer_type_validation is unrelated to local_files_only still making API requests." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Qwen3-VL-Moe loading breakage and FP8 inference support are not the same bug." + "reason": "Qwen3-VL-Moe loading regression vs FP8 infer support request; not the same bug." }, { - "left": "issue:43299", - "right": "issue:43867", + "left": "issue:44483", + "right": "issue:45290", "accept": false, - "reason": "Qwen3VL MoE loading regression and a state-dict sorting load error are distinct loading problems." + "reason": "Both are chat/template issues, but one is a v5 chat-completions request failure and the other is a tool-call template crash." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "Smollm3 RoPE-layer mismatch and GLM-5 RoPE implementation discussion are not the same underlying issue." + "reason": "RoPE layer mismatch in Smollm3 is unrelated to GLM-5 RoPE implementation discussion." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-Moe loading regression vs state_dict-sorted load error are different concrete failures." }, { "left": "issue:44483", "right": "issue:45381", "accept": false, - "reason": "API request acceptance and Qwen2.5-VL video position-id correctness are unrelated." + "reason": "Chat completions rejection is unrelated to Qwen2.5-VL video vision_position_ids being wrong." }, { "left": "issue:43901", "right": "issue:44655", "accept": false, - "reason": "Documentation drift for `return_all_scores` and inability to save Pipeline objects are different issues." + "reason": "Docs mentioning return_all_scores do not match saving Pipeline objects." }, { - "left": "issue:43299", - "right": "issue:45753", + "left": "issue:42994", + "right": "issue:44655", "accept": false, - "reason": "A Qwen3VL MoE model-loading regression is not the same as an infinite-loop generation bug on a specific image." + "reason": "Quantized model save failure is different from Pipeline.save_pretrained failure." }, { "left": "issue:36683", "right": "issue:43475", "accept": false, - "reason": "Gemma3Config missing `vocab_size` and SAM 3 video missing `fpn_position_embeddings` are separate missing-attribute bugs in different models." + "reason": "Gemma3Config vocab_size missing is unrelated to SAM 3 vision encoder output missing fpn_position_embeddings." }, { - "left": "issue:42994", - "right": "issue:44655", + "left": "issue:44222", + "right": "issue:45479", "accept": false, - "reason": "Quantized model saving failure and saving Pipeline objects are different save-path bugs." + "reason": "FP8 MoE save/load bug is unrelated to a zero-loss classification bug across models." }, { - "left": "issue:43352", - "right": "issue:43937", + "left": "issue:42490", + "right": "issue:43012", "accept": false, - "reason": "FlashAttention 2 unsupported for Nemotron and GLM-5 generation config invalid are unrelated model-specific issues." + "reason": "Trailing-slash import warning is unrelated to bfloat16 compile precision warnings." }, { - "left": "issue:44077", - "right": "issue:44380", + "left": "issue:43012", + "right": "issue:44683", "accept": false, - "reason": "`post_init` allowance in patchtsmixer is unrelated to GPT-2 attention scaling being ignored." + "reason": "Precision warning during compile is unrelated to flex_attention compilation failure." }, { - "left": "issue:43867", - "right": "issue:45216", + "left": "issue:43618", + "right": "issue:43761", "accept": false, - "reason": "State-dict sorting load error and Qwen3.5 checkpoint saving regression are different persistence bugs." + "reason": "Two different CLIP output regressions with different missing fields; not one duplicate." }, { - "left": "issue:36010", - "right": "issue:42757", + "left": "issue:42757", + "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different symbols and different upstream modules; not the same missing export." + "reason": "Different import paths and missing symbols; no shared underlying bug." }, { - "left": "issue:42898", - "right": "issue:43066", + "left": "issue:38617", + "right": "issue:43502", "accept": false, - "reason": "Tokenizer decoder-type behavior change and wrong tokenizer decoder type are related only superficially; the reported problems and likely fixes differ." + "reason": "Configuration import error is unrelated to unwanted network requests under local_files_only." }, { - "left": "issue:36683", - "right": "issue:44077", + "left": "issue:44038", + "right": "issue:44230", "accept": false, - "reason": "A config attribute missing on Gemma3 and a `post_init` constraint issue in patchtsmixer are unrelated." + "reason": "Model-loading regression and FP8 inference support are not the same change." }, { - "left": "issue:43611", - "right": "issue:44655", + "left": "issue:44483", + "right": "issue:45290", "accept": false, - "reason": "Model loading via `base_model_prefix` and Pipeline serialization are separate APIs with different breakages." + "reason": "Both touch chat APIs, but they are distinct failures in different code paths." }, { - "left": "issue:43976", - "right": "issue:44938", + "left": "issue:43756", + "right": "issue:44485", "accept": false, - "reason": "Python version support failure in Transformers 5.1.0 and a Python 3.14 load failure are not the same issue." + "reason": "Different RoPE-related issues in different models; no clear shared fix." }, { - "left": "issue:36683", - "right": "issue:43525", + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Different load/save failures; no evidence of one underlying bug." + }, + { + "left": "issue:42994", + "right": "issue:44655", "accept": false, - "reason": "Gemma3Config missing `vocab_size` and Llama4Config missing `pad_token_id` are different missing-config-field regressions." + "reason": "Quantized model saving and Pipeline.save_pretrained are different save mechanisms." }, { "left": "issue:43352", - "right": "issue:45593", + "right": "issue:43937", "accept": false, - "reason": "Unsupported FlashAttention 2 for Nemotron and D-FINE auxiliary-loss omission are unrelated model bugs." + "reason": "Flash Attention support error is unrelated to invalid GenerationConfig handling." }, { - "left": "issue:44263", - "right": "issue:45440", + "left": "issue:44077", + "right": "issue:44380", "accept": false, - "reason": "A `torch.split()` return-value issue in GlmMoeDsaIndexer and DeepseekV3MoE divergence from remote implementation do not describe the same bug." + "reason": "patchtsmixer post_init validation is unrelated to GPT2 attention scaling under SDPA/FlashAttention." }, { - "left": "issue:43618", + "left": "issue:43867", "right": "issue:45216", "accept": false, - "reason": "Missing CLIP attentions and incorrect Qwen3.5 checkpoint saving are unrelated regressions." + "reason": "State_dict-sorted load error and v5.4.0 checkpoint corruption are related by loading/saving, but not the same concrete bug." }, { - "left": "issue:36683", - "right": "issue:44242", + "left": "issue:36010", + "right": "issue:42757", "accept": false, - "reason": "A missing config attribute and missing load-balancing loss when `output_router_logits=False` are different defects." + "reason": "Different import failures from different packages and symbols; unrelated." } ] }, @@ -13854,10 +13695,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:28282", "issue:33453", @@ -13866,56 +13707,66 @@ "issue:41669", "issue:42490", "issue:42890", + "issue:42898", "issue:43010", "issue:43064", + "issue:43066", "issue:43352", - "issue:43502", + "issue:43525", "issue:43575", + "issue:43611", "issue:43618", - "issue:43723", "issue:43867", "issue:43931", "issue:43976", "issue:43992", - "issue:44062", "issue:44075", "issue:44077", - "issue:44112", "issue:44188", + "issue:44242", "issue:44246", + "issue:44263", "issue:44355", "issue:44360", "issue:44380", "issue:44484", "issue:44492", - "issue:44556", + "issue:44655", "issue:44855", "issue:44857", "issue:44938", - "issue:44964", "issue:44977", "issue:45071", + "issue:45216", "issue:45278", "issue:45310", - "issue:45341", "issue:45357", "issue:45375", "issue:45381", "issue:45440", "issue:45478", "issue:45561", - "issue:45600", + "issue:45593", "issue:45850" ], "soft_pairs": [ + "issue:42898|issue:43066", + "issue:36683|issue:44077", + "issue:43611|issue:44655", + "issue:43976|issue:44938", + "issue:36683|issue:43525", + "issue:43352|issue:45593", + "issue:43618|issue:45216", + "issue:44263|issue:45440", + "issue:36683|issue:44242", "issue:44188|issue:44380", "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:44355|issue:44855", "issue:36683|issue:43064", "issue:42890|issue:45561", "issue:44938|issue:45071", @@ -13931,235 +13782,244 @@ "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:43618|issue:44977" ], - "prepared_review_unit_hash": "7f99eedff8b3aa07e8bc0f6313560b6bb3f3c152b31f3d0a5e700c78358ac974", + "prepared_review_unit_hash": "3aea0afb79d4415ca791cd63fdd2b996a98669e303975976408185eba7cc3431", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 35639, - "estimated_input_tokens": 8910, - "estimated_eval_tokens": 18076 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37070, + "estimated_input_tokens": 9268, + "estimated_eval_tokens": 18792 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous. One soft duplicate is clear: 45310 and 45478 are the same Qwen3.5 MoE from_pretrained regression. Most other pairs only share broad themes like loading/import failures or training issues, but not the same concrete bug.", - "confidence": 0.78, - "canonical_issue_reason": "issue:45310 is the cleanest anchor for the only clear duplicate pair in this set: it is the earlier, slightly more specific report of the Qwen3.5 MoE from_pretrained failure, and issue:45478 is essentially the same title later on.", + "summary": "This cluster is mostly a grab bag of Transformers v5 regression reports: import/load failures, model-specific config/key mismatches, tokenizer behavior changes, and a few performance/parallelism issues. The only plausible duplicate edge is the import-time slowdown pair.", + "confidence": 0.58, + "canonical_issue_reason": "issue:45278 is the broadest representative of the shared v5 breakage/import-regression theme across the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the best overall issue to keep as the representative duplicate target because it is concrete, reproducible, and has an exact duplicate; the rest of the cluster is mostly unrelated or too broad to serve as a better canonical.", + "best_issue_reason": "issue:45278 is the most representative issue because it captures the broad version-upgrade regression pattern rather than a single model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42898", + "right": "issue:43066", + "accept": false, + "reason": "Both are tokenizer-related v5 changes, but one is about clean-up spacing behavior and the other about decoder type; different bugs." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Missing Gemma3 config attrs and patchtsmixer post_init gating are unrelated model-specific issues." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "Base-model-prefix loading breakage and Pipeline save_pretrained failure affect different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both concern Python-version compatibility, but they report different failures and likely different causes." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3 missing vocab_size and Llama4 missing pad_token_id are separate config omissions." + }, + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "Flash Attention support error for Nemotron is unrelated to D-FINE auxiliary-loss handling." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIPOutput attentions assignment and Qwen3.5 save_pretrained checkpoint corruption are different bugs." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "GlmMoeDsaIndexer torch.split behavior and DeepseekV3MoE divergence are different model implementation issues." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Missing Gemma3Config vocab_size and missing load-balancing loss with output_router_logits=False are unrelated." + }, { "left": "issue:44188", "right": "issue:44380", "accept": false, - "reason": "Both are attention/backend bugs, but they describe different code paths and failures (compile branching vs SDPA/FlashAttention scaling)." + "reason": "Both mention attention behavior, but one is a compile-time branching issue and the other is backend scaling config handling." }, { "left": "issue:43064", "right": "issue:44492", "accept": false, - "reason": "One is a distributed training/optimizer-state bug; the other is a cache-strategy typo. No shared underlying fix." + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to a cache-strategy typo." }, { "left": "issue:43352", "right": "issue:43931", "accept": false, - "reason": "Different model-specific load failures: unsupported Flash Attention vs weight-shape mismatch." + "reason": "Nemotron Flash Attention support and Qwen3-VL weight-shape mismatch are unrelated model-specific failures." }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "UMT5 encoder missing embed_tokens.weight is unrelated to the Qwen3.5 MoE from_pretrained regression." + "reason": "Both involve from_pretrained errors, but for different models and different missing-state behavior." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "Both mention imports/regressions, but one is about decorating cache update with no_grad and the other is broad import errors after upgrade; not the same bug." + "reason": "Cache update no_grad decoration is unrelated to broad import-error regressions." }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "State-dict sorting/load error is not the same as a missing config field silently dropped by strict config handling." - }, - { - "left": "issue:44355", - "right": "issue:44855", - "accept": false, - "reason": "Both are import-time problems, but the root causes differ (compiled Python files vs torch.jit.script parsing on Python 3.13)." + "reason": "A sorted-state_dict load error and a missing Qwen3_5MoeVisionConfig field are different issues." }, { "left": "issue:41669", "right": "issue:44246", + "accept": true, + "reason": "Both point to the same import-time slowdown problem; one explicitly identifies wildcard imports in models as the cause." + }, + { + "left": "issue:44355", + "right": "issue:44855", "accept": false, - "reason": "Both concern import performance, but 41669 has a specific import-star root cause while 44246 is only a vague slowdown report." + "reason": "Running compiled Python files and TorchScript parse/IndentationError on Python 3.13 are different failure modes." }, { "left": "issue:36683", "right": "issue:43064", "accept": false, - "reason": "Gemma3Config vocab_size missing and distributed optimizer-state corruption are unrelated." + "reason": "Config attribute absence and FSDP2/PEFT optimizer-state mismatch are unrelated." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "A missing set_seed in integration tests is not the same as an xdist race on captured_info.txt." + "reason": "Seed-related flaky tests and xdist race on captured_info.txt are different testing issues." }, { "left": "issue:44938", "right": "issue:45071", "accept": false, - "reason": "Python 3.14 import failure and PretrainedConfig type-checking breakage are different compatibility issues." + "reason": "Python 3.14 import failure and PretrainedConfig type-checking regression are different problems." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Load failure with sorted state_dict is not the same as save_pretrained writing incorrect visual encoder keys." + "reason": "These are both save/load regressions, but one is a generic state_dict ordering issue and the other is Qwen3.5 visual-key corruption." }, { "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "One is a specific no_grad decoration bug; the other is a vague complaint about many broken models." + "reason": "No-grad cache updates and a generic complaint that v5 breaks too many models are not the same bug." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "The UMT5 encoder weight-missing issue is unrelated to the Qwen3.5 MoE from_pretrained regression." + "reason": "Both are from_pretrained errors, but they target different Qwen variants and different symptoms." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "Cache update no_grad and Python-version compatibility for Transformers 5.1.0 are unrelated." + "reason": "Cache update semantics and Python-version compatibility are unrelated." }, { "left": "issue:44938", "right": "issue:45381", "accept": false, - "reason": "General Python 3.14 loading failure and qwen2.5-vl video position-id bug are different problems." + "reason": "Python 3.14 load failure and Qwen2.5-VL video vision_position_ids bug are unrelated." }, { "left": "issue:43618", "right": "issue:44077", "accept": false, - "reason": "CLIPOutput attentions disappearing and patchtsmixer post_init constraints are unrelated model/API issues." + "reason": "CLIPOutput attentions regression and patchtsmixer post_init policy are different issues." }, { "left": "issue:42490", "right": "issue:44075", "accept": false, - "reason": "Local-files-only path warning and SGD optimizer args being ignored are unrelated." + "reason": "Local-path import warning and SGD optimizer args not being used are unrelated." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Tensor-parallel training bug and Qwen2-57B load OOM are not the same failure mode." + "reason": "Tensor-parallel training bug and Qwen2-57B-A14B-Instruct OOM are different scaling problems." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "A missing ReLU in the DSA indexer is unrelated to DeepseekV3MoE divergence from remote implementation." + "reason": "DSA indexer ReLU discussion and DeepseekV3MoE divergence are unrelated implementation issues." }, { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "PyTorch-missing AutoModel ImportError and tokenizer-loading regression are different issues." + "reason": "AutoModel missing PyTorch and tokenizer loading regression are different loading failures." }, { "left": "issue:43867", "right": "issue:44484", "accept": false, - "reason": "State-dict sorting/load error is unrelated to max_shard_size being 50GB." + "reason": "Generic model-loading error and max_shard_size behavior/question are unrelated." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIPOutput attentions and LwDetrImageLoss AMP/CUDA crash are unrelated." + "reason": "CLIP attentions regression and LwDetrImageLoss AMP crash are unrelated." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "CLIPOutput attentions issue is unrelated to Qwen3.5 flash-attention generation failure." - }, - { - "left": "issue:42890", - "right": "issue:44964", - "accept": false, - "reason": "A flaky integration test and a model-loading regression are not the same bug." - }, - { - "left": "issue:42890", - "right": "issue:44112", - "accept": false, - "reason": "A test seeding issue is unrelated to a stale device override CI failure." - }, - { - "left": "issue:42890", - "right": "issue:45600", - "accept": false, - "reason": "A flaky test case and an auto_mappings config reference breakage are unrelated." - }, - { - "left": "issue:43502", - "right": "issue:44062", - "accept": false, - "reason": "local_files_only network leakage and AddedToken keyword duplication are unrelated loader/tokenizer bugs." - }, - { - "left": "issue:43723", - "right": "issue:44556", - "accept": false, - "reason": "Tokenizer loading in v5 and checkpoint reload failures after upgrade are too broad to be the same concrete bug." - }, - { - "left": "issue:42890", - "right": "issue:45341", - "accept": false, - "reason": "A test seeding problem and a testing_utils bug are different CI/test issues." - }, - { - "left": "issue:45310", - "right": "issue:45478", - "accept": true, - "reason": "These are the same Qwen3.5 MoE from_pretrained error with nearly identical titles; 45478 is a later duplicate of the same concrete bug." + "reason": "CLIP attentions assignment and Qwen3.5 flash-attention generation failure are different bugs." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the cluster does look like a mix of v5 regression reports spanning import/load failures, tokenizer changes, config/key mismatches, and a few performance/parallelism issues. The canonical issue choice is reasonable as a broad representative, and the one accepted soft-edge pair (41669/44246) is a plausible duplicate on import-time slowdown. The rejected pairs are mostly conservative and do not overclaim sameness based on weak title similarity alone." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -14171,10 +14031,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:30333", "issue:30990", @@ -14187,21 +14047,22 @@ "issue:42548", "issue:42757", "issue:42831", + "issue:42890", "issue:43010", "issue:43065", "issue:43232", "issue:43299", "issue:43502", - "issue:43526", "issue:43576", "issue:43673", + "issue:43723", "issue:43824", "issue:43827", "issue:43874", - "issue:43901", + "issue:44062", + "issue:44112", "issue:44222", "issue:44230", - "issue:44261", "issue:44315", "issue:44351", "issue:44355", @@ -14210,24 +14071,29 @@ "issue:44485", "issue:44492", "issue:44556", - "issue:44623", "issue:44655", "issue:44749", "issue:44908", "issue:44938", "issue:44961", + "issue:44964", "issue:45071", "issue:45125", - "issue:45230", - "issue:45362", + "issue:45341", "issue:45375", "issue:45468", "issue:45478", - "issue:45850" + "issue:45600" ], "soft_pairs": [ + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43723|issue:44556", "issue:44222|issue:45125", "issue:44387|issue:44556", + "issue:42890|issue:45341", "issue:42548|issue:44351", "issue:43010|issue:43065", "issue:43502|issue:44485", @@ -14235,8 +14101,8 @@ "issue:45125|issue:45478", "issue:30990|issue:31795", "issue:43010|issue:43232", - "issue:30333|issue:33453", "issue:45125|issue:45375", + "issue:30333|issue:33453", "issue:43299|issue:44556", "issue:43502|issue:44222", "issue:42831|issue:43874", @@ -14253,288 +14119,282 @@ "issue:43576|issue:45071", "issue:43576|issue:43824", "issue:31795|issue:38617", - "issue:44961|issue:45468", "issue:41628|issue:42548", + "issue:44961|issue:45468", "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" + "issue:44485|issue:44961" ], - "prepared_review_unit_hash": "ba0b530ff6a1f979552383221100b55dece16a967e5aa249decadb3a1ac55bba", + "prepared_review_unit_hash": "dd0001691f318a3e65fce21d50a06beffabcb49b697492f2d1ca72f8bad9a163", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 40, - "serialized_chars": 38925, - "estimated_input_tokens": 9732, - "estimated_eval_tokens": 19720 + "serialized_chars": 39022, + "estimated_input_tokens": 9756, + "estimated_eval_tokens": 19768 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is a loose set of Transformers/HF regressions and docs/import issues, not a near-duplicate set. No soft edge looks like the same underlying bug/change, so all candidate pairs should be rejected.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 44556 is the best broad representative of the cluster\u2019s main theme: version-upgrade regressions that break model reload/loading across Transformers v5.", + "summary": "This cluster is noisy and spans many unrelated Transformers issues: import errors, model-loading regressions, test flakiness, docs, FP8/quantization, and other model-specific bugs. None of the proposed soft pairs look like the same underlying defect.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue stands out: the items are not duplicates of one another and cover several distinct bug classes.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44556 is the clearest, most generally representative bug report in the set; it captures the repeated v5 loading regression pattern better than the more model-specific or documentation-only issues.", + "best_issue_reason": "No issue is a good global canonical representative because the cluster is heterogeneous rather than one concrete bug family.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "SamHQ integration-test flakiness is unrelated to a Phi-4 multimodal model-loading failure." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Different failures: missing set_seed in SamHQ tests vs a GraniteSpeech CI device-override issue." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "SamHQ test nondeterminism is not the same as stale auto_mappings references to removed Sam3LiteText configs." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "A local_files_only network leak and an AddedToken keyword collision are unrelated code paths." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Both mention loading, but one is AutoTokenizer loading in v5 and the other is checkpoint reload after a version upgrade; not the same bug." + }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "Both are FP8/tensor-parallel themed, but one is about FP8 save_pretrained while the other is about a missing tensor-parallel plan for Qwen3.5-MoE; different failure modes." + "reason": "FP8 save_pretrained for MoE and a missing tensor-parallel plan are distinct issues." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "One reports CUDA reserved-memory OOM under int4 quantization, the other is a reload failure after upgrading versions; not the same bug." + "reason": "Int4 quantization OOM and checkpoint reload incompatibility are different regressions." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "A SamHQ flaky test is not the same as a generic testing_utils bug." }, { "left": "issue:42548", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but they involve different symbols and likely different missing exports; too broad to treat as duplicates." + "reason": "Missing PreTrainedModel import and missing HybridCache import are separate symbol-export problems." }, { "left": "issue:43010", "right": "issue:43065", "accept": false, - "reason": "One is about no_grad decoration for cache/layer update methods, the other is a dummy Conv2d in Sam3PixelDecoder; unrelated code paths." + "reason": "Cache update no_grad behavior and a dummy Conv2d in Sam3PixelDecoder are unrelated." }, { "left": "issue:43502", "right": "issue:44485", "accept": false, - "reason": "local_files_only still making API requests is unrelated to a GLM-5 RoPE implementation discussion." + "reason": "Local-files-only network requests do not match a GLM-5 RoPE implementation bug." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Both mention compiled/v5 behavior, but one is about compiled Python files failing and the other about a Chinese-described slowdown after upgrade; no clear same bug." + "reason": "Compiled Python file load errors and a training/filtering slowdown after upgrade are different symptoms." }, { "left": "issue:45125", "right": "issue:45478", "accept": false, - "reason": "Both involve Qwen3.5 MoE, but one is tensor-parallel metadata and the other is a from_pretrained loading error in v5.4.0; not enough evidence of one underlying defect." + "reason": "A missing _tp_plan for tensor parallelism is not the same as a Qwen3.5 MoE from_pretrained failure." }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "Sentence Transformers loading hangs versus confusing model.forward documentation; one is a runtime bug, the other is docs." + "reason": "Sentence Transformers getting stuck loading is unrelated to documentation confusion in model.forward." }, { "left": "issue:43010", "right": "issue:43232", "accept": false, - "reason": "Cache update no_grad issue versus generation kwargs after sync_gpus; different generation internals and symptoms." + "reason": "Decorating cache update methods with no_grad is a different change than fixing generation kwargs after sync_gpus." }, { - "left": "issue:30333", - "right": "issue:33453", + "left": "issue:45125", + "right": "issue:45375", "accept": false, - "reason": "MLFlow reporting on training failure is unrelated to tokenizer loading regression." + "reason": "Tensor-parallel planning and a missing config field silently dropped by @strict are different bugs." }, { - "left": "issue:45125", - "right": "issue:45375", + "left": "issue:30333", + "right": "issue:33453", "accept": false, - "reason": "Both mention Qwen3.5 MoE, but one is tensor-parallel planning and the other is a missing config field silently dropped by strict validation." + "reason": "MLFlow failure reporting and a tokenizer-loading regression are unrelated." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Qwen3VL MoE loading breakage in v5.0.0.dev0 is model-specific and separate from the general v4.57-to-v5.3 reload regression." + "reason": "Qwen3VL MoE loading in v5.0.0.dev0 and reload failure after upgrading to v5.2/v5.3 are not the same concrete issue." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "API requests despite local_files_only=True is unrelated to FP8 save_pretrained behavior." + "reason": "A local_files_only API leak is unrelated to FP8 save_pretrained for MoE models." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "FineGrainedFP8 accuracy issue and missing get_number_of_image_patches are different FP8/multimodal problems." + "reason": "An FP8 accuracy issue and a missing image-processor method are different defects." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Liger Kernel not applied with model_init is unrelated to the DSA indexer lacking a ReLU." + "reason": "Liger Kernel not applied via model_init has nothing to do with the DSA indexer ReLU discussion." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "local_files_only network leakage and a nonsense-titled issue are unrelated." + "reason": "A real loading/network regression and an unrelated placeholder issue titled 'racoon' are not duplicates." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled file errors are not the same as PretrainedConfig type-checking regressions." + "reason": "Compiled Python file errors and v5.4.0 PretrainedConfig type-checking breakage are different problems." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "MLFlow failure reporting and tensor-parallel training bugs affect different subsystems and failure modes." + "reason": "MLFlow job status reporting and tensor-parallel training bugs are unrelated." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Compiled Python file failures are unrelated to inability to save Pipeline objects." + "reason": "Compiled-file loading errors and inability to save Pipeline objects are different code paths." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Docs still referencing pipeline() are unrelated to the unrelated placeholder issue." + "reason": "Docs still referencing pipeline() and an unrelated 'racoon' issue are not the same bug." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "FP8 save_pretrained and FP8 inference support are related by theme but not the same concrete bug." + "reason": "Both mention FP8/MoE, but one is about saving pretrained weights and the other about inference support." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading breakage are different model-loading failures." + "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading breakage are different concrete failures." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "Missing is_offline_mode import and broken transformers env command are distinct CLI/API regressions." + "reason": "An import error from huggingface_hub is not the same as the transformers env command breaking in v5." }, { "left": "issue:33453", "right": "issue:36296", "accept": false, - "reason": "Tokenizer loading regression and tensor-parallel training bug are different areas and symptoms." + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." }, { "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "Broken env command is unrelated to PretrainedConfig type checking." + "reason": "Broken transformers env command and PretrainedConfig type-checking regression are different issues." }, { "left": "issue:43576", "right": "issue:43824", "accept": false, - "reason": "Broken env command and missing Qwen2_5_VLForConditionalGeneration import are separate issues." + "reason": "The env command bug and AutoTokenizer/AutoImageProcessor import failures are not the same underlying defect." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Docs confusion for model.forward is unrelated to the missing layer_type_validation import error." - }, - { - "left": "issue:44961", - "right": "issue:45468", - "accept": false, - "reason": "Placeholder/nonsense issue versus Gemma-4 audio positional encoding bug; no duplicate signal." - }, - { - "left": "issue:41628", - "right": "issue:42548", - "accept": false, - "reason": "AutoImageProcessor import failure and PreTrainedModel import failure are both imports, but not the same missing symbol or path." - }, - { - "left": "issue:38617", - "right": "issue:43576", - "accept": false, - "reason": "Missing import from configuration_utils and a broken env CLI command are unrelated." - }, - { - "left": "issue:43576", - "right": "issue:44938", - "accept": false, - "reason": "Broken env command and Python 3.14 load failure are different compatibility problems." - }, - { - "left": "issue:43673", - "right": "issue:44492", - "accept": false, - "reason": "Generation cache missing in chunked_prefill and a typo in cache strategies are unrelated." + "reason": "Documentation confusion in model.forward is unrelated to a missing layer_type_validation import." }, - { - "left": "issue:44908", - "right": "issue:44961", - "accept": false, - "reason": "Scheduler kwargs being ignored is unrelated to the placeholder issue." - }, - { - "left": "issue:44485", - "right": "issue:44961", + { + "left": "issue:41628", + "right": "issue:42548", "accept": false, - "reason": "GLM-5 RoPE implementation discussion is unrelated to the placeholder issue." + "reason": "AutoImageProcessor import failure and PreTrainedModel import failure are separate symbol export regressions." }, { - "left": "issue:36296", - "right": "issue:43901", + "left": "issue:44961", + "right": "issue:45468", "accept": false, - "reason": "Tensor-parallel training bug and docs mentioning return_all_scores are unrelated." + "reason": "The placeholder 'racoon' issue is unrelated to Gemma-4 audio positional encoding." }, { - "left": "issue:41628", - "right": "issue:44355", + "left": "issue:38617", + "right": "issue:43576", "accept": false, - "reason": "Importing AutoImageProcessor fails versus compiled Python files erroring; different problems." + "reason": "Missing layer_type_validation import and the v5 env-command failure are different bugs." }, { - "left": "issue:36296", - "right": "issue:43526", + "left": "issue:43576", + "right": "issue:44938", "accept": false, - "reason": "Tensor-parallel training bug and BeitImageProcessorFast reduce_labels bug are different subsystems." + "reason": "Broken env command and Python 3.14 load failure are distinct issues." }, { - "left": "issue:45362", - "right": "issue:45850", + "left": "issue:43673", + "right": "issue:44492", "accept": false, - "reason": "Qwen3.5-35B chat crash and the broad 'too many models break' complaint are not a single concrete bug." + "reason": "Chunked-prefill GenerationMixin cache missing and a cache-strategy typo are not the same defect." }, { - "left": "issue:44261", - "right": "issue:44360", + "left": "issue:44908", + "right": "issue:44961", "accept": false, - "reason": "Layernorm config precision error and DSA indexer ReLU issue are unrelated." + "reason": "Scheduler kwargs handling is unrelated to the placeholder issue titled 'racoon'." }, { - "left": "issue:44623", - "right": "issue:45230", + "left": "issue:44485", + "right": "issue:44961", "accept": false, - "reason": "Missing files on processor.save_pretrained and a generic bug report are not the same underlying issue." + "reason": "GLM-5 RoPE implementation discussion is unrelated to the placeholder issue titled 'racoon'." } ] }, @@ -14553,43 +14413,43 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ - "issue:31795", - "issue:33453", + "issue:36296", + "issue:41628", "issue:41669", "issue:42371", "issue:42890", "issue:43352", "issue:43408", - "issue:43519", "issue:43525", + "issue:43526", "issue:43572", "issue:43576", "issue:43673", - "issue:43704", "issue:43827", "issue:43874", + "issue:43901", "issue:43976", "issue:44038", "issue:44077", "issue:44246", + "issue:44261", "issue:44273", "issue:44295", "issue:44297", "issue:44315", "issue:44351", + "issue:44355", "issue:44360", "issue:44393", - "issue:44485", "issue:44492", "issue:44556", - "issue:44655", + "issue:44623", "issue:44704", - "issue:44829", "issue:44861", "issue:44908", "issue:44945", @@ -14599,21 +14459,26 @@ "issue:45125", "issue:45230", "issue:45278", - "issue:45310", "issue:45341", - "issue:45468", + "issue:45362", "issue:45478", "issue:45542", "issue:45753", "issue:45850" ], "soft_pairs": [ + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "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:44393|issue:45753", "issue:44038|issue:45125", - "issue:44393|issue:45071", "issue:43576|issue:44556", + "issue:44393|issue:45071", "issue:43525|issue:45850", "issue:41669|issue:43673", "issue:44556|issue:45092", @@ -14637,113 +14502,138 @@ "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" + "issue:43827|issue:44908" ], - "prepared_review_unit_hash": "d98dfe4a6ac6e40dea166701353f7e49b023fdea0bbce10aff582cf635e5fbea", + "prepared_review_unit_hash": "f5b0bd2f43c28a53d29a269fba5c9a8b1a00ab8f74f6bd919d79c19c6a1d6ab1", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 41, - "serialized_chars": 39338, - "estimated_input_tokens": 9835, - "estimated_eval_tokens": 19926 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 36, + "serialized_chars": 37285, + "estimated_input_tokens": 9322, + "estimated_eval_tokens": 18900 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly false-positive similarity: these issues span unrelated bugs, v5 regression complaints, model-specific errors, docs, and performance/import topics. No soft edge is safe to merge as the same underlying bug/change.", - "confidence": 0.91, - "canonical_issue_reason": null, + "summary": "This cluster is mostly a grab-bag of unrelated issues, with a loose theme of v5 migration regressions and model-specific breakages, but no soft pair looks like a true duplicate. There are no PRs in the cluster.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45850 is the broadest umbrella in the set and best matches the cluster\u2019s general theme of widespread v5 breakage, though it is very vague.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44273 is the closest broad anchor because it is open and about loading/lazy-loading behavior, which overlaps the import-time regressions in the cluster. It is still only an umbrella, not a true duplicate canonical.", + "best_issue_reason": "issue:45278 is the most useful representative because it is concrete about upgrade-induced breakage while still capturing the broader regression pattern.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Different problems: tensor parallel training vs a docs mismatch for text classification." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Import/export failure for AutoImageProcessor is unrelated to compiled Python file errors." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training and BEiT image processor label reduction are unrelated code paths." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Specific Qwen3.5 chat crash is not the same as a broad complaint about many models breaking." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "Different subsystems: MLA layernorm config precision vs DSA indexer activation logic." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "One is a specific processor save_pretrained bug; the other is an unspecific placeholder report." + }, { "left": "issue:44273", "right": "issue:45542", "accept": false, - "reason": "Both mention loading/import behavior, but one is lazy loading and the other is a TensorFlow backend detection problem; not the same bug." + "reason": "Lazy loading behavior is unrelated to the TensorFlow backend/tensorboard installation issue." }, { "left": "issue:44273", "right": "issue:45003", "accept": false, - "reason": "Import slowdown and unsafe sys.modules access are related themes, but they are distinct failure modes with different fixes." + "reason": "Both touch loading/import mechanics, but not the same concrete bug or failure mode." }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Both are Qwen3-VL/Qwen3_5 user-facing failures, but one is 2D box output corruption and the other is an infinite-loop/image-specific hang." + "reason": "Different model-family visual bugs: bbox hallucination vs infinite loop on a specific image." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Both involve Qwen3 MoE models, but one is a generic transformers 5.0 bug report and the other is a missing tensor-parallel plan attribute." + "reason": "General Qwen3-VL bug is not the same as missing tensor-parallel plan metadata." }, { - "left": "issue:44393", - "right": "issue:45071", + "left": "issue:43576", + "right": "issue:44556", "accept": false, - "reason": "A Qwen3-VL output bug and a PretrainedConfig type-checking regression are unrelated code paths." + "reason": "v5 env-command breakage and checkpoint reload incompatibility are separate failures." }, { - "left": "issue:43576", - "right": "issue:44556", + "left": "issue:44393", + "right": "issue:45071", "accept": false, - "reason": "Both are v5 upgrade regressions, but one breaks the env command and the other breaks checkpoint reload; different issues." + "reason": "A vision-model bbox output issue does not match a PretrainedConfig typing regression." }, { "left": "issue:43525", "right": "issue:45850", "accept": false, - "reason": "A missing pad_token_id on Llama4Config is a concrete config bug; the other is only a generic complaint about many models breaking." + "reason": "A missing pad_token_id on Llama4Config is a specific config bug, not the same as a broad v5 complaint." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-star removal and missing GenerationMixin cache in chunked prefill are different regressions." + "reason": "Import-star performance issues and missing generation cache are different code-path problems." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both concern v5 compatibility, but one is checkpoint reload after upgrade and the other is remote-code/meta-init incompatibility." + "reason": "Both involve model loading after version changes, but the underlying failures differ." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "A cache-strategy typo is not the same underlying problem as a broad v5 breakage complaint." + "reason": "A typo in cache strategies is not the same as a generic report that many models break." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "StableLmConfig missing pad_token_idx is a specific config regression, not the same as a generic 'too many models break' report." + "reason": "StableLmConfig missing pad_token_idx is a specific config regression, not the broad v5 breakage claim." }, { "left": "issue:42371", @@ -14755,175 +14645,103 @@ "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "Processor kwargs forwarding and scheduler kwargs handling affect different subsystems and code paths." + "reason": "Both mention kwargs, but one is processor loading and the other is scheduler behavior." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Missing set_seed in tests and inverse_sqrt scheduler kwargs are unrelated." + "reason": "A flaky integration test is unrelated to scheduler kwargs handling." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "A specific import-error report after upgrade is not the same underlying bug as a vague general complaint." + "reason": "Both are broad v5 regressions, but one is about import errors and the other about many models breaking; not the same bug." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Both involve import behavior, but one is intermittent import slowness and the other is lazy-loading malfunction; not the same concrete defect." + "reason": "Import slowness is not the same as a lazy-loading malfunction." }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "Model-type warning for sam3_tracker and Liger Kernel not applied with model_init are unrelated." + "reason": "Model-type warning and Liger Kernel application in model_init are unrelated." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python-version compatibility failure and Qwen3-VL hallucination/output error are unrelated." + "reason": "Python version compatibility and a Qwen3-VL output bug are unrelated." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash Attention 2 support missing for NemotronH vs a Qwen3-VL output bug are different model-specific problems." + "reason": "Flash Attention support for NemotronH is unrelated to Qwen3-VL bounding-box errors." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer save metadata mismatch and a generic bug report are not the same issue." - }, - { - "left": "issue:43576", - "right": "issue:44908", - "accept": false, - "reason": "An env CLI breakage and a scheduler kwarg bug are different components." + "reason": "Tokenizer save metadata mismatch is not the same as an unspecific bug report." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "Position_ids buffer access and a generic bug report do not match." + "reason": "Position_ids buffer access error is a distinct model-state bug." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs and PretrainedConfig type checking are unrelated." + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are separate issues." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Import-star cleanup and missing HybridCache export are different import-surface issues." + "reason": "Import-star cleanup/performance is unrelated to missing HybridCache exports." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "A model import-performance issue and a testing_utils bug are unrelated." + "reason": "A model import-star issue is not the same as a testing_utils bug." }, { "left": "issue:44492", "right": "issue:44945", "accept": false, - "reason": "A cache-strategy typo and incorrect pipeline-parallel output are different bugs." + "reason": "Cache strategy typo and pipeline-parallelism output errors are unrelated." }, { "left": "issue:43874", "right": "issue:45850", "accept": false, - "reason": "A missing multimodal-token helper and a generic v5 complaint are not the same change or bug." + "reason": "Missing a model method in GLM46V is a specific implementation bug, not a broad v5 breakage report." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Two Qwen3.5/Qwen3-VL reports, but one is bbox output hallucination and the other is a from_pretrained error for Qwen3.5 MoE." + "reason": "Different Qwen bugs affecting different models and behaviors." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Optional post_init handling and tied-weight-key AttributeError are different implementation bugs." + "reason": "Optional post_init policy and tied-weight key crashes are not the same underlying bug." }, { "left": "issue:43827", "right": "issue:44908", "accept": false, - "reason": "Docs still referencing pipeline() and scheduler kwargs handling are unrelated." - }, - { - "left": "issue:31795", - "right": "issue:33453", - "accept": false, - "reason": "Documentation confusion about forward args and tokenizer-loading regression are not the same issue." - }, - { - "left": "issue:41669", - "right": "issue:44908", - "accept": false, - "reason": "Import-time model loading changes and scheduler kwargs are unrelated." - }, - { - "left": "issue:44315", - "right": "issue:44829", - "accept": false, - "reason": "Liger Kernel application with model_init and flash_attention_3 training degeneration are different problems." - }, - { - "left": "issue:43576", - "right": "issue:44273", - "accept": false, - "reason": "v5 env CLI breakage and lazy-loading malfunction are separate code paths." - }, - { - "left": "issue:44655", - "right": "issue:44861", - "accept": false, - "reason": "Pipeline save_pretrained failure and tied-weight-key AttributeError are unrelated." - }, - { - "left": "issue:44360", - "right": "issue:45468", - "accept": false, - "reason": "DSA indexer/ReLU discussion and Gemma4AudioRelPositionalEncoding are completely different areas." - }, - { - "left": "issue:45230", - "right": "issue:45310", - "accept": false, - "reason": "Both are generic bug reports around Qwen3.5 Moe, but the descriptions point to different failure modes and no shared concrete fix path." - }, - { - "left": "issue:44273", - "right": "issue:44908", - "accept": false, - "reason": "Lazy-loading/import behavior and scheduler kwargs are different subsystems." - }, - { - "left": "issue:43519", - "right": "issue:44485", - "accept": false, - "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are separate model math bugs." - }, - { - "left": "issue:43519", - "right": "issue:44908", - "accept": false, - "reason": "A processor timestamp bug and a scheduler kwargs bug are unrelated." - }, - { - "left": "issue:41669", - "right": "issue:43704", - "accept": false, - "reason": "Import-star removal/performance and VRAM leakage in multi-threaded dataloaders are different issues." + "reason": "Docs still referencing pipeline() is unrelated to inverse_sqrt scheduler kwargs handling." } ] }, @@ -14942,10 +14760,10 @@ "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-10000-402", + "cluster_id": "cluster-10000-403", "nodes": [ "issue:30333", "issue:31515", @@ -14955,6 +14773,7 @@ "issue:36296", "issue:37428", "issue:38617", + "issue:41669", "issue:42371", "issue:42913", "issue:43066", @@ -14963,20 +14782,26 @@ "issue:43519", "issue:43525", "issue:43572", + "issue:43576", "issue:43606", "issue:43618", "issue:43704", "issue:44230", "issue:44261", "issue:44263", + "issue:44273", "issue:44315", + "issue:44360", "issue:44485", "issue:44492", "issue:44623", + "issue:44655", + "issue:44829", "issue:44861", "issue:44908", "issue:44998", "issue:45092", + "issue:45230", "issue:45290", "issue:45310", "issue:45341", @@ -14984,6 +14809,17 @@ "issue:45850" ], "soft_pairs": [ + "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", "issue:31795|issue:34689", "issue:31795|issue:37428", "issue:44315|issue:45092", @@ -14998,8 +14834,8 @@ "issue:44261|issue:45468", "issue:42913|issue:43066", "issue:44908|issue:44998", - "issue:44861|issue:45290", "issue:44492|issue:44998", + "issue:44861|issue:45290", "issue:44998|issue:45850", "issue:43618|issue:44998", "issue:44998|issue:45341", @@ -15014,214 +14850,283 @@ "issue:31515|issue:33453", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "9d58d72e9dd4d0bea4f322d9024f6ba304d633bf070d0057703d98c5c7bed327", + "prepared_review_unit_hash": "3d8ea24ce17851162fea502cf03773ee5ee3996a059a72bcf0186c62cca178c9", "component_budget": { - "node_count": 402, - "item_count": 402, - "soft_pair_count": 1504, - "serialized_chars": 775933, - "estimated_input_tokens": 193984, - "estimated_eval_tokens": 388224 + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 }, "budget": { - "node_count": 35, - "item_count": 35, - "soft_pair_count": 29, - "serialized_chars": 28339, - "estimated_input_tokens": 7085, - "estimated_eval_tokens": 14426 + "node_count": 42, + "item_count": 42, + "soft_pair_count": 40, + "serialized_chars": 35533, + "estimated_input_tokens": 8884, + "estimated_eval_tokens": 18024 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of Transformers issues around loading, tokenizer/model regressions, and v5 compatibility. The soft links look like weak topical similarity rather than true duplicates; I would not merge any of the candidate pairs.", + "summary": "The cluster is still mostly heterogeneous. The tokenizer pair (42913/43066) is clearly related and likely stems from the same v5 tokenizer transition, but with only title-level evidence it should be treated as possibly related rather than a definite duplicate. The rest of the soft edges remain conservative rejections across different code paths or features.", "confidence": 0.78, - "canonical_issue_reason": "issue:45850 is the broadest umbrella in the set and best matches the cluster\u2019s general theme of v5 regressions breaking many models, though it is too vague to serve as a precise duplicate target.", + "canonical_issue_reason": "issue:42913 is the broadest tokenizer-v5 regression report in the set; issue:43066 looks closely related, but the available evidence is not strong enough to treat them as the same bug with high confidence.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45850 is the most generally representative issue for this cluster because it describes widespread breakage, not a single narrow symptom.", + "best_issue_reason": "issue:42913 is the best overall issue candidate because it captures the broader user-visible tokenizer behavior change, making it the most useful umbrella if the pair later proves to be the same underlying regression.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Different problems: documentation confusion vs tokenizer loading regression." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Unrelated: import-star cleanup/perf issue vs scheduler kwarg handling." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Both are training-related, but they describe different failure modes and code paths." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Different features: env command breakage vs lazy loading behavior." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving pipeline objects is unrelated to tied-weight key crash handling." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer activation issue vs Gemma-4 audio positional encoding bug." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report vs a specific Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading and inverse_sqrt scheduler kwargs are different subsystems." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp bug vs GLM-5 RoPE implementation issue." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "No shared code path: processor timestamp math vs scheduler configuration." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star refactor/perf discussion is unrelated to VRAM leakage in multi-threaded loading." + }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Both involve model/loading docs or regressions, but one is a documentation confusion issue and the other is a specific Llama 3.2 model-loading failure." + "reason": "Documentation confusion is not the same as a model-loading regression for a specific checkpoint." }, { "left": "issue:31795", "right": "issue:37428", "accept": false, - "reason": "Different problems: documentation ambiguity vs an import error for a flash-attention helper." + "reason": "Different surfaces: model.forward docs vs flash-attention import error." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Both touch model initialization, but one is about Liger Kernel not being applied and the other is remote-code checkpoint incompatibility with v5 meta init." + "reason": "Both touch model creation/loading, but the concrete incompatibilities differ." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "Both are architecture-specific math/positioning bugs, but they affect different models and different implementations." + "reason": "Different model architectures and different implementation bugs." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leakage in multi-threaded inference is unrelated to RoPE implementation issues." + "reason": "VRAM leak in threaded inference is unrelated to RoPE math." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 API guidance and VRAM leakage are unrelated issues." + "reason": "TF32 settings API change is unrelated to the dataloader-thread VRAM leak." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "One is unwanted network access during local loading; the other is a timestamp calculation bug in a processor." + "reason": "Local-files-only network access bug is unrelated to processor timestamp calculation." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Processor timestamp math and missing saved files are different code paths and symptoms." + "reason": "Processor timestamp bug and save_pretrained missing files are different code paths." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "A tokenizer/processor timestamp bug is not the same as a dataloader-thread VRAM leak." + "reason": "Processor timestamp logic vs multi-thread VRAM leak are unrelated." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "Different models and different failure modes: torch.split return handling vs audio positional encoding." + "reason": "Different low-level math/indexing issues in different models." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device mismatch is unrelated to Gemma audio positional encoding." + "reason": "CPU offload device mismatch is unrelated to Gemma-4 positional encoding." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "Precision error from missing rms_norm_eps is not the same as an audio positional encoding bug." + "reason": "Precision/config epsilon issue is not the same as Gemma-4 audio encoding bug." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both concern tokenizer behavior in v5, but one is a broad behavior change and the other is a specific wrong decoder type issue." + "reason": "Highly related tokenizer-v5 reports, but title-level evidence is not enough to call them a definite duplicate or the same regression." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler kwargs handling is unrelated to the unrelated 'Unemployment' issue." + "reason": "Scheduler kwargs bug is unrelated to an unemployment placeholder issue." }, { - "left": "issue:44861", - "right": "issue:45290", + "left": "issue:44492", + "right": "issue:44998", "accept": false, - "reason": "A tied-weights helper crash and a chat template crash are distinct failures in different utilities." + "reason": "Typo in cache strategy naming is unrelated to the placeholder issue." }, { - "left": "issue:44492", - "right": "issue:44998", + "left": "issue:44861", + "right": "issue:45290", "accept": false, - "reason": "A cache-strategy typo is unrelated to the unrelated 'Unemployment' issue." + "reason": "Tied-weight-key crash and chat-template tool-call crash are different failure points." }, { "left": "issue:44998", "right": "issue:45850", "accept": false, - "reason": "The second is a broad v5 breakage report; the first is not a technical bug report and is clearly unrelated." + "reason": "Placeholder/unemployment issue is unrelated to a broad v5 breakage complaint." }, { "left": "issue:43618", "right": "issue:44998", "accept": false, - "reason": "CLIPOutput attentions regression is unrelated to the unrelated 'Unemployment' issue." + "reason": "CLIPOutput attentions regression is unrelated to the placeholder issue." }, { "left": "issue:44998", "right": "issue:45341", "accept": false, - "reason": "A testing_utils bug and an unrelated non-technical issue are not duplicates." + "reason": "Unemployment placeholder is unrelated to a testing_utils bug." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_id in Llama4Config and a tied-weights list crash are different config/utility bugs." + "reason": "Missing pad_token_id in Llama4Config is unrelated to tied-weight key handling." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is unrelated to _get_tied_weight_keys crashing on list input." + "reason": "StableLmConfig pad_token_idx regression is unrelated to tied-weight key extraction." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Both are import/loading-related, but one is slow checkpoint loading and the other is a missing import symbol." + "reason": "Checkpoint loading slowness and missing import errors are different issues." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 support for Qwen models and missing processor save files are different feature/bug areas." + "reason": "FP8 inference support request is unrelated to processor save_pretrained file omissions." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow reporting on failed training jobs is unrelated to slow checkpoint loading." + "reason": "MLflow reporting on failed training jobs is unrelated to checkpoint loading speed." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Slow checkpoint loading and tensor-parallel training bugs are different problems." + "reason": "Checkpoint loading slowdown vs tensor-parallel training bug are different problems." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Loading slowness is not the same as confusing forward-argument documentation." + "reason": "Loading performance issue and model.forward documentation confusion do not share the same code path." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "Both mention Qwen and v5-era errors, but one is FP8 inference support and the other is a from_pretrained failure." + "reason": "FP8 support request is unrelated to Qwen3.5 MoE from_pretrained failure." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Slow from_pretrained checkpoint loading and tokenizer-loading regression are related only at a high level, not the same bug." + "reason": "Checkpoint load slowness and tokenizer loading regression are different behaviors." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching support for audio models is a different capability gap from Qwen FP8 inference support." + "reason": "Continuous batching audio support and FP8 inference support are separate feature gaps." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The analysis is mostly grounded, but it overstates the tokenizer pair: from the packet we can see strong topical similarity between issue:42913 and issue:43066, yet not enough to call them a clear duplicate or the same regression with confidence. The summary should hedge more (e.g., 'likely related' or 'possibly duplicate') unless there is body-level evidence. The rest of the soft-edge rejections are conservative." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -15234,8 +15139,8 @@ "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": [ @@ -15247,12 +15152,12 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "8a6c846e734d045b44600385112d43b3f53d7b57a0c7532082b0b6f99aff1343", + "prepared_review_unit_hash": "482c132974ebc86002c363525641bbdfcd419c87d0a5b54f721f1dcb3804d248", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2479, + "serialized_chars": 2477, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -15260,7 +15165,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2479, + "serialized_chars": 2477, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -15269,24 +15174,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These three issues do not look like duplicates: one is about Tapas tokenization mismatching TensorFlow, one is about an unhelpful auth error when downloading a private model, and one is about failing to load bert-base-uncased. They share only broad Transformers/model-loading context.", - "confidence": 0.89, - "canonical_issue_reason": "issue #16618 is the most concrete and user-facing of the set, with a specific model-load failure tied to bert-base-uncased.", + "summary": "The three issues do not look like duplicates of one another: one is about Tapas tokenization behavior, one about a private-model download/login error message, and one about a generic model-loading failure for bert-base-uncased.", + "confidence": 0.95, + "canonical_issue_reason": "There is no strong canonical duplicate here; the reports describe different failure modes. If forced to anchor the cluster, issue 16618 is the broadest model-loading report, but it still does not match the other two.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the best representative issue because it has the clearest reproducible failure and a specific affected model.", + "best_issue_reason": "Issue 16618 is the best anchor only in the sense that it is the most general and discussed model-loading complaint. It is still not a true duplicate of the Tapas tokenization or private-model/login issues.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Different symptoms and layers: Tapas tokenization parity vs. a model loading failure for bert-base-uncased." + "reason": "Tapas tokenization mismatch is a different underlying problem from a bert-base-uncased model-loading failure." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "Auth/download error for private models is unrelated to a load failure for a public model." + "reason": "Private-model download/login error message is unrelated to the generic 'can't load model' report." } ] }, @@ -15305,8 +15210,8 @@ "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": [ @@ -15316,7 +15221,7 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "13f17d72a3aed6f0289d0cadad0118b386fab32c1f56fe21683d43065ddf5517", + "prepared_review_unit_hash": "c354484ed5f5b9b5cdd845c5c5aa1f7675bf1c7808b7ec5ebc4c5558e24a1def", "component_budget": { "node_count": 2, "item_count": 2, @@ -15338,18 +15243,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are superficially similar \u201csupport for more architectures\u201d requests, but they target different features: Flash Attention 2 vs GGUF. They should not be treated as duplicates.", + "summary": "These are two unrelated feature-request issues: one for Flash Attention 2 support on more architectures, the other for GGUF support on more architectures. They share only a broad \u201ccommunity contribution\u201d framing and are not duplicates.", "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a duplicate of the other; they request support for different capabilities and should remain separate.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Same broad framing, but different underlying work: Flash Attention 2 support is unrelated to GGUF support. They would not be merged into one issue." + "reason": "Different underlying requests and code paths: Flash Attention 2 support vs GGUF support. Same broad architecture-support theme, but not the same bug/change." } ] }, @@ -15368,8 +15273,8 @@ "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": [ @@ -15391,12 +15296,12 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "a6c85be2455c5216a65b3503c14ecc827bf8e64f8ae98a75d392a2a78ee8f3e2", + "prepared_review_unit_hash": "450c0ab5018b102e02fe9c93ea3087291043bb36c8a87aa00417fd6462a99c8c", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 10, - "serialized_chars": 6443, + "serialized_chars": 6442, "estimated_input_tokens": 1611, "estimated_eval_tokens": 3478 }, @@ -15404,7 +15309,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 10, - "serialized_chars": 6443, + "serialized_chars": 6442, "estimated_input_tokens": 1611, "estimated_eval_tokens": 3478 }, @@ -15413,72 +15318,72 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are all documentation-translation requests, but they point to different target languages or separate placeholder instances, so they should not be deduplicated into one underlying issue.", - "confidence": 0.86, - "canonical_issue_reason": null, + "summary": "This cluster mixes two concrete locale requests (Turkish, Spanish) with three near-identical generic template issues. The generic template issues are the best representative of the cluster, but none of the pairs are strong enough to merge as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": "issue:44365 is the cleanest representative of the near-identical generic template-style issues; the Turkish and Spanish issues are distinct locale-specific requests.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43834 is the cleanest representative of the generic i18n translation template, but the cluster does not contain a true duplicate set because the requests appear language-specific.", + "best_issue_reason": "issue:44365 best captures the cluster\u2019s shared template wording and is closest to the other generic entries.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Turkish translation request vs a separate placeholder translation issue; different underlying language target." + "reason": "Turkish docs translation and a generic placeholder translation issue are not the same concrete request." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Turkish translation request vs a separate placeholder translation issue; not the same language or change." + "reason": "Turkish locale request versus a generic template issue; different underlying task." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "Specific Turkish request and a generic placeholder translation issue are not the same underlying request." + "reason": "Concrete Turkish translation request does not match the generic placeholder issue." }, { "left": "issue:27088", "right": "issue:28936", "accept": false, - "reason": "Turkish vs Spanish docs translation; same broad category but clearly different underlying requests." + "reason": "Different target languages (Turkish vs Spanish) make these distinct issues." }, { "left": "issue:28936", "right": "issue:43834", "accept": false, - "reason": "Spanish request vs a separate generic placeholder translation issue; different language target." + "reason": "Spanish translation request is not the same as the generic template issue." }, { "left": "issue:28936", "right": "issue:44365", "accept": false, - "reason": "Spanish request vs a separate placeholder translation issue; not the same concrete translation task." + "reason": "Spanish locale request versus a generic placeholder issue; not the same underlying bug/change." }, { "left": "issue:28936", "right": "issue:44370", "accept": false, - "reason": "Spanish request vs a separate placeholder translation issue; different underlying language target." + "reason": "Different concrete locale requests; only broad translation theme is shared." }, { "left": "issue:43834", "right": "issue:44370", "accept": false, - "reason": "Both are template-like i18n issues, but there is no evidence they refer to the same language or exact request." + "reason": "These are near-identical template issues, but the evidence is insufficient to say they are the same concrete issue." }, { "left": "issue:43834", "right": "issue:44365", "accept": false, - "reason": "Near-identical template text is not enough; likely distinct language-specific translation requests." + "reason": "Highly similar generic wording, but no explicit evidence of one underlying issue rather than repeated template entries." }, { "left": "issue:44365", "right": "issue:44370", "accept": false, - "reason": "Two placeholder translation issues, but not enough evidence they represent the same concrete request." + "reason": "Nearly identical placeholder text, but not enough proof they refer to the same concrete task." } ] }, @@ -15497,8 +15402,8 @@ "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": [ @@ -15555,12 +15460,12 @@ "issue:37015|issue:45027", "issue:43837|issue:45177" ], - "prepared_review_unit_hash": "80b5173ee9ceb62227c9dd5007d0f25731782ad32b1cdd73cca3d95126edbf61", + "prepared_review_unit_hash": "6a52ed0d3a7b09a51fdcaa56a1c4a79e48b8c0ffd821a2496aa43c1baa34260b", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20708, + "serialized_chars": 20706, "estimated_input_tokens": 5177, "estimated_eval_tokens": 10610 }, @@ -15568,7 +15473,7 @@ "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20708, + "serialized_chars": 20706, "estimated_input_tokens": 5177, "estimated_eval_tokens": 10610 }, @@ -15577,234 +15482,222 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "A loose cluster of model-request issues spanning unrelated models and modalities (text, vision, audio, OCR). They are thematically similar but do not look like duplicate reports of the same underlying request.", - "confidence": 0.94, - "canonical_issue_reason": "issue:43671 is the most active representative of the cluster, but it is still a distinct Qwen3-TTS support request rather than a duplicate of the neighboring ASR/audio/model requests.", + "summary": "This cluster is a collection of broadly similar model-addition requests, but the underlying models, modalities, and code paths are different. I do not see true duplicates or a single canonical issue/PR for merge triage.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:43671 is the best single issue to anchor this loose cluster because it is well-discussed and representative of the broader audio-model request subgroup, even though the items are not duplicates.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different requested models: EuroBert vs DEIMv2; same pattern of model request, not the same change." + "reason": "EuroBert config support vs DEIMv2 addition: different model families and likely different implementation paths." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert text model request vs Qwen3-TTS audio support; different code paths and artifacts." + "reason": "EuroBert model config request vs Qwen3-TTS speech support; unrelated modalities and code changes." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "EuroBert config addition is unrelated to RF-DETR model support." + "reason": "EuroBert config vs RF-DETR object detection model; different architecture and files to touch." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are distinct model additions with different architectures." + "reason": "RF-DETR and DEIMv2 are distinct vision models; same broad subsystem, but not the same underlying change." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "RF-DETR detection model vs LFM2.5 Audio support; unrelated requests." + "reason": "RF-DETR detector vs LFM2.5 Audio model; different modality and implementation scope." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "RF-DETR and the weight-sparse transformer request are different concrete models." + "reason": "RF-DETR addition vs a sparse transformer request; unrelated model families and code paths." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR vision model request is not the same as Qwen3-ASR audio support." + "reason": "RF-DETR detection model vs Qwen3-ASR speech recognition; different modality and concrete change." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR and Qwen3-TTS target different model families and functionality." + "reason": "RF-DETR detection model vs Qwen3-TTS support; not the same bug/change." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT and Qwen3-ASR are unrelated model requests." + "reason": "NeoBERT text model request vs Qwen3-ASR speech request; different model targets." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT text-model support vs a sparse-transformer request; not the same bug/change." + "reason": "NeoBERT addition vs sparse transformer support; different architecture and likely different files." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT and LFM2.5 Audio are different models/modalities." + "reason": "NeoBERT vs LFM2.5 Audio; text model request and audio model request are not duplicates." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are different model additions." + "reason": "RF-DETR and NeoBERT are unrelated model additions across different domains." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are distinct model requests, not duplicates." + "reason": "NeoBERT and ModernVBERT are different model requests; only broad theme of adding a model." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture support and Qwen3-ASR support are different concrete requests." + "reason": "MiniCPM3 architecture request vs Qwen3-ASR support; different model families and tasks." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 and the OpenAI sparse transformer request are unrelated." + "reason": "MiniCPM3 architecture vs weight-sparse transformer request; not the same concrete change." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 and ModernVBERT are separate model additions." + "reason": "MiniCPM3 architecture request vs ModernVBERT models; distinct model integrations." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral TTS support are different model families and modalities." + "reason": "MiniCPM3 architecture vs Voxtral TTS support; unrelated model/task." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 vision request and Qwen3-TTS audio request are unrelated." + "reason": "DEIMv2 vision model request vs Qwen3-TTS speech support; different modality and code path." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT and Qwen3-ASR are different support requests." + "reason": "ModernVBERT models vs Qwen3-ASR support; different model family and task." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT is a BERT variant request; Qwen3-TTS is an audio-model request." + "reason": "ModernVBERT models vs Qwen3-TTS support; not the same underlying change." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT and the generic RoPE BERT-like request are related in theme but not the same underlying issue." + "reason": "ModernVBERT model addition vs broad BERT-like RoPE discussion; related theme but not a duplicate." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "BERT-like models with RoPE vs Voxtral TTS; different model classes and code paths." + "reason": "BERT-like RoPE architecture discussion vs Voxtral TTS support; unrelated request scope." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are related family requests but distinct tasks and implementations." + "reason": "Qwen3-TTS vs Qwen3-ASR are related by family name but target different speech tasks and fixes." }, { "left": "issue:43671", - "right": "issue:43909", + "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are different audio model requests." + "reason": "Both are speech-related, but Qwen3-TTS and Voxtral-4B-TTS-2603 are different model integrations." }, { "left": "issue:43671", - "right": "issue:44121", + "right": "issue:45177", "accept": false, - "reason": "Qwen3-TTS support and the sparse-transformer request are unrelated." + "reason": "Qwen3-TTS support vs DeepSeek-OCR2 addition; different modalities and code paths." }, { "left": "issue:43671", - "right": "issue:45027", + "right": "issue:44121", "accept": false, - "reason": "Qwen3-TTS and Voxtral TTS are separate model integrations." + "reason": "Qwen3-TTS support vs sparse transformer request; different model class and implementation." }, { "left": "issue:43671", - "right": "issue:45177", - "accept": false, - "reason": "Qwen3-TTS support and DeepSeek-OCR2 are different modalities and requests." - }, - { - "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are distinct audio model support requests." - }, - { - "left": "issue:43837", - "right": "issue:44121", - "accept": false, - "reason": "Qwen3-ASR and the sparse-transformer request are unrelated." + "reason": "Qwen3-TTS and LFM2.5 Audio are both audio-related but still distinct model requests." }, { "left": "issue:43837", - "right": "issue:45027", + "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different audio tasks/models." + "reason": "Qwen3-ASR and LFM2.5 Audio are separate speech-model requests, not the same change." }, { "left": "issue:43837", - "right": "issue:45177", + "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are not the same underlying change." + "reason": "Qwen3-ASR support vs EUPE model request; different model families and functionality." }, { "left": "issue:43837", - "right": "issue:45322", + "right": "issue:44121", "accept": false, - "reason": "Qwen3-ASR and EUPE are distinct model requests." + "reason": "Qwen3-ASR speech support vs sparse transformer request; unrelated code paths." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "LFM2.5 Audio 1.5B and SAM3-LiteText are different model additions." + "reason": "LFM2.5 Audio vs SAM3-LiteText; audio model request versus vision/text model request." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Sparse transformer request vs EUPE request; no concrete overlap in the underlying model change." + "reason": "Sparse transformer model request vs EUPE encoder request; distinct architectures and fixes." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are separate audio-model support requests." + "reason": "Qwen3-ASR is speech recognition, while Voxtral-4B-TTS-2603 is text-to-speech; opposite tasks." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated model requests." + "reason": "NeoBERT text model request vs Voxtral TTS support; unrelated model additions." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model families and tasks." + "reason": "Qwen3-ASR speech support vs DeepSeek-OCR2; different model domains and code changes." } ] }, @@ -15823,8 +15716,8 @@ "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": [ @@ -15845,82 +15738,82 @@ "issue:43668|issue:44031", "issue:43668|issue:43813" ], - "prepared_review_unit_hash": "c731ec4ecbc851041bc7f48f15f2dae9639e74c4fdb30083f95937f2f3ac51ad", + "prepared_review_unit_hash": "abd24aa4ec8712eb8c481d9e4576fa44d8d857b0de0b0dfd84a082c73bbba98c", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6293, - "estimated_input_tokens": 1574, - "estimated_eval_tokens": 3404 + "serialized_chars": 6288, + "estimated_input_tokens": 1572, + "estimated_eval_tokens": 3400 }, "budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6293, - "estimated_input_tokens": 1574, - "estimated_eval_tokens": 3404 + "serialized_chars": 6288, + "estimated_input_tokens": 1572, + "estimated_eval_tokens": 3400 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues are only loosely text-similar; they span unrelated areas (normalization behavior, Mask2Former loss plumbing, config typing, quantization typos, and tokenizer warnings) and do not look like duplicates of the same underlying bug.", - "confidence": 0.92, + "summary": "These issues are a loose similarity cluster, not a duplicate set: they cover unrelated bugs across model configs, loss plumbing, quantization typos, and tokenizer warnings. No pair looks like the same underlying fix.", + "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:44031 is the broadest user-facing regression in the set (tokenizers warning everywhere after a version bump), so it is the best representative issue, though it is not a duplicate of the others.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Both mention normalization, but one is about Llama4TextL2Norm semantics and the other is a ModernBERTConfig type hint; different code paths and fixes." + "reason": "Both mention normalization, but one asks about Llama4TextL2Norm semantics while the other is a ModernBERTConfig type-hint issue; different models and different defect types." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Mask2Former ignore_value usage and kwargs not being forwarded to loss are different bugs in different parts of the loss pipeline." + "reason": "Unrelated bugs: Mask2Former ignore_value is unused, versus kwargs not being forwarded to a loss function." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2Former loss handling and tokenizer regex warnings are unrelated subsystems with no shared concrete bug." + "reason": "Different subsystems and symptoms: Mask2Former loss parameter handling versus tokenizer regex warning behavior." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "A Mask2Former loss/configuration issue is not the same as a quantization typo in a different feature area." + "reason": "Mask2Former ignore_value handling is unrelated to a typo in a quantization attribute name." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "These concern unrelated models and defect types: unused ignore_value versus an incorrect type hint." + "reason": "One is a model-loss parameter bug, the other is a config type-hint mistake in a different model." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Passing kwargs to a loss function is a different issue from a config annotation problem." + "reason": "Loss-kwargs forwarding bug and ModernBERTConfig type annotation bug are distinct code paths and fixes." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "ModernBERT config typing and tokenizer regex warnings are unrelated; no shared underlying change or bug." + "reason": "A config type hint issue is not the same underlying problem as tokenizer regex warnings after a version change." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "Incorrect type hint in a config class and a specific typo in a quantization field are distinct defects." + "reason": "ModernBERTConfig norm_eps typing and the quantization_operation typo are unrelated changes." } ] }, @@ -15939,8 +15832,8 @@ "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": [ @@ -15950,7 +15843,7 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "25defb6e84f9477312afafff52ed668cd4994c028a143d65f45ad21450aa6ce2", + "prepared_review_unit_hash": "651d192913ec6eec67697e1ade1dd96774269597b3950612700611f589bf9bba", "component_budget": { "node_count": 2, "item_count": 2, @@ -15972,18 +15865,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are not duplicates: one requests block decoding behavior, the other requests DeepSeek v3.2 model support. They describe different user-facing changes and different code paths.", - "confidence": 0.97, - "canonical_issue_reason": null, + "summary": "The two issues are unrelated: one asks for block decoding support, the other for DeepSeek v3.2 support. They should not be deduplicated.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue; the requests target different features/problem domains.", "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a good canonical representative for the other; they are unrelated. If forced, 43037 is more specific, while 41084 is too vague to serve as a cluster anchor.", + "best_issue_reason": "Neither is a duplicate of the other. If one must represent the cluster, 'DeepSeek v3.2 support' is the clearer standalone feature request.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different underlying requests: block decoding configuration vs adding support for a specific model version. No shared bug or change target." + "reason": "Different underlying requests: block decoding implementation vs DeepSeek v3.2 model support. They share no concrete bug/change." } ] }, @@ -16002,8 +15895,8 @@ "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": [ @@ -16013,12 +15906,12 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "5290df8cbd033c3775db66ee7ffa8f9bc4be36475fed9a3c237d30ada5cf0904", + "prepared_review_unit_hash": "6c435e1d99eb3655afb5f87c4e82b59593e2891a8719dca43f33696443f93722", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1584, + "serialized_chars": 1583, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -16026,7 +15919,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1584, + "serialized_chars": 1583, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -16035,18 +15928,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues are related only at the broad Trainer subsystem level, but they describe different problems: one is about `remove_unused_column` behavior/customizability, the other about FLOPS estimation for custom trainers. They should not be deduplicated.", - "confidence": 0.94, - "canonical_issue_reason": "Issue #43598 is the more concrete, narrowly scoped Trainer behavior change; #43600 is a separate FLOPS-accounting concern and not the same underlying bug.", + "summary": "Two closed issues touch Trainer customization, but they describe different problems: one about `remove_unused_column` behavior, the other about FLOPs estimation for custom trainers. They are related in theme, not the same underlying bug.", + "confidence": 0.89, + "canonical_issue_reason": "Issue #43598 is the stronger canonical issue because it states a concrete Trainer behavior (`remove_unused_column`) and a specific customization limitation, making the scope clearer.", "canonical_pr_reason": null, - "best_issue_reason": "#43598 is the better representative issue because it has a specific actionable target (`remove_unused_column`) and a clearer expected fix path.", + "best_issue_reason": "#43598 is the best representative issue: it is narrowly actionable and describes an explicit Trainer setting that likely needs design/behavior changes.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "Different code paths and outcomes: one concerns column pruning customization in Trainer, the other concerns FLOPS estimation for custom trainers. They share the Trainer area but not the same underlying bug/change." + "reason": "The issues concern different code paths and outcomes: one is about unused-column removal in Trainer data handling, the other about FLOPs accounting for custom trainers. Shared customization context is not enough to treat them as duplicates." } ] }, @@ -16065,8 +15958,8 @@ "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": [ @@ -16076,12 +15969,12 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "3066966d528d6f060e5d7a3f64cdc0801355f436c79c94fc5d92707c4eca7a61", + "prepared_review_unit_hash": "f7e521b2970c2a7842af7f4234efce91d1aa4351c4b6a173b1ded8855040ba6e", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1611, + "serialized_chars": 1612, "estimated_input_tokens": 403, "estimated_eval_tokens": 1062 }, @@ -16089,7 +15982,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1611, + "serialized_chars": 1612, "estimated_input_tokens": 403, "estimated_eval_tokens": 1062 }, @@ -16098,18 +15991,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related only at a very broad Transformers/model-registration level, but they are not the same issue: one asks for Qwen3-Omni auto-class registration, the other asks for sequence-classification support for Qwen3.5.", - "confidence": 0.95, - "canonical_issue_reason": "No canonical duplicate: issue 43684 is a broad AutoModel registration request for Qwen3-Omni, while 44405 is a separate task-specific request for AutoModelForSequenceClassification support on Qwen3.5.", + "summary": "These are different feature requests for different Qwen model families and different AutoModel heads, so they should not be clustered as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43684 is the broader request and is specifically about registering Qwen3-Omni with AutoModel and AutoModelForConditionalGeneration, which is the clearest standalone issue here.", "canonical_pr_reason": null, - "best_issue_reason": "43684 is the broader, more central issue if a single issue must represent the topic, but it should not subsume 44405 because the model family and requested capability differ.", + "best_issue_reason": "Issue 43684 is the best representative because it names the concrete registration gap and is broader than the more specialized sequence-classification request in 44405.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Reject: different underlying requests. 43684 is about adding Qwen3-Omni registration to auto classes; 44405 is about enabling sequence classification for Qwen3.5. They target different model/config paths and are not the same bug/change." + "reason": "Different model variants and different tasks: Qwen3-Omni registration for base/generation auto classes versus Qwen3.5 sequence-classification support. They do not appear to be the same underlying bug or change." } ] }, @@ -16128,8 +16021,8 @@ "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": [ @@ -16146,7 +16039,7 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "6cd681caaebece3f205458182afd319b3f6f08aeacde9d178eeed33d0e704de9", + "prepared_review_unit_hash": "e4931f27018694fbc8f63c50aa15a21db45e1d1820b2e87bbe638a99013d98ac", "component_budget": { "node_count": 4, "item_count": 4, @@ -16168,57 +16061,54 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster contains one clearly different issue ('Fett') and three issues with the same 'huggingface' title. The available evidence is limited to title similarity, timestamps, and body-length differences, so the huggingface items are best treated as related-looking but not proven duplicates. I\u2019d keep 43845 as the reference issue only because it is the earliest of that trio.", - "confidence": 0.61, - "canonical_issue_reason": "issue:43845 is the earliest of the three huggingface-titled issues and is the most reasonable anchor for that small cluster, but the evidence here is not strong enough to prove the others are duplicates.", + "summary": "All four issues are too under-specified to confidently deduplicate. Three share the same vague title, but there is no body/context to confirm they describe the same underlying problem; the lone different title looks unrelated.", + "confidence": 0.32, + "canonical_issue_reason": "issue:43845 is the best placeholder canonical issue because it is the earliest of the repeated 'huggingface' titles, but the cluster lacks enough detail to establish a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43845 is the best overall issue candidate because it predates the other huggingface reports and appears to be the most representative of that subgroup.", + "best_issue_reason": "issue:43845 is the strongest issue candidate only by virtue of being the earliest repeated-title report; still, the report content is too thin to be a reliable canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles and no body text or other evidence tying them to the same underlying issue." + "reason": "Titles do not match, and there is no body/detail tying 'Fett' to the 'huggingface' reports." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "Different titles and no concrete evidence beyond a weak soft similarity signal." + "reason": "No substantive evidence of the same underlying bug; titles are unrelated." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "Different titles; the packet does not show enough to conclude duplication." + "reason": "No content links this issue to the 'huggingface' reports." }, { "left": "issue:43845", "right": "issue:43846", "accept": false, - "reason": "Same title and close timestamps, but the packet only shows similarity signals and body-length differences, not enough to confirm the same issue." + "reason": "Identical vague titles are not enough to confirm the same bug without body/context." }, { "left": "issue:43845", "right": "issue:43859", "accept": false, - "reason": "Same title, but only weak observable evidence is available here; body text is missing, so duplication is not established." + "reason": "Same broad title, but no description or targets to verify a shared underlying issue." }, { "left": "issue:43846", "right": "issue:43859", "accept": false, - "reason": "Same title alone is insufficient; the packet does not provide enough detail to accept this as a duplicate." + "reason": "Same repeated title, but insufficient evidence to treat them as definite duplicates." } ] }, - "evaluator_result": { - "accept": false, - "feedback": "The summary is mostly grounded, but the soft-edge decisions are too strong for the packet. The data only shows title similarity, close timestamps for 43845/43846, and body-length differences; it does not show the actual body text or enough evidence to conclude the three 'huggingface' issues are duplicates with high confidence. In particular, the claims about 'placeholder content' and 'same vague subject matter' overstate what is observable here. A more conservative verdict would keep these as unaccepted soft matches." - }, - "evaluator_used": true, - "retried": true, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -16231,8 +16121,8 @@ "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": [ @@ -16253,88 +16143,88 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "70723412500245f4618c7719cc67f9f9cffd1ca94d517cf1dbf068c1ce5b36a9", + "prepared_review_unit_hash": "e7553489ffd9fd8dd1946c6ae387cdb2f37296faf2f0adff2aa79a41ca7d5d28", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5794, - "estimated_input_tokens": 1449, - "estimated_eval_tokens": 3154 + "serialized_chars": 5791, + "estimated_input_tokens": 1448, + "estimated_eval_tokens": 3152 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5794, - "estimated_input_tokens": 1449, - "estimated_eval_tokens": 3154 + "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": "This cluster is mostly low-signal spam-like issues plus one generic documentation suggestion; there is no clear underlying bug/change shared across them.", - "confidence": 0.96, - "canonical_issue_reason": "No canonical issue: the items are unrelated and too vague/spammy to represent one duplicated problem.", + "summary": "These are low-signal, likely unrelated spam/placeholder issues. Two pairs share the exact same placeholder title, but there is no evidence of a shared underlying bug or concrete change, so no soft merges are justified.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44371 is the earliest and simplest representative of the spam-like cluster, but only as a bookkeeping anchor rather than because it clearly matches a real underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44418 is the least spam-like and most issue-like title, but it is still far too generic to be a strong canonical target.", + "best_issue_reason": "issue:44371 is the best single issue to keep as the cluster representative because it is earliest and generic, but the cluster itself does not appear to describe a real deduplicable issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are just '' placeholders; no concrete shared bug or change." + "reason": "Same placeholder title, but the content is too empty to establish the same underlying issue or bug." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Both are just '' placeholders; no concrete shared bug or change." + "reason": "Same placeholder title, but no concrete evidence links them to the same problem." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "Spam placeholder versus generic documentation request; not the same underlying issue." + "reason": "These titles are not meaningfully the same issue; one is spam-like and the other is a generic documentation suggestion." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder versus another spam-like title; no shared concrete problem." + "reason": "No shared bug/change is visible; the titles are unrelated." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "Generic docs suggestion versus spam placeholder; not a duplicate pair." + "reason": "Generic documentation suggestion versus spam placeholder; no same underlying issue is evident." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "Generic docs suggestion versus spam placeholder; not a duplicate pair." + "reason": "Generic documentation suggestion versus spam placeholder; not the same concrete problem." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Identical spam-like titles, but there is no real underlying bug/change to unify." + "reason": "Identical placeholder titles alone are not enough to confirm the same underlying bug or change." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder versus unrelated spam-like title; no concrete shared issue." + "reason": "No concrete overlap beyond low-signal similarity; the titles do not indicate the same issue." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder versus unrelated spam-like title; no concrete shared issue." + "reason": "No concrete overlap beyond low-signal similarity; the titles do not indicate the same issue." } ] }, @@ -16353,8 +16243,8 @@ "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": [ @@ -16364,12 +16254,12 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "5258bfbf88b33c7d05662c4a9169cb35009b0e5a59469f8e7b8b242bbb938e4e", + "prepared_review_unit_hash": "18ff4fd5a3b447a07bf1f906b8f1152897c2896f2b36757fb50f2a162fa6d0cd", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1646, + "serialized_chars": 1645, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -16377,7 +16267,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1646, + "serialized_chars": 1645, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -16386,28 +16276,28 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues have an exact title match and very similar body sizes, so they are likely the same request, but the bodies themselves are not visible here, so this should be treated as a probable duplicate rather than a certain one.", - "confidence": 0.88, - "canonical_issue_reason": "issue #45145 is the better canonical thread because it was created first and already has an inbound reference, making it the more established issue.", + "summary": "The two closed issues have identical titles and fairly similar lengths, but the packet only provides soft-similarity evidence. With no explicit links, shared targets, or body-level confirmation, this should be treated as a tentative match rather than a confirmed duplicate. The soft edge is rejected.", + "confidence": 0.71, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue #45145 is the best representative issue because it is earlier, has slightly more reference activity, and appears to be the original thread for the same topic.", + "best_issue_reason": "Issue #45145 is the best provisional issue candidate because it is earlier and already has an inbound reference, but the evidence is not strong enough to confirm a duplicate/canonical merge.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", - "accept": true, - "reason": "Exact title match plus very similar body length strongly suggests the same underlying issue, but without the bodies this should be read as a likely/probable duplicate rather than a definite one." + "accept": false, + "reason": "Identical titles and soft similarity alone are not enough to confirm the same underlying issue. The packet does not show near-identical bodies, explicit links, or shared targets, and deterministic_accept is false." } ] }, "evaluator_result": { "accept": false, - "feedback": "The packet supports strong similarity and an exact title match, but it does not expose the issue bodies, so claiming \u201cstrongly overlapping content\u201d or a definite duplicate is a bit too strong. The soft-edge verdict should stay conservative (e.g. likely duplicate / probable same issue), and the confidence should be lower than 0.99 given the limited evidence." + "feedback": "The packet supports only a soft-similarity match and identical titles; it does not show the bodies are near-identical or that these are definitely duplicates. The soft-edge verdict is too strong: deterministic_accept is false in the packet, so a conservative verdict would be uncertain or tentative rather than accept." }, "evaluator_used": true, "retried": true, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -16473,8 +16363,8 @@ "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": [ @@ -16484,12 +16374,12 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "5d2a879d76386fd537b9b0f047977585d1167b218b6f1c41c429fa3fad4f1674", + "prepared_review_unit_hash": "d777f1c0f728e4c2f0d9379e5a5d306a24a02001acda5f42275aa70ac42f104c", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1667, + "serialized_chars": 1668, "estimated_input_tokens": 417, "estimated_eval_tokens": 1090 }, @@ -16497,7 +16387,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1667, + "serialized_chars": 1668, "estimated_input_tokens": 417, "estimated_eval_tokens": 1090 }, @@ -16506,18 +16396,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate 4-bit inference bugs: one in Gemma4/audio modules causing a uint8 `torch.finfo()` TypeError, and one in `BitsAndBytesConfig` where `llm_int8_skip_modules` drops the default `lm_head` exclusion and triggers an AssertionError. They share only a broad theme, not the same underlying failure.", - "confidence": 0.96, - "canonical_issue_reason": "Issue 45674 is the better canonical issue for the cluster because it states a clearer, more general regression in 4-bit inference configuration and has a concrete, actionable failure mode. Issue 45672 is a separate Gemma4/audio-module-specific type error.", + "summary": "The two issues both involve 4-bit inference behavior in the Gemma/BitsAndBytes stack, but they describe different failures: one is a torch.finfo() TypeError triggered by uint8 weights in audio modules, and the other is an AssertionError caused by llm_int8_skip_modules clearing the default lm_head exclusion. They are related by broad quantization context, not the same underlying bug.", + "confidence": 0.95, + "canonical_issue_reason": "Issue #45674 is the better canonical issue for the cluster only if one wants the broadest 4-bit BitsAndBytes inference regression bucket, but the reports are not duplicates and should stay separate. #45672 is more specific to Gemma4 audio-module dtype handling; #45674 is a distinct configuration/skip-modules bug.", "canonical_pr_reason": null, - "best_issue_reason": "45674 is the strongest representative issue: it is broader, more self-contained, and describes a configuration bug with an explicit causal chain and reproducible assertion failure.", + "best_issue_reason": "#45674 is the stronger standalone issue for a generic 4-bit inference regression because it includes a clear configuration trigger and an AssertionError tied to BitsAndBytesConfig behavior. #45672 is narrower and tied to a specific model/module path.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Both are 4-bit inference problems, but the code paths and failures differ: Gemma4/audio `torch.finfo()` on uint8 weights versus `BitsAndBytesConfig` skip-module handling and `lm_head` exclusion. They do not look like the same bug." + "reason": "Different root causes and different failure modes: torch.finfo(TypeError) on uint8 weights in audio modules versus AssertionError from llm_int8_skip_modules removing the default lm_head exclusion. Shared 4-bit inference context is too broad to treat as the same bug." } ] }, @@ -16536,8 +16426,8 @@ "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": [ @@ -16547,40 +16437,40 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "ecea8af619346c989f5b900b9772e6679e44788b4c0501647c8dfaca0dd8fb7b", + "prepared_review_unit_hash": "f6e1eb981b2d5914e3cebc0d8c22d011bb9afd6544ba674821e33e8d38a9649d", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1477, - "estimated_input_tokens": 370, - "estimated_eval_tokens": 996 + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1477, - "estimated_input_tokens": 370, - "estimated_eval_tokens": 996 + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues appear unrelated and spam-like, each containing only a different person\u2019s name and date of birth. They do not describe the same bug or request, so they should not be clustered as duplicates.", - "confidence": 0.98, - "canonical_issue_reason": "No canonical issue: the items are unrelated and lack any shared problem statement or technical context.", + "summary": "The cluster contains two extremely sparse issue reports with unrelated personal-name-and-date titles. They do not look like duplicate bug reports; they look more like low-signal/spam entries.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45762 is the earliest issue and is no less representative than the other, but there is no evidence these two are the same underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a good canonical choice; both look like standalone, non-technical/spam entries rather than duplicate reports.", + "best_issue_reason": "issue:45762 is the best cluster representative only because it is earlier; the pair does not appear to be a true duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "Different names and dates of birth with no shared bug, feature, or code context; not the same underlying issue." + "reason": "Reject: the titles are different names/dates with no shared bug description, code path, or explicit linkage; they do not appear to be the same underlying issue." } ] }, @@ -16599,8 +16489,8 @@ "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": [ @@ -16610,7 +16500,7 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "9e00e8d85a689e610ece8633b33399b2de1d6ef9148503043f8a5ef9a91619c7", + "prepared_review_unit_hash": "b21478d066a696f4f8d33b987830cc99e3cb128ee2e394a1af77d7ad1e3f0fb7", "component_budget": { "node_count": 2, "item_count": 2, @@ -16632,18 +16522,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues are body-less and their titles are just different personal-name/date strings; they do not appear to describe the same bug or request, so this is not a duplicate cluster.", - "confidence": 0.98, - "canonical_issue_reason": "No true canonical issue: both entries are content-free and unrelated, so there is no shared underlying problem to canonicalize.", + "summary": "The two closed issues are low-signal, name/date-only entries and do not describe the same bug, feature, or change. They should not be treated as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 45764 is only marginally cleaner as a representative because its title is slightly more formatted, but it is not a meaningful duplicate target.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "Reject: the titles are different personal-name/date strings with no body, code path, or problem statement indicating the same underlying issue." + "reason": "The titles are different personal-name/date placeholders with no shared problem statement or code context, so they do not appear to represent the same underlying issue." } ] }, @@ -16662,8 +16552,8 @@ "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": [ @@ -16683,12 +16573,12 @@ "issue:45871|issue:45873", "issue:45872|issue:45873" ], - "prepared_review_unit_hash": "b3add61107fbb46a35dc68775a64dd282d1d15f7503d0c9760d7ed0c2c855311", + "prepared_review_unit_hash": "6d7a66659b142f6dbae83a3964a0288c04d876e311248cbcd76da525026fd505", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5727, + "serialized_chars": 5726, "estimated_input_tokens": 1432, "estimated_eval_tokens": 3120 }, @@ -16696,7 +16586,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5727, + "serialized_chars": 5726, "estimated_input_tokens": 1432, "estimated_eval_tokens": 3120 }, @@ -16705,66 +16595,66 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The set contains three unrelated issue topics: one dataset listing, one duplicate example request pair, and one duplicate scraping-service request pair. Only the exact-topic pairs should be treated as duplicates.", - "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue fits the whole set because the items split into separate topics; if forced to pick a representative, issue 45872 best captures the concrete feature request and has an exact duplicate in 45873.", + "summary": "The cluster is not one single duplicate set: it splits into two exact-duplicate issue pairs (45870/45871 and 45872/45873). Issue 45869 is only loosely related by topic and does not look like a duplicate of either pair.", + "confidence": 0.93, + "canonical_issue_reason": "45870 is the clearest representative of the 'Example: Financial time series prediction with DataForge' thread because it is an exact duplicate of 45871 and has the strongest direct match in the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45872 is the strongest representative issue overall: it is specific, actionable, and its duplicate 45873 is clearly the same request. The other issues are either a different topic or a less distinctive example request.", + "best_issue_reason": "45870 is the best single issue to keep as the representative for one duplicate thread; it is an exact duplicate pair with 45871 and is more central than the loosely related dataset request in 45869.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45869", "right": "issue:45870", "accept": false, - "reason": "Different topics: a dataset bundle listing versus an example request; they are not the same underlying issue." + "reason": "Related financial/data topic, but the dataset bundle request and the DataForge example are different underlying issues." }, { "left": "issue:45869", "right": "issue:45871", "accept": false, - "reason": "Different topics: dataset listing versus example request; no evidence they describe the same bug or change." + "reason": "Same as 45869 vs 45870: related theme, but not the same issue." }, { "left": "issue:45870", "right": "issue:45871", "accept": true, - "reason": "Same title and apparent same example-request content; these look like exact duplicates." + "reason": "Same title and same apparent content; this looks like a direct duplicate." }, { "left": "issue:45870", "right": "issue:45872", "accept": false, - "reason": "Both mention financial time series, but one is an example request and the other adds a scraping service; different underlying requests." + "reason": "Both mention financial time series/DataForge, but one is an example request and the other is a scraping-service/project request; not the same concrete issue." }, { "left": "issue:45870", "right": "issue:45873", "accept": false, - "reason": "Example-request issue versus scraping-service request; not the same concrete change." + "reason": "Related broad topic, but different request and likely different underlying change." }, { "left": "issue:45871", "right": "issue:45872", "accept": false, - "reason": "Same as above: example request and scraping-service request are distinct issues." + "reason": "Different issue themes; no sign they describe the same change or bug." }, { "left": "issue:45871", "right": "issue:45873", "accept": false, - "reason": "Same as above: not the same underlying request." + "reason": "Different issue themes; only broad topical overlap." }, { "left": "issue:45872", "right": "issue:45873", "accept": true, - "reason": "Same title and same feature request wording; these look like exact duplicates." + "reason": "Same title and same apparent content; this looks like a direct duplicate." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded and conservative overall. The packet supports two exact duplicate pairs (45870/45871 and 45872/45873) plus the distinct dataset-listing issue 45869. The soft-edge verdicts are appropriately cautious, and the summary does not overclaim beyond the titles/body metadata provided." + "feedback": "The summary is well grounded in the packet: 45870/45871 share the same title and metadata, as do 45872/45873, while 45869 is only topically similar. The conservative non-duplicate calls for the cross-pair comparisons are reasonable, and the representative selection of 45870 is supported by the evidence." }, "evaluator_used": true, "retried": false, @@ -16780,8 +16670,8 @@ "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-39895-13", "nodes": [ @@ -16820,7 +16710,7 @@ "pull_request:43823|pull_request:45795", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "9abf53ffbd26050355ff6ec4f66f07905444f05ae5d9e4d027b51f28ed4bfae3", + "prepared_review_unit_hash": "2c866de12382430c951b6cadfa7bc35cb039a1b6b01e180f7db511fdf6119abf", "component_budget": { "node_count": 13, "item_count": 13, @@ -16842,132 +16732,132 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster is mostly a set of unrelated PRs that only share broad transformer-platform themes. The only true duplicate pair is the two fixed_cross_entropy changes (43251 and 43254), which both address the same cross-entropy kwargs propagation bug.", - "confidence": 0.96, + "summary": "This cluster is mostly a grab bag of unrelated PRs; the only clear duplicate is the pair of loss-utils fixes around `fixed_cross_entropy`. Everything else targets different models, docs, or subsystems and should stay separate.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the best canonical PR: it explicitly targets issue 43240, and its diff directly implements the cross-entropy kwargs fix in a concrete, bug-focused way. PR 43254 is essentially the same change but less specific.", + "canonical_pr_reason": "PR 43251 is the best canonical representative for the one real duplicate pair: it has the explicit issue link, a focused fix in `loss_utils.py`, and the companion PR 43254 is just an alternate formulation of the same `cross_entropy` kwargs change.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the strongest representative of the cluster because it is the only clearly duplicate-safe match and the clearest substantive bug fix among the items. The rest are either unrelated model additions, docs, tests, or broader refactors.", + "best_pr_reason": "PR 43251 is the strongest standalone PR in the set because it is a concrete bug fix with a linked issue and a narrow scope; it is also the right anchor for deduplicating 43254.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Different artifacts: Videoprism model addition vs Executorch dynamic-shape export test. Same ecosystem, but not the same underlying bug or change." + "reason": "Unrelated changes: new VideoPrism model/docs vs an ExecuTorch dynamic-shape test. Same \u201cmodel tooling\u201d theme is too broad for duplicate merging." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Mistral tokenizer missing methods vs adding MobileLLM model support. Unrelated code paths and goals." + "reason": "Tokenizer-method cleanup for MistralCommon vs adding a new MobileLLM model. Different codepaths and goals." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer API addition vs Executorch export test; no shared bug/change." + "reason": "Tokenizer API addition vs ExecuTorch export test; no shared bug or mergeable fix." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor-pretrained robustness changes across multiple components vs a new MobileLLM model. Broadly similar area, but not the same fix." + "reason": "Processor robustness changes across several model processors vs a brand-new MobileLLM model. Too broad and not the same change." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Cross-entropy kwargs fix vs new MobileLLM model. Completely different functionality." + "reason": "`fixed_cross_entropy` kwargs support is unrelated to adding MobileLLM; different subsystem and code path." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Loss utility kwargs fix vs Mistral4 test/model cleanup. Different concrete code-paths." + "reason": "Loss utility kwargs fix vs Mistral4 test/model updates; not the same underlying bug or patch." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch export test vs Mistral4 tests/integration changes. Same general testing focus only, not the same bug." + "reason": "ExecuTorch dynamic-shape export test vs Mistral4 test/model work; same word \u201ctest\u201d is not enough." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Executorch export test vs new model implementation. No common underlying fix." + "reason": "ExecuTorch export coverage vs a new model addition. No shared concrete fix." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "MobileLLM model addition vs config-resolution order fix. Unrelated changes." + "reason": "New MobileLLM model implementation vs a config-resolution ordering fix in core modeling utils. Different problems." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM model addition vs Falcon output-interface refactor. Different models and issues." + "reason": "New MobileLLM model vs Falcon output-interface refactor; separate model families and unrelated changes." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon refactor vs Mistral4 test fix. Broadly model-internals, but not the same concrete problem." + "reason": "Falcon output-collection refactor vs Mistral4 test/model changes. Same general area of model code, but not the same concrete bug/change." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon refactor vs model-creation skill/doc scaffolding. Not the same change." + "reason": "Falcon model refactor vs a model-creation skill PR. Completely different artifact types and purposes." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test/integration work vs CLIP-like layrnorm renaming. Only superficial model-code overlap." + "reason": "Mistral4 test/model adjustments vs a `layrnorm` typo normalization fix. Not the same code-path issue." }, { "left": "pull_request:44827", "right": "pull_request:45795", "accept": false, - "reason": "Mistral4 tests vs docs for adding audio/video processors. Different artifact types and goals." + "reason": "Mistral4 work vs docs for adding audio/video processor guides. Documentation-only and unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 test fix vs config resolution order fix. Not the same bug or code path." + "reason": "Mistral4 tests/model integration vs core `cls.config` resolution ordering fix. Different defects." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 tests vs model-creation skill scaffolding. Unrelated." + "reason": "Mistral4 code/test fixes vs a model-creation skill PR; no shared fix or merge path." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "MobileLLM implementation vs a model-creation skill/doc PR. One is code, the other is workflow scaffolding." + "reason": "MobileLLM model addition vs model-creation skill scaffolding. The skill may be related conceptually, but it is not the same underlying change." }, { "left": "pull_request:43823", "right": "pull_request:45795", "accept": false, - "reason": "MobileLLM model addition vs docs-only audio/video processor guide. Same general repo area, but not the same underlying change." + "reason": "MobileLLM model addition vs docs for audio/video processor components. Different artifacts and no shared bug." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs make the same concrete fix in src/transformers/loss/loss_utils.py: pass supported kwargs through to nn.functional.cross_entropy. Same underlying bug and same code path." + "reason": "Both PRs change `src/transformers/loss/loss_utils.py` to extend `fixed_cross_entropy` with the same `cross_entropy` kwargs support; they are two formulations of the same concrete fix and could be merged into one PR." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only clearly mergeable duplicate pair is 43251/43254: both touch `src/transformers/loss/loss_utils.py`, share issue target 43240, and implement the same cross-entropy kwargs propagation fix. The other pairwise rejections are appropriately cautious given the mostly unrelated model-addition/docs/test/refactor diffs." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted duplicate pair, 43251/43254, is a plausible single bugfix in the same file/function and the reasons do not overclaim. The other pairwise rejects are also appropriately cautious given the different files, subsystems, and purposes." }, "evaluator_used": true, "retried": false, @@ -16983,8 +16873,8 @@ "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-40546-2", "nodes": [ @@ -16994,7 +16884,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "82f0204e3794a854372e15717388d78f73fcf4572dc30025108011b4414d2d81", + "prepared_review_unit_hash": "143b2d09dbf2d179c236e716bd4dad6c534e94998a23957633c5ab0340a54840", "component_budget": { "node_count": 2, "item_count": 2, @@ -17016,18 +16906,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related VibeVoice PRs, but they are not duplicates: one implements the base VibeVoice model, the other adds a realtime/tokenizer extension on top of that stack.", - "confidence": 0.9, + "summary": "These are related VibeVoice pull requests, but they target different deliverables: one implements the base VibeVoice model, while the other adds VibeVoice Realtime and the acoustic tokenizer. The overlap is mostly shared integration/docs work, not the same underlying change.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the foundational VibeVoice implementation and is the cleaner representative of the core codebase change; #42781 is a later draft that adds realtime-specific pieces and additional tokenizer work.", + "canonical_pr_reason": "PR 40546 is the better canonical PR for this cluster because it is the mature, non-draft base VibeVoice implementation and has substantial review activity; PR 42781 is a separate realtime extension.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the best single representative for the cluster because it targets the main VibeVoice integration, while #42781 is a broader follow-up focused on realtime support rather than the same concrete change.", + "best_pr_reason": "PR 40546 is the best representative PR: it is non-draft, broader and more stable, and represents the core VibeVoice support rather than the newer realtime variant.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Related subsystem, but not the same underlying change: #40546 implements VibeVoice, while #42781 adds VibeVoice Realtime plus acoustic tokenizer and generation updates. They could be sequenced, but not safely merged as one duplicate PR." + "reason": "Do not merge as duplicates: 40546 implements base VibeVoice, while 42781 adds VibeVoice Realtime plus acoustic-tokenizer-related changes. They share model-family integration files, but they are not the same concrete code-path fix/change." } ] }, @@ -17046,8 +16936,8 @@ "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-40755-2", "nodes": [ @@ -17057,7 +16947,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "eccac72176cacba026efbaa63d6697a14292fde466ae3f130a357c9f45d14b01", + "prepared_review_unit_hash": "9690a074679da35a5baf8f3cb2dd353dca5edd27b304cd0ae287408a2080c480", "component_budget": { "node_count": 2, "item_count": 2, @@ -17079,18 +16969,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are unrelated feature additions in different model families: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be clustered as duplicates.", + "summary": "These two pull requests are unrelated feature additions: one adds covariate forecasting to TimesFM, the other adds image-classification support for DINOv3 ViT. They do not appear to fix the same underlying bug or implement the same change.", "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR is appropriate here because the PRs address different codepaths, different models, and different user-facing features.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "Neither PR is a duplicate of the other; if forced to pick a representative, the TimesFM PR is more substantial in scope, but it should not be treated as the canonical match for this pair.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different model features and codepaths: TimesFM forecasting with covariates versus DINOv3 image classification support. They do not appear to fix the same underlying bug or implement the same change." + "reason": "Different models and different code paths: TimesFM forecasting with external covariates versus DINOv3 image-classification support. They are separate feature PRs, not the same underlying change." } ] }, @@ -17172,8 +17062,8 @@ "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-41797-3", "nodes": [ @@ -17185,46 +17075,46 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "4014c9485ebdd55920a0ec29bd6423e8c59c67cc1830ff403c6a9a76bb1c0d51", + "prepared_review_unit_hash": "a02fd570bcd3780b5002132933c432f7820c2a1c48f31a6e58108649de6f4f62", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10409, - "estimated_input_tokens": 2603, - "estimated_eval_tokens": 5462 + "serialized_chars": 10408, + "estimated_input_tokens": 2602, + "estimated_eval_tokens": 5460 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10409, - "estimated_input_tokens": 2603, - "estimated_eval_tokens": 5462 + "serialized_chars": 10408, + "estimated_input_tokens": 2602, + "estimated_eval_tokens": 5460 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition PRs (DeepSeekOCR, Isaac, Kimi2-6) that share Transformers boilerplate but target different models and codepaths. They are similar in structure, not duplicates.", - "confidence": 0.97, + "summary": "These are three separate model-addition pull requests for different models (DeepSeek OCR, Isaac, Kimi2-6). They share some generic registration/documentation files, but they do not appear to fix the same underlying code path or represent mergeable duplicate changes.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical duplicate exists here; the PRs introduce different models and only overlap on standard registry/docs plumbing.", + "canonical_pr_reason": "Kimi2-6 is the best single representative of this cluster because it is the broadest and most complete model-addition PR, with the most extensive auto-mapping and model integration changes plus high review activity.", "best_issue_reason": null, - "best_pr_reason": "pull_request:45630 is the most substantial/complete of the three, with the broadest integration surface and highest review activity, so it is the best representative if one must be chosen.", + "best_pr_reason": "Kimi2-6 is the strongest PR to keep as the cluster representative: it has the largest scope and touches several core integration points, whereas the other two are separate model integrations with distinct architectures and files.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different models and different concrete implementations (DeepSeek OCR vs Isaac). Shared auto-registration/docs changes are boilerplate, not the same underlying change." + "reason": "Different models and different implementation targets: DeepSeek OCR vs Isaac. Shared files are generic model-registration scaffolding, not evidence of the same bug/change." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different model families and codepaths (Isaac vs Kimi2-6). They overlap only in model-addition scaffolding, so they should not be merged as duplicates." + "reason": "Both are model additions, but for unrelated model families (Isaac vs Kimi2-6) with distinct code paths and files. Similar auto-registration edits are too generic to treat as duplicates." } ] }, @@ -17243,8 +17133,8 @@ "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-42975-2", "nodes": [ @@ -17254,12 +17144,12 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "6880d87af83a6f314d67f40978f05e355ce393993b25fa1f92fbd999058dc2c0", + "prepared_review_unit_hash": "0c428493b254e4843c60a3ec766ebaf4495d6cd78d340966acc9261072a83712", "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 }, @@ -17267,7 +17157,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5935, + "serialized_chars": 5934, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -17276,18 +17166,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are not duplicates: one PR is a broad GitHub Actions runner/action compatibility sweep, while the other is a narrower docker/build-push-action upgrade. They share workflow files but target different actions and likely different maintenance goals.", - "confidence": 0.95, + "summary": "Both PRs are GitHub Actions maintenance updates, but they target different action families and different upgrade goals: one is a broad Node 24 compatibility sweep, the other is a latest-version bump for Docker-related workflows. They are related in theme but not the same underlying change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the broader and more distinctive workflow-actions compatibility update, touching many common actions and clearly centered on Node 24 support.", + "canonical_pr_reason": "PR #42975 is the broader workflow-actions compatibility upgrade and better represents the cluster\u2019s maintenance theme.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the best representative of the cluster because it is the more general GitHub Actions upgrade effort; 42976 is a separate docker action version bump.", + "best_pr_reason": "PR #42975 is the better representative because it covers a wider set of workflow action upgrades aimed at compatibility, not just one action family.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Different underlying changes: 42975 upgrades core GitHub Actions for Node 24 compatibility, while 42976 only bumps docker/build-push-action versions. Shared workflow files alone are not enough to merge them as duplicates." + "reason": "Different underlying changes: #42975 upgrades multiple GitHub Actions for Node 24 compatibility, while #42976 updates Docker build actions to newer versions. They overlap in workflows but do not fix the same concrete problem and would not be one merged PR." } ] }, @@ -17306,8 +17196,8 @@ "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-42978-7", "nodes": [ @@ -17330,12 +17220,12 @@ "pull_request:44601|pull_request:45838", "pull_request:45490|pull_request:45838" ], - "prepared_review_unit_hash": "71bf6872e4c25f1cfd83a617bf5d6e42cc60aa58a4e32794d07f9ccbd83ba56f", + "prepared_review_unit_hash": "8599e537014e802cd203d58d9bb8ea826c5d2d47205d6eb1bf0bb29fdba97e35", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23540, + "serialized_chars": 23537, "estimated_input_tokens": 5885, "estimated_eval_tokens": 12026 }, @@ -17343,7 +17233,7 @@ "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23540, + "serialized_chars": 23537, "estimated_input_tokens": 5885, "estimated_eval_tokens": 12026 }, @@ -17352,66 +17242,66 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is not a duplicate set: it mixes unrelated model-addition PRs (ViT NEPA, Molmo, Molmo2, Lfm2Audio, CTSM, PP-LCNetV4/PP-OCRv6) plus a distributed loading feature PR. The shared files are mostly generic docs/auto-registry touchpoints, not evidence of the same underlying change.", - "confidence": 0.97, - "canonical_issue_reason": null, - "canonical_pr_reason": null, - "best_issue_reason": null, - "best_pr_reason": null, + "summary": "This cluster is heterogeneous: several unrelated model-addition PRs (ViT NEPA, Molmo, Molmo2, Lfm2 Audio, CTSM, PP-OCRv6) plus one pipeline-parallel infrastructure PR. They share template files and auto-mapping scaffolding, but not the same underlying change or code-path.", + "confidence": 0.99, + "canonical_issue_reason": "No canonical issue: the items do not point to one shared bug or feature request; they are separate model integrations and one distributed-loading refactor.", + "canonical_pr_reason": "No canonical PR: there is no duplicate set here, only distinct PRs with similar repository boilerplate.", + "best_issue_reason": "No best issue candidate in this cluster because the artifacts are not tracking a single issue.", + "best_pr_reason": "No best PR candidate; the PRs address different models or unrelated infrastructure, so none is a representative duplicate target.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different model families: ViT NEPA vs Molmo. Overlap is only in shared docs/auto-registration files, so they are not the same change." + "reason": "Both are new model-addition PRs, but they implement different models (ViT NEPA vs Molmo) and are not the same change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different model additions: ViT NEPA vs Molmo2. Similar repo plumbing, but distinct models and code paths." + "reason": "ViT NEPA and Molmo2 are distinct model integrations with different files, configs, and tests; no shared underlying bug or feature." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA model addition and CTSM model addition are unrelated; shared auto/docs edits are not enough to merge as duplicates." + "reason": "These add different models (ViT NEPA vs CTSM); similarity is only in boilerplate docs/auto-registration." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are separate model implementations with different files, tests, and docs; not the same concrete change." + "reason": "Molmo and Molmo2 are separate model families/implementations; they are not one mergeable code-path fix." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo vs CTSM are different model PRs; only broad Transformers registry/docs files overlap." + "reason": "Molmo and CTSM are unrelated model additions that only overlap on generic repository scaffolding." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are distinct model additions with different architectures and integration work." + "reason": "Molmo2 and CTSM are different model integrations with different architectures and tests, so not duplicates." }, { "left": "pull_request:43973", "right": "pull_request:45838", "accept": false, - "reason": "Lfm2Audio is an audio model addition, while PP-OCRv6 is text recognition; they do not fix or add the same feature." + "reason": "Lfm2 Audio is an audio model addition, while PP-OCRv6 is text-recognition; they do not fix the same code-path." }, { "left": "pull_request:44601", "right": "pull_request:45838", "accept": false, - "reason": "Pipeline-parallel loading support is a distributed runtime feature, not the same underlying change as adding PP-OCRv6 models." + "reason": "Pipeline-parallel loading support is infrastructure work, not the same as adding PP-OCRv6 model support." }, { "left": "pull_request:45490", "right": "pull_request:45838", "accept": false, - "reason": "CTSM model support and PP-OCRv6 text recognition support are separate model additions with different code paths." + "reason": "CTSM and PP-OCRv6 are different model additions with separate model code and tests; shared docs/auto files are not enough to merge them." } ] }, @@ -17430,8 +17320,8 @@ "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-43291-3", "nodes": [ @@ -17444,12 +17334,12 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "3286a1b997550785ea6937a6c31ec88b81b9e34e5b9d99896de4b8bdfc75cb81", + "prepared_review_unit_hash": "5fb89160d436495c1e8df74d51c48829412234c848509bf3feab23df72102875", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7092, + "serialized_chars": 7091, "estimated_input_tokens": 1773, "estimated_eval_tokens": 3802 }, @@ -17457,7 +17347,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7092, + "serialized_chars": 7091, "estimated_input_tokens": 1773, "estimated_eval_tokens": 3802 }, @@ -17466,30 +17356,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs are unrelated despite superficial test or refactor similarity. The only substantive code fix is the FP8/dequant PR; the others are Whisper test cleanup and likely unrelated test edits.", - "confidence": 0.92, + "summary": "These PRs are not duplicates of one another. #43665 is clearly a bogus/test-only change, while #43291 is a Whisper tokenizer/test fix and #44815 is a separate FP8/dequantization fix. The best representative PR in the cluster is #44815 because it is the most substantive and complete change, but it is not the same underlying change as the others.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44815 is the strongest canonical PR because it makes a real cross-file code-path fix in model loading / FP8 integration, with supporting model and test changes. The other PRs are mostly test-oriented and do not appear to target a comparable underlying bug.", + "canonical_pr_reason": "#44815 is the strongest standalone PR: it contains a concrete code-path fix across loading/FP8 quantization, with supporting model and test updates, and looks like a real mergeable change rather than a test placeholder.", "best_issue_reason": null, - "best_pr_reason": "PR #44815 is the best standalone PR in this cluster: it addresses a concrete dequantization/loading bug across implementation files and is more likely to be the primary fix than the test-only Whisper PR or the unrelated CLIP/ViT test edits.", + "best_pr_reason": "#44815 is the best PR to represent the cluster because it is the most substantial and technically coherent fix; #43291 is narrower and #43665 is not a credible fix at all.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Both are test-heavy and titled generically, but they touch different models and different code paths. No evidence they fix the same underlying bug or could be merged as one PR." + "reason": "Whisper tokenizer/test fix vs. a dummy PR that inserts failing asserts in CLIP/ViT tests; not the same underlying bug or change." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper tokenizer/test changes are unrelated to the FP8 model-loading/dequant fix; they do not share a concrete bug or code path." + "reason": "Different subsystems and failure modes: Whisper decoding/tests versus FP8 dequant/model-loading changes. No concrete shared code-path problem." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "CLIP/ViT test edits are unrelated to the model-loading and FP8 dequantization changes in the other PR. Similarity is only superficial." + "reason": "#43665 is test-only and intentionally failing, while #44815 is a real FP8/dequant fix. They are unrelated." } ] }, @@ -17508,8 +17398,8 @@ "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-43488-2", "nodes": [ @@ -17519,7 +17409,7 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "cc0da4d37115da1eed115d806035b4062aaf6eb0ceb0b62618a42efb3531d19f", + "prepared_review_unit_hash": "2a07bf45aaa8205ffc127256a33fa2ce18819292ef28091495423d79164c9534", "component_budget": { "node_count": 2, "item_count": 2, @@ -17541,18 +17431,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs were grouped only by weak textual overlap, but they target different changes: one is a small repo-bot/versioning test PR, the other is a larger workflow/testing-utils PR. They are not duplicates.", - "confidence": 0.96, + "summary": "Two open \"don't merge\" PRs are clustered only by a shared Vit test file, but their actual changes are unrelated: one is a setup/version/dependency probe, the other rewires CI/workflow/testing utilities. They should not be merged or triaged as duplicates.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43532 is the better canonical representative for the cluster because it is the more substantive change set, but the cluster itself does not look like a true duplicate set.", + "canonical_pr_reason": "No clear canonical PR: the two PRs target different code paths and different kinds of changes, so neither can represent the cluster cleanly.", "best_issue_reason": null, - "best_pr_reason": "PR #43532 is the strongest standalone PR: it has broader, coherent implementation changes across workflows and test utilities, whereas #43488 is a small synthetic/bot-check PR.", + "best_pr_reason": "Neither PR is a good global best fit because the cluster does not contain a single underlying bug/change; the shared test file is incidental.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Reject: the diffs address different code paths and workflows. #43488 is a tiny setup/version/dependency/test-bot change, while #43532 rewires CI comment handling and related testing/notification utilities. Shared Vit test file is incidental, not evidence of the same underlying fix." + "reason": "Reject: the PRs do not fix the same concrete problem. 43488 changes setup/version/dependency metadata and a Vit test, while 43532 changes GitHub workflows, testing utilities, and notification code. The shared test file is incidental." } ] }, @@ -17571,8 +17461,8 @@ "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-43612-2", "nodes": [ @@ -17582,12 +17472,12 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "4f85f9d57a0be40960dcb74d2b1132e2f69c4f30b37d8ebba6cf84cfb18c19e3", + "prepared_review_unit_hash": "b3e164d796d4604d736e6b76e00f76dc76fe9e7f7dc0fdf82520885d13bf027c", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6081, + "serialized_chars": 6082, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17595,7 +17485,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6081, + "serialized_chars": 6082, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17604,18 +17494,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two distinct pipeline-addition PRs: one for Promptable Concept Segmentation and one for Promptable Visual Segmentation. They share infrastructure and docs changes, but target different task surfaces and model integrations, so they should not be deduplicated.", - "confidence": 0.94, + "summary": "These are two separate feature PRs: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share some scaffolding and docs-generation files, but they target different tasks, models, and pipeline implementations.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43613 is the broader/more representative pipeline addition in this cluster, with more model coverage and a wider set of related files, so it is the better canonical PR for the family of promptable segmentation pipeline work.", + "canonical_pr_reason": "No canonical PR: the two pull requests implement different pipelines with different underlying models and task docs, so they are not duplicates.", "best_issue_reason": null, - "best_pr_reason": "PR #43613 is the strongest standalone representative of the cluster because it covers the larger promptable segmentation pipeline feature set and touches more of the relevant integration surface.", + "best_pr_reason": "Neither PR is a duplicate of the other; each is independently suitable for its own feature area, but there is no single best PR for this cluster.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "They are related in theme but not the same change: #43612 adds Promptable Concept Segmentation, while #43613 adds Promptable Visual Segmentation with different pipeline classes, task docs, and model/test coverage. Shared scaffolding alone is not enough to merge them." + "reason": "Different underlying features: concept segmentation vs visual segmentation. Shared documentation and metadata files are incidental and do not indicate the same code-path change." } ] }, @@ -17634,8 +17524,8 @@ "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-43651-2", "nodes": [ @@ -17645,7 +17535,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "99bf667256d9f0f91897a5f68df5f8eeb313fa7a6e532fd2a097fe011f75b9b8", + "prepared_review_unit_hash": "a331ddd38e9a591ed9f6dfcf5e565693719aa97d64b4c5e1eeb4473a4903852a", "component_budget": { "node_count": 2, "item_count": 2, @@ -17667,18 +17557,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests touch `src/transformers/trainer.py`, but they address different Trainer extension points: gradient-accumulation loss scaling vs. signature-column filtering. They are not duplicates and should not be merged together.", - "confidence": 0.97, + "summary": "The two PRs both touch `trainer.py` and expose override hooks for custom trainers, but they change different code paths: one adjusts gradient-accumulation loss scaling, the other column filtering based on the model signature. They are related in theme, not duplicates.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43651 is the better canonical representative only by marginal triage criteria: it has more discussion activity and a clearer, self-contained Trainer behavior change.", + "canonical_pr_reason": "PR #43651 is the more self-contained trainer behavior change, centered on a specific training-step loss-scaling path; #43663 is a separate signature/column-filtering hook.", "best_issue_reason": null, - "best_pr_reason": "PR 43651 is the best overall representative for this cluster because it is the more substantial and better-scoped Trainer change, but there is no true duplicate relationship between the PRs.", + "best_pr_reason": "PR #43651 is the stronger representative for this cluster because it makes a concrete, narrowly-scoped trainer fix with an explicit code-path change, whereas #43663 is a distinct extension point.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different problems and code paths: one alters loss scaling during training, the other exposes signature-column extraction for dataset filtering. Sharing `trainer.py` is not enough to treat them as the same change." + "reason": "Reject: they modify different trainer behaviors. #43651 changes gradient accumulation loss scaling in `training_step`; #43663 changes signature-column extraction for dataset column filtering. Shared file/theme alone is not enough to treat them as the same underlying change." } ] }, @@ -17697,8 +17587,8 @@ "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-43656-3", "nodes": [ @@ -17710,55 +17600,55 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "2fa1cfefe214b30bf6750df3626d722986eb93294e7f12ce261400cd160304a2", + "prepared_review_unit_hash": "6821dc0977996c891be054f8611885230304dc3f6448093d1a12264aadc54a4f", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, - "estimated_input_tokens": 1498, - "estimated_eval_tokens": 3252 + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, - "estimated_input_tokens": 1498, - "estimated_eval_tokens": 3252 + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "`43842` is the cleanest focused fix for the TypeAdapter NameError in `src/transformers/cli/serve.py`. `43836` appears to target the same underlying pydantic/TypeAdapter annotation problem and shares issue `43824`, but `43656` is tied to a different issue and its shown changes are unrelated annotation cleanup, so it should not be grouped with the others.", - "confidence": 0.89, + "summary": "The three PRs all cluster around the same `src/transformers/cli/serve.py` TypeAdapter/annotation NameError family. PR 43842 is the cleanest and most narrowly scoped fix; the other two look like broader variants of the same underlying change.", + "confidence": 0.81, "canonical_issue_reason": null, - "canonical_pr_reason": "`43842` is the most explicit and narrowly scoped fix for the TypeAdapter NameError when pydantic is unavailable, with the smallest targeted change set.", + "canonical_pr_reason": "43842 is the most focused fix: it directly makes the `TypeAdapter` annotation safe when pydantic is absent, with minimal extra refactoring.", "best_issue_reason": null, - "best_pr_reason": "`43842` is the best representative PR because it most directly fixes the concrete failure path with minimal, clearly relevant code changes.", + "best_pr_reason": "43842 best represents the cluster because it cleanly and directly addresses the runtime `TypeAdapter` NameError in `serve.py` without pulling in unrelated typing cleanup or refactor churn.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", - "accept": false, - "reason": "`43656` is linked to issue `43576` and the visible diff is annotation cleanup around `PreTrainedModel`/`ProcessorMixin`, not the same TypeAdapter/pydantic NameError fix as `43842`." + "accept": true, + "reason": "Both target the same `serve.py` TypeAdapter NameError in the CLI; 43656 is a broader typing cleanup, but the underlying bug and code path match." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Both target the same `serve.py` TypeAdapter annotation path, share explicit issue `43824`, and plausibly fix the same NameError failure mode." + "reason": "Both are fixes for the same `serve.py` TypeAdapter annotation/pydantic NameError. 43836 is broader, but the core change is the same and could plausibly live in one PR." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The analysis overstates the evidence for `pull_request:43656`. In the packet, 43656 is tied to issue `43576` and its diff preview only shows annotation cleanup around `PreTrainedModel`/`ProcessorMixin`; there is no grounded evidence that it is the same TypeAdapter/pydantic NameError fix as 43842. By contrast, 43836 and 43842 both point to issue `43824` and both touch the TypeAdapter annotation path in `src/transformers/cli/serve.py`, so that pair looks plausibly related. But the summary\u2019s claim that all three PRs are variants of the same bug fix is not supported by the packet, so the result should be rejected." + "accept": true, + "feedback": "The summary is grounded in the packet: all three PRs touch `src/transformers/cli/serve.py` and are clearly about the same annotation/`TypeAdapter` NameError family. The soft-edge accepts are conservative enough because each pair shares the same file and bug theme, and the differences look like broader vs. narrower implementations that could reasonably be merged into one fix PR." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17837,8 +17727,8 @@ "review_unit_count": 2, "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-43996-28", "nodes": [ @@ -17911,8 +17801,8 @@ "pull_request:44073|pull_request:44101", "pull_request:44059|pull_request:44071", "pull_request:44056|pull_request:44101", - "pull_request:44059|pull_request:44068", "pull_request:44073|pull_request:44161", + "pull_request:44059|pull_request:44068", "pull_request:44018|pull_request:44059", "pull_request:44101|pull_request:44161", "pull_request:43997|pull_request:44017", @@ -17944,20 +17834,20 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "f360717493969ebf0a24d513849308095ef6bac5efdadcde4e7fbbf07e257496", + "prepared_review_unit_hash": "92967931b730d88016831534c673a26d12c6b6402eb50aad370bed6cb3252421", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84899, - "estimated_input_tokens": 21225, - "estimated_eval_tokens": 42706 + "serialized_chars": 84895, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 }, "budget": { "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75096, + "serialized_chars": 75094, "estimated_input_tokens": 18774, "estimated_eval_tokens": 37804 }, @@ -17966,450 +17856,528 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is an umbrella of model-by-model output-tracing refactors, not one single bug fix. Most PRs are separate backend-specific changes; the strongest duplicate-like edges are within the GPT-Neo and GPT-J branches.", - "confidence": 0.84, - "canonical_issue_reason": "#43979 is the natural umbrella issue: it tracks the standardized output-tracing refactor across many model implementations.", - "canonical_pr_reason": "#44066 is the clearest representative PR: it explicitly targets #43979 and covers the core GPT-J/CodeGen output-tracing refactor rather than a side branch.", - "best_issue_reason": "#43979 best serves as the cluster issue because it is the common tracker all of these model-specific refactors point back to.", - "best_pr_reason": "#44066 is the best canonical PR because it is the most central, explicitly linked implementation of the shared refactor theme.", + "summary": "This cluster is mostly a campaign of model-specific refactors to standardized output tracing / capture_outputs. It is not one duplicate bugfix cluster; only a few PRs are true near-duplicates on the same concrete model code path (notably GPT-J/GPT-Neo).", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44066 is the best representative anchor: it is a substantial, explicit GPT-J/CodeGen output-tracing refactor with the issue link, and it sits at the center of the clearest duplicate overlap with 44722 and 44085.", + "best_issue_reason": null, + "best_pr_reason": "PR 44066 is the strongest single PR to keep: it covers the shared GPT-J/CodeGen tracing change, has the explicit tracking link, and is the cleanest duplicate target among the cluster.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model backends (FNet/CVT vs GPT-J); same high-level refactor theme, but not the same concrete code path." + "reason": "Different model code paths (CVT/FNet vs GPT-J); same theme, but not the same fix." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different models and code paths; only the umbrella output-tracing theme is shared." + "reason": "Different models and different implementation paths; only the refactor theme overlaps." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both are GPT-J output-tracing refactors in the same implementation area; one looks like a narrower or later split of the same change." + "reason": "Same GPT-J output-tracing refactor in the same file; 44066 is the broader earlier version and 44085 is a near-duplicate subset." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "Different backends (RegNet/ResNet bundle vs EfficientNet); same issue family, but not the same concrete fix." + "reason": "ResNet-family vs EfficientNet; same umbrella issue target is not enough to merge these." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths; shared refactor language is not enough." + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen and EfficientNet are separate implementations; no shared concrete bug/change." + "reason": "GPT-J/CodeGen refactor vs EfficientNet refactor; different models." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are unrelated model paths; same umbrella refactor only." + "reason": "MobileNetV2 vs DeBERTa v2; different concrete changes." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen vs MGP-STR; different code paths and different model families." + "reason": "GPT-J/CodeGen and MGP-STR are different model implementations." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen vs MPT; same refactor pattern, but not the same underlying change." + "reason": "GPT-J/CodeGen vs MPT; same refactor style, different code path." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Both target GPT-Neo output tracing in the same file family and appear to be the same refactor split/rebase." + "reason": "Same GPT-Neo output-tracing refactor in the same file; later PR is a near-duplicate." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen vs GPT-Neo; different model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J are related but separate model code paths and separate refactors." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated implementations." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR vs GPT-J/CodeGen; not the same underlying change." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet vs GPT-J; different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo vs ResNet; same theme only at a high level." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet vs MPT; different model code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen; not the same concrete fix." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert; unrelated model implementations." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "MPT vs MGP-STR; different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert; different models." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 vs MGP-STR; unrelated refactors." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J vs MGP-STR; different model code paths." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT vs Flaubert/XLM; same broad refactor theme only." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet vs GPT-J; not mergeable as one PR." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo vs MPT; different concrete changes." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert vs Flaubert/XLM; different model code paths." }, { - "left": "pull_request:44066", - "right": "pull_request:44068", + "left": "pull_request:44059", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are distinct model implementations; not the same fix." + "reason": "GPT-2 vs MPT; different implementations." }, { - "left": "pull_request:44018", - "right": "pull_request:44066", + "left": "pull_request:44056", + "right": "pull_request:44101", "accept": false, - "reason": "GPT-Neo and GPT-J are different code paths; only the general refactor theme overlaps." + "reason": "MPNet vs Flaubert/XLM; same theme, different code paths." }, { - "left": "pull_request:44019", - "right": "pull_request:44722", + "left": "pull_request:43996", + "right": "pull_request:44017", "accept": false, - "reason": "ResNet and GPT-J/CodeGen are unrelated implementations." + "reason": "CVT/FNet vs Segformer; unrelated model changes." }, { - "left": "pull_request:44086", - "right": "pull_request:44722", + "left": "pull_request:43996", + "right": "pull_request:44056", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are different code paths; shared output-tracing language is too broad." + "reason": "CVT/FNet vs MPNet; different code paths." }, { - "left": "pull_request:44019", - "right": "pull_request:44085", + "left": "pull_request:44071", + "right": "pull_request:44076", "accept": false, - "reason": "ResNet and GPT-J are separate model implementations." + "reason": "MPT vs ImageGPT; different model implementations." }, { - "left": "pull_request:44018", - "right": "pull_request:44019", + "left": "pull_request:44074", + "right": "pull_request:44101", "accept": false, - "reason": "GPT-Neo and ResNet are different model families; not the same concrete change." + "reason": "TextNet vs Flaubert/XLM; unrelated concrete changes." }, { - "left": "pull_request:44019", - "right": "pull_request:44071", + "left": "pull_request:44074", + "right": "pull_request:44161", "accept": false, - "reason": "ResNet and MPT are unrelated backends." + "reason": "TextNet vs LongT5; different code paths." }, { - "left": "pull_request:44068", - "right": "pull_request:44722", + "left": "pull_request:44056", + "right": "pull_request:44068", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different implementations, despite similar decorator refactor wording." + "reason": "MPNet vs GPT-Neo; not the same underlying fix." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are different code paths." + "reason": "GPT-Neo vs Flaubert; different model code paths." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen are different model backends." + "reason": "MPT vs GPT-J/CodeGen; unrelated changes." }, { - "left": "pull_request:44018", - "right": "pull_request:44116", + "left": "pull_request:44068", + "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and Flaubert are unrelated implementations." + "reason": "GPT-Neo vs MGP-STR; different code paths." }, { "left": "pull_request:44018", - "right": "pull_request:44086", + "right": "pull_request:44059", "accept": false, - "reason": "GPT-Neo and MGP-STR are separate code paths." + "reason": "GPT-Neo vs GPT-2; same refactor style, different model code paths." }, { "left": "pull_request:44018", - "right": "pull_request:44085", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and GPT-J are different model families." + "reason": "GPT-Neo vs MPT; not mergeable as a single duplicate." }, { - "left": "pull_request:44071", - "right": "pull_request:44085", + "left": "pull_request:44056", + "right": "pull_request:44161", "accept": false, - "reason": "MPT and GPT-J are unrelated code paths." + "reason": "MPNet vs LongT5; different implementations." }, { - "left": "pull_request:44068", - "right": "pull_request:44086", + "left": "pull_request:43997", + "right": "pull_request:44074", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated model implementations." + "reason": "RegNet vs TextNet; unrelated concrete changes." }, { - "left": "pull_request:44059", - "right": "pull_request:44086", + "left": "pull_request:43997", + "right": "pull_request:44161", "accept": false, - "reason": "GPT-2 and MGP-STR are different code paths." + "reason": "RegNet vs LongT5; different model code paths." }, { - "left": "pull_request:44085", - "right": "pull_request:44086", + "left": "pull_request:44010", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-J and MGP-STR are unrelated models." + "reason": "SqueezeBert vs MPT; not the same fix." }, { - "left": "pull_request:44098", - "right": "pull_request:44101", + "left": "pull_request:44074", + "right": "pull_request:44161", "accept": false, - "reason": "ViLT and Flaubert/XLM are different model families." + "reason": "TextNet vs LongT5; different models." }, { - "left": "pull_request:44059", - "right": "pull_request:44722", + "left": "pull_request:44098", + "right": "pull_request:44101", "accept": false, - "reason": "GPT-2 and GPT-J/CodeGen are different implementations." + "reason": "ViLT vs Flaubert/XLM; only broad output-tracing similarity." }, { - "left": "pull_request:44018", - "right": "pull_request:44071", + "left": "pull_request:44073", + "right": "pull_request:44161", "accept": false, - "reason": "GPT-Neo and MPT are unrelated code paths." + "reason": "VisualBert vs LongT5; separate model refactors." }, { - "left": "pull_request:44017", - "right": "pull_request:44722", + "left": "pull_request:44056", + "right": "pull_request:44071", "accept": false, - "reason": "SegFormer and GPT-J/CodeGen are different models; same refactor theme only." + "reason": "MPNet vs MPT; unrelated code paths." }, { - "left": "pull_request:44017", + "left": "pull_request:44018", "right": "pull_request:44161", "accept": false, - "reason": "SegFormer and LongT5 are separate backends." + "reason": "GPT-Neo vs LongT5; different model implementations." }, { - "left": "pull_request:44017", - "right": "pull_request:44073", + "left": "pull_request:43997", + "right": "pull_request:44017", "accept": false, - "reason": "SegFormer and VisualBert are unrelated implementations." + "reason": "RegNet vs Segformer; different model families and code paths." }, { - "left": "pull_request:44068", - "right": "pull_request:44071", + "left": "pull_request:44010", + "right": "pull_request:44018", "accept": false, - "reason": "GPT-Neo and MPT are different code paths." + "reason": "SqueezeBert vs GPT-Neo; different model changes." }, { - "left": "pull_request:44071", - "right": "pull_request:44086", + "left": "pull_request:44017", + "right": "pull_request:44071", "accept": false, - "reason": "MPT and MGP-STR are unrelated model families." + "reason": "Segformer vs MPT; unrelated code paths." }, { - "left": "pull_request:43997", + "left": "pull_request:44017", "right": "pull_request:44073", "accept": false, - "reason": "RegNet and VisualBert are different implementations." + "reason": "Segformer vs VisualBert; not the same underlying fix." }, { - "left": "pull_request:44017", - "right": "pull_request:44071", + "left": "pull_request:44010", + "right": "pull_request:44044", "accept": false, - "reason": "SegFormer and MPT are unrelated code paths." + "reason": "SqueezeBert vs DeBERTa v2; different models and refactors." }, { - "left": "pull_request:44073", - "right": "pull_request:44101", + "left": "pull_request:44044", + "right": "pull_request:44074", "accept": false, - "reason": "VisualBert and Flaubert/XLM are different models." + "reason": "DeBERTa v2 vs TextNet; unrelated concrete changes." }, { - "left": "pull_request:44059", - "right": "pull_request:44071", + "left": "pull_request:44044", + "right": "pull_request:44129", "accept": false, - "reason": "GPT-2 and MPT are separate code paths." + "reason": "DeBERTa v2 vs SpeechT5; same theme only at a very high level." }, { - "left": "pull_request:44056", - "right": "pull_request:44101", + "left": "pull_request:44044", + "right": "pull_request:44154", "accept": false, - "reason": "MPNet and Flaubert/XLM are different model families." + "reason": "DeBERTa v2 vs Vits; different model code paths." }, { - "left": "pull_request:44059", - "right": "pull_request:44068", + "left": "pull_request:44010", + "right": "pull_request:44073", "accept": false, - "reason": "GPT-2 and GPT-Neo are different implementations." + "reason": "SqueezeBert vs VisualBert; unrelated changes." }, { - "left": "pull_request:44073", + "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "VisualBert and LongT5 are unrelated backends." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44059", - "accept": false, - "reason": "GPT-Neo and GPT-2 are different code paths." + "reason": "Segformer vs LongT5; different implementations." }, { - "left": "pull_request:44101", - "right": "pull_request:44161", + "left": "pull_request:44073", + "right": "pull_request:44101", "accept": false, - "reason": "Flaubert/XLM and LongT5 are different model families." + "reason": "VisualBert vs Flaubert/XLM; different models." }, { "left": "pull_request:43997", - "right": "pull_request:44017", + "right": "pull_request:44056", "accept": false, - "reason": "RegNet and SegFormer are separate model implementations." + "reason": "RegNet vs MPNet; unrelated model code paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44056", + "left": "pull_request:44059", + "right": "pull_request:44068", "accept": false, - "reason": "RegNet and MPNet are different code paths." + "reason": "GPT-2 vs GPT-Neo; separate model refactors." }, { - "left": "pull_request:44071", - "right": "pull_request:44076", + "left": "pull_request:44059", + "right": "pull_request:44161", "accept": false, - "reason": "MPT and ImageGPT are unrelated model families." + "reason": "GPT-2 vs LongT5; unrelated fixes." }, { - "left": "pull_request:44074", + "left": "pull_request:44019", "right": "pull_request:44101", "accept": false, - "reason": "TextNet and Flaubert/XLM are different implementations." + "reason": "ResNet vs Flaubert/XLM; different concrete changes." }, { "left": "pull_request:44056", - "right": "pull_request:44161", + "right": "pull_request:44086", "accept": false, - "reason": "MPNet and LongT5 are unrelated code paths." + "reason": "MPNet vs MGP-STR; different model code paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44018", + "left": "pull_request:44071", + "right": "pull_request:44129", "accept": false, - "reason": "RegNet and GPT-Neo are different model families." + "reason": "MPT vs SpeechT5; unrelated changes." }, { - "left": "pull_request:43997", - "right": "pull_request:44161", + "left": "pull_request:44010", + "right": "pull_request:44086", "accept": false, - "reason": "RegNet and LongT5 are unrelated implementations." + "reason": "SqueezeBert vs MGP-STR; different implementations." }, { "left": "pull_request:44074", - "right": "pull_request:44161", + "right": "pull_request:44154", "accept": false, - "reason": "TextNet and LongT5 are different code paths." + "reason": "TextNet vs Vits; different model code paths." }, { - "left": "pull_request:44018", - "right": "pull_request:44161", + "left": "pull_request:44017", + "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo and LongT5 are unrelated model families." + "reason": "Segformer vs GPT-J/CodeGen; same tracking issue only." }, { - "left": "pull_request:43997", - "right": "pull_request:44071", + "left": "pull_request:44066", + "right": "pull_request:44086", "accept": false, - "reason": "RegNet and MPT are different backends." + "reason": "GPT-J/CodeGen vs MGP-STR; not the same concrete fix." }, { - "left": "pull_request:44010", + "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBert and MPT are unrelated models." + "reason": "GPT-J/CodeGen vs MPT; different model implementations." }, { "left": "pull_request:44018", "right": "pull_request:44129", "accept": false, - "reason": "GPT-Neo and SpeechT5 are separate code paths." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44073", - "accept": false, - "reason": "SqueezeBert and VisualBert are different model families." + "reason": "GPT-Neo vs SpeechT5; unrelated code paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44074", - "accept": false, - "reason": "RegNet and TextNet are unrelated implementations." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44129", + "left": "pull_request:44073", + "right": "pull_request:44154", "accept": false, - "reason": "RegNet and SpeechT5 are different code paths." + "reason": "VisualBert vs Vits; different model refactors." }, { - "left": "pull_request:44071", - "right": "pull_request:44129", + "left": "pull_request:44059", + "right": "pull_request:44086", "accept": false, - "reason": "MPT and SpeechT5 are unrelated model families." + "reason": "GPT-2 vs MGP-STR; separate model changes." }, { - "left": "pull_request:44010", - "right": "pull_request:44018", + "left": "pull_request:44074", + "right": "pull_request:44101", "accept": false, - "reason": "SqueezeBert and GPT-Neo are different implementations." + "reason": "TextNet vs Flaubert/XLM; unrelated models." }, { - "left": "pull_request:43996", - "right": "pull_request:44161", + "left": "pull_request:44059", + "right": "pull_request:44071", "accept": false, - "reason": "FNet/CVT and LongT5 are unrelated code paths." + "reason": "GPT-2 vs MPT; different code paths." }, { - "left": "pull_request:43996", - "right": "pull_request:44017", + "left": "pull_request:44018", + "right": "pull_request:44086", "accept": false, - "reason": "FNet/CVT and SegFormer are different model families." + "reason": "GPT-Neo vs MGP-STR; not the same fix." }, { - "left": "pull_request:44010", - "right": "pull_request:44044", + "left": "pull_request:44044", + "right": "pull_request:44154", "accept": false, - "reason": "SqueezeBert and DeBERTa v2 are separate implementations." + "reason": "DeBERTa v2 vs Vits; different model code paths." }, { "left": "pull_request:44044", - "right": "pull_request:44074", + "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa v2 and TextNet are unrelated code paths." + "reason": "DeBERTa v2 vs SpeechT5; unrelated concrete changes." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Both are the same GPT-J/CodeGen output-tracing refactor and would plausibly collapse into one PR." + "reason": "Same GPT-J/CodeGen output-tracing refactor; 44722 is a later near-duplicate/superset of the same code-path change." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both center on the same GPT-J output-tracing change; 44722 looks like a duplicate or superseding split." + "reason": "Both target the GPT-J output-tracing refactor on the same file; 44722 subsumes the same concrete change." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are unrelated model implementations." - }, - { - "left": "pull_request:43996", - "right": "pull_request:44007", - "accept": false, - "reason": "FNet/CVT and RegNet/ResNet/RT-DETR are different code paths; same umbrella refactor is not enough." + "reason": "GPT-J vs SpeechT5; different model code paths." }, { "left": "pull_request:43996", "right": "pull_request:44129", "accept": false, - "reason": "FNet/CVT and SpeechT5 are unrelated models." + "reason": "CVT/FNet vs SpeechT5; not the same fix." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa v2 and SpeechT5 are different backends." + "reason": "DeBERTa v2 vs SpeechT5; unrelated model implementations." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa v2 and VITS are unrelated implementations." + "reason": "DeBERTa v2 vs Vits; different code paths." } ] }, "evaluator_result": { "accept": true, - "feedback": "The cluster summary is grounded in the packet: #43979 is the shared umbrella issue, and the selected PRs are all consistent with the same output-tracing refactor family. The soft-edge calls are conservative overall, especially in rejecting cross-model pairs. The accepted pairs (GPT-J/CodeGen, GPT-Neo) do look mergeable as single same-bugfix PRs based on overlapping files and issue linkage." + "feedback": "The summary is grounded in the packet: it correctly treats this as a set of model-specific output-tracing refactors rather than one uniform bugfix, and the few accepted pairs are limited to the same concrete code paths (GPT-J/CodeGen and GPT-Neo). The duplicate/near-duplicate claims stay conservative, and the representative PR choice is supported by the shared issue links and filename overlap." }, "evaluator_used": true, "retried": false, @@ -18425,8 +18393,8 @@ "review_unit_count": 2, "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-43996-28", "nodes": [ @@ -18447,20 +18415,20 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "51ff27ad0cd8c7de8c50c2ca74ab79184e31060d02e6648fc60b66aa0f2d6b00", + "prepared_review_unit_hash": "ca166b957b69b7f2c10e6e12d04f5e9d1278d7a4a0b9d9dc0987ea8c509384c3", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84899, - "estimated_input_tokens": 21225, - "estimated_eval_tokens": 42706 + "serialized_chars": 84895, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17124, + "serialized_chars": 17122, "estimated_input_tokens": 4281, "estimated_eval_tokens": 8818 }, @@ -18469,48 +18437,48 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs are all part of a broader standardized output-tracing migration across different models, but they are not duplicates of one another. Each PR targets a separate model implementation and would not plausibly be merged into a single code-path fix/change.", - "confidence": 0.91, + "summary": "These PRs are all model-specific migrations to standardized output capture/tracing APIs, but they touch different architectures and code paths. They are related by refactor style, not true duplicates, so the soft edges should be rejected.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44073 is the clearest representative of the cluster: it directly refactors one model to use the standardized output-capture pattern and has a clean, explicit title/diff.", + "canonical_pr_reason": "No single duplicate PR exists here; if one representative is needed, 44129 is the strongest anchor because it ties the refactor to an explicit issue target and a concrete SpeechT5 output-capture change.", "best_issue_reason": null, - "best_pr_reason": "PR #44073 is the best single representative because it is a straightforward, model-specific instance of the output-tracing migration and is more clearly described than several of the others.", + "best_pr_reason": "44129 is the best representative of the cluster because it is explicitly scoped to one model, references an issue, and shows the standardized output-capture migration clearly without being overly broad.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Same broad migration theme, but FocalNet and ImageGPT are different model code paths; these are separate model-specific refactors, not one duplicate change." + "reason": "Both are output-capture refactors, but they affect different models (FocalNet vs ImageGPT) and different hook wiring. Same migration theme, not the same underlying change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Both standardize output tracing, but VisualBert and TextNet are distinct implementations with separate forwards and tests; not the same underlying fix." + "reason": "VisualBert and TextNet are separate model implementations with distinct forward paths; this is a shared refactor pattern, not one mergeable duplicate PR." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "MPNet vs VisualBert are unrelated model paths; similarity is only at the framework-refactor level, so they should not be merged as duplicates." + "reason": "MPNet and VisualBert each update their own model-specific output tracing logic. They are not fixing the same concrete bug or code path." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "These are separate model migrations with different affected classes and forward logic; not one concrete bug/change." + "reason": "These are separate per-model standardized-output refactors in different files and architectures, so they should not be treated as duplicates." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are different architectures and modules; same refactor pattern, but not the same code-path problem." + "reason": "RegNet and SqueezeBert are unrelated model code paths; the shared wording around standardized outputs is too broad to merge as one PR." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 touch different model internals and output contracts; this is a shared migration style, not a duplicate fix." + "reason": "SqueezeBert and SpeechT5 both mention output tracing, but they change different modules and mechanisms. They are not the same underlying bug/change." } ] }, @@ -18529,8 +18497,8 @@ "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-43998-13", "nodes": [ @@ -18590,274 +18558,268 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "89410d97d80124899d4e226b9e71e64da499254d08cbdb67441ce994042575a4", + "prepared_review_unit_hash": "c0c449d51ddb5cc027f0511b4b96d91f7fd186dec97325fcc2d2e237b35ec7a3", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40170, - "estimated_input_tokens": 10043, - "estimated_eval_tokens": 20342 + "serialized_chars": 40161, + "estimated_input_tokens": 10041, + "estimated_eval_tokens": 20338 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40170, - "estimated_input_tokens": 10043, - "estimated_eval_tokens": 20342 + "serialized_chars": 40161, + "estimated_input_tokens": 10041, + "estimated_eval_tokens": 20338 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This is a batch of similar output-tracing refactors across many different model implementations. They share the same refactor theme, but they are not duplicate PRs because each changes a distinct code path and model file(s).", - "confidence": 0.97, + "summary": "A broad similarity cluster of model-specific output-tracing refactors. The PRs share a naming/template pattern, but they touch different architectures and code paths, so none look like true duplicates.", + "confidence": 0.86, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44025 is a good representative because it covers the same refactor pattern in two closely related depth-anything files, making it more central than the single-file PRs.", + "canonical_pr_reason": "No single canonical PR: these are separate model-specific output-tracing refactors, not duplicates.", "best_issue_reason": null, - "best_pr_reason": "PR 44025 is the clearest exemplar of the cluster\u2019s recurring can_return_tuple/output-tracing change, but it still is not a duplicate of the others.", + "best_pr_reason": "PR #44025 is the strongest representative of the pattern because it updates two closely related depth-anything files and clearly applies the can_return_tuple refactor, but it still is not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model implementations and files; same refactor theme, but not the same underlying bug/change." + "reason": "Different model families and files (timm_backbone vs upernet); only the refactor style matches." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Separate model code paths; these are parallel refactors, not one mergeable fix." + "reason": "Different code paths in unrelated architectures (timm_backbone vs vision_text_dual_encoder)." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different model families and forward paths; not the same concrete change." + "reason": "timm_backbone and univnet are unrelated implementations; same output-tracing theme only." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Unrelated model implementations; similarity is only at the refactor pattern level." + "reason": "Distinct model stacks (timm_backbone vs mamba/falcon_mamba); not the same bug or change." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Distinct models and files; not one underlying bug or patch." + "reason": "timm_backbone and rwkv are different code paths; similarity is only in refactor pattern." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "Different model classes and output-capturing code paths." + "reason": "mobilenet_v1 and univnet are unrelated model implementations." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Same refactor motif, but separate model-specific changes." + "reason": "Different architectures and filenames; no shared concrete fix." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Different model families; these could not plausibly be one PR for a single code-path fix." + "reason": "mobilenet_v1 vs depth_anything are separate model families, not one duplicate change." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Separate encoder/decoder-related code paths; not duplicate fixes." + "reason": "Different wrapper/model code paths (mobilenet_v1 vs vision_encoder_decoder)." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "Different model wrappers and files; only broadly similar refactoring." + "reason": "mobilenet_v1 and speech_encoder_decoder are unrelated; only the refactor template overlaps." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Different model architectures; same pattern but not the same bug/change." + "reason": "vision_text_dual_encoder and univnet fix different modules and behaviors." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Distinct model-specific forward logic, so not duplicate PRs." + "reason": "Different model code paths (vision_text_dual_encoder vs upernet)." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "No shared concrete code path; just the same output-tracing cleanup pattern." + "reason": "vision_text_dual_encoder is not the same subsystem as mamba/falcon_mamba." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "vision_text_dual_encoder and codegen are separate model families; no shared concrete bug." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different model families and target files; not one mergeable fix." + "reason": "Different architectures and files; same output-tracing refactor only." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "Separate model implementations; not the same underlying issue." + "reason": "univnet and upernet are unrelated models with different forward paths." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different code paths and model internals; not duplicates." + "reason": "univnet is separate from the mamba/falcon_mamba code path." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "These are parallel refactors in different models, not one concrete fix." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44029", - "accept": false, - "reason": "Different models and call paths; similarity is too broad to merge." + "reason": "univnet vs depth_anything: different model families, not one mergeable fix." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Model-specific refactors only; not the same bug or change." + "reason": "upernet and mamba/falcon_mamba are unrelated subsystems." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Falcon/Mamba code differs from SuperPoint; not the same underlying fix." + "reason": "mamba/falcon_mamba and superpoint are different model implementations." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Different subsystems and forward implementations; not mergeable as one PR." + "reason": "mamba/falcon_mamba and codegen do not share the same concrete code path." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen are unrelated code paths despite similar refactor wording." + "reason": "timm_backbone and codegen are unrelated; only the refactor motif overlaps." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "Different model families and implementation details; not duplicate changes." + "reason": "univnet and codegen touch different model stacks and behaviors." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "These touch different model code paths and should stay separate." - }, - { - "left": "pull_request:44000", - "right": "pull_request:44004", - "accept": false, - "reason": "Only the refactor pattern matches; the underlying model changes do not." + "reason": "upernet vs codegen is a broad theme match only, not a duplicate fix." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Depth Anything and Vision Encoder-Decoder are distinct model paths; not one concrete bug." + "reason": "depth_anything and vision_encoder_decoder are separate code paths; same tracing refactor pattern only." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Different encoder/decoder wrapper implementations, so not duplicates." + "reason": "depth_anything and speech_encoder_decoder are unrelated models." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Separate model code paths; similarity is only at the refactor level." + "reason": "depth_anything vs superpoint: different architectures and files." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different model architectures and files; not the same fix." + "reason": "depth_anything and rwkv are separate model families." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Distinct models and output semantics; not one PR-worthy duplicate." + "reason": "depth_anything and DPR do not appear to address the same underlying change." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "Vision Encoder-Decoder and Speech Encoder-Decoder are separate implementations; not the same change." + "reason": "vision_encoder_decoder and speech_encoder_decoder are different wrapper models with distinct code paths." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "Different model code paths and refactor targets." + "reason": "vision_encoder_decoder vs superpoint is not the same bug or refactor target." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "Unrelated model internals; only the output-tracing motif overlaps." + "reason": "vision_encoder_decoder and rwkv are unrelated implementations." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Different models and fixes; not duplicate PRs." + "reason": "vision_encoder_decoder and DPR fix different model paths; no duplicate evidence." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech Encoder-Decoder and SuperPoint are unrelated code paths." + "reason": "speech_encoder_decoder and superpoint are different models with no shared concrete code path." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different model families; not one underlying bug or patch." + "reason": "speech_encoder_decoder vs rwkv is only superficially similar." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Separate implementation targets, so they should not be merged as duplicates." + "reason": "speech_encoder_decoder and DPR are unrelated model wrappers." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated model code paths." + "reason": "superpoint and rwkv are different architectures; not mergeable as one PR." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Distinct architectures and fixes; not the same underlying change." + "reason": "superpoint and DPR touch different subsystems and fixes." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR touch different model paths; no duplicate bug/change evidence." + "reason": "rwkv and DPR are separate model families; shared theme is too broad." } ] }, @@ -18876,8 +18838,8 @@ "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-44662-3", "nodes": [ @@ -18890,52 +18852,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "5764fe0ecb80aa5a0dc923f844fa4d58ac3b813f493c0e8ae10c6b4614fefb44", + "prepared_review_unit_hash": "5798c6c949682eb10ebd90b6c158b13566ffebd924fb8b31088291dea8e3c449", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10914, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10911, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10914, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10911, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition PRs for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share only standard Transformers boilerplate and auto-registration/docs patterns, not the same underlying bug or change.", - "confidence": 0.98, + "summary": "These are three separate model-implementation PRs, not duplicates. Their overlap is limited to shared Transformers boilerplate such as docs, auto-mapping, and registry updates.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45075 is the most complete and mature representative of the cluster: it has the largest implementation surface, dedicated conversion/modeling/processing files, tests, and the most review activity.", + "canonical_pr_reason": "No canonical PR: PenguinVL, DeepSeek-OCR-2, and Voxtral TTS are different model families with different codepaths and assets; the shared files are generic integration boilerplate.", "best_issue_reason": null, - "best_pr_reason": "PR 45075 is the best single representative because it appears the most fully developed and validated of the three model integration PRs.", + "best_pr_reason": "No single PR is a better representative of the others because each adds a distinct model implementation rather than the same change.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model integrations (PenguinVL vs Voxtral TTS) with different model code and tests; overlap is only shared Transformers scaffolding and docs registration." + "reason": "PenguinVL and Voxtral TTS are unrelated model additions; they only share registry/docs scaffolding, not the same fix or code path." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different model additions (PenguinVL vs DeepSeek-OCR-2); shared filenames are generic auto/docs files, not evidence of the same code-path fix." + "reason": "PenguinVL and DeepSeek-OCR-2 are different models with different implementation files and targets; overlap is just boilerplate integration work." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are unrelated model implementations with distinct functionality and files; common changes are broad integration boilerplate only." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model adds, not the same underlying bug/change, despite similar auto-registration edits." } ] }, @@ -18954,8 +18916,8 @@ "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-44979-2", "nodes": [ @@ -18965,7 +18927,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "357374bc38f95c8d4cd41d965fa7dc96e22c19f58f10072449b1bb351ca201d8", + "prepared_review_unit_hash": "13f8ce690cf9d377542f6eecdb0176d09666983a2b42fec4d16093d04d38ae20", "component_budget": { "node_count": 2, "item_count": 2, @@ -18987,18 +18949,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related fusion efforts, but they are not the same change: one adds a generic Module Fusion API, while the other wires a specific n-to-1 kernel fusion path through KernelConfig and model loading. The overlap is architectural, not duplicate-level.", - "confidence": 0.9, + "summary": "These are related only at a high level (both mention fusion), but they target different abstractions and code paths: one introduces a generic module-fusion API, the other adds KernelConfig-based n-to-1 kernel fusion integration. They should not be deduplicated.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44979 is the cleaner canonical representative of the cluster because it introduces the underlying Module Fusion API, which is the more general and foundational change.", + "canonical_pr_reason": "PR #45363 is the broader, more concrete implementation: it wires fusion into model loading and runtime behavior via KernelConfig and integration changes, with an example demonstrating end-to-end use.", "best_issue_reason": null, - "best_pr_reason": "PR 45363 is the most concrete end-user-facing implementation in the cluster: it applies fusion through KernelConfig, touches runtime integration, and includes an example demonstrating the feature.", + "best_pr_reason": "PR #45363 is the better representative of the cluster because it has the clearer user-facing change and more specific implementation surface; PR #44979 is a separate generic API proposal rather than the same change.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "They share the broad fusion theme, but they are not the same underlying bug/change. 44979 adds the generic fusion API; 45363 adds a specific KernelConfig-based n-to-1 fusion implementation and integration work. They would not plausibly be merged as one PR." + "reason": "Both involve fusion, but #44979 adds a generic module-fusion API layer while #45363 implements KernelConfig-driven kernel fusion for models. They do not appear to fix the same concrete problem or be mergeable into one PR without mixing distinct features." } ] }, @@ -19017,8 +18979,8 @@ "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-45086-2", "nodes": [ @@ -19028,7 +18990,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "6fe0cea44a93f2a2d4196647e9de5229ffb33077db5f780703cbb9447ab62d22", + "prepared_review_unit_hash": "e0c0c0c4ef2e6f8fc425e62610c9d954c10b0533509edc59aa4d7cf360a66a33", "component_budget": { "node_count": 2, "item_count": 2, @@ -19050,18 +19012,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests address the same AttributeError in `_patch_mistral_regex` on the same code path, with essentially the same fix in `src/transformers/tokenization_utils_tokenizers.py`. PR 45317 is the stronger candidate because it includes tests and slightly more discussion, while 45086 is a smaller earlier version of the same change.", - "confidence": 0.97, + "summary": "Both PRs address the same Mistral regex AttributeError in the same code path; PR 45317 is the more complete variant because it includes the fix plus tests.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the more complete implementation of the same fix: it contains the same code-path correction plus test coverage and appears to supersede the smaller earlier PR.", + "canonical_pr_reason": "PR 45317 is the better canonical PR because it fixes the same bug as 45086 but also adds test coverage, making it the more complete change set.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 best represents the cluster because it directly fixes the reported AttributeError and adds tests, making it the best standalone candidate for merge.", + "best_pr_reason": "PR 45317 is the best overall representative: same underlying AttributeError fix, same target file/issue, and it includes accompanying tests.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying bug and same code change in the same file; the later PR looks like a fuller version of the earlier one and they could plausibly be merged into one PR." + "reason": "Same underlying AttributeError in _patch_mistral_regex, same file and issue target, and the changes are directly compatible as one merged fix." } ] }, @@ -19080,8 +19042,8 @@ "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-45115-2", "nodes": [ @@ -19091,7 +19053,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "adabfa90ac93eddfe5d3f363a57c21ac722bf3bff6131848dce95c2cffe3240d", + "prepared_review_unit_hash": "1710a959541fbc879a60bda82a6e51c2cdcc00e33cccb3134594347c93fae2ec", "component_budget": { "node_count": 2, "item_count": 2, @@ -19113,18 +19075,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related NemotronH refactors, but they are not the same underlying PR: one focuses on inheritance/conversion mapping, while the other introduces separate NemotronHDense/NemotronHSparse model/docs/test plumbing.", - "confidence": 0.92, + "summary": "The two PRs are related to NemotronH, but they are not duplicates: one is a narrow conversion-mapping refactor, while the other is a much broader split/cleanup that introduces NemotronH Dense and Sparse model families. They do not appear to fix the same concrete code-path problem.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45569 is the broader, more complete change: it adds the new dense/sparse model split, docs, auto-mappings, and tests, making it the better representative of the NemotronH redesign work.", + "canonical_pr_reason": "PR 45569 is the better canonical PR because it is the larger, more complete architectural change: it introduces the Dense/Sparse model split, updates auto mappings/docs/tests, and rewires the NemotronH packaging. PR 45115 is a narrower conversion-mapping follow-up.", "best_issue_reason": null, - "best_pr_reason": "PR 45569 is the best global PR candidate because it covers the user-visible architecture update and associated documentation/testing, rather than just internal refactor/conversion mapping.", + "best_pr_reason": "PR 45569 is the best overall representative of the cluster because it covers the main refactor rather than just a supporting conversion-mapping update.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Both are about NemotronH, but 45115 is mainly inheritance/conversion-mapping refactoring while 45569 adds the dense/sparse model split, docs, and tests. They do not appear to fix the same concrete code-path problem and would not plausibly be merged as one PR." + "reason": "Both touch NemotronH, but 45115 is limited to checkpoint conversion key renames while 45569 is a broader model-architecture and docs/test refactor. They are not the same underlying change and would not plausibly merge into one PR without conflating distinct work." } ] }, @@ -19143,8 +19105,8 @@ "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-45332-2", "nodes": [ @@ -19154,7 +19116,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "7eee8f017657e54293637933ee0140e6eb46b8652c75a795dd583ba2f346b7b8", + "prepared_review_unit_hash": "0a8b80624263d0f1dfbffb04fab0be63e0e857b9a93c8d866a92900d6cee3bf6", "component_budget": { "node_count": 2, "item_count": 2, @@ -19176,18 +19138,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are related through the new heterogeneity framework, but they are not duplicates: one adds per-layer config support, the other adds broader heterogeneous modeling/cache support that builds on it.", - "confidence": 0.84, + "summary": "These are related but distinct PRs: one introduces heterogeneous per-layer config support, while the other adds broader heterogeneous modeling/cache/masking changes. They share foundation code, but they do not look like the same underlying change and should not be merged as duplicates.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the broader umbrella change: it adds heterogeneous model support across cache/modeling/masking and also wires in per-layer config handling. PR #45333 is a narrower config-only foundation.", + "canonical_pr_reason": "PR #45332 is the broader, more representative change: it covers the actual heterogeneous model support path and includes the config work plus downstream modeling/cache updates.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the best representative of the cluster because it covers the larger end-user feature and incorporates the related config plumbing, while #45333 is just the prerequisite configuration layer.", + "best_pr_reason": "PR #45332 is the best single PR for the cluster because it subsumes the config-only groundwork and reflects the larger end-to-end feature work.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Reject: these share the heterogeneity infrastructure, but they address different layers of the feature. #45333 adds per-layer configuration APIs/serialization; #45332 adds modeling/cache changes for heterogeneous models. They do not fix the same concrete bug and would not plausibly be merged as one duplicate PR." + "reason": "Related feature area, but not the same concrete code-path change. #45333 is config-only per-layer support; #45332 is a wider modeling/cache implementation that could not be safely collapsed into the same PR." } ] }, @@ -19206,8 +19168,8 @@ "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-45415-2", "nodes": [ @@ -19217,12 +19179,12 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "041cb13d77e0902f98f4b782556d7a6670842a1a2a536689b5400a7e97dc0d45", + "prepared_review_unit_hash": "20e61d369bc72585296ed200cb92af4e444de2d68a8291adddcbcbafe644340d", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5513, + "serialized_chars": 5514, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -19230,7 +19192,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5513, + "serialized_chars": 5514, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -19239,18 +19201,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are both type-checking related, but they are not the same change: #45415 is a broad pyright/type-ignore sweep across many transformers modules, while #45425 adds new typing protocols/helpers and specific modeling_utils/PEFT-related refinements.", + "summary": "These two PRs are both typing-related, but they are not the same change: one is a broad type-checking sweep across many files, while the other adds specific typing protocols/helpers around modeling_utils and PEFT integration. I would not merge them as duplicates.", "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical duplicate PR: the scopes differ materially, with #45415 doing a wide repo-level typing cleanup and #45425 introducing targeted typing abstractions plus specific integration fixes.", + "canonical_pr_reason": "PR 45425 is the more focused, self-contained typing update; PR 45415 is a broad repository-wide type-checking sweep.", "best_issue_reason": null, - "best_pr_reason": "#45425 is the more focused representative of the cluster because it adds concrete typing infrastructure and code-path-specific adjustments, whereas #45415 is mostly a broad mechanical typing pass.", + "best_pr_reason": "PR 45425 has a tighter scope and a clearer concrete change than the sweeping type-checking pass in 45415.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Do not treat as duplicates: they share typing-related files, but #45415 is a broad type-checking cleanup and config change, while #45425 introduces new typing protocols and targeted modeling_utils/PEFT support. They are not the same underlying fix and would not plausibly merge into one PR." + "reason": "Both are typing-oriented, but they address different underlying work: 45415 broadly enables type checking across many files, while 45425 adds specific typing protocols/helpers for modeling_utils/PEFT. They do not fix the same concrete code-path and are not safely mergeable as one PR." } ] }, @@ -19269,8 +19231,8 @@ "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-45487-6", "nodes": [ @@ -19289,12 +19251,12 @@ "pull_request:45858|pull_request:45926", "pull_request:45890|pull_request:45926" ], - "prepared_review_unit_hash": "33eea6df34abf1368e7374ae60ff396f7869644ad13fa8e4a602a94f15bab514", + "prepared_review_unit_hash": "cc07df82d9c420fc26e1ea3d022baf33f2cb12f0c1dba903a851deeb3d048ab9", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 6, - "serialized_chars": 14719, + "serialized_chars": 14720, "estimated_input_tokens": 3680, "estimated_eval_tokens": 7616 }, @@ -19302,7 +19264,7 @@ "node_count": 6, "item_count": 6, "soft_pair_count": 6, - "serialized_chars": 14719, + "serialized_chars": 14720, "estimated_input_tokens": 3680, "estimated_eval_tokens": 7616 }, @@ -19311,48 +19273,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster mixes two unrelated themes: model-parallel device-placement fixes for specific models and XPU expectation-only test updates. None of the PRs appear to be the same concrete change, so the soft duplicates should be rejected.", - "confidence": 0.89, + "summary": "These PRs are loosely related by model-parallel/XPU themes, but they are not duplicates: they target different models and different code paths, and several are just test expectation updates. The only substantive code fix in the set is the Gemma4 parallel bug fix; the rest are model-specific and should stay separate.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45487 is the clearest code-fix PR: it addresses a concrete model-parallel device-placement bug in the model forward path and includes targeted model/test changes, making it the best representative of the fix-oriented subset.", + "canonical_pr_reason": "PR #45817 is the strongest standalone change: it fixes a concrete model-parallel device-placement bug in Gemma4 code, rather than only adjusting expectations. It is the best representative if one PR must be chosen, though the cluster is not a true duplicate set.", "best_issue_reason": null, - "best_pr_reason": "PR 45487 is the strongest standalone candidate because it fixes an actual runtime bug in model code rather than only updating expectations, and its title/body clearly describe the affected behavior.", + "best_pr_reason": "PR #45817 is the best candidate for global relevance because it addresses an actual runtime bug in a production code path and has the broadest substantive fix among the candidates. The others are narrower, model-specific, or test-only updates.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:45843", "accept": false, - "reason": "Both are model-parallel fixes, but for different models and different code paths. They share a theme, not the same underlying bug, so they should not be merged as duplicates." + "reason": "Different models and different bug surfaces: AltCLIP/ChineseCLIP device placement vs Deimv2 model-parallel cleanup. Same general theme, but not the same underlying fix." }, { "left": "pull_request:45487", "right": "pull_request:45926", "accept": false, - "reason": "45487 fixes model-parallel device placement in model code; 45926 only adds XPU test expectations for a different model. Different artifacts and different underlying changes." + "reason": "AltCLIP/ChineseCLIP parallel bug fix vs HyperCLOvax XPU test expectations. These are unrelated model-specific changes." }, { "left": "pull_request:45817", "right": "pull_request:45843", "accept": false, - "reason": "These target different model families (Gemma4 vs Deimv2) with model-specific parallel fixes. The similarity is too broad to treat as the same bug." + "reason": "Both are model-parallel related, but they fix different models and different code paths: Gemma4 vs Deimv2." }, { "left": "pull_request:45858", "right": "pull_request:45890", "accept": false, - "reason": "Both are test expectation updates, but for different models and different numeric baselines. They do not fix the same code-path problem." + "reason": "Both are XPU expectation updates, but for different models and tests. Test-only expectation changes for separate models are not duplicates." }, { "left": "pull_request:45858", "right": "pull_request:45926", "accept": false, - "reason": "Both add XPU expectations, but for unrelated models. This is a shared testing pattern, not a duplicate change." + "reason": "Hy_v3 XPU expectations and HyperCLOvax XPU expectations are separate model test updates, not one underlying bug or change." }, { "left": "pull_request:45890", "right": "pull_request:45926", "accept": false, - "reason": "These are separate expectation-only test updates for different models, with no indication they resolve the same underlying issue." + "reason": "Different models and different expected outputs; these are independent CI/test expectation tweaks, not duplicates." } ] }, @@ -19371,8 +19333,8 @@ "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-45548-2", "nodes": [ @@ -19382,7 +19344,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "5acf4919cd5982b1534ce5cf93b60e47e7a40aee062be335cd38b94fe13a2ebc", + "prepared_review_unit_hash": "f146f2afe94c6ded07abb0734397157881e94dbdbbeda33768f3be961573c4a2", "component_budget": { "node_count": 2, "item_count": 2, @@ -19404,18 +19366,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are about expert parallelism and share `modeling_utils.py`, but they target different failure modes and code paths: one fixes config serialization/`has_ep` for ZeRO-3 loading, the other fixes expert parameters being overwritten during FSDP2 loading. They are related, not duplicates.", - "confidence": 0.93, + "summary": "Both PRs concern expert parallelism loading, but they fix different code paths: one is about serializing `distributed_config` and exposing `has_ep` for accelerate/ZeRO-3 loading, while the other prevents expert parameters from being overwritten during FSDP2/rank-0 broadcast. They are related, but not duplicates.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45662 is the better representative of the cluster because it addresses a concrete EP loading corruption bug in the parameter assignment path and touches the broader loading pipeline that actually causes the overwrite.", + "canonical_pr_reason": "PR #45662 is the better canonical representative because it targets a concrete loading corruption bug in the parameter assignment path and its fix is tightly scoped to the overwrite mechanism.", "best_issue_reason": null, - "best_pr_reason": "PR #45662 is the strongest standalone candidate: it has the clearest concrete symptom, the most targeted fix, and the broader scope within the EP/FSDP2 loading flow.", + "best_pr_reason": "PR #45662 is the strongest standalone PR in the cluster: it addresses a specific, well-defined failure mode with direct code-path changes across loading and MoE integration.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Both involve expert parallelism, but #45548 fixes `distributed_config` serialization and `has_ep` for accelerate/ZeRO-3 loading, while #45662 fixes expert tensors being overwritten by rank-0 broadcast during FSDP2 loading. Different bugs, different code paths." + "reason": "They share the broad EP/loading theme, but fix different underlying bugs: #45548 adds `distributed_config` serialization and `has_ep` for accelerate launch + ZeRO-3, while #45662 fixes expert tensors being overwritten by rank-0 broadcast in FSDP2. Not the same change." } ] }, @@ -19434,8 +19396,8 @@ "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-45639-2", "nodes": [ @@ -19445,7 +19407,7 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "8829ecaae4fa7bec17035e4ec1d79d8e814307cf8c8f10a14bff0a6e80b5d674", + "prepared_review_unit_hash": "a47ec3f2f9b39738fa2f8a145c7e328dc9e2780094e79e916cf0944a0f967d95", "component_budget": { "node_count": 2, "item_count": 2, @@ -19467,18 +19429,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same underlying captured_info/xdist collision problem on issue #45561; PR #45645 subsumes #45639 by including the same testing_utils fix plus CI artifact handling updates.", - "confidence": 0.94, + "summary": "Both PRs target the same xdist-safe captured_info problem in testing_utils; 45645 looks like a broader follow-up that subsumes the core fix from 45639 and adds CI artifact handling.", + "confidence": 0.82, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45645 is the better canonical PR because it contains the xdist-safe captured_info file fix from #45639 and extends it with the workflow changes needed to read multiple captured_info artifacts in CI.", + "canonical_pr_reason": "PR 45645 is the better canonical representative because it includes the core testing_utils xdist-safe change plus the surrounding CI/log-capture updates and tests.", "best_issue_reason": null, - "best_pr_reason": "PR #45645 is the most complete representation of the fix and its operational follow-through, while #45639 is a narrower subset of the same code-path change.", + "best_pr_reason": "PR 45645 best represents the cluster since it addresses the same captured_info collision issue more completely than the narrower 45639 fix.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same concrete captured_info xdist-collision bug; #45645 builds on the exact testing_utils change from #45639 and adds compatible CI log aggregation, so these could plausibly be merged together." + "reason": "Both PRs fix the same captured_info xdist collision path; 45645 expands the same fix with CI artifact handling, so they belong to the same cluster." } ] }, @@ -19626,8 +19588,8 @@ "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-45975-2", "nodes": [ @@ -19637,7 +19599,7 @@ "soft_pairs": [ "pull_request:45975|pull_request:45977" ], - "prepared_review_unit_hash": "2bd58020a5e46afd6cd75d1f798ef4763c861d160372c87600eade563cdf846e", + "prepared_review_unit_hash": "e593e013e862586428bc362889057b3a199d1c12a63db05dfafd2d013d8f1c6d", "component_budget": { "node_count": 2, "item_count": 2, @@ -19659,18 +19621,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs in the same GGUF/Apple Silicon area, but they implement different layers of the stack: one adds a CLI/integration path for an optional kernels-community Metal fast path, the other adds a new GGUF linear/matmul implementation and related quantizer/modeling changes. Related, but not the same fix/change.", - "confidence": 0.92, + "summary": "Two open PRs share a GGUF/Apple Silicon/kernels-community theme, but they implement different features on different code paths: one adds an optional serving-side Metal dequant fast path, the other adds a new GGUF linear-matmul integration with tests. They are related, but not duplicates.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45977 is the more central, self-contained implementation of the GGUF-on-Apple-Silicon feature; PR 45975 is a narrower integration/CLI follow-up around optional kernels-community selection.", + "canonical_pr_reason": "PR 45977 is the more central, self-contained implementation PR: it introduces the new GGUF linear path and accompanying quantizer/modeling integration, whereas PR 45975 is a narrower optional fast-path/configuration change for serving.", "best_issue_reason": null, - "best_pr_reason": "PR 45977 is the best representative because it introduces the core inference-time GGUF matmul path and the main code changes; PR 45975 mostly wires that capability into serving and help text.", + "best_pr_reason": "PR 45977 looks like the stronger standalone PR for the cluster because it contains the core new code and validation coverage; PR 45975 is more of an adjacent enhancement to serving/help text and fast-path selection.", "soft_edge_verdicts": [ { "left": "pull_request:45975", "right": "pull_request:45977", "accept": false, - "reason": "Different concrete changes: 45975 updates serve/model-manager integration and documentation for optional kernels-community Metal dequant, while 45977 adds a new GGUF linear backend and quantizer/modeling support. Same broad subsystem, but not one mergeable bug fix." + "reason": "Same broad GGUF/Metal/kernels-community area, but not the same concrete change: 45975 is about an optional serving-time dequant fast path and CLI/model-manager plumbing, while 45977 adds a new GgufLinear matmul implementation plus quantizer/modeling integration. Different code paths and merge scopes." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index ae03b8b30deada8dab39533ee1d0b10e9b1f28c1..a73b23ba610aa9047ff01f1d4e141cfd2825fe5d 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260516t060035z", + "analysis_id": "hybrid-model-20260516t120032z", "archived_artifacts": { - "hybrid": "snapshots/20260516T060035Z/analysis-runs/hybrid-model-20260516t060035z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260516T060035Z/analysis-runs/hybrid-model-20260516t060035z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-16T06:02:31Z", + "published_at": "2026-05-16T12:09:08Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260516T060035Z", + "snapshot_id": "20260516T120032Z", "variant": "hybrid" } diff --git a/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.json b/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..d8a377e9c66bd7f45a86e4dcef04da01e6338129 --- /dev/null +++ b/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.json @@ -0,0 +1,2243 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260516T120032Z", + "generated_at": "2026-05-16T12:09:06Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43656-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43824, + "canonical_pr_number": 43656, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43656, + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43656, + "right_pr_number": 43836, + "code_similarity": 0.36, + "size_similarity": 0.176, + "file_overlap": 1.0, + "area_overlap": 0.051, + "patch_similarity": 0.048, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ] + } + ] + }, + { + "left_pr_number": 43656, + "right_pr_number": 43842, + "code_similarity": 0.405, + "size_similarity": 0.5, + "file_overlap": 1.0, + "area_overlap": 0.0, + "patch_similarity": 0.036, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 30, + 36 + ], + [ + 315, + 323 + ], + [ + 665, + 671 + ], + [ + 931, + 937 + ], + [ + 1843, + 1849 + ], + [ + 1868, + 1874 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + }, + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.805, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.854, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 713, + 720 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 699, + 705 + ], + [ + 1301, + 1307 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44002-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44002, + "issue_numbers": [], + "pr_numbers": [ + 44002, + 44029 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44002, + "right_pr_number": 44029, + "code_similarity": 0.135, + "size_similarity": 0.43, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "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-44002-2", + "canonical_pr_number": 44002, + "duplicate_pr_numbers": [ + 44029 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44002-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-45081-3", + "canonical_pr_number": 45317, + "duplicate_pr_numbers": [ + 45086 + ], + "target_issue_number": 45081, + "reason": "PRs in cluster-45081-3 are treated as duplicates because they converge on issue #45081 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45561-3", + "canonical_pr_number": 45645, + "duplicate_pr_numbers": [ + 45639 + ], + "target_issue_number": 45561, + "reason": "PRs in cluster-45561-3 are treated as duplicates because they converge on issue #45561 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45647-3", + "canonical_pr_number": 45738, + "duplicate_pr_numbers": [ + 45737 + ], + "target_issue_number": 45647, + "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + } + ], + "best_issue": { + "cluster_id": "cluster-45647-3", + "issue_number": 45647, + "reason": "Issue #45647 is the strongest global issue candidate because it is open, belongs to a cluster with 3 artifacts, and carries 12 discussion comments plus 8 inbound references.", + "score": 162.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..6320a6af0f9d156d477d5c1006d18196d53dfcff --- /dev/null +++ b/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,19647 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260516T120032Z", + "generated_at": "2026-05-16T12:09:06Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "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:39290|issue:43531", + "issue:41093|issue:43638" + ], + "prepared_review_unit_hash": "da6a3f199e7807061fab7cb571fb9b918b1be1615fe85a514fa79539e21d5134", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 62, + "serialized_chars": 46384, + "estimated_input_tokens": 11596, + "estimated_eval_tokens": 23448 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous, but it contains two clear duplicate subgroups: ZeRO-3/Bert index-out-of-bounds failures and the v5 AutoTokenizer wrong-token-ID regression. Most other pairs share a broad subsystem but look like distinct bugs or regressions.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45920 is the broadest and most representative issue in the tokenizer regression subgroup, covering multiple model families; issue:45812 looks like a narrower Granite-specific instance of the same v5 token-ID bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best single anchor for the cluster because it captures the widest concrete bug pattern among the listed issues and is likely to subsume related reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different failures: Qwen3.5 config attribute access vs streaming chat/completions handling." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Different model/runtime problems; shared GPU/MoE context is too broad to call duplicate." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Both are model-specific device/dtype issues, but with different models and failure modes." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Different concrete dtype/device mismatch cases; not the same bug." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "AMD loading issue vs GraniteMoEHybrid invalid-method call are unrelated code-paths." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different Qwen NVFP4 runtime error vs AMD GPU loading failure." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Collective mismatch under DeepSpeed Zero3 vs ONNX export failure are unrelated." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Both are model/export related, but one is ONNX export and the other is FineGrainedFP8 runtime behavior." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export error and cudaErrorAssert during auto device mapping are different bugs." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs cleanup, but they target different removed features and likely separate edits." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export issue and GenerationMixin import breakage are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Similar-looking tensor/device errors, but different models and failure surfaces." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both mention index/mask shape failures, but the model/setup context is different enough that they do not clearly match." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Same general IndexError family, but one is ZeRO-3/Bert size-0 initialization and the other is a mask-shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different problems: generic mask/tensor shape mismatch vs GPT-OSS MoE tensor-parallel failure." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different model/trainer paths; no clear same underlying bug." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice_preset vs ModernBERT ONNX export are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Different models and failure modes under DeepSpeed; not the same bug." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3/Bert index-0-out-of-bounds failure; the newer report is just a non-pretrained Bert variant." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy call vs GPT-OSS MoE tensor-parallel failure are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different bugs: detokenization regression vs LoRA merge/save/load mismatch." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Quantized Qwen runtime error and LoRA merge mismatch are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation checkpointing/FSDP recomputation mismatch is not the same as a mask indexing error." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both involve DeepSpeed, but one is a 2-D weight training error and the other is a collective mismatch." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": false, + "reason": "Same Qwen3_5Moe embedding class, but one is CPU-offload incompatibility and the other is uninitialized-memory after materialization; not clearly the same bug." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "Both involve zero-3 / model-parallel contexts, but the specific failure paths differ." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different model families and different runtime errors." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Different dtype/device issues in different models; too broad to merge." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version compatibility and NVFP4 runtime error are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different model/runtime problems despite both being numerical/backend issues." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Video StopIteration in Qwen3-vl-embedding is unrelated to MPS histogram support." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Different failures in different code paths; only broad backend overlap." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch vs trainer signature change are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "FSDP activation-checkpointing mismatch and GenerationMixin import breakage are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Different runtime bugs; no shared concrete code path." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": false, + "reason": "Both are index-out-of-bounds under ZeRO-3, but different models and likely different root causes." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs issues: return_all_scores behavior vs removed run command reference." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Gemma3 sliding_window/vLLM attribute issue and Qwen3 auto device mapping cuda assert are different." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "Different product areas: AMD GPU loading vs table-question-answering crash." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure and device-mismatch forward error are not the same underlying bug." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger Kernel cross-entropy invocation and video StopIteration are unrelated." + }, + { + "left": "issue:45812", + "right": "issue:45920", + "accept": true, + "reason": "Same v5 AutoTokenizer wrong-token-ID regression; 45920 is the broader multi-model umbrella report." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Checkpoint corruption and NemotronH checkpoint-loading failure are different issues." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unit-test load failure vs checkpoint corruption are not the same bug." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/Gemma sliding-window problems with distinct symptoms and models." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are shape/index errors, but the reported models and contexts differ enough that they do not clearly duplicate." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Dtype mismatch in Mistral-3 vs GraniteMoEHybrid invalid method call are unrelated." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Invalid method call in GraniteMoEHybrid vs MPS histogram unsupported type are different bugs." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model families and different backend failures." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Different model/runtime contexts; not the same concrete bug." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Qwen NVFP4 runtime error and TRL SFT unpacking failure are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy call and TRL SFT trainer unpacking issue are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Both are ZeRO-3 index-out-of-bounds reports, but the model families and likely root causes differ." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions in v5, but they refer to different removed features and should not be merged as duplicates." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/Gemma sliding-window failures, not the same code-path problem." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Mask/index shape mismatch and ZeRO-3 Bert zero-size index error are different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it identifies the two clearly supported duplicate subgroups (43596/43638 and 45812/45920) and otherwise treats the remaining pairs conservatively as likely distinct issues. The accepted soft-edge verdicts are supported by the issue titles and stay within the evidence available." + }, + "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-10000-403", + "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:43792|issue:45901", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43975|issue:45901", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:44292|issue:45901", + "issue:39290|issue:45823", + "issue:43404|issue:43866", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:41093|issue:41762", + "issue:45800|issue:45823", + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:45020|issue:45800", + "issue:43531|issue:45070", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:45542|issue:45800", + "issue: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": "760f2b5f3289c04cd12e4a07530fe4a5fc9b83dde8ab9e673816e6bd3fbe2de2", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38765, + "estimated_input_tokens": 9692, + "estimated_eval_tokens": 19640 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue reports. The only near-match is the custom-module loading pair, but the available metadata is not enough to confirm a shared root cause, so it should stay tentative rather than merged as a duplicate.", + "confidence": 0.57, + "canonical_issue_reason": "Issue 45698 is the better anchor for the cluster: it states the broader from_pretrained/save_pretrained custom-module loading failure. Issue 45632 looks related, but the packet does not firmly establish that it is the same bug rather than a specific variant.", + "canonical_pr_reason": null, + "best_issue_reason": "Most actionable issue in the set: open and centered on a concrete custom-module loading path with a clear user-facing failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom-module loading, but the evidence is too thin to prove the same underlying bug; one points to a cache-path collision, the other to wrong module selection after save/load." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Mostly conservative, but a bit too assertive for the evidence in the packet. The phrase \"open, clearly reproducible\" is not grounded by the supplied metadata alone, and the accepted 45632\u219445698 pairing is plausible but not strongly established beyond title similarity. Please keep the duplicate call softer unless the bodies explicitly show the same root cause." + }, + "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": 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-10000-403", + "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": "15c378b83f1c57bcf067669b20e229fb48e9ec7ffea7255ff33614baad816dc1", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36587, + "estimated_input_tokens": 9147, + "estimated_eval_tokens": 18550 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The duplicate cluster is mostly solid around the Transformers 5.x non-persistent-buffer regression: 43950, 43644, and 44534 all point to the same underlying corruption bug. Issue 45902 is related in the same area, but the packet only supports it as a narrower symptom, not a confirmed duplicate.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43950 is the best canonical representative because it describes the regression at the right level of generality\u2014`from_pretrained()` corrupting non-persistent buffers in Transformers 5.x\u2014and it is directly corroborated by 43644 and 44534. 45902 looks related, but this packet does not establish it as the same bug with enough certainty.", + "canonical_pr_reason": null, + "best_issue_reason": "43950 is the strongest issue anchor for triage: it names the broad regression clearly, matches the shared non-persistent-buffer failure mode, and cleanly subsumes the confirmed duplicates 43644 and 44534.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "Unrelated topics: a DSA indexer discussion vs a docs typo about a removed command." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is not the same bug as tied-weights handling in translation models." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure is a different problem from translation-model tied weights." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo is unrelated to the removed transformers run command docs issue." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Different model/code-path failures: Qwen3.5 input embedding unpacking vs GraniteMoEHybrid invalid method calls." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Both are model-related, but they involve different models and concrete failures with no shared underlying bug shown." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Same underlying non-persistent-buffer regression; both titles describe the same junk/corruption behavior in Transformers v5." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "No shared bug: Qwen NVFP4 loading error vs GraniteMoEHybrid invalid method issue." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Both mention SigLIP2, but one is a docs/example error and the other is a text-embedding quality discrepancy." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Direct duplicate reports of the same non-persistent-buffer junk/corruption regression." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Different models and failure modes: dtype mismatch under autocast vs Qwen3.5 position_ids/SDPA behavior." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Trainer API mismatch and Gemma3 DeepSpeed loading failure are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Importing AutoImageProcessor and torch-version incompatibility are separate issues." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Checkpoint corruption is not the same as generic loading noise." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": false, + "reason": "The packet only shows a narrower uninitialized-memory symptom after `meta \u2192 to_empty(cuda)`; it does not clearly establish the same non-persistent-buffer regression." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Bitsandbytes unexpected-kwarg failure and missing Float8 storage type are different compatibility bugs." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "Both involve tokenization/model behavior, but the reported failures and likely root causes differ." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error for Voxtral is unrelated to Molmo's tied-weights attribute error." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both concern SigLIP2, but unexpected zero probabilities and degraded text embeddings are different symptoms with no clear same root cause." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Both are Qwen-related, but Flash Attention crash from 3D position_ids is different from CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states handling is a different bug from non-persistent-buffer materialization corruption." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Voxtral AutoTokenizer error and glm-4v loading failure are unrelated." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing with PEFT LoRA and int4 memory/OOM regression are different training-performance issues." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "Both mention SigLIP2, but embedding quality and HF-vs-JAX implementation discrepancy are not the same bug." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise and a specific model load failure are different issues." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "A missing-fields bug in AutoConfig with trust_remote_code is not the same as broad remote_code breakage." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization of a specific model and a Python 3.13 flash_attn import KeyError are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Different models and failures; no shared underlying code-path problem is evident." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Two separate model-loading complaints with no concrete shared bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "LoRA gradient checkpointing and Qwen3 MoE memory usage are different training-performance problems." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "glm-4v loading and Molmo tied-weights attribute error are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading failure and Qwen3Moe FineGrainedFP8Config failure are separate model/config issues." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and GLM5 are different model-loading failures." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The 43950/43644/44534 cluster is well grounded, but the 43950\u219445902 duplicate call is too strong given the packet. 45902\u2019s title only shows an uninitialized-memory issue after meta\u2192to_empty(cuda) materialization; the packet does not clearly establish that it is the same non-persistent-buffer regression. Because soft-edge verdicts need to stay conservative, I can\u2019t accept this as written." + }, + "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": 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-10000-403", + "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:43638|issue:45823", + "issue:43257|issue:43866", + "issue:43792|issue:44220", + "issue:43872|issue:44291", + "issue:42915|issue:43872", + "issue:43940|issue:45313", + "issue:41553|issue:44991", + "issue:43854|issue:44863", + "issue:36331|issue:41093", + "issue:43257|issue:45305", + "issue:42947|issue:45923", + "issue:44928|issue:45588", + "issue:43872|issue:45538", + "issue:41093|issue:44805", + "issue:41553|issue:44488", + "issue:44479|issue:44560", + "issue:44530|issue:44863", + "issue:24643|issue:30064", + "issue:45325|issue:45902", + "issue:43366|issue:43828" + ], + "prepared_review_unit_hash": "ebfd7b3d6b6706316dcf46caee9e35259dfa6eb8fddc944b4240d6d8bc325a14", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 38071, + "estimated_input_tokens": 9518, + "estimated_eval_tokens": 19292 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous model-loading/training regressions, with only a few true duplicates. The clearest duplicate groups are the docs cleanup around removed v5 pipeline tasks, the bitsandbytes/_is_hf_initialized init_empty_weights TypeError, and the identical mask/tensor shape IndexError reports.", + "confidence": 0.78, + "canonical_issue_reason": "44291 is the most precise report of the bitsandbytes/_is_hf_initialized regression, naming the exact failing path and version; it best serves as the canonical issue for that duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "44291 is the strongest standalone issue in the cluster: concrete, reproducible, and root-caused, unlike the broader or more speculative reports nearby.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "Different failures: MPS Int histogram support vs Gemma4 PLE device placement mismatch." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Both mention Qwen/LoRA, but one is a hf4.x\u2192hf5.x compatibility break and the other is a tie_word_embeddings warning." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Unrelated bugs: missing Qwen2_5_VL import vs bitsandbytes Int8Params/_is_hf_initialized TypeError." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Too broad and different: remote_code regressions vs a device_map forward mismatch." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Different root causes: tokenizer mapping helper failure vs generic remote_code breakage." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer load failure for a specific model vs flash-attn fallback gating; no shared code-path." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Different runtime issues: autocast dtype mismatch vs device mismatch." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex crash vs flash-attn fallback blocking; unrelated fixes." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both are the same docs regression after v5 pipeline removals; one is just a narrower phrasing of the same cleanup." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Both are regressions, but one is broad remote_code breakage and the other is a specific Kimi-K2.5 tokenizer codec/warning issue." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Different model bugs: untied lm_head weights vs non-persistent buffer corruption." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "Key error loading MobileLLM vs flash-attn fallback gating; no same underlying defect." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Both are Qwen-related regressions, but one is a Qwen3_moe LoRA compatibility problem and the other is a generic remote_code breakage." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "Different code paths: DeepSpeed ZeRO-3/Bert IndexError vs Gemma4 device mismatch." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Different model-loading failures: Qwen3 MOE weight conversion vs Ovis2 checkpoint corruption." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Possible audio-processing relation, but the titles are not specific enough to treat as the same bug." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same bitsandbytes/_is_hf_initialized incompatibility; the second issue states the exact root cause and reproducer more clearly." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Both involve model/loading regressions, but they are different bugs with different failure modes." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Similar DeepSpeed ZeRO-3 symptoms, but different Qwen model families and different reported failure details." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer issues for different models; not the same underlying defect." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different model-specific loading failures with no shared error path." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Unexpected compute_loss kwarg vs tensor-mask shape mismatch; unrelated bugs." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Weight conversion under Accelerate/DeepSpeed vs gradient averaging under GAS; different layers of the stack." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "Both mention checkpointing, but one is LoRA checkpointing ineffective and the other is a missing model flag on a trust_remote_code variant." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "Different failures: RLHF gradient explosion/SDPA fallback vs flash_attention.py handling of sink-less models." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes init error vs CLIPTokenizer max length constant; unrelated." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same mask/tensor shape mismatch error class with essentially identical failure message; these look like duplicate reports of the same indexing bug." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Both are tokenizer-related, but they concern different models and different failure modes." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-input regressions, but the affected models and errors differ enough to keep separate." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache linear_attention group crash vs NemotronH checkpoint loading failure; not the same bug." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Training DeepSpeed weight-shape error vs image processor segmentation-map failure; unrelated." + }, + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "Different rotary/positioning bugs on different architectures; no shared fix path." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss support vs Phi-tiny-MoE autocast dtype mismatch; unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative overall. The three accepted duplicate pairs are defensible from the titles/body metadata: the docs pipeline-removal reports, the bitsandbytes/_is_hf_initialized TypeError reports, and the matching mask/tensor shape IndexError reports. No soft-edge verdict stands out as an overstatement, and the cluster-level summary matches the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "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:43366|issue:44589", + "issue:42915|issue:43957", + "issue:43645|issue:43646", + "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": "f24971b2b5c110f07a07ae8f1558b0fb5567ccbca900b5f3470c3a3788d50a86", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37191, + "estimated_input_tokens": 9298, + "estimated_eval_tokens": 18852 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated issues. Only two duplicate pairs look strong enough to merge: the two custom-model initialization regressions and the two non-persistent-buffer regression reports.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 44534 is the clearest canonical anchor for the non-persistent-buffer regression: it states the concrete Transformers v5 corruption bug directly and matches the near-verbatim duplicate 43644.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44534 is the best single issue to represent the strongest duplicate pair in this set because it names the exact bug class and is more precise than the alternate duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Same broad model family, but different failures: FSDP2 KeyError during training vs device-mismatch during forward. Not the same concrete bug." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "Different models and unrelated symptoms (batched AudioFlamingo3 leakage vs Whisper empty-transcription generation)." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Unrelated topics: GGUF/gpt-oss support vs Qwen3-MoE sliding_window behavior." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Both are loading/runtime issues, but one is a Transformers v5 buffer-corruption regression and the other is a long-OCR index error in Kosmos2.5." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different models and different attention paths (Bamba SDPA compile failure vs Qwen3.5 flash-attention crash)." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Import error for a specific class vs meta-device model-loading breakage; not the same bug." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "Support request vs storage-type/type-error regression; no shared underlying code-path." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Different problems: Qwen3-MoE FP8 failure vs generic torch.device(\"meta\") loading breakage." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These describe the same Transformers v5 custom-model initialization regression; one is just a notebook-specific reproduction of the same bug." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both mention Qwen, but one is a video embedding StopIteration and the other is an SFT-trainer unpacking failure; different code paths." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "No shared bug: inability to run a script vs GGUF architecture support." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "ImportError for GenerationMixin and Qwen3-MoE FP8 failure are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer-mapping edge case vs Gemma4 PLE device mismatch; different subsystems and failure modes." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but the evidence only shows similar bad outputs, not the same concrete bug or fix path." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "Transformers v5 _is_hf_initialized regression vs Kosmos2.5 OCR index error; unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Different failure modes and different model contexts; not the same bug." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both involve config validation, but the model targets and likely fixes differ; too weak to merge." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "DeepSpeed ZeRO-3/Bert indexing failure is unrelated to add-new-model-like tokenizer mapping behavior." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Different issues: ZeRO-3/Bert index error vs tokenizer-mapping failure." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer-mapping failure and a tensor mask shape mismatch are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Different loading issues: gpu+cpu offload dequantization vs mmap OOM mitigation." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Near-verbatim duplicate reports of the same Transformers v5 non-persistent-buffer corruption regression." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Both involve SigLIP2, but one reports zero probabilities and the other a docs-example model/processor mismatch plus quantization failure; not enough evidence of one shared bug." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Completely different models and failures (GLM5 vs Qwen3.5 flash-attention generation)." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "LoRA/qwen3_moe version incompatibility and BitNet packed-weight loading are different bugs." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Different code paths and symptoms: ZeRO-3 weight loading vs save_pretrained key serialization." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Different models and failures: Qwen3 device-map cuda assert vs Qwen3-MoE FP8 config issue." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading complaints, but they involve different BERT models and there is no evidence they share the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative on the soft edges. The two accepted pairs look reasonably mergeable for the same bugfix, and the rejected pairs are phrased cautiously rather than overstating shared causality. No obvious overclaiming." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 6, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:36010|issue:39404", + "issue:43404|issue:43454", + "issue:41720|issue:44155", + "issue:43425|issue:43957", + "issue:44402|issue:44488", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:45663|issue:45759", + "issue:43335|issue:45663", + "issue:43873|issue:44387", + "issue:44291|issue:44756", + "issue:45663|issue:45859", + "issue:44155|issue:45823", + "issue:44292|issue:44912", + "issue:44387|issue:44756", + "issue:43854|issue:45216", + "issue:43957|issue:44756", + "issue:44743|issue:44960", + "issue:45276|issue:45292", + "issue:45684|issue:45698" + ], + "prepared_review_unit_hash": "8b6e105dd047439290cb11385c8f075ebbb2d04edf68d53cdd5ea94923fc8340", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37771, + "estimated_input_tokens": 9443, + "estimated_eval_tokens": 19142 + }, + "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 Transformer regressions. The only clear duplicate-like subgroup is the `resize_token_embeddings` propagation bug around Gemma4/T5Gemma, so that is the best canonical thread; the rest should stay separate.", + "confidence": 0.73, + "canonical_issue_reason": "issue:45292 is the broadest statement of the `resize_token_embeddings` regression, and the Gemma4/T5Gemma reports look like model-specific manifestations of the same underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 is the cleanest representative of the only convincing duplicate cluster in this set; it generalizes the same embedding-resize failure that shows up in the related model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenizer behavior, but they hit different model families and different failures: DeepSeek V3/R1 pre-tokenizer override vs Granite token-id regression." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Same SigLIP2 family, but one is a broken doc example with model/processor mismatch and quantization issues; the other is a model loading/pipeline output regression." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Completely different models and failure modes; Qwen3 MoE conversion under accelerate/deepspeed is not the same bug as GLM-4.7-Flash loading in tests." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading complaints, but they concern different models and likely different root causes, so this is too broad to merge." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "These are distinct Qwen3-related load problems: one is hf4.x\u2192hf5.x LoRA compatibility, the other is a shape mismatch for Qwen3-VL-30B." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory/quantization, but one is Qwen3 MoE training efficiency and the other is offloading failure with quantization; not the same concrete bug." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers 5.0 regressions, but one is junk non-persistent buffers and the other is custom model initialization in Jupyter notebooks." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different model-specific crashes: Qwen3.5 chat crash versus Gemma4Processor missing `_tokenizer` in serve." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "These are both memory-related, but one is training memory inefficiency and the other is int4 quantization reserved-memory/OOM behavior." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both touch flash attention, but the root causes differ: packed-sequence misinterpretation of position_ids versus `s_aux=None` AttributeError." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "LoRA hf4.x\u2192hf5.x incompatibility is unrelated to the generic `resize_token_embeddings` output-embedding bug." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": true, + "reason": "Both describe the same `resize_token_embeddings` failure to update tied output/input embeddings, just surfaced in different model classes." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "One is save/from_pretrained mishandling `extra_state`; the other is `init_empty_weights` rejecting `_is_hf_initialized`." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Importing `GenerationMixin` from `transformers.generation` and Whisper `return_language` pipeline behavior are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both mention lm_head tying, but they are different multimodal model classes with no evidence of the same exact code-path bug." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "These are unrelated: Qwen3 device-map cuda asserts versus AudioFlamingo3 batched track-state leakage." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version incompatibility is a dependency issue, while the meta-device report is a model-loading regression in Transformers 5.x." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Both involve tokenizer/model vocab problems, but the specific models and symptoms differ, so this is not a clear duplicate." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "SigLIP2 doc/model issues are unrelated to the GLM5 report." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing with PEFT LoRA is unrelated to the T5/apex RMSNorm memory leak." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma-4 FSDP2 shared_kv_states behavior and Qwen multimodal `text_config` unwrapping are different model-integration bugs." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and Gemma-4 FSDP2 attention-state rebuilding are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Quantization/offloading behavior and int4 reserved-memory OOM are related only at a very broad level, not as the same bug." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "`init_empty_weights` argument handling and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Gemma-4 FSDP2 attention state handling and Qwen3_5Moe CPU-offload incompatibility are different issues." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batched inference state leakage is unrelated to Gemma4 device-mismatch during forward." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Different quantization formats and failures: NVFP4 loading error versus MXFP4 fallback to bf16." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Both involve OOMs, but one is int4 reserved-memory growth and the other is disabling mmap on Strix Halo." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "GLM-4.7-Flash test loading and Qwen3.5 save_pretrained regression are separate model/load paths." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading regressions and Strix Halo mmap OOM are not the same bug." + }, + { + "left": "issue:44743", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3 recurrent-state reset with cache is unrelated to the GLM5 report." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "These are the same `resize_token_embeddings` defect, with 45276 being a model-specific manifestation and 45292 the broader report." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "`save_pretrained` permission propagation and `from_pretrained` loading the wrong custom module are different custom-model save/load problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only clearly supported duplicate cluster is the resize_token_embeddings trio around 45276/45292/45335, and the other soft-edge rejections avoid overclaiming sameness across different model-specific failures." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 7, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:44402|issue:44451", + "issue:43257|issue:44863", + "issue:43828|issue:43957", + "issue:43425|issue:43828", + "issue:44683|issue:45823", + "issue:44589|issue:44756", + "issue:39404|issue:45701", + "issue:43931|issue:44863", + "issue:43425|issue:45823", + "issue:43906|issue:44530", + "issue:43611|issue:43645", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:39404|issue:44912", + "issue:43901|issue:44509", + "issue:44265|issue:44898", + "issue:44479|issue:44805", + "issue:43994|issue:44079", + "issue:43299|issue:43931", + "issue:43425|issue:44918", + "issue:44589|issue:45084", + "issue:39404|issue:44671", + "issue:44164|issue:45759", + "issue:36032|issue:43452", + "issue:43596|issue:44683", + "issue:44671|issue:44991" + ], + "prepared_review_unit_hash": "859dd7b0156528b7b121dc0b6663950ccc58462cf636f9fe085dd04c5f7eeae3", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37968, + "estimated_input_tokens": 9492, + "estimated_eval_tokens": 19240 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a loose cluster of Transformers v5 regression reports, not one tight duplicate set. The only clear duplicate-like pairs are the two tokenizer-embedding resize issues and the two Qwen3-VL loading reports; the rest are related at a broad subsystem level but describe different bugs.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43611 is the broadest, most representative report of the v5 model-loading breakage theme in this cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best single issue to anchor the cluster because it captures the most general loading-regression pattern rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Both involve training/gradient behavior, but the eval-mode checkpointing restriction is a different bug than the Qwen3.5 NaN/SDPA fallback issue." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "Extra state handling in save/from_pretrained and disabling mmap on Strix Halo are unrelated failure modes." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both mention gradient checkpointing, but one is PEFT/LoRA effectiveness and the other is an eval-mode restriction; different code paths." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video-input regression for Qwen/VL models and strict-config loading for granite_speech are different issues." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model init in Jupyter notebooks and Trainer resume/max_steps calculation are separate problems." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Flash-attention s_aux=None crash and Gemma4 FSDP2 shared_kv_states KeyError are not the same bug." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Both report resize_token_embeddings failing to update downstream output/decoder embeddings; same underlying embedding-resize bug." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook-defined custom model initialization and extra_state serialization are different failure modes." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Tokenizer vocab-size mismatch and inability to load ScandiBERT are related to loading, but not the same concrete defect." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed and NemotronH checkpoint loading are separate model-loading regressions." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch and meta-device loading failures are different code-path problems." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility is too broad and not the same as the Phi-tiny-MoE autocast dtype mismatch." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Torch>=2.9 flex_attention compilation and Gemma4 PLE device-mapping mismatch are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure and mmap OOM on Strix Halo are distinct runtime issues." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper return_language pipeline regression and tokenizer-version-dependent tokenization changes are different symptoms and code paths." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and NemotronH checkpoint loading are different model families and bugs." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Generic Torch incompatibility and Gemma4 device mismatch are not the same bug." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "An isolated reproduction of a prior issue and a PagedAttentionCache linear_attention crash are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both are v5 custom-model loading regressions, but one is base_model_prefix handling and the other is notebook-defined initialization; not the same concrete bug." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Torch 2.10 incompatibility and Mistral-3 dtype mismatch are separate issues." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache group-type crash and template-node compilation error are different failures." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline behavior and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Docs drift for return_all_scores and docs for removed pipeline tasks are both documentation issues, but not the same one." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export export failure with torch_compilable_check and Perceiver non-default-resolution failure are different bugs." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Qwen video-input regression and a mask-shape IndexError are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP2 nonsense predictions and ModelOutput key assignment are separate problems." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": true, + "reason": "Both concern Qwen3-VL / Qwen3VL model loading failing under v5, with shape-mismatch-style symptoms; same underlying loading regression is plausible." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch incompatibility and Qwen3.5 embedding unpacking are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup failure and non-template node compilation error are different issues." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline regression and CamemBERT masked-LM prediction regression are different model-specific bugs." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "Extra_state serialization and from_config text_config unwrapping are distinct loading/serialization issues." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5 tokenizer loading conflict and gguf_file breaking from_pretrained are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Deepspeed ZeRO3/BertModel index error and flex_attention compilation failure are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT prediction regression and tokenizer-loading failure for est-roberta are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately cautious. The stated duplicate-like pairs are supported by the issue titles, and the rejected pairs are conservative rather than overstated. I don\u2019t see a soft-edge verdict that clearly stretches the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "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:44164|issue:44479", + "issue:44737|issue:45859", + "issue:43582|issue:43632", + "issue:44488|issue:45081", + "issue:44661|issue:44683", + "issue:44488|issue:44987", + "issue:40990|issue:43421", + "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:44451|issue:44987", + "issue:43452|issue:43482", + "issue:43541|issue:45084", + "issue:43644|issue:43646", + "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:45084|issue:45507", + "issue:43089|issue:45987", + "issue:43404|issue:44466" + ], + "prepared_review_unit_hash": "0f1a4b7ab6d55316dcfc40cb23c10cb20d25059e5d6b52d3a3824c6347348d7a", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37261, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are mostly unrelated issue reports, with only a loose concentration around Transformers v5 loading/initialization regressions. No soft pair is a confident duplicate match.", + "confidence": 0.73, + "canonical_issue_reason": "issue:43646 is the broadest representative of the recurring v5 model-initialization breakage theme, and is the closest anchor for nearby custom-model/load regressions in this set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best single issue to represent the cluster because it captures the most general and reusable failure mode among the listed reports, even though the overall cluster is not a tight duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Different subsystems and failures: GPU broadcast TypeError in Trainer vs Whisper pipeline return_language behavior." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory, but one is Qwen3 MoE training inefficiency and the other is mmap/OOM on Strix Halo; different bugs and code paths." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but one is a generic tokenizer load failure and the other is a Mistral regex patch crash; not the same underlying defect." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Save/from_pretrained extra_state handling and a video-input regression in Qwen models are unrelated." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Different models and issues: XLNet CPU device placement vs Qwen3_5 MoE CPU offload compatibility." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon caching allocator TypeError and the _is_hf_initialized v5 regression are distinct problems." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Both affect loading, but one is a model-loading regression for sleng-bert and the other is a Mistral tokenizer regex patch crash." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Different features entirely: tokenizer mapping handling vs compiled flex_attention on torch >= 2.9." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are model-load failures, but they target different models and appear to stem from different breakages." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity on gpt-oss-20b is unrelated to TokenizersBackend not updating its post-processor." + }, + { + "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 serialization; different failure points." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Both are audio-feature related, but the reported failures are different enough that they do not look like the same bug." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral image-preprocessor 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 a BERT model loading failure." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "AutoConfig trust_remote_code field loss and PagedAttentionCache invalid group type are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer special-token method conflict and Qwen3 MoE FP8 failure are unrelated." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper-related, but one is batch_decode skip_special_tokens behavior and the other is empty-transcription generation after align_special_tokens." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counting and multi-image IterableDataset fine-tuning are unrelated." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward and StaticCache.get_seq_length type mismatch are different issues." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different model loading regressions for different checkpoints; no clear shared bug." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both involve GGUF loading, but one is a broad from_pretrained/gguf_file breakage and the other is a Qwen2.5-specific v5 failure; not enough evidence they are the same concrete bug." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing error on Mixtral is unrelated to the non-template-node compilation TypeError." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 initialization/load regressions, but one is non-persistent buffer junk and the other is custom model initialization; they are not clearly the same bug." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Qwen3 MoE FP8 training failure and Qwen3.5 PagedAttentionCache group-type crash are different code paths." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "device_map auto offload/dequantized-model loading and GGUF loading failure are different problems." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Qwen3.5 output_hidden_states bug and Qwen2.5-VL rope index scaling bug are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "T5 tokenizer method conflict and custom model initialization in Jupyter notebooks are different failures." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Different failing checkpoints and different load paths; both are generic loading regressions but not the same bug." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Molmo tied-weights attribute error and tokenizer loading failure for est-roberta are unrelated." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Template-node compilation TypeError and GraniteMoEHybrid invalid method call are different issues." + }, + { + "left": "issue:43089", + "right": "issue:45987", + "accept": false, + "reason": "Generation GPU-sync overhead and StaticCache seq-length return type are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Mistral3 lm_head tying bug and device-dependent lm_head serialization inconsistency are related only broadly, not the same concrete defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 9, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:43792", + "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:42915|issue:44291", + "issue:43404|issue:45127", + "issue:43632|issue:44756", + "issue:44062|issue:44987", + "issue:36032|issue:43742", + "issue:44479|issue:45325", + "issue:43296|issue:43531", + "issue:42915|issue:44589", + "issue:40444|issue:45325", + "issue:43531|issue:44877", + "issue:43611|issue:44534", + "issue:36032|issue:41720", + "issue:43425|issue:44403", + "issue:40990|issue:44811", + "issue:41553|issue:43582", + "issue:44079|issue:45663", + "issue:43632|issue:44534", + "issue:42175|issue:45542", + "issue:43792|issue:44589" + ], + "prepared_review_unit_hash": "8bb62c9f48b3130628f2de6138546da2786395e054524b4d4ade1aff3cf9a162", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37221, + "estimated_input_tokens": 9306, + "estimated_eval_tokens": 18868 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a semantic grab-bag of Transformers regressions, with the strongest common thread being v5-era loading/serialization breakages. Most soft pairs are only loosely related by subsystem or model family, not by the same concrete bug.", + "confidence": 0.42, + "canonical_issue_reason": "issue:43611 is the broadest representative of the main theme in this cluster: Transformers v5 loading regressions. Its title is generic enough to cover several nearby load/init failures, without being tied to one narrow model.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best single issue to represent the cluster because it captures the shared \u2018v5 breaks model loading\u2019 pattern more cleanly than the model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Both are audio-related, but one is a chat-template sampling-rate default and the other is a batching/padding-mask correctness bug in MIMI." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different models and different failures: SigLIP2 bad outputs vs OmDet-Turbo processor/model input-size mismatch." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization breakage is not the same bug as non-persistent buffers being filled with junk." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Both are multimodal loading/input errors, but Llava Next segfault and Qwen3OmniMoe video ValueError are distinct code paths." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook/custom-model init failure is unrelated to the buffer-initialization corruption described in 44534." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic loading noise is not the same underlying problem as a tokenizer regex patch crash." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Different audio model families and different bugs: padding-mask batching vs DAC latent/forward mismatch." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3Moe FP8 config failure is unrelated to the template-node compilation error." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export failure with torch_compilable_check is a different issue from OmDet-Turbo processor input sizing." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "A model load failure for ScandiBERT is not the same as the Mistral tokenizer regex patch crash." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": false, + "reason": "These are related Qwen3.5 save_pretrained regressions, but 45357 is a narrower visual-encoder-key follow-up rather than the same concrete bug as 45216." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Different failure modes: loading a specific model repo vs crashing inside Mistral regex patching." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Feature-extraction audio issue and compiled flex_attention torch-version incompatibility are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Different model/setup and different root cause: Qwen3Moe FP8 config vs init_empty_weights unexpected argument." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both touch tied weights, but one is a missing lm_head tie in Mistral3 and the other is LoRA merge collapse after vocab extension." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized flag breakage is unrelated to the mmap/OOM issue on Strix Halo." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "Duplicate AddedToken special-arg handling is not the same as loading physical-intelligence/fast failing." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict and MobileLLM key error are different loading bugs." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both concern Qwen vision/video behavior, but the broad video-input regression is not the same as the still-image temporal position_id scaling bug." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL loading in vLLM and Qwen3-MoE sliding_window are unrelated failures." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3Moe FP8 config failure is not the same as the missing Float8 storage type issue." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "IterableDataset multi-image finetuning failure is different from the Qwen2.5-VL rope-index scaling regression." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE and strict-config loading for granite_speech are distinct problems." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Generic model-loading breakage is not the same bug as junk-filled non-persistent buffers." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer loading conflict and Qwen3 auto-device-map CUDA assert are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch version incompatibility and loading noise are not the same concrete issue." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on gpt-oss is unrelated to Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to the Apple Silicon warmup TypeError." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment and Gemma4 shared_kv_states/FSDP2 are different bugs." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "_is_hf_initialized regression and non-persistent buffer corruption are distinct v5 breakages." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Pip extras/backend dependency omission and tensorboard-without-TensorFlow backend errors are related only loosely, not the same bug." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper model runtime failure and missing Float8 storage object 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": 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-10000-403", + "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: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:43818|issue:45357", + "issue:44683|issue:45020", + "issue:44403|issue:44991", + "issue:44462|issue:45812", + "issue:33666|issue:40444", + "issue:43482|issue:45538", + "issue:43317|issue:43856", + "issue:43381|issue:45923", + "issue:44829|issue:45479", + "issue:35707|issue:40444", + "issue:44291|issue:44589", + "issue:44079|issue:44534", + "issue:43482|issue:43525", + "issue:43377|issue:45491", + "issue:43749|issue:44079", + "issue:40444|issue:45381", + "issue:43531|issue:44291", + "issue:41720|issue:45081", + "issue:43644|issue:44079", + "issue:44265|issue:45072", + "issue:45325|issue:45381", + "issue:42175|issue:43296", + "issue:43632|issue:45072", + "issue:43994|issue:44898", + "issue:43611|issue:43646", + "issue:43454|issue:44466", + "issue:45325|issue:45834" + ], + "prepared_review_unit_hash": "c21410207077f01a4dd113af1719d7eafb9936856fbcedcda2f7a5482e66726f", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35748, + "estimated_input_tokens": 8937, + "estimated_eval_tokens": 18130 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated bug reports spanning different models, loading paths, and regressions. I found no high-confidence duplicate pair among the soft edges, so the cluster should not be merged as a duplicate set.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45020 is the best umbrella anchor: it is broad, well-documented, and represents a major transformer-v5 regression class rather than a narrow model-specific symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most representative and actionable issue in this mixed cluster, with the broadest scope and strongest discussion trail.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both involve tokenization behavior, but one is runtime post-processor refresh and the other is add_special_tokens/BOS-EOS behavior for a specific tokenizer; not the same bug." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Different model families and failure modes: Video-LLaVA tower architecture vs Qwen3.5 save_pretrained key serialization." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Torch 2.9 flex_attention compilation failure is a distinct backend regression from remote_code model loading breakage." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Unnecessary loading noise and tokenizer-loading failure are separate symptoms in different code paths." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both are AutoTokenizer issues, but one ignores tokenizer.json while the other returns wrong Granite token IDs; not clearly the same defect." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Different Qwen2-VL/Qwen2.5-VL training workflows and distinct multi-image dataloader failure." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading under v5 and CLIPTokenizer model_max_length behavior are unrelated tokenizer/model-loading bugs." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Device-map offload load failure and Qwen3 MoE training memory usage are different problems in different phases." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "Eval-mode gradient checkpointing restriction is not the same as a missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Both end in degenerate training, but one is flash_attention_3-specific and the other is a num_labels=1 loss formulation bug." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image finetuning failure." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different initialization path from Float8 storage resolution failures." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment and non-persistent buffer junk are separate internal state-management issues." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "GGUF loading regression and missing pad_token_id on Llama4Config are not the same underlying bug." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Batch-vs-single MIMI padding-mask mismatch and Gemma3 NaNs from all-padding windows are different model-specific attention/padding bugs." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM-efficient loading and ModelOutput key handling are unrelated subsystems." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Multi-image prompt finetuning failure is distinct from Qwen2.5-VL video vision_position_ids regression." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights argument handling are different regressions." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Auto device mapping cudaErrorAssert on A800 is unrelated to Mistral tokenizer regex patch crashes." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk and ModelOutput key assignment bugs are different internal behaviors." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export with torch_compilable_check and bfloat16 dtype mismatches are not the same code-path problem." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL position-id regressions, but one is still-image temporal scaling and the other is video vision_position_ids; related, but not confidently the same bug." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Missing TensorFlow backend from pip extras and PaddleOCR-VL load failure are unrelated packaging/loading issues." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized breakage in v5 is unrelated to dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and Perceiver resize/interpolation failure are different model-specific vision issues." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both mention transformers v5 breakage, but base_model_prefix loading and custom model initialization are separate failures." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "AyaVision weight tying failure and lm_head.weight serialization inconsistency are related only at a high level; not the same bug." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Qwen2.5-VL temporal position-id scaling and Kosmos2.5 OCR index error are different model behaviors." + } + ] + }, + "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-10000-403", + "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:44991", + "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:44291|issue:44877", + "issue:43606|issue:44265", + "issue:43262|issue:43746", + "issue:40990|issue:45584", + "issue:44568|issue:45920", + "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:43377|issue:44898", + "issue:43257|issue:45923", + "issue:43454|issue:45072", + "issue:43526|issue:43883", + "issue:40990|issue:42947", + "issue:43881|issue:44991" + ], + "prepared_review_unit_hash": "db777973969792720703289d080eb2c5367d361d79033a059bfe131a5a350879", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36471, + "estimated_input_tokens": 9118, + "estimated_eval_tokens": 18492 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: it contains many unrelated issue reports across model loading, tokenization, quantization, audio, vision, and device-mapping paths. None of the soft pairs look like the same underlying bug/change, so they should all remain separate.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue: the items span distinct subsystems and failure modes rather than one duplicate family.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue candidate; none is a clear superset or central representative of the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Different symptoms and scope: Whisper runtime failure vs a general torch.device(\"meta\") loading regression affecting multiple models." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Unrelated bugs: FineGrainedFP8Config failure for Qwen3Moe vs GGUF loading failure for Qwen2.5 under transformers v5." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "Different version stacks and failure modes: PaddleOCR-VL/vLLM load issue vs torch 2.4.1 and transformers 5.8.0 incompatibility." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both mention OOM, but one is an int4 quantization memory regression and the other is a model-specific Sam3Video CUDA OOM." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Different code paths: checkpoint resume key mismatch vs Qwen2.5-VL rope/position-id scaling bug." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Different models and issues: Qwen video-input regression vs Gemma4 PLE device mismatch during forward." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Separate model-loading failures for different checkpoints; no shared concrete bug is evident." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "One is an init_empty_weights argument regression; the other is strict config validation blocking granite_speech config loading." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "Different subsystems: CPU offload device mismatch vs torch.export failure around torch_compilable_check." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sampling-rate default bug vs GraniteSpeech PEFT checkpoint loading issue are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "Different model/workflow failures: GPT-OSS perplexity anomaly vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different tokenizers and likely different root causes." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "Unrelated: Bark voice_preset does not work vs progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Different regressions: quantization/offloading behavior vs version-dependent tokenization changes." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crash on NER/padding vs export failure with torch_compilable_check are different bugs." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "No common underlying bug: generation cache handling vs Qwen3 device-mapping cudaErrorAssert." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to DAC.from_latents not matching forward pass." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Different models and failure causes: Qwen3 auto device mapping assert vs Gemma4 PLE device mismatch." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "AyaVision lm_head tying bug is unrelated to Bamba SDPA/torch.compile failure." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Different modalities and root causes: MIMI batching/padding-mask bug vs OmDet-Turbo processor size mismatch." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both involve offloading/quantization, but one is dequantized-model loading with device_map=auto and the other is a broader offloading complaint." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Documentation/model-processor mismatch and quantization example errors are unrelated to Qwen2.5-VL multi-image finetuning failure." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Different config regressions: missing pad_token_idx in StableLmConfig vs not unwrapping text_config for composite multimodal configs." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Different image/audio preprocessing bugs: MIMI padding-mask mismatch vs Perceiver non-default resolution failure." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Distinct issues: Qwen3 MOE weight conversion under accelerate/deepspeed vs missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Different bugs in different models: weight tying corruption vs dtype mismatch during bfloat16 inference." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "Unrelated issues: BeitImageProcessorFast reduce_labels bug vs Molmo missing all_tied_weights_keys attribute." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Different problem domains: perplexity regression on GPT-OSS vs gradient checkpointing ineffectiveness with PEFT LoRA." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer/model loading failures for different models; no evidence of a shared 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": 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-10000-403", + "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:43749|issue:44534", + "issue:43454|issue:43720", + "issue:41720|issue:43322", + "issue:43296|issue:44877", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:42617|issue:42915", + "issue:40990|issue:45701", + "issue:43404|issue:45357", + "issue:45632|issue:45684", + "issue:44186|issue:45072", + "issue:44423|issue:45406", + "issue:43577|issue:43708", + "issue:44387|issue:45704", + "issue:44877|issue:44991", + "issue:43873|issue:44756", + "issue:36331|issue:42617", + "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:41720|issue:42617", + "issue:43550|issue:43606", + "issue:42915|issue:43317", + "issue:43316|issue:44913", + "issue:43295|issue:45701", + "issue:43526|issue:43881", + "issue:44671|issue:44743", + "issue:41720|issue:45161" + ], + "prepared_review_unit_hash": "055bb3b15fe5c63f4e0d8b5ff9018299da87fcbac732b251cd536d1a89a09aa1", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37368, + "estimated_input_tokens": 9342, + "estimated_eval_tokens": 18940 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are a mixed set of unrelated model-, tokenizer-, loading-, and trainer-specific bugs. None of the soft pairs look like the same underlying defect closely enough to merge, so there is no single canonical issue for this cluster.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both involve saving/serialization, but the bugs are different: tied lm_head serialization vs incorrect visual encoder keys for Qwen3.5." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "Both mention v5/loading regressions, but one is FSDP CPU-efficient loading and the other is non-persistent buffer initialization; different fixes." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different models and code paths: AyaVision lm_head tying vs BitNet packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Separate failures on different models: CUDA assert with auto device mapping vs segfault loading Llava Next." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "One is a PaddleOCR-VL/vLLM load failure, the other is strict config blocking granite_speech; only loosely related to loading." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Both are Qwen-related, but one is device-mapping CUDA assert and the other is flash-attention generation behavior." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma-family, but the concrete bugs differ: variable name collision in Gemma3n vs device mismatch in Gemma4 PLE." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "Unrelated: a 3d_parallel.py runtime issue versus a FineGrainedFP8Config failure on Qwen3Moe." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Perplexity on GPT-OSS-20B is not the same defect as a tokenization behavior change across versions." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Different bugs: Mistral3 lm_head tying vs Qwen3.5 visual encoder key serialization." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Both are save/load path issues, but one is cache path collision and the other is file permission propagation; not the same bug." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crash on NER/batched padding is unrelated to dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both crash in serve, but the failing attributes and models differ: str.to on multimodal inputs vs Gemma4Processor._tokenizer." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "One is a dtype loading bug in Blip2; the other is a Trainer max_steps resume calculation bug." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Different regression classes: int4 CUDA memory growth vs apex.FusedRMSNorm memory leak in T5." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Both are load failures, but config strictness and tokenizer loading are different root causes." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both touch memory/offload, but one is quantization offloading behavior and the other is Strix Halo mmap OOM." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "CustomTrainer.compute_loss signature break is unrelated to a 3d_parallel.py execution failure." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Different failures: Trainer API mismatch versus Qwen3Moe FP8 loading." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile with SDPA on Bamba is a different code path from accelerate loading of packed BitNet weights." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Incorrect batched video processor shapes are unrelated to version-dependent tokenization changes." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both are vision preprocessing issues, but one is wrong processor output size and the other is non-default resolution handling in Perceiver." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer crash on NER/padding is unrelated to OmDet-Turbo image size mismatch." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Both involve Qwen3.5, but one is a video-input regression and the other is input-embedding unpacking in TRL SFT training." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert is unrelated to the 3d_parallel.py failure." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "torch.compile/SDPA failure is not the same as a CPU-offload device mismatch on suno/bark-small." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Different loading problems: FineGrainedFP8Config failure vs dequantized model load failure with device_map=auto." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Config API discrepancy and GPTNeoX rotary_pct reload regression are different configuration bugs." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "A processor.tokenizer/image-passing regression is not the same as a broad tokenization change across versions." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BEiT Fast label reduction bug is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM prediction corruption is unrelated to Qwen3.5 recurrent-state reset behavior." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both mention Qwen/GPT-OSS family problems, but one is CUDA assert with auto mapping and the other is tensor parallelism not working for 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-10000-403", + "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:43421|issue:45701", + "issue:30064|issue:34634", + "issue:44492|issue:44509", + "issue:41720|issue:43746", + "issue:43606|issue:43720", + "issue:43550|issue:43653", + "issue:43873|issue:45704", + "issue:44514|issue:44545", + "issue:43606|issue:43653", + "issue:43531|issue:45759", + "issue:42490|issue:43329", + "issue:34634|issue:41720", + "issue:34567|issue:35707", + "issue:44625|issue:45479", + "issue:43421|issue:43927", + "issue:44368|issue:45357", + "issue:43782|issue:45381", + "issue:44451|issue:44991", + "issue:44898|issue:45072" + ], + "prepared_review_unit_hash": "0cd57974f2896455cf38930e2c6d37761d7d992c22e38e53d9b9e343e170dc44", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36654, + "estimated_input_tokens": 9164, + "estimated_eval_tokens": 18584 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are clearly unrelated despite surface similarity. Only issue 44514 and issue 44545 look like true duplicates of the same Qwen2_5_VLProcessor batched-padding crash.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44545 is the best canonical issue in the set because it is part of the only exact duplicate pair, has the same concrete repro as 44514, and carries slightly more discussion/inbound reference signal.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44545 is the strongest issue to keep as representative: it names the exact failing code path, matches 44514 nearly verbatim, and appears to be the more established report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Different bugs in different tokenizer paths: Mistral regex patch crash vs Granite token-id regression." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Unrelated: Qwen3-MoE sliding-window behavior vs StableLm config missing pad_token_idx." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Different model families and failures: Qwen3OmniMoe video ValueError vs Qwen3VL weight_only load error." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to a script execution problem for 3d_parallel.py." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Runtime special-token post-processor update bug is not the same as Granite token IDs being wrong." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizers and failure modes: LayoutLMv2 batching crash vs MLuke AttributeError." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Llava Next segfault are separate loading/runtime issues." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Metrics label dropping and SAM3 text/bbox weirdness are different subsystems and symptoms." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer is unrelated to Qwen3.5 streaming chat/completions failure." + }, + { + "left": "issue:33357", + "right": "issue:35707", + "accept": false, + "reason": "MacOS bus error on CLIP model loading is not the same as generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "A runtime special-token update bug is not the same as a broad tokenization version-change regression." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Void segmentation maps and Bark voice_preset are unrelated model/data-path bugs." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A docs typo is not the same as stale pipeline-task documentation after v5 removal." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3 auto device-mapping cuda assert and GraniteSpeech PEFT local-load failure are different code paths." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "CPU offload device mismatch and BitNet packed-weight unpacking are separate loading/offload defects." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba is unrelated to BigBirdTokenizer special-token registration." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization/offloading behavior and T5 apex FusedRMSNorm memory leak are not the same bug." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Near-verbatim duplicate: both report Qwen2_5_VLProcessor.apply_chat_template crashing on batched input with padding=False." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Device-mismatch CPU offload bug is unrelated to BigBirdTokenizer mask-token registration." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE is not the same as AutoModelForCausalLM.from_config not unwrapping text_config." + }, + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "Trailing-slash local-model import warning and a multimodal video-token helper bug are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice_preset failure and Qwen3 device-mapping cudaErrorAssert are different problems." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counter not updating is unrelated to progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and degenerate zero-loss classification are different sequence-classification issues." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Special-token post-processor updating and DiaConfig losing custom token IDs after save/load are distinct bugs." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "tie_word_embeddings warning in Qwen3.5 LoRA training is unrelated to incorrect visual-encoder keys in save_pretrained." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Qwen3VL weight_only loading error is not the same as Qwen2.5-VL video vision_position_ids being wrong." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Failed model loading for ScandiBERT and tokenizer loading regression for est-roberta are different model-specific issues." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver image-classification interpolation bug and dtype mismatches in SwitchTransformers/TimmWrapperModel are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: issue 44514 and 44545 are near-verbatim duplicates with matching titles and compatible repros, and the inbound-reference counts support choosing 44545 as canonical. The soft-edge rejections stay conservative and rely on clearly different titles/failure modes. No PR-pair mergeability concerns apply here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:39692", + "issue:40444", + "issue:41720", + "issue:42886", + "issue:42915", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43819", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue: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: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:43531|issue:44589", + "issue:45759|issue:45859", + "issue:44062|issue:44451", + "issue:39692|issue:44610", + "issue:45704|issue:45923", + "issue:44918|issue:44936", + "issue:43421|issue:43653", + "issue:45588|issue:45759", + "issue:45663|issue:45923", + "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:41720|issue:45704", + "issue:43596|issue:44220", + "issue:39692|issue:43873", + "issue:45356|issue:45907", + "issue:43746|issue:43873", + "issue:40444|issue:43746", + "issue:42915|issue:43746", + "issue:43540|issue:44008", + "issue:44220|issue:44661", + "issue:43720|issue:43819", + "issue:30064|issue:36010", + "issue:45183|issue:45479" + ], + "prepared_review_unit_hash": "6ed42d43a328c893dc5dbd2b5d25c483d47c9ec7bc705ec92735a4db84f5cebc", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36483, + "estimated_input_tokens": 9121, + "estimated_eval_tokens": 18498 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a single duplicate group: the items span many unrelated bugs/features across tokenizers, multimodal models, training, quantization, and offloading. None of the soft-similarity pairs are close enough to merge as the same underlying change or bug.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Different problems: one is about PatchTSMixer post_init being optional, the other about Qwen3.5 num_labels propagation." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Both involve loading/models, but the failures are different: one is a loading regression for a specific repo, the other is PIL image processors incorrectly requiring torchvision." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Separate code paths: Qwen3-MoE sliding-window logic vs a storage-class lookup error when loading float8 tensors." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Related to Qwen 3.5/3.6 multimodal configs, but one is about from_config not unwrapping text_config and the other is CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "Both are tokenizer-related, but one is an AddedToken constructor error and the other is a model-loading failure for a specific checkpoint." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both touch vision models, but one is a docs/example mismatch and quantization issue; the other is an OmDet-Turbo processor/model input-size mismatch." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "Unrelated model internals: apex FusedRMSNorm memory leak in T5 vs missing supports_gradient_checkpointing on a trust_remote_code model." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different training failures: Qwen3.5 embedding unpacking with TRL SFT trainer vs trainer.evaluate failing after train." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both concern tokenizers, but one is runtime special-token/post-processor updates; the other is BigBirdTokenizer special-token registration for mask decoding." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention crash on sink-less models is unrelated to Qwen multimodal config handling." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Different model families and failures: Gemma-4 FSDP2 shared_kv_states bug vs Nemotron-3-Nano-Omni missing gradient-checkpointing support." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Both involve offline/cache behavior, but one is tokenizer cache loading on HF_HUB_OFFLINE and the other is an unconditional model_info() call in _patch_mistral_regex." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Training-mode/eval-mode checkpointing issue is not the same as the ZeRO-3 gradient growth bug." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Tokenizer post-processor updates are unrelated to LayoutLMv2Tokenizer crashes on NER inputs and batched padding/truncation." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Both affect model outputs, but one is a SigLIP2 loading/pipeline issue and the other is a CamemBERT masked-LM regression in v5." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Different model/config bugs: missing pad_token_id on Llama4Config vs sliding_window behavior in Qwen3-MoE." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "Apex/T5 RMSNorm memory leak is not the same as Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both mention fix_mistral_regex, but one is a crash in the regex patch path and the other is a Kimi-K2.5 codec regression plus misleading warning." + }, + { + "left": "issue:41720", + "right": "issue:45704", + "accept": false, + "reason": "Qwen3 CUDA assert with auto device mapping is a different failure mode from a T5 RMSNorm memory leak." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Different subsystems: deepspeed zero3 init with BertModel vs _torch_extract_fbank_features audio extraction." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "Docs/example SigLIP2 errors are unrelated to the broader offloading-with-quantization behavior issue." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Both touch HF Hub/tokenizer utilities, but one is a tokenizer codec/regression issue and the other is list_repo_files not forwarding revision." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "PEFT local checkpoint loading for GraniteSpeech is not the same as offloading misbehavior under quantization." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "Multi-image IterableDataset finetuning failure is unrelated to PEFT-adapter local checkpoint loading." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and GraniteSpeech PEFT loading failure are distinct code paths." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Both are multimodal, but one is a Qwen3OmniMoe video-processing ValueError and the other is a Gemma 3n variable-name collision causing an AttributeError." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction bug is unrelated to add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Both are BitNet/DAC model issues, but one is about unpacking packed weights during accelerate loading and the other is DAC.from_latents not matching forward due to missing STE." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Completely different areas: image processor void segmentation maps vs a transformers.GenerationMixin import error." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "General input validation XOR messaging bug is not the same as the single-label-classification num_labels=1 zero-loss 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": 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-10000-403", + "nodes": [ + "issue:30064", + "issue:36331", + "issue:39692", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "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:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45381", + "issue:45584", + "issue:45685", + "issue:45834", + "issue:45987" + ], + "soft_pairs": [ + "issue:43618|issue:43697", + "issue:43653|issue:43720", + "issue:43335|issue:43756", + "issue:43295|issue:45834", + "issue:43716|issue:44008", + "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:43421|issue:44811", + "issue:43577|issue:43818", + "issue:43540|issue:45381", + "issue:43782|issue:44977", + "issue:44448|issue:44671", + "issue:45584|issue:45834", + "issue:39692|issue:45834", + "issue:44561|issue:45020", + "issue:44485|issue:44509", + "issue:44821|issue:45084", + "issue:30064|issue:36331", + "issue:43825|issue:43994" + ], + "prepared_review_unit_hash": "bad9cfe50f4027d92ca536d4150bb144eb49d6a6ece6e34252dd4c153ef84463", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36057, + "estimated_input_tokens": 9015, + "estimated_eval_tokens": 18286 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Loose cluster of Transformers regression reports and model-specific bugs. The soft pairs mostly share broad themes (v5 regressions, tokenizers, multimodal loading) but not the same concrete bug or code path, so none should be merged as duplicates.", + "confidence": 0.69, + "canonical_issue_reason": "issue:45020 is the broadest umbrella report here and best captures the cluster\u2019s general \u201crecent versions break remote_code models\u201d regression theme, even though the other issues are distinct specific bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 has the widest scope and is the most representative single issue for this mixed regression cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Both are v5 behavioral regressions, but one is a missing CLIP attentions output and the other is RT-DETR output drift; different model paths and fixes." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration vs BitNet packed-weight loading are unrelated bugs in different subsystems." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different model/config issues: sparse-layer creation in SwitchTransformers vs RoPE layer count mismatch in Smollm3." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Both concern multimodal processing, but one is processor/tokenizer API breakage and the other is long OCR input indexing in Kosmos2.5." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different models and failures: dtype mismatch in Mistral-3 image preprocessing vs a Gemma 3n attribute collision." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "One is torch.compile/SDPA on Bamba-9B-v2; the other is bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Different code paths: SDPA compilation failure vs DAC latent conversion not matching forward pass." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "Generic AddedToken argument conflict vs a specific model loading failure; no shared concrete bug." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Segfault while loading Llava Next is unrelated to an MPS histogram kernel missing for Int tensors." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Non-persistent buffer corruption during from_pretrained vs StaticCache returning the wrong type; different mechanisms." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2 tokenizer padding/NER crash and Perceiver image classification failure are separate model-specific bugs." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both touch _patch_mistral_regex, but one is an offline model_info call and the other is an AttributeError on backend_tokenizer; distinct failures." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE is unrelated to trust_remote_code config field loss." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "BigBird tokenizer special-token registration and DAC latent conversion are different bugs with no shared code path." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config/loading behavior, but one is missing fields from trust_remote_code and the other is strict config blocking granite_speech." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token post-processor updates vs Whisper batch_decode skip_special_tokens behavior are different tokenizer API issues." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing are unrelated multimodal model bugs." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both are video-related, but they affect different Qwen models and different failures (video input validation vs vision_position_ids)." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3VL from_pretrained weight_only error and Qwen3.5 flash-attention generation failure are different issues." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Distinct model regressions: Pegasus output drift vs CamemBERT masked-LM prediction errors." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription generation failure is unrelated to Kosmos2.5 long OCR input indexing." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "A broken SigLIP2 docs example is not the same bug as a Kosmos2.5 OCR index error." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "44561 is a specific remote_code break caused by removing is_torch_fx_available; 45020 is a broader umbrella report, not the same concrete bug." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "RoPE implementation discussion for GLM-5 and stale docs about removed pipeline tasks are different concerns." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "Loading AutoImageProcessor from URL and a template-node compilation TypeError are unrelated." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "ImageProcessor void segmentation maps and CustomTrainer.compute_loss argument mismatch are completely different bugs." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Wrong pipeline error message about translation tasks and nonsensical SigLIP2 outputs are separate issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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-10000-403", + "nodes": [ + "issue:34634", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:42175", + "issue:43262", + "issue:43329", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43644", + "issue:43650", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:44060", + "issue:44186", + "issue:44291", + "issue:44368", + "issue:44442", + "issue:44479", + "issue:44554", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44857", + "issue:44936", + "issue:44991", + "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:41720|issue:44991", + "issue:43644|issue:43749", + "issue:44186|issue:44442", + "issue:44479|issue:45834", + "issue:43606|issue:45072", + "issue:44805|issue:44936", + "issue:43825|issue:43827", + "issue:43577|issue:43582", + "issue:34634|issue:36010", + "issue:44671|issue:45701", + "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:43262|issue:43819", + "issue:43526|issue:43697", + "issue:43526|issue:44554", + "issue:34634|issue:36331", + "issue:45459|issue:45803", + "issue:45084|issue:45538", + "issue:43742|issue:45020", + "issue:43329|issue:45600" + ], + "prepared_review_unit_hash": "b822be1294093627d358262f328fbe3045fb09937c3f4db57f9a94d7ee011d34", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35509, + "estimated_input_tokens": 8878, + "estimated_eval_tokens": 18012 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most candidates are broad-similarity false positives (same subsystem or release, but different concrete bugs). Only the Qwen tied-weights warning reports look like the same underlying issue.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44060 is the clearest, most concrete report of the Qwen tied-weights warning bug; issue:44368 reads like a downstream duplicate/symptom of the same warning path.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44060 best captures the root bug with a specific mis-tie (`embed_tokens.weight` vs `linear_attn.dt_bias`) and broad enough scope to serve as the canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Different failures: Qwen3 auto device-map CUDA assert vs tokenizer import/load failure for est-roberta." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both concern v5 loading behavior, but one is non-persistent buffer corruption and the other is FSDP CPU RAM efficient loading; not the same bug." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer problems, but one is LayoutLMv2 NER/padding crashes and the other is AutoTokenizer loading FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Both are multimodal input bugs, but on different models and code paths (video regression vs OCR long-input index error)." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Device-mismatch CPU-offload bug for Bark vs bfloat16 dtype mismatch in different models." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Both are runtime errors, but one is a mask/tensor shape mismatch and the other is train-then-evaluate behavior." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Related to v5 pipeline removals, but one is an error message bug and the other is outdated docs; not the same concrete fix." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype persistence vs Apple Silicon caching allocator TypeError are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset issue is unrelated to the GenerationMixin import error." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT masked-LM regression and generic tokenization changes are not the same bug." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "OmDet-Turbo image-size mismatch vs dtype mismatch in other models." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Qwen VL load-time `weight_only` error vs still-image rope-index scaling bug are different paths." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to dtype mismatch." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Missing TensorFlow backend in install extras is unrelated to tokenizer regex patch crash." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both are tokenizer/processor crashes, but one is a Mistral regex patch bug and the other is a Gemma4Processor missing attribute." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both touch model loading, but one is FSDP CPU RAM efficient loading and the other is init_empty_weights argument mismatch." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "The titles are unrelated; one is a placeholder issue and the other is a reproduction of a different issue." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon warmup TypeError and CUDA float16 AMP crash are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": true, + "reason": "Same underlying tied-weights warning bug in Qwen3/Qwen3.5-family models; both report the incorrect warning path and should be fixed together." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio processor sampling-rate default bug vs DAC latent/forward mismatch are different issues." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Beit reduce_labels bug and RTDetrV2 output drift are different model-specific regressions." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and MPS attention correctness are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice preset failure is unrelated to CustomTrainer.compute_loss signature breakage." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both involve exception handling, but in different code paths and with different root causes; too broad to merge." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation TypeError and CLIPTokenizer max_length bug are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Specific MobileLLM key error is not the same as broad remote_code breakage." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Multimodal token counting bug and removed auto_mappings config references are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. Most soft-edge rejections are conservative and the reasons track distinct titles/subsystems. The single accepted Qwen pair is a plausible match based on the shared tied-weights warning theme. No clear overstatement beyond the available packet evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 17, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:43638", + "issue:43643", + "issue:43645", + "issue:43653", + "issue:43696", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44479", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45042", + "issue:45356", + "issue:45357", + "issue:45488", + "issue:45701", + "issue:45759", + "issue:45859" + ], + "soft_pairs": [ + "issue:43653|issue:44912", + "issue:43638|issue:44936", + "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:36010|issue:43645", + "issue:39692|issue:44912", + "issue:43257|issue:43329", + "issue:43550|issue:44912", + "issue:43720|issue:44610", + "issue:43257|issue:43696", + "issue:43454|issue:43577", + "issue:43531|issue:45042", + "issue:43329|issue:44479", + "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:34567|issue:40990", + "issue:43329|issue:43450", + "issue:44568|issue:45488", + "issue:43257|issue:43931", + "issue:43606|issue:45859", + "issue:44849|issue:45701", + "issue:43697|issue:45357" + ], + "prepared_review_unit_hash": "329319f65b49f5f036ae111771bbc3968d1117f6cc937d7c63ce6bc5d8536037", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36996, + "estimated_input_tokens": 9249, + "estimated_eval_tokens": 18754 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly unrelated and grouped by surface similarity. The 43329\u219444479 pair is only weakly related through multimodal/video vocabulary; the packet does not establish they are the same underlying bug or a mergeable shared fix.", + "confidence": 0.69, + "canonical_issue_reason": "issue:44479 is the best canonical issue because it captures the broader user-facing video-input regression across multiple Qwen VL variants. issue:43329 is narrower and may be adjacent, but the packet does not prove it is the same defect.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the strongest representative due to broader impact and clearer regression framing; issue:43329 is more specific and less well-supported as the root of the broader behavior.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: BigBird special-token registration vs MXFP4 quantization loading fallback." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Both are trainer failures, but the concrete breakages differ: ZeRO-3 indexing vs evaluate-after-train behavior." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading/tokenizer paths, but they point to different models and code paths." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "PEFT local-checkpoint loading and Whisper batch_decode special-token handling are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage lookup error is unrelated to PIL backend torchvision dependency checks." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Different model families and failure modes: zero probabilities vs image-size mismatch." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Generic model-load test failure vs flash-attention generation bug; no shared code-path evidence." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent reconstruction mismatch and DiaConfig save/load token-ID loss are distinct bugs." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import error and Jupyter custom-model initialization breakage are different regressions." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Documentation example errors are not the same bug as MXFP4 quantization loading fallback." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE weight conversion during accelerate+deepspeed loading is unrelated to a multimodal video-token helper bug." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile SDPA failure on Bamba is unrelated to git-oss quantization fallback behavior." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Packed-weight unpacking during loading and processor image-size mismatch are different issues." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "One is a loading/conversion bug, the other is an OOM problem; not the same underlying defect." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "Weight tying/generation garbage text and dtype propagation on BLIP2 are separate model-loading issues." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior is unrelated to PIL backend torchvision requirements." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Both mention multimodal/video handling, but the packet only shows surface overlap; it does not establish the same concrete code path or a mergeable shared fix." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio processor chat-template sampling-rate default and Whisper batch_decode skipping special tokens are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Trailing-slash local model warning is unrelated to Qwen3 MoE weight conversion/loading issues." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Importing GenerationMixin and custom compute_loss signature breakage are separate API regressions." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Tokenizer BOS/EOS handling and Kimi-K2.5 codec handling are different tokenizer regressions." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and Strix Halo mmap/OOM are different memory/loading problems." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading is unrelated to composite Qwen config unwrapping." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer token-count tracking and GPT-oss perplexity are unrelated training issues." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Video-token counting helper bug and batched video processor shape bug are different layers and not clearly the same defect." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "mdeberta special-token insertion and LlamaTokenizer pre-tokenizer override are distinct tokenizer regressions." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE loading/conversion bug and Qwen3-VL weight-shape mismatch are not the same issue." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "CPU-offload device mismatch for bark-small is unrelated to Qwen3_MoeTextRotaryEmbedding CPU-offload compatibility." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Hidden-state output bug and version-dependent tokenization change are not the same code-path problem." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetr output drift in v5 and Qwen3.5 visual-encoder save_pretrained keys are unrelated regressions." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary is mostly grounded, but it overstates the evidence for the 43329 \u2194 44479 link. The packet only shows surface overlap in multimodal/video processing; it does not establish that 43329 is the underlying helper bug behind 44479 or that they share the same code path in a mergeable way. The canonical/best-issue choice may be reasonable, but the wording should stay more 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": 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-10000-403", + "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:45042", + "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:44291|issue:45042", + "issue:44987|issue:45538", + "issue:42915|issue:43742", + "issue:42915|issue:44821", + "issue:33357|issue:34567", + "issue:43257|issue:43756", + "issue:41720|issue:43540", + "issue:44479|issue:45381", + "issue:43452|issue:43582", + "issue:44987|issue:45907", + "issue:42915|issue:45538", + "issue:43927|issue:44912", + "issue:42175|issue:43824", + "issue:43317|issue:45538", + "issue:43540|issue:44479", + "issue:43540|issue:44560", + "issue:44062|issue:44991", + "issue:42175|issue:44938", + "issue:43577|issue:45072", + "issue:38175|issue:44898", + "issue:42175|issue:44488", + "issue:43404|issue:45987", + "issue:45137|issue:45405", + "issue:28282|issue:34689", + "issue:43906|issue:45381", + "issue:43742|issue:44291", + "issue:42915|issue:43749", + "issue:44737|issue:45588", + "issue:43540|issue:45823", + "issue:43526|issue:45479", + "issue:28282|issue:29127", + "issue:43756|issue:45325", + "issue:43582|issue:43782" + ], + "prepared_review_unit_hash": "ce7a726130df70933c358c835abaddde8c47dfe69b84311926510a0df49db796", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37711, + "estimated_input_tokens": 9428, + "estimated_eval_tokens": 19112 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: many unrelated model-loading, packaging, dtype, and video-processing bugs were grouped by superficial similarity. The only strong duplicate-like pair is the Qwen2.5-VL / Qwen3-VL video-input regression pair.", + "confidence": 0.78, + "canonical_issue_reason": "issue 44479 is the broadest, most concrete report of the shared Qwen VL video-input regression, and it can naturally subsume the narrower qwen2.5-vl-specific report in 45381.", + "canonical_pr_reason": null, + "best_issue_reason": "issue 44479 is the best representative because it describes the regression at the right level of abstraction and covers multiple affected Qwen VL variants.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Different failures: unexpected _is_hf_initialized argument during init_empty_weights vs PIL image processors incorrectly requiring torchvision." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "One is a model load failure for a specific repo; the other is a tokenizer max_length constant issue." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Both involve loading, but they are different code paths and errors: Qwen3Moe FP8 config vs MobileLLM key error." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Unrelated problems: Qwen3Moe FP8 loading vs AutoImageProcessor failing to load from URL." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Bus error on MacOS CLIP loading is unrelated to TrainerState num_input_tokens_seen not updating." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different subsystems: Qwen3 MoE weights with accelerate/deepspeed vs Smollm3 RoPE layer selection." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Auto device map CUDA assert on A800 is not the same bug as Qwen3OmniMoe video ValueError." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "These describe the same Qwen VL video-input regression in 5.3.0; 45381 is a narrower instance of the broader bug reported in 44479." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Different failures: gguf_file loading breaks vs an Apple Silicon caching_allocator_warmup TypeError." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Specific model-loading regression vs a repo-files API forwarding bug; not the same underlying issue." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Qwen3Moe FP8 loading failure is unrelated to CLIPTokenizer's model_max_length constant." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig token IDs are lost on save/load, while git-oss-20b falls back from MXFP4 quantization." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Packaging/backend dependency issue vs missing Qwen2_5_VL class import; different problems." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "device_map auto/offload loading failure is unrelated to tokenizer max_length behavior." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Both are Qwen video-related, but the model families and failure modes differ; not enough evidence of the same bug." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Different Qwen video errors (ValueError vs StopIteration) and different model variants; not a clear duplicate." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "AddedToken special-kwarg TypeError is unrelated to tokenizer loading failure for EMBEDDIA/est-roberta." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Tensorflow backend packaging issue is not the same as Python 3.14 import/load failure." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both mention dtype, but one is BLIP2 dtype propagation and the other is bfloat16 inference mismatches in different models." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 zero probabilities and Perceiver non-default resolution failure are distinct model-specific bugs." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Dependency/backend packaging issue is unrelated to the cjvt/sleng-bert loading failure." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "lm_head weight tying bug and StaticCache get_seq_length return type bug are unrelated." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque IndexError is unrelated to the PEFT version bump problem." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Missing PyTorch ImportError and Llama 3.2 Vision model loading regression are different failures." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "An isolated reproduction of another issue is not enough to treat it as the same bug as the qwen2.5-vl video-position-id regression." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "KeyError while loading MobileLLM is unrelated to init_empty_weights passing an unexpected _is_hf_initialized argument." + }, + { + "left": "issue:43749", + "right": "issue:42915", + "accept": false, + "reason": "FSDP_CPU_RAM_EFFICIENT_LOADING regression is not the same as Qwen3Moe FineGrainedFP8Config failure." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU arange device bug is unrelated to flash_attention.py crashing on sink-less models." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Qwen3OmniMoe video ValueError and Gemma4 PLE device mismatch are different model-specific runtime errors." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to degenerate zero-loss sequence classification." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Missing PyTorch dependency error is unrelated to LayoutLMv3's box-information error message." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both involve RoPE/position handling, but they affect different models and different mechanics; not the same bug." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "AppleSilicon TypeError in warmup is unrelated to Qwen3VL from_pretrained weight_only=True failure." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the soft-edge judgments stay conservative: the only accepted pair, 44479/45381, is well-supported by the issue titles, while the rest are reasonably rejected as different bugs or insufficiently evidenced duplicates. The cluster-level heterogeneity summary is also consistent with the packet." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 19, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "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:44291|issue:44821", + "issue:44062|issue:45081", + "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:43452|issue:44843", + "issue:44514|issue:45290", + "issue:44466|issue:45005", + "issue:43295|issue:45356", + "issue:43452|issue:43577", + "issue:43819|issue:44811", + "issue:44936|issue:45823" + ], + "prepared_review_unit_hash": "4286c10dfb75180238aeb880b92e16b61ff6b3273d83460cfbeed60394065476", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36185, + "estimated_input_tokens": 9047, + "estimated_eval_tokens": 18350 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a mix of unrelated Transformers bug reports; only a couple of pairs look like true duplicates or near-duplicates. The strongest shared themes are SigLIP2 output regressions and tied-weights serialization issues.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 45920 is the broadest and most actionable representative: it is an open, current v5 regression affecting AutoTokenizer across multiple models, which makes it the best cluster anchor among otherwise heterogeneous reports.", + "canonical_pr_reason": null, + "best_issue_reason": "45920 is the best overall issue to keep: it is open, directly user-facing, and spans multiple affected models rather than a single niche symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Both report SigLIP2 producing incorrect outputs; one frames it as a HF-vs-JAX discrepancy and the other as nonsensical results via AutoModel/pipeline, which looks like the same underlying model bug." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Both are training-related regressions, but one is about TrainerState token counting and the other is a compute_loss signature change; different failures and code paths." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "These involve unrelated loading failures: init_empty_weights/_is_hf_initialized versus loading AutoImageProcessor from URL." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer issues, but one is AddedToken construction and the other is a Mistral regex/backend_tokenizer crash; not the same bug." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Different subsystems: Qwen3.5 save_pretrained visual key serialization versus global AutoTokenizer token-id regression." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both concern config handling, but the root causes differ: missing fields from trust_remote_code AutoConfig versus a specific Qwen3_5MoeVisionConfig field being dropped by strict parsing." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading complaints, but gguf_file breakage and a specific cjvt/sleng-bert load failure do not point to the same code-path." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Both are multimodal model failures, but they affect different models and symptoms; not enough to treat as one bug." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "PIL/torchvision backend requirements are unrelated to the Mistral tokenizer AttributeError." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "Different loading errors: a key error for MobileLLM versus missing Float8 storage object." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to AutoImageProcessor URL loading." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "These are unrelated CI/dependency/config-reference issues." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different regressions: RTDetrV2 output mismatch versus Qwen3.5 checkpoint saving correctness." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are distinct problems." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL issues, but one is chat-template batching and the other is video vision_position_ids; different code paths." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "A save_pretrained sharding-size question is unrelated to AutoProcessor kwargs forwarding." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight loading and Perceiver image classification failures are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed ZeRO-3 Gemma3 loading and trainer.evaluate-after-train failures are separate issues." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "One is a DeepSpeed training RuntimeError; the other is a LayoutLMv3 error-message clarity issue." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "num_labels propagation in Qwen3.5 and strict config blocking granite_speech are different configuration bugs." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file loading breakage and offline mistral-regex model_info calls are unrelated tokenizer/loading bugs." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both are apply_chat_template crashes, but the triggers differ substantially: batched padding=False versus assistant tool-call messages with no content." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": true, + "reason": "Both point to tied-weights serialization problems in v5; the device-dependent lm_head.weight behavior and translation-model tied-weight breakage are plausibly the same save_pretrained bug." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Processor/tokenizer access regressions and Kimi-K2.5 codec/fix_mistral_regex issues are different tokenizer bugs." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC from_latents/STE mismatch and Whisper batch_decode skip_special_tokens handling are unrelated." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Trainer evaluate failure and Gemma4 device mismatch during forward are separate runtime issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The canonical issue choice is supported by the packet: 45920 is open, user-facing, and spans multiple models under a single AutoTokenizer v5 regression. The two accepted soft pairs are plausible duplicates/near-duplicates based on titles alone, and the rejected pairs are mostly appropriately cautious. I don\u2019t see material overstatement." + }, + "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-10000-403", + "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:43504", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "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:45491", + "issue:45588", + "issue:45701", + "issue:45704", + "issue:46002" + ], + "soft_pairs": [ + "issue:38175|issue:43295", + "issue:30064|issue:33666", + "issue:44464|issue:44743", + "issue:43653|issue:44361", + "issue:44361|issue:44442", + "issue:43643|issue:44561", + "issue:43653|issue:44568", + "issue:41720|issue:43906", + "issue:43688|issue:45440", + "issue:43688|issue:45704", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:45491|issue:46002", + "issue:43577|issue:43697", + "issue:28282|issue:35141", + "issue:44843|issue:44991", + "issue:43688|issue:45701", + "issue:43646|issue:43749", + "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:43577|issue:44554", + "issue:43122|issue:43906", + "issue:43577|issue:45588", + "issue:43504|issue:43550", + "issue:32090|issue:34567", + "issue:41720|issue:44464", + "issue:43504|issue:43720", + "issue:43504|issue:44610", + "issue:32090|issue:33666", + "issue:43452|issue:44451", + "issue:43742|issue:44821", + "issue:43278|issue:43688" + ], + "prepared_review_unit_hash": "de34865d7e6df05cc33f45c023f0045a527f78b8661131f50d118943e5d080b1", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38481, + "estimated_input_tokens": 9621, + "estimated_eval_tokens": 19498 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is largely heterogeneous. A few items share a broad tokenizer/regression theme, but none of the soft pairs appear to be the same underlying bug or change, so all soft edges are rejected.", + "confidence": 0.86, + "canonical_issue_reason": "Issue #45701 is the broadest, most umbrella-like report in the set: it explicitly centers on version-dependent tokenization changes, which is the only recurring theme spanning multiple nearby issues.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45701 is the best representative issue for this cluster because it is the most general tokenization-regression report and has inbound attention, even though the cluster is too mixed to collapse into one duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Unrelated failures: SigLIP2 zero probabilities vs custom model init/processor.tokenizer regression." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Different domains and bugs: void segmentation maps vs Qwen2-VL multi-GPU training." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both are Qwen-related, but one is compiled-forward chunked generation inconsistency and the other is recurrent-state reset in modular code; different code paths." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Tokenizer issues, but different models and symptoms: BigBird special-token registration vs MLuke task AttributeError." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer loaders and different exceptions; no clear shared underlying bug." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "One is missing fields from trust_remote_code config loading; the other is a v5.0 API removal breaking trust_remote_code models." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both involve special tokens, but they affect different tokenizers and different behaviors (decode output vs BOS/EOS addition)." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "No concrete overlap: Qwen3 A800 cudaErrorAssert vs an isolated reproduction of a different issue." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "MoE-related but different defects: auxiliary-loss normalization vs divergence from the remote DeepSeekV3 implementation." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Completely different bugs: MoE loss normalization vs T5/apex RMSNorm memory leak." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "ImportError for missing PyTorch vs Trainer NoneType broadcast error; unrelated." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Missing PyTorch ImportError vs MacOS bus error in CLIP loading; unrelated." + }, + { + "left": "issue:45491", + "right": "issue:46002", + "accept": false, + "reason": "Both mention NaNs, but the trigger and code path differ: sliding-window/all-padding embeddings vs classification-head NaNs after checkout/init." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Different model families and failures: BLIP2 dtype propagation vs RTDetrV2 output divergence." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but one is an offline model_info call in _patch_mistral_regex and the other is a specific tokenizer load failure." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Different defect types: auxiliary-loss normalization vs broad tokenization version-change report." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Custom model initialization breakage vs FSDP CPU RAM efficient loading; different subsystems and bugs." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Both are token-related, but one is special-token registration and the other is config loss of custom token IDs; not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding-window issue vs MobileLLM pretrained load KeyError; unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile + SDPA failure vs token-ID persistence/config bug; unrelated." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both affect generation, but one is compiled-forward chunked generation inconsistency and the other is a flash-attention regression in Qwen3.5." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "torch.compile/SDPA bug vs tokenizer AttributeError; unrelated." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype propagation vs an MPS attention correctness issue; different models and failure modes." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Version-dependent tokenization change vs isolated reproduction of a different issue; no shared underlying bug." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Dtype propagation bug vs flash_attention crash on s_aux=None; unrelated." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Pretrained load legacy-field issue vs Bamba torch.compile/SDPA failure; unrelated." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast TypeError vs TrainerState counter not updating; different training bugs." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Qwen3 auto device mapping assert vs chunked generation inconsistency under compile; different problems." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Legacy-field model loading bug vs BitNet packed-weight unpacking issue; different code paths." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Pretrained-load legacy field vs processor/model input-size mismatch; unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast NoneType error vs Qwen2-VL multi-GPU training request; unrelated." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both are load failures, but one is gguf_file breaking AutoTokenizer/AutoModel loading and the other is a specific tokenizer load regression for ScandiBERT." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Different loading failures: MobileLLM KeyError vs AutoImageProcessor-from-URL problem." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Embedding dtype drift in evaluate vs MoE auxiliary-loss normalization; 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": 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-10000-403", + "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:43825", + "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:45759", + "issue:45803", + "issue:45812", + "issue:45823", + "issue:45987", + "issue:46002" + ], + "soft_pairs": [ + "issue:33666|issue:36010", + "issue:44849|issue:45357", + "issue:43525|issue:43572", + "issue:43606|issue:43927", + "issue:43493|issue:43825", + "issue:43262|issue:43295", + "issue:43720|issue:43927", + "issue:43756|issue:44913", + "issue:44568|issue:45812", + "issue:44625|issue:46002", + "issue:28218|issue:33357", + "issue:43720|issue:44361", + "issue:33666|issue:36331", + "issue:39692|issue:43493", + "issue:43540|issue:44977", + "issue:44964|issue:45405", + "issue:43334|issue:43572", + "issue:43493|issue:43844", + "issue:45803|issue:45987", + "issue:43278|issue:43844", + "issue:43756|issue:45083", + "issue:43334|issue:45759", + "issue:43257|issue:43299", + "issue:45200|issue:45229", + "issue:44488|issue:44843", + "issue:39692|issue:43295", + "issue:43824|issue:44589", + "issue:43646|issue:44466", + "issue:45229|issue:45823", + "issue:43504|issue:43606", + "issue:43572|issue:44291", + "issue:33357|issue:33666" + ], + "prepared_review_unit_hash": "5b61a481dadd4dd1b07afc58f09abcd9d5c741e48a2836f9f23212ba73a7f6bf", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37566, + "estimated_input_tokens": 9392, + "estimated_eval_tokens": 19040 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated standalone bug reports. None of the soft pairs look like the same concrete underlying defect, so I would not merge any of them as duplicates. The strongest canonical issue candidate is the Granite tokenizer regression because it is broad, clearly framed, and has the most evidence of reuse.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45812 is the broadest and most central report here: it describes a silent tokenizer regression across all Granite models and already has inbound references, making it the best candidate to anchor related reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the best global issue representative because it is specific enough to reproduce, broad enough to absorb nearby tokenizer reports, and appears to be the highest-signal open regression in the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Both are ML import/training problems, but one is Qwen2-VL multi-GPU training and the other is a GenerationMixin import error; different failure modes and code paths." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Both mention Qwen3.5, but one is an output_hidden_states bug and the other is incorrect save_pretrained visual encoder keys; not the same fix." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both are missing pad token config fields, but for different models and different attributes (pad_token_id vs pad_token_idx); too model-specific to be one bug." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "One is a device mismatch with CPU offload, the other is a config/token-ID loss causing generation IndexError; unrelated underlying defects." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation mismatch vs. a pipeline error-message regression; different subsystems and fixes." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat template sampling-rate default and processor.tokenizer regression are both multimodal API issues, but they affect different paths and are not the same bug." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to DiaConfig custom token ID persistence." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Smollm3 RoPE layer count bug and GPTNeoX rotary_pct reload regression involve different config fields and models." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both concern tokenization behavior, but one is BOS/EOS not being added for mdeberta-v3-base while the other is Granite token IDs being wrong across models; not the same defect." + }, + { + "left": "issue:44625", + "right": "issue:46002", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and NaNs in classification heads are different symptoms with different root causes." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer spacing after added tokens is unrelated to a MacOS bus error loading a CLIP model." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight loading for BitNet AutoBitLinear is unrelated to MLukeTokenizer task AttributeError." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL and a CustomTrainer.compute_loss signature break are separate training issues with different fixes." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "SigLIP2 docs example errors are documentation/example problems; the other is a model implementation discrepancy." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3OmniMoe video input processing and Qwen3.5 flash-attention generation issues are different code paths." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal and an unreleased PEFT version pin are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both are pad-token related, but one is Qwen3-VL missing pad_token_id on config and the other is StableLmConfig missing pad_token_idx after v5; not one shared bug." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch and ZeRO-3 gradient growth are distinct numerical/training issues." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except in Fuyu tensor conversion and StaticCache.get_seq_length return-type bug are unrelated API/safety issues." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift during evaluate and abnormal gradient growth under ZeRO-3 are different symptoms and fixes." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "RoPE-layer dropping in Smollm3 and qwen3_omni_moe feature-extract length behavior are unrelated model internals." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3-VL pad_token_id absence and AutoModelForCausalLM.from_config not unwrapping text_config are different multimodal config problems." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Qwen3 MOE weight conversion during accelerate/deepspeed loading and Qwen3VL Moe loading breakage are similar only at a family level, but not the same concrete bug." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Gemma4 mm_token_type_ids defaulting and Gemma4 multi-GPU CUDA OOM are not the same underlying issue." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "A model failing to load and an offline-mode failure in _patch_mistral_regex stem from different causes." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "SigLIP2 docs errors and processor.tokenizer regression are both multimodal, but one is an example mismatch/quantization issue and the other is a runtime API regression." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Importing a missing Qwen2.5-VL class and missing Float8 storage support are unrelated import/type issues." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage and inconsistent lm_head.weight serialization are different model lifecycle bugs." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 multi-GPU OOM and PLE device mismatch during forward are different runtime resource problems." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "BEiT legacy-field loading failure and bark-small CPU-offload device mismatch are unrelated model-loading bugs." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "StableLmConfig missing pad_token_idx and init_empty_weights rejecting _is_hf_initialized are separate compatibility regressions." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "A MacOS bus error loading CLIP and Qwen2-VL multi-GPU training are wholly 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": 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-10000-403", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29942", + "issue:30333", + "issue:34567", + "issue:37428", + "issue:38175", + "issue:42490", + "issue:43232", + "issue:43278", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43575", + "issue:43582", + "issue:43606", + "issue:43653", + "issue:43696", + "issue:43701", + "issue:43844", + "issue:43927", + "issue:43957", + "issue:43994", + "issue:44112", + "issue:44315", + "issue:44361", + "issue:44423", + "issue:44464", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44589", + "issue:44734", + "issue:44792", + "issue:44849", + "issue:44964", + "issue:44977", + "issue:45072", + "issue:45084", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45405", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45823" + ], + "soft_pairs": [ + "issue:44589|issue:45520", + "issue:43927|issue:44361", + "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:29942|issue:30333", + "issue:42490|issue:43696", + "issue:44521|issue:45290", + "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:37428|issue:43957", + "issue:45072|issue:45198", + "issue:45200|issue:45823", + "issue:44315|issue:44849", + "issue:43493|issue:43701" + ], + "prepared_review_unit_hash": "fd6be3534eeb26b48acf08a7a4c17a3e56164cf8e5002c49071a5bb07744888d", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 34877, + "estimated_input_tokens": 8720, + "estimated_eval_tokens": 17696 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: most items are unrelated bug reports that only share broad subsystem words (tokenization, generation, flash-attn, device/dtype, serving). None of the soft pairs look like the same underlying bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Both are import/runtime failures, but they affect different symbols and failure modes; not the same bug." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "One is config save/load causing generation index errors; the other is a tokenizer AttributeError in tasks." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both involve serve, but one crashes on multimodal input conversion and the other on KV-cache continuation indexing." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Different components and symptoms: BEiT legacy-field loading vs BigBirdTokenizer special-token registration." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Both are generation-related, but one is compiled forward inconsistency and the other is empty-transcription/chat-template behavior." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Different models and code paths; one is CPU offload device mismatch, the other is a stale CI test override." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Different bugs: SigLIP2 wrong outputs vs a broad position-id key warning across many models." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "OOM during tensor-parallel model load is unrelated to a PEFT version requirement issue." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "Embedding dtype drift and checkpoint key mismatch are unrelated training/eval issues." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A janus image-generation test failure is unrelated to the PEFT version bump." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "FlashAttention test failures and MLFlow reporting on failed jobs are different subsystems and failures." + }, + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Import warning on trailing-slash paths is unrelated to a GPT-oss OOM." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both are apply_chat_template issues, but one is multimodal assistant masks and the other is tool-call content handling." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient growth and Phi-4 multimodal loading are unrelated problems." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing after added tokens is unrelated to TrainerState token-count tracking." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "Different flex-attention/MPS correctness and version-check issues; no shared code-path bug." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Compile-time node handling and flash-attn import lookup are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention output issues are different failures." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing in Qwen3OmniMoe is not the same as Gemma 4 token-type defaults for text-only fine-tuning." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure and SigLIP2 zero-probability outputs are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is a different bug from Qwen3.5 hidden-states behavior." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Missing flash-attention helper import and meta-device model-loading breakage are distinct issues." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "Bfloat16 dtype mismatches and Wav2Vec2 save/tokenization failures do not share the same underlying bug." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Token-type-id defaults and Gemma4 PLE device mismatch are different problems." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applied with model_init is unrelated to Qwen3.5 output_hidden_states behavior." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 JAX/HF discrepancy and resume-from-checkpoint key mismatch 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-10000-403", + "nodes": [ + "issue:28218", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:42490", + "issue:42915", + "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:44554", + "issue:44610", + "issue:44792", + "issue:44898", + "issue:44936", + "issue:44987", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45245", + "issue:45325", + "issue:45356", + "issue:45412", + "issue:45563", + "issue:45584" + ], + "soft_pairs": [ + "issue:43295|issue:44610", + "issue:44554|issue:45356", + "issue:44898|issue:45412", + "issue:44466|issue:45127", + "issue:43572|issue:44987", + "issue:44792|issue:45563", + "issue:37428|issue:43824", + "issue:43572|issue:43957", + "issue:45200|issue:45325", + "issue:43295|issue:43450", + "issue:43844|issue:44936", + "issue:43334|issue:43525", + "issue:43824|issue:43975", + "issue:43295|issue:43873", + "issue:43388|issue:43526", + "issue:42915|issue:43824", + "issue:38175|issue:45412", + "issue:38175|issue:43493", + "issue:44514|issue:44521", + "issue:44442|issue:45198", + "issue:28218|issue:35141", + "issue:42490|issue:43493", + "issue:43278|issue:43856", + "issue:43653|issue:44112", + "issue:43450|issue:43575", + "issue:43827|issue:43901", + "issue:44206|issue:45584", + "issue:45127|issue:45245", + "issue:43819|issue:45083" + ], + "prepared_review_unit_hash": "9cb2039c1dd20c5ddd9fb136ad8c12400b4491ed915f9e424b458496ef22e61d", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36673, + "estimated_input_tokens": 9169, + "estimated_eval_tokens": 18594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These soft edges are mostly false positives: they share broad subsystem or model-family overlap, but not the same concrete bug. No PRs are present. The set is heterogeneous overall, with no strong duplicate cluster.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 44521 is the closest thing to a cluster anchor because it is open, recent, and has the highest user-facing activity among the remaining items, but the surrounding issues are too heterogeneous to treat it as a true canonical duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "44521 is the best overall representative only in the loose sense of being the most active, general multimodal regression here; it is not a valid dedup target for the other items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Both are multimodal processor regressions, but one is a processor.tokenizer/image-handling regression and the other is a video/input-size mismatch; different code paths and fixes." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "One is an MPS attention correctness bug; the other is a tokenizer codec/warning regression. No shared underlying defect." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver interpolation failure and RT-DETR memory release are unrelated bugs in different models/subsystems." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both involve tied/serialization semantics, but one is inconsistent lm_head serialization by device and the other is LoRA merge collapse after vocab extension; not the same fix." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Both are model-loading regressions, but the reported symptoms and likely causes differ; too little evidence they are the same bug." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure and a stale paged-generate warning are distinct generation issues." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are ImportErrors, but for different missing symbols in different modules; not the same underlying import breakage." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "One is a missing pad_token_idx config regression; the other is a meta-device model-loading failure affecting some models. Not the same bug." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma 4 mm_token_type_ids defaulting and Qwen2.5-VL rope-index scaling are separate model-specific correctness issues." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Both touch processors, but one is about processor.tokenizer/image routing and the other is batched video output shape; different defects." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "Gradient explosion under ZeRO-3 and evaluate() failing after train() are not the same training-state problem." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Same symptom class (missing pad_token_id), but different config classes/models and no evidence of a shared root cause." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "An import error for Qwen2.5-VL and a detokenization regression in DeepSeek Coder are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor-tokenizer regression vs quantization offloading behavior; too different to merge." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both concern labels, but one drops tuple label elements in gather_for_metrics while the other reduces labels incorrectly in an image processor; not the same path." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "FP8-config failure in Qwen3MoE and a Qwen2.5-VL import error are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero-probability behavior and RT-DETR memory cleanup are entirely different bugs." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Both are SigLIP2-related, but one reports zero probabilities and the other a broader HF-vs-JAX discrepancy; not enough to treat as the same concrete bug." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Same processor family and similar API surface, but one is a batched padding=False crash and the other is zero assistant masks for multimodal inputs; different failure modes." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizer/model families and different failure modes: loading FastSpeech2ConformerTokenizer vs save_pretrained/tokenization failures in Wav2Vec2." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing after added tokens and embedding reinitialization after resize are separate tokenizer/model-weight bugs." + }, + { + "left": "issue:42490", + "right": "issue:43493", + "accept": false, + "reason": "Path-with-trailing-slash import warning and SigLIP2 implementation discrepancy are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Training/eval dtype drift and Qwen3 MoE memory inefficiency are different problems." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and a GraniteSpeech CI device-override test failure do not share the same bug." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batched video processor shape bug and tensor-parallel OOM while loading a large model are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs regressions about pipelines, but they refer to different pipeline APIs and deprecations; not duplicates." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported center argument in a feature extractor and Whisper empty-transcription failure after align_special_tokens are different audio bugs." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA/tied-weights collapse after vocab extension is unrelated to the 2^24 category limit runtime error." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent/STE mismatch and qwen3_omni_moe feature-length helper behavior are unrelated 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": 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-10000-403", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:43262", + "issue:43278", + "issue:43335", + "issue:43425", + "issue:43450", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43825", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44292", + "issue:44351", + "issue:44360", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44610", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:45072", + "issue:45083", + "issue:45200", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45520", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:43262|issue:43450", + "issue:43819|issue:44112", + "issue:44610|issue:44857", + "issue:37428|issue:43425", + "issue:43335|issue:43550", + "issue:43606|issue:45083", + "issue:45290|issue:45381", + "issue:44448|issue:44743", + "issue:44857|issue:45593", + "issue:45200|issue:45588", + "issue:43278|issue:43825", + "issue:37428|issue:44351", + "issue:44360|issue:44561", + "issue:29942|issue:32090", + "issue:44206|issue:45823", + "issue:43611|issue:43931", + "issue:39692|issue:43526", + "issue:43335|issue:43653", + "issue:43819|issue:44493", + "issue:43550|issue:44112", + "issue:43335|issue:43504", + "issue:44855|issue:45083", + "issue:45310|issue:45478", + "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:43335|issue:44112", + "issue:44462|issue:44561", + "issue:44561|issue:44779", + "issue:43720|issue:44112" + ], + "prepared_review_unit_hash": "6fd9d30c8f8c0aeffc2e20a26b81b7d0f1cead8db6e9f43239e1f0011357da02", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37677, + "estimated_input_tokens": 9420, + "estimated_eval_tokens": 19096 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly unrelated issue reports; there is one clear duplicate pair: the Qwen3.5 MoE `from_pretrained` regression in issue:45310 and issue:45478. The rest share broad subsystem keywords but describe different bugs/code paths.", + "confidence": 0.95, + "canonical_issue_reason": "issue:45310 is the earlier, fuller report of the same Qwen3.5 MoE `from_pretrained` regression; issue:45478 is a near-identical follow-up.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best canonical anchor because it captures the duplicated bug clearly and predates the later duplicate report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Different processors and failures: audio chat template sampling-rate default vs batched video shape bug." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "Different models and code paths: DAC latent/STE mismatch vs GraniteSpeech CI device override test." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Different components and symptoms: processor input size mismatch vs LwDetr loss AMP crash." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "One is an import error for a flash-attn helper; the other is broad Torch 2.10 compatibility." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "Different model families and bugs: SwitchTransformers config layer creation vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch for Bark vs a helper length-calculation bug in qwen3_omni_moe." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Different failures: chat template with tool calls vs Qwen2.5-VL video position IDs." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output regression is unrelated to Qwen recurrent-state reset logic." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "Different training-time failures: float16 AMP crash in LwDetrImageLoss vs missing auxiliary losses in D-FINE." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 `mm_token_type_ids` defaulting issue is unrelated to flash_attention `s_aux=None` crash." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift during evaluate is not the same as the v5 pipeline translation-task error message bug." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and causes (`_flash_supports_window_size` vs `HybridCache`)." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer ReLU discussion is unrelated to removal of `is_torch_fx_available` breaking trust_remote_code models." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and Trainer `_gpu_broadcast_one` NoneType errors are different issues." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Unsupported `center` arg in LasrFeatureExtractor is unrelated to Gemma4 PLE device mismatch under `device_map=\"auto\"`." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Generic `base_model_prefix` loading breakage is not the same as Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 docs/model mismatch and quantization failure is unrelated to BeitImageProcessorFast `reduce_labels` truncation." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to BigBirdTokenizer mask-token decode behavior." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC forward/latent mismatch is unrelated to the position-id key issue affecting many models." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba torch.compile SDPA failure is unrelated to the GraniteSpeech CI stale device override test." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers layer-count config bug is unrelated to Beit pretrained preset loading with legacy fields." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 `IndentationError` in DebertaV2 import is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same Qwen3.5 MoE `from_pretrained` regression, with matching title and failure mode." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation is unrelated to the bfloat16 dtype mismatch in inference." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 box-clarity error message and Trainer `_gpu_broadcast_one` TypeError are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both involve Qwen3_5/MoE/offload, but one is a flash_attention `s_aux=None` crash and the other is a rotary-embedding CPU-offload incompatibility." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 docs/quantization issue is unrelated to the position-id key regression." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime failure is not the same as the Python 3.13 `flash_attn` import KeyError." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output differences and DeepSeek tokenizer regressions are different bugs." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 zero-probabilities bug is unrelated to the position-id key regression." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Same as the other SwitchTransformers/dtype pair: unrelated bugs in the same broad area." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "SwitchTransformers config bug and GraniteSpeech CI device override test are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer.json loading behavior and `is_torch_fx_available` removal are unrelated regressions." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Trust-remote-code breakage from helper removal is unrelated to DeepSeek tokenizer output changes." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet accelerate unpacking bug is unrelated to the GraniteSpeech stale device override test." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The one accepted duplicate pair (issue:45310 / issue:45478) is well-supported by matching titles and the same Qwen3.5 MoE from_pretrained regression, and the rest of the soft-edge rejections are phrased cautiously without overstating evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:10000", + "issue:15354", + "issue:28218", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:40444", + "issue:41720", + "issue:42490", + "issue:43278", + "issue:43329", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43701", + "issue:43723", + "issue:43854", + "issue:43873", + "issue:43927", + "issue:43976", + "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:44977|issue:45229", + "issue:42490|issue:43854", + "issue:40444|issue:43526", + "issue:34689|issue:35141", + "issue:44448|issue:44977", + "issue:43606|issue:44857", + "issue:43723|issue:44554", + "issue:44857|issue:45072", + "issue:28218|issue:32090", + "issue:44977|issue:45563", + "issue:43927|issue:45698", + "issue:43701|issue:45083", + "issue:44568|issue:45491", + "issue:43550|issue:45083", + "issue:37428|issue:44987", + "issue:45198|issue:45803", + "issue:29942|issue:35141", + "issue:45372|issue:45588", + "issue:43873|issue:44493", + "issue:32090|issue:33357", + "issue:45459|issue:45712", + "issue:43873|issue:45229", + "issue:45245|issue:45563", + "issue:43412|issue:45588", + "issue:43278|issue:43329", + "issue:41720|issue:45229", + "issue:10000|issue:15354", + "issue:43976|issue:45440", + "issue:42490|issue:43575", + "issue:45372|issue:45406" + ], + "prepared_review_unit_hash": "6c1dda20d1cfded88b308eefeb07a2750a3a65dde9cac36b07ff6983183be230", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36341, + "estimated_input_tokens": 9086, + "estimated_eval_tokens": 18428 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very heterogeneous: most items are unrelated issues spanning tokenization, model loading, precision/device-mismatch, attention kernels, and multimodal processor bugs. None of the soft-edge pairs look like true duplicates of the same underlying bug/change.", + "confidence": 0.95, + "canonical_issue_reason": "Issue #42490 is the clearest generic loading-path bug in the set, with a reproducible and narrowly scoped root cause (local model path normalization trailing slash).", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #42490 is a good representative because it is a concrete, user-facing loading regression with a clear failure mode and likely straightforward fixability.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Different failure modes and subsystems: flash-attention generation behavior vs multi-GPU CUDA OOM." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Both are loading-related, but one is a path-trailing-slash warning and the other is a specific model-load failure for a named checkpoint." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Unrelated areas: multimodal iterable dataset finetuning vs BeitImageProcessorFast label reduction." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading regression vs token-embedding resize/post-init reinitialization; not the same bug." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different models and errors; Pegasus output drift across versions is not the same as Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch is a different concrete bug than float16 AMP crashes in LWDETR loss." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are unrelated code paths." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "Both mention dtype/precision, but they affect different models and different execution paths; not one bug." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer spacing after added token is unrelated to Trainer broadcast TypeError." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation failure vs a stale warning in paged generate(); different underlying issues." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load flows, but one loses custom token IDs in config and the other loads the wrong custom module; distinct defects." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint key mismatch is unrelated to the qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token handling and Gemma3 NaN embeddings are different bugs." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA failure for Bamba is unrelated to qwen3_omni_moe feature-length computation." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "Both are load-time issues around flash attention, but the concrete failures and target code paths differ." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure and a bare-except swallowing errors in Fuyu are not the same defect." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization after resize." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 processor loading fails due to a missing dependency import, while the other is a flash-attention AttributeError on sink-less models." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior and unexpected position-id keys are distinct problems." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast NoneType error is unrelated to a MacOS bus error with a CLIP model." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer protobuf error handling and leftover dummy classes are unrelated repository hygiene/runtime issues." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization offloading behavior is not the same as a multi-GPU OOM during Gemma4 inference." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-cardinality limit error and stale generate warning are unrelated." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export failures and flash-attention sinkless-model AttributeError are different code paths." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype drift in evaluation is unrelated to the undefined video-branch helper issue." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Auto device mapping cudaErrorAssert and CUDA OOM are different failure classes." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBert issue and torch.jit generator-expression export issue are unrelated and very old." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility issue is unrelated to DeepSeekV3MoE divergence from remote implementation." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "Local-path loading warning is unrelated to tensor-parallel OOM on a large Qwen model." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Gemma4 processor import failure and Gemma4Processor missing _tokenizer in serve are different concrete 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": 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-10000-403", + "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:43065|issue:43994", + "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:25251|issue:32090", + "issue:44206|issue:44479", + "issue:43994|issue:45412", + "issue:44186|issue:45198", + "issue:43066|issue:44462", + "issue:44361|issue:45198", + "issue:44451|issue:45520", + "issue:42915|issue:42994", + "issue:44871|issue:44977", + "issue:44265|issue:45198", + "issue:43756|issue:45440", + "issue:29942|issue:30064", + "issue:43421|issue:45491", + "issue:33357|issue:39692", + "issue:43257|issue:43278", + "issue:29127|issue:34567", + "issue:32090|issue:33290", + "issue:42490|issue:43873", + "issue:44610|issue:45412", + "issue:45440|issue:45593" + ], + "prepared_review_unit_hash": "8f232ed4bae1f726392dbc8e96089e6056012ec297a05f53016c5f5789bc8f1b", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35789, + "estimated_input_tokens": 8948, + "estimated_eval_tokens": 18152 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are a broad mix of unrelated tokenizer, loading, training, quantization, and vision bugs. The soft pairs mostly share only broad subsystem overlap, so none look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Different models and failure modes: Sam3PixelDecoder dummy Conv2d vs SigLIP2 bad AutoModel/pipeline output." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Tokenizer spacing bug vs LayoutLMv3 error-message clarity issue; unrelated root causes." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Sam3PixelDecoder placeholder layer is unrelated to RT-DETR memory not being released." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor import failure and protobuf error masking are separate tokenizer-loading problems." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "LwDetr float16 AMP crash is unrelated to flash-attention s_aux=None handling." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Both are v5 regressions, but one is generation-output drift and the other is tied-weight serialization inconsistency." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token decode bug is unrelated to Qwen recurrent-state reset logic." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Both involve Gemma-related code, but one is a flash-attention AttributeError and the other is a device-map forward mismatch." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Eval-mode dtype change and gradient-checkpointing-in-eval are distinct issues." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nesting regression is unrelated to Trainer NoneType broadcast failure." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported feature arg in LasrFeatureExtractor does not match the Qwen video-input regression." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 inference regression is unrelated to RT-DETR memory cleanup." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 tokenizer NER/padding crash and Wav2Vec2 save/tokenization failure are different code paths." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Wrong tokenizer decoder type and ignoring tokenizer.json are separate tokenizer-loading behaviors." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLuke tokenizer AttributeError is unrelated to Wav2Vec2 save_pretrained/tokenization failure." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model load failure for ScandiBERT and flash_attn KeyError on Python 3.13 are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and quantized-model saving failure are both quantization-related but different bugs." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "EOS config mismatch and flash-attention generation regression are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failure with torch_compilable_check is unrelated to Wav2Vec2 save/tokenization problems." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Different model implementations and defects: RoPE-layer drop vs DeepseekV3MoE divergence." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to void segmentation map processing." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime post-processor update bug and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error on CLIP model load is unrelated to SigLIP2 documentation-example mistakes." + }, + { + "left": "issue:43257", + "right": "issue:43278", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed is unrelated to BF16-to-FP32 eval dtype drift." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and TrainerState token counter updates are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer broadcast TypeError and Adafactor+deepspeed OOM are distinct training issues." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Trailing-slash local model import warning is unrelated to quantization offloading behavior." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR memory retention." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepseekV3MoE implementation divergence and D-FINE auxiliary-loss omission are different 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": 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-10000-403", + "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:43761", + "issue:43824", + "issue:43931", + "issue:44062", + "issue:44077", + "issue:44079", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44625", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44977", + "issue:45003", + "issue:45072", + "issue:45103", + "issue:45245", + "issue:45372", + "issue:45440", + "issue:45491", + "issue:45584", + "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:43381|issue:43701", + "issue:45103|issue:45372", + "issue:29942|issue:36010", + "issue:43526|issue:44186", + "issue:29127|issue:33357", + "issue:43334|issue:43531", + "issue:44625|issue:45584", + "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:43575|issue:43701", + "issue:44743|issue:44811", + "issue:43441|issue:45588", + "issue:43232|issue:43388", + "issue:43646|issue:44077", + "issue:43761|issue:44079", + "issue:43575|issue:44387", + "issue:45003|issue:45440" + ], + "prepared_review_unit_hash": "cd69876bda4584e3eae62d9a3a1df6bfda0eb8b70d8926057462ec7ad151d05b", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36134, + "estimated_input_tokens": 9034, + "estimated_eval_tokens": 18324 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a heterogeneous mix of unrelated Transformers issues (imports, generation, tokenizer/image processor bugs, flash-attention, model-specific regressions). I don\u2019t see a single underlying bug or change that ties them together strongly enough to pick one canonical representative or merge any soft-edge pair.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "One is a specific missing export for `Qwen2_5_VLForConditionalGeneration`; the other is a vague dependency/loading problem with no shared code-path evidence." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-related, but they affect different models and different failure modes (`BigBirdTokenizer` special-token registration vs `AutoTokenizer` loading `FastSpeech2ConformerTokenizer`)." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "Different model families and bugs: CLIPVision hidden-states regression vs Qwen3_5 MoE rotary embedding CPU-offload incompatibility." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BEiT image processor label reduction bug is unrelated to Kosmos2.5 OCR long-input index errors." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode and checkpoint resume key mismatch are distinct training/runtime issues." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "Auto-docstring annotation handling is unrelated to the `ReasoningEffort` import failure in Gemma 4 processor loading." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures are not the same as a `GenerationMixin` import removal/visibility issue." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Different processor/tokenizer code paths and symptoms: label reduction in BEiT vs NER/padding crashes in LayoutLMv2Tokenizer." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error messaging and a MacOS bus error on community CLIP loading are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL `pad_token_id` loading failure and Qwen3-MoE sliding-window behavior are different bugs." + }, + { + "left": "issue:44625", + "right": "issue:45584", + "accept": false, + "reason": "`num_labels` propagation in Qwen3.5 config is unrelated to Whisper empty-transcription generation after token alignment." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation regression is unrelated to the 2^24 category limit runtime error." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error messaging issue and embedding reinitialization in `post_init` are different model behaviors." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Chunked generation with compiled forward and Gemma3 NaN embeddings under mixed-length sliding-window batching are not the same problem." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FineGrainedFP8Config failure for Qwen3Moe and Qwen3-VL weight-shape mismatch are separate model-loading bugs." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch in unrelated models are different subsystems and code paths." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and LasrFeatureExtractor unsupported-arg crashes are unrelated processor bugs." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "BEiT label reduction and LwDetrImageLoss float16/CUDA crash affect different components and do not share an underlying change." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Local-path slash import warning and gradient-checkpointing-in-eval are unrelated." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "`AddedToken` duplicate `special` argument is unrelated to `list_repo_files` not forwarding `revision`." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Tensor-parallel OOM for Qwen2-57B and resume-from-checkpoint key mismatch are distinct issues." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3.5 recurrent-state reset bug and Whisper `batch_decode` skip_special_tokens handling are unrelated generation/decoder issues." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Ministral-3 flash-attention failure and sink-less flash_attention.py `s_aux=None` crash are both attention-related but not the same concrete bug." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs update after `sync_gpus` and `gather_for_metrics` dropping tuple labels are unrelated distributed-training bugs." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Custom model initialization breakage in Transformers 5.0.0 and `patchtsmixer` post_init contract change are not the same underlying change." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "CLIPVision hidden_states regression and `ModelOutput` None-key assignment are separate model-output bugs." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both can OOM, but one is TP loading of a specific Qwen model while 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` is unrelated to DeepSeekV3MoE divergence from the remote implementation." + } + ] + }, + "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-10000-403", + "nodes": [ + "issue:33290", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42490", + "issue:42907", + "issue:43065", + "issue:43316", + "issue:43381", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43611", + "issue:43643", + "issue:43720", + "issue:43723", + "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:44617", + "issue:44743", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45372", + "issue:45479", + "issue:45698", + "issue:45759", + "issue:45803" + ], + "soft_pairs": [ + "issue:43723|issue:45479", + "issue:44442|issue:45803", + "issue:43761|issue:44188", + "issue:43316|issue:43525", + "issue:44479|issue:45290", + "issue:42907|issue:45698", + "issue:44442|issue:44898", + "issue:33290|issue:34567", + "issue:42490|issue:44743", + "issue:34689|issue:43611", + "issue:33290|issue:35141", + "issue:33290|issue:34689", + "issue:43381|issue:43873", + "issue:43931|issue:45216", + "issue:43493|issue:43827", + "issue:43316|issue:45759", + "issue:44077|issue:44479", + "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:43065|issue:44617" + ], + "prepared_review_unit_hash": "cd0c2215d24199ab904202b2c39e1bea1c174085af4b9bc89a72f227948b149a", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36328, + "estimated_input_tokens": 9082, + "estimated_eval_tokens": 18420 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is highly heterogeneous: the soft pairs mostly connect unrelated loading, config, tokenizer, vision, training, and docs bugs. No pair looks like the same underlying change or defect, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: these items are not duplicates of one bug, but a grab bag of unrelated regressions and API mismatches.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative because there is no one underlying problem to centralize.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Different failures: tokenizer loading in v5 vs degenerate loss in sequence classification." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Unrelated code paths: AutoTokenizer loading vs Fuyu tensor conversion error handling." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "Different subsystems: CLIPVision hidden_states regression vs attention-kernel divergence under torch.compile." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config-related, but they affect different models and bugs: Gemma3TextConfig API mismatch vs Llama4Config missing pad_token_id." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Different Qwen chat/video issues: video-input regression vs tool-call chat-template crash." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load, but one is dequantized model saving and the other is wrong custom-module loading after save_pretrained; not the same bug." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Completely different models and paths: tokenizer loading vs Perceiver image resizing/interpolation." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "Different training problems: DeepSpeed/Adafactor OOM vs TrainerState token counter not updating." + }, + { + "left": "issue:42490", + "right": "issue:44743", + "accept": false, + "reason": "Local-path import warning is unrelated to recurrent-state caching behavior in Qwen3.5." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both concern model loading, but they are distinct regressions with different root causes and model families." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "OOM with Adafactor is unrelated to embedding reinitialization in post_init." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Different bugs: optimizer memory blowup vs Llama 3.2 Vision model loading failure." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and quantization offloading are separate execution paths." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Weight-shape mismatch on Qwen3-VL loading is unrelated to a save_pretrained checkpoint regression in Qwen3.5." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation discrepancy is unrelated to docs still referencing pipeline()." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Different config-loading problems: Gemma3TextConfig API mismatch vs not unwrapping text_config in AutoModelForCausalLM.from_config." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTST post_init validation and Qwen video-input regression are unrelated bugs." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading and tokenizer loading are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Different import failures: AutoImageProcessor export vs mistral_common ReasoningEffort dependency." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct reload behavior do not share the same code path." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and Qwen3-VL weight mismatch are separate loading failures." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama model-loading regression and GenerationMixin import error are different issues." + }, + { + "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 and CustomTrainer compute_loss signature mismatch are distinct trainer bugs." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to unrecognized model config loading." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 IndentationError in Deberta import is unrelated to ZeRO3 deque underflow." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video processing in Qwen3OmniMoe and batched chat-template tool-call handling are different failures." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy and granite_speech strict-config loading are different model/config issues." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Backend packaging for TensorFlow is unrelated to Gemma3TextConfig API behavior." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video CUDA OOM are not the same defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:25251", + "issue:28282", + "issue:32090", + "issue:35141", + "issue:41950", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43388", + "issue:43404", + "issue:43441", + "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:45127", + "issue:45200", + "issue:45406", + "issue:45563", + "issue:45584", + "issue:45698" + ], + "soft_pairs": [ + "issue:25251|issue:28282", + "issue:43295|issue:43825", + "issue:43404|issue:43441", + "issue:43673|issue:44743", + "issue:44162|issue:44792", + "issue:16998|issue:22355", + "issue:43388|issue:43688", + "issue:41950|issue:43475", + "issue:44077|issue:44534", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:44871|issue:45584", + "issue:43761|issue:44479", + "issue:43295|issue:44871", + "issue:45127|issue:45200", + "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:32090|issue:35141", + "issue:45563|issue:45584", + "issue:44464|issue:44871", + "issue:43065|issue:44610" + ], + "prepared_review_unit_hash": "1c4a8bc4ef0772382cba602527de0897b316460d693c4df8fdc0e99e5aad97ac", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36103, + "estimated_input_tokens": 9026, + "estimated_eval_tokens": 18308 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are mostly unrelated model/loading/training regressions, so I found no convincing duplicate cluster beyond loose subsystem similarity. The strongest representative issue is the custom-module loading regression.", + "confidence": 0.27, + "canonical_issue_reason": "issue:45698 is the clearest broad, user-facing loader regression in the set, with a concrete save/load repro and active discussion.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 best represents a high-impact core `from_pretrained` failure and is the most actionable issue in the group.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Different failures: pipeline output shape vs missing PyTorch import path." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Both touch processors/tokenizers, but one is a v5 regression in custom code handling while the other is just an incorrect error message for unsupported translation tasks." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Same model family, but different bugs: weight tying vs FlashAttention failure." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both are cache-related, but they affect different mechanisms and code paths (chunked prefill cache vs recurrent state reset)." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "Completely different domains: ESM2 model breakage vs Janus image generation test failure." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Unrelated: max length handling for DeBERTa vs missing `transformers.onnx` module." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Training-related, but one is metric gathering on last batch and the other is auxiliary-loss normalization." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Both involve vision/video models, but the bugs are different: processor selection vs missing attribute in SAM3 video output." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "One is a model class API constraint; the other is a v5 buffer-initialization regression." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "Unrelated: torch.compile SDPA OOM vs checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "Different issues: CPU offload device mismatch vs resume checkpoint key mismatch." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Both mention tokenization/generation, but one is an eos_token_id config mismatch and the other is an empty-transcription generation crash." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "Different model families and failure modes: CLIP hidden_states regression vs Qwen video-input regression." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Processor/tokenizer regression vs eos_token_id inconsistency; not the same underlying bug." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "Both are model config/training issues, but one is LoRA/embedding collapse after merge and the other is a missing default for `mm_token_type_ids`." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "Different symptoms and paths: running a 3D script vs OOM when loading a specific model with tensor parallelism." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both involve loading, but one is a `gguf_file` path bug and the other is an unrecognized custom model/config issue." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Different model-loading problems: OOM on large Qwen with tp vs key error for MobileLLM-125M." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "Both are service/runtime crashes, but they stem from different serve code paths and different root causes." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model init breakage is unrelated to GPTNeoX config reload losing `rotary_pct`." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Both concern loading/saving, but one is a legacy field in BEiT preset loading and the other is wrong custom-module resolution after save/load." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Unrelated: CUDA OOM in SAM3 video vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Different training/inference bugs: CLIP hidden_states regression vs missing load-balancing loss." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Related to Qwen3-VL/Next, but one is a shape mismatch on load and the other is a tied-weights warning bug." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Different failures: distributed broadcast NoneType vs output embedding reinitialization after resizing token embeddings." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Paged generation warning bug vs Whisper align_special_tokens crash; not the same issue." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is unrelated to eos_token_id config mismatch." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision model issues, but one is a dummy Conv2d in SAM3 pixel decoder and the other is a processor/model image-size mismatch." + } + ] + }, + "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-10000-403", + "nodes": [ + "issue:35141", + "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:44479", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44734", + "issue:44737", + "issue:44792", + "issue:44855", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:44964", + "issue:44977", + "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:44792|issue:44977", + "issue:44479|issue:44734", + "issue:44521|issue:45381", + "issue:43827|issue:43994", + "issue:44464|issue:45563", + "issue:44534|issue:44913", + "issue:43906|issue:45290", + "issue:44190|issue:44964", + "issue:44933|issue:45362", + "issue:41720|issue:45245", + "issue:44792|issue:45600", + "issue:44855|issue:45588", + "issue:35141|issue:42490", + "issue:43388|issue:43582", + "issue:45127|issue:45357", + "issue:44737|issue:45803", + "issue:44462|issue:45907", + "issue:43335|issue:44855", + "issue:44077|issue:44079", + "issue:44938|issue:45542", + "issue:43644|issue:44913", + "issue:43550|issue:44190", + "issue:43976|issue:44855", + "issue:43540|issue:44734", + "issue:44112|issue:45600", + "issue:44496|issue:45803", + "issue:43335|issue:44190", + "issue:43650|issue:44220", + "issue:45276|issue:45584" + ], + "prepared_review_unit_hash": "691a63f3334cc7339cda6012cef477e06f4f82a59d60f039980072dc8263cea5", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36467, + "estimated_input_tokens": 9117, + "estimated_eval_tokens": 18490 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All proposed soft edges look like loose topic/keyword similarity, not the same underlying bug or change. I would reject every candidate pair; the set is heterogeneous and there is no clear canonical issue/PR for the whole group.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Different failures in different models: Janus image generation test vs Qwen3.5 flash-attention behavior." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation/runtime bugs, but one is a Qwen VL video regression and the other is KV-cache indexing in serve; not the same code path." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal/chat-template issues, but one is assistant masks for multimodal inputs and the other is Qwen2.5-VL vision \u0564\u056b\u0580 ids; distinct bugs." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs referencing removed pipeline() APIs is unrelated to a bad AutoModel/pipeline inference result." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Chunked compiled generation inconsistency is unrelated to a stale warning in paged generate()." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer initialization and GPTNeoX config reload defaults are different problems." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "Insufficient evidence that the isolated reproduction matches the tool-call crash; only a generic chat-template similarity is visible." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "A local dataset loading issue is unrelated to loading a multimodal model." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing/nonexistent import from image_utils is unrelated to a Qwen3.5 chat crash." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "CUDA assert with auto device mapping has nothing to do with the category-count limit error." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus test failure and stale auto_mappings references are unrelated." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 import/torch.jit parsing issue is unrelated to flash_attention crashing on s_aux=None." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "Embedding resize/post_init reinit bug is unrelated to loading local model paths with trailing slashes." + }, + { + "left": "issue:43388", + "right": "issue:43582", + "accept": false, + "reason": "Metric label handling bug is unrelated to an Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge with extended vocabulary on tied embeddings is unrelated to incorrect visual encoder keys during save_pretrained." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "CPU device placement bug in XLNet is unrelated to a bare-except error swallowing interrupts in Fuyu conversion." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer resolution from repository files is unrelated to list_repo_files failing to forward revision." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "Sparse layer creation in SwitchTransformers is unrelated to DebertaV2 import parsing on Python 3.13." + }, + { + "left": "issue:44077", + "right": "issue:44079", + "accept": false, + "reason": "These are both model-output/config related, but they describe different bugs: optional post_init handling vs key assignment when previously None." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 import failure is unrelated to the TensorFlow-backend warning from tensorboard-only installs." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Junk non-persistent buffers and GPTNeoX rotary_pct reload regression are not the same issue." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to loading a local dataset script." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python version compatibility issue is unrelated to a specific DebertaV2 import parser error." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError is unrelated to serve KV-cache continuation tensor indexing." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "GraniteSpeech CI test flake is unrelated to stale Sam3LiteText auto-mapping references." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "Model config missing model_type is unrelated to Fuyu's broad exception handling." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "Sparse-layer config bug is unrelated to local dataset loading." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Placeholder issue title is unrelated to _torch_extract_fbank_features()." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 resize_token_embeddings behavior and Whisper empty-transcription failure are different code paths and symptoms." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:39692", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:42490", + "issue:42907", + "issue:43065", + "issue:43295", + "issue:43404", + "issue:43441", + "issue:43479", + "issue:43531", + "issue:43643", + "issue:43673", + "issue:43824", + "issue:43854", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44112", + "issue:44186", + "issue:44190", + "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:45216", + "issue:45245", + "issue:45276", + "issue:45335", + "issue:45375", + "issue:45446", + "issue:45584", + "issue:45600", + "issue:45632" + ], + "soft_pairs": [ + "issue:39692|issue:44190", + "issue:45245|issue:45584", + "issue:41950|issue:44016", + "issue:43295|issue:45276", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:36246|issue:38617", + "issue:38175|issue:43065", + "issue:44186|issue:44734", + "issue:42175|issue:44279", + "issue:44683|issue:45446", + "issue:44016|issue:44220", + "issue:44466|issue:44913", + "issue:43404|issue:45216", + "issue:44246|issue:45003", + "issue:44734|issue:45632", + "issue:44561|issue:45632", + "issue:42490|issue:45632", + "issue:43643|issue:44496", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:43854|issue:44964", + "issue:42907|issue:43441", + "issue:43976|issue:44987", + "issue:44016|issue:44062", + "issue:43295|issue:45335", + "issue:43673|issue:44336", + "issue:43531|issue:45600", + "issue:43824|issue:44933" + ], + "prepared_review_unit_hash": "6b7c6a00d477b5a48013c4fc9b2d8b1f0049a99d4cea74e0b9297402eceed074", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36414, + "estimated_input_tokens": 9104, + "estimated_eval_tokens": 18464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of Transformers issues, mostly import/load regressions, model/config mismatches, and a few unrelated tokenizer, docs, and serving bugs. The soft-similarity pairs are not strong duplicates; they usually share a subsystem or theme, not the same underlying defect.", + "confidence": 0.89, + "canonical_issue_reason": "issue:44964 is the clearest, most reproducible bug report in the set: a specific model load failure against latest Transformers with a concrete target and narrow scope.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44964 is the best representative issue for this cluster because it is concrete, actionable, and centered on a single user-visible regression rather than a broad or ambiguous symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39692", + "right": "issue:44190", + "accept": false, + "reason": "Different problems: notebook/example errors vs local dataset loading failure in a training script." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Unrelated bugs: category-count limit vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Different artifacts and failures: pipeline processor lookup vs notebook syntax error." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Both involve model APIs, but one is a processor/tokenizer regression and the other is embedding resize not propagating." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different config bugs affecting different multimodal models and different fields." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and different code paths." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Distinct missing-import failures in unrelated modules." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Unrelated model behavior bug vs pixel decoder implementation issue." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Different tokenizer/NER crash vs serving KV-cache tensor indexing crash." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Generic dependency/install complaint is not the same as a missing TensorFlow backend in the torch extra." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Related area, but different concrete failures: compiled flex_attention on new torch vs an incorrect version check for AuxRequest import." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and audio feature extraction bug are unrelated." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Weight-serialization/tieing regression is separate from GPTNeoX rotary_pct reload behavior." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Different models and different save/tie semantics; not the same underlying bug." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowness and unsafe sys.modules access are not the same defect." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serving KV-cache crash and trust_remote_code cache-path collision are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Both mention trust_remote_code, but one is a missing helper removal breakage and the other is a cache-path collision." + }, + { + "left": "issue:42490", + "right": "issue:45632", + "accept": false, + "reason": "Both concern local-path handling, but one is a warning on trailing slashes and the other is a leaf-directory cache collision." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading is different from an unrecognized model/config error." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Model load failure for Phi-4-multimodal-instruct is not the same as stale auto_mappings references breaking CI." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI test flake in GraniteSpeech is unrelated to model loading for Phi-4-multimodal-instruct." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Both are model load reports, but they concern different models and likely different root causes." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Dequantized save failure and FlashAttention failure in Ministral are distinct issues." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Version/platform compatibility issue is not the same as failing to load a specific model." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and tokenization API TypeError are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Different regression targets: processor/tokenizer behavior vs decoder embedding resize propagation." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache regression and ANSI formatting in loading_report are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Sliding-window model bug and stale auto_mappings references are different code paths." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but one is a missing top-level export and the other is a nonexistent image_utils import." + } + ] + }, + "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-10000-403", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:43295", + "issue:43299", + "issue:43335", + "issue:43381", + "issue:43450", + "issue:43479", + "issue:43525", + "issue:43526", + "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:45042", + "issue:45081", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45325", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45584", + "issue:45593", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45907" + ], + "soft_pairs": [ + "issue:44496|issue:45042", + "issue:43526|issue:43901", + "issue:43299|issue:45216", + "issue:43335|issue:45593", + "issue:44075|issue:44368", + "issue:45335|issue:45584", + "issue:43976|issue:44279", + "issue:43381|issue:45593", + "issue:43901|issue:44496", + "issue:43299|issue:45357", + "issue:44496|issue:45759", + "issue:44521|issue:45325", + "issue:41950|issue:45020", + "issue:44351|issue:45278", + "issue:44242|issue:45200", + "issue:43976|issue:45405", + "issue:43479|issue:43525", + "issue:44779|issue:45812", + "issue:41950|issue:45823", + "issue:38175|issue:44617", + "issue:44683|issue:45542", + "issue:43577|issue:45216", + "issue:39692|issue:43901", + "issue:44279|issue:45405", + "issue:43299|issue:43854", + "issue:43295|issue:44779", + "issue:41950|issue:43650", + "issue:44462|issue:45081", + "issue:45081|issue:45907", + "issue:44297|issue:44462", + "issue:44016|issue:44291", + "issue:43450|issue:44279" + ], + "prepared_review_unit_hash": "ebb1fbfbaded5448d5f51f4780313240f3907517830fc4ed4be167d727ab072f", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36853, + "estimated_input_tokens": 9214, + "estimated_eval_tokens": 18684 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are separate bugs across tokenizers, processors, configs, and model-loading paths. I don\u2019t see any soft pair that clearly describes the same underlying defect, so I rejected them all. The closest umbrella issue is the broad AutoTokenizer/tokenizer-loading regression, but even that is not a true duplicate anchor for the rest.", + "confidence": 0.67, + "canonical_issue_reason": "issue:44462 is the broadest tokenizer-loading regression in the set and has the most obvious overlap with the other tokenizer-related reports, but the cluster is still not a single duplicate bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the best representative issue because it is broad, user-facing, and sits near several tokenizer-related reports, making it the most plausible triage anchor despite the lack of true duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Different bugs: model config recognition vs PIL image processor torchvision dependency." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast label handling is unrelated to a docs/behavior mismatch for TextClassificationPipeline." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3VL loading regression and Qwen3.5 save_pretrained regression are different code paths." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "Sparse-layer initialization and D-FINE auxiliary-loss logic are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "SGD argument handling is unrelated to a tie_word_embeddings warning." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize propagation and Whisper empty-transcription handling are different problems." + }, + { + "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 denoising/aux-loss behavior." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs drift for return_all_scores does not match AutoTokenizer ignoring tokenizer.json." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both mention Qwen3.5, but one is model loading and the other is incorrect visual-encoder checkpoint keys." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "AutoTokenizer repository-file handling and composite config unwrapping are different bugs." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Multimodal assistant masks and Qwen2.5-VL rope indexing are distinct code paths." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup is unrelated to remote_code model breakage." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "A specific HybridCache import error is not the same as a broad import-errors-after-upgrade report." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Load-balancing loss routing and Gemma 4 mm_token_type_ids defaults are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python support regression and a PEFT minimum-version bump are different issues." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Multimodal config default initialization and missing pad_token_id are not the same bug." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and likely different code paths." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video processor lookup and Gemma4 PLE device placement are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "Zero probabilities for SigLIP2 and a Sam3Video OOM are clearly different failures." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "flex_attention compilation on torch 2.9 is unrelated to TensorBoard/TensorFlow backend installation." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint serialization are different model-loading bugs." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "SigLIP2 doc example errors are not the same as a TextClassificationPipeline docs mismatch." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A dependency problem is not the same as bumping MIN_PEFT_VERSION too early." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3VL loading regression and GLM-4.7-Flash test loading are unrelated model-specific issues." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Custom processor.tokenizer breakage is not the same as Deepseek tokenizer output regressions." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "Video pipeline processor lookup and a placeholder issue title are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Ignoring tokenizer.json and a Mistral regex patch crash are different tokenizer bugs." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer regex patch failure is unrelated to list_repo_files revision forwarding." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer_class metadata mismatch and ignoring tokenizer.json are distinct save/load issues." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batching shape is unrelated to a dependency issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:33290", + "issue:42175", + "issue:42994", + "issue:43065", + "issue:43122", + "issue:43262", + "issue:43317", + "issue:43441", + "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:44297", + "issue:44336", + "issue:44361", + "issue:44466", + "issue:44521", + "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:45656", + "issue:45712", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:33290|issue:45656", + "issue:43441|issue:45834", + "issue:45600|issue:45712", + "issue:43065|issue:44898", + "issue:42994|issue:43317", + "issue:44466|issue:45276", + "issue:44261|issue:44263", + "issue:44623|issue:45397", + "issue:43650|issue:45290", + "issue:44623|issue:44749", + "issue:43441|issue:44683", + "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:44297|issue:45397", + "issue:43824|issue:43976", + "issue:44188|issue:44336", + "issue:43525|issue:43881", + "issue:43525|issue:43643" + ], + "prepared_review_unit_hash": "e4edceb586338d007116c60bb541d9de33c8eeebe712c9c4195fd7ff3f24e42c", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35964, + "estimated_input_tokens": 8991, + "estimated_eval_tokens": 18238 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are largely unrelated Transformers issues. The soft-pair candidates mostly share broad vocabulary (e.g. deepspeed, apply_chat_template, loading, tokenizer) but do not appear to be the same concrete bug or change, so I reject all soft edges.", + "confidence": 0.89, + "canonical_issue_reason": "issue:44521 is the broadest and most referenced issue in the set, so it is the best available anchor if one must be chosen, though the collection is not a true duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 has the widest scope and strongest discussion/inbound-reference signal, making it the most representative issue among otherwise unrelated reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both involve deepspeed/optimizer behavior, but one is OOM during Adafactor use and the other is double optimizer stepping; different concrete failures." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "Unrelated bugs: FlashAttention failure for Ministral-3 vs long OCR index error in Kosmos2.5." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both touch generated/dummy mappings, but one is stale Sam3LiteText references and the other is leftover dummy classes; different fixes." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Different models and symptoms: dummy Conv2d in Sam3PixelDecoder vs Perceiver resolution/interpolation failure." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model saving failure and dequantized-model offload loading failure are separate code paths." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "One is device-dependent lm_head serialization, the other is resize_token_embeddings not updating Gemma4 embedding/output layers." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "Different model internals: MLA layernorm epsilon precision issue vs torch.split return handling in GlmMoeDsaIndexer." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing files on processor.save_pretrained is not the same as ZeRO3 from_pretrained failure for gemma-4." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "The first is a vague data request; the second is a specific apply_chat_template crash with tool-call assistant messages." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "processor.save_pretrained file omission and Chinese performance regression after upgrade are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Both mention attention/flash, but the failures are on different models and different triggers." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "Tokenizer special-token registration bug and D-FINE auxiliary-loss logic are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both concern apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant_mask generation." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer loading regression and ESM2 model breakage are different issues." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error is unrelated to Gemma4 device-mismatch during forward." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache missing in chunked_prefill and CLIPVisionModel hidden_states regression are separate bugs." + }, + { + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "Packaging/backend omission is not the same as a Python-version compatibility failure." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer AttributeError and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Both are model/tokenizer regressions in v5, but the affected models and failure modes differ." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Importing sentence-transformers fails due to missing nn; the other is a TensorFlow backend packaging issue." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to incorrect SigLIP2 inference results." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Loading a specific model on transformers>=5.1.0 and tensorboard-only TensorFlow backend issues are different." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenization behavior change and a vague 'ADD THE DATA' request do not describe the same bug." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch is unrelated to gemma-4 ZeRO3 loading." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Missing Qwen2.5-VL export and Python 3.9/3.10 compatibility are unrelated." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Attention-kernel divergence under torch.compile is unrelated to ANSI code emission in loading_report." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Llama4Config missing pad_token_id and glm-4v-9b load failure are different model-specific issues." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "A missing config attribute in Llama4Config is not the same as trust_remote_code dropping fields from AutoConfig." + } + ] + }, + "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-10000-403", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:43232", + "issue:43299", + "issue:43352", + "issue:43450", + "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:44617", + "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" + ], + "soft_pairs": [ + "issue:43450|issue:44617", + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:43901|issue:44246", + "issue:44336|issue:44373", + "issue:45561|issue:45563", + "issue:42491|issue:43299", + "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:44336|issue:44485", + "issue:36246|issue:42757", + "issue:43526|issue:45003", + "issue:36246|issue:44351", + "issue:45003|issue:45561", + "issue:43673|issue:44561", + "issue:44246|issue:44871", + "issue:44242|issue:44857", + "issue:44295|issue:44749", + "issue:44162|issue:45200", + "issue:36246|issue:43596", + "issue:44779|issue:45292", + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:43901|issue:45003", + "issue:45292|issue:45701", + "issue:43232|issue:44336", + "issue:44496|issue:45003", + "issue:44987|issue:45459" + ], + "prepared_review_unit_hash": "0f1dc857b05fe3a4cf5f0842988a3941516c9115db91c2dbcc3e317afb77295e", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36335, + "estimated_input_tokens": 9084, + "estimated_eval_tokens": 18424 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers regressions (imports, model-specific loading, generation, docs, testing, and performance). Only one soft pair looks like a plausible duplicate; the rest are too different in code path or failure mode to merge.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 44877 is the clearest concrete bug in the cluster and the best representative of the only strong overlap: strict config handling dropping required model fields during loading.", + "canonical_pr_reason": null, + "best_issue_reason": "44877 is the most suitable single issue to anchor the cluster because it matches the same strict-config code path as the only plausible duplicate candidate and is more specific than the broader version-breakage reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Different bugs: pipeline processor selection vs CUDA OOM in Sam3Video." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "One is a storage/type import failure; the other is a Qwen chat/runtime crash." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Import export regression vs Python-version compatibility issue; not the same bug." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs mismatch vs a MoE load-balancing loss bug in training." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "Different scopes: terminal ANSI output vs a wrong docstring." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "Test race condition vs a stale generation warning; unrelated code paths." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen/MoE, but one is LoRA compatibility across versions and the other is a model-loading failure." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Similar symptom shape, but different models and loss mechanisms." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Buffer registration error vs ZeRO-3 from_pretrained loading problem." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video pipeline processor lookup vs audio feature extraction; unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import performance issue vs unrecognized model/config loading failure." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Both Qwen-related, but sliding_window handling and chat crashes are different problems." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Specific model/Flash-Attn incompatibility vs a generic Flash Attention topic." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI-report formatting vs GLM-5 RoPE implementation; no overlap." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols and modules." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "Image-processor label reduction bug vs unsafe sys.modules access; unrelated." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing exports from different parts of the package." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Import/module safety bug vs a test file race condition." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Both are v5 regressions, but generation cache and trust_remote_code import removal are different code paths." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import slowdown vs Gemma eos_token_id config mismatch." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Different failures: missing auxiliary loss vs AMP/CUDA crash." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position_ids buffer error vs a data-filtering performance regression." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "Different models and different bugs; not mergeable." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Import symbol issue vs DeepSpeed zero3/BertModel indexing error." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer output regression vs embedding-resize synchronization bug." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": true, + "reason": "Both point to the same strict-config code path dropping required fields from model configs." + }, + { + "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": "Docs issue vs unsafe module lookup; no common underlying bug." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Resize-embeddings behavior vs version-dependent tokenization changes." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs bug vs terminal ANSI output bug." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Config/model recognition vs sys.modules access safety." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure vs tokenizer exception masking; different layers." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and conservative overall. The summary matches the packet\u2019s titles and the one accepted soft pair (44877/45375) is the only clearly defensible overlap: both are strict-config omissions in model config loading. The other rejections stay appropriately cautious and do not overclaim duplicate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:42886", + "issue:42994", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43482", + "issue:43540", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44246", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44466", + "issue:44623", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:44995", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45230", + "issue:45278", + "issue:45310", + "issue:45335", + "issue:45356", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45563", + "issue:45588", + "issue:45600", + "issue:45656", + "issue:45759" + ], + "soft_pairs": [ + "issue:43065|issue:43408", + "issue:45375|issue:45759", + "issue:42886|issue:45229", + "issue:43262|issue:44246", + "issue:43257|issue:45137", + "issue:44995|issue:45200", + "issue:43475|issue:43540", + "issue:44060|issue:44077", + "issue:45397|issue:45656", + "issue:43653|issue:44162", + "issue:44466|issue:45335", + "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:45230|issue:45397", + "issue:28282|issue:30990" + ], + "prepared_review_unit_hash": "809bad2185657622bcbcf4e78bac2cf52e89f42376d6bf7ee7ef8e005a9f1a7a", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36006, + "estimated_input_tokens": 9002, + "estimated_eval_tokens": 18260 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very heterogeneous: it mixes unrelated tokenizer, generation, model-loading, DeepSpeed, SAM3, Gemma, Qwen, and save/load bugs. I do not see any soft pair that is clearly the same underlying issue; all should stay separate. The broadest representative is the generic v5 regression/import report, but it still does not meaningfully cover the rest.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45278 is the most umbrella-like report (\u201cmany import errors after update\u2026\u201d), so it is the closest thing to a cluster representative, even though the cluster itself is too mixed to have a truly good canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the broadest issue in the set and the closest fit for a representative cluster label.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Both are SAM3-related, but one is about a dummy Conv2d in the pixel decoder and the other is a model-type warning for sam3_video vs sam3_tracker; different bugs." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal config handling, but one is about a missing config field being dropped and the other is about AutoModelForCausalLM.from_config not unwrapping text_config; not the same fix." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache loading and Gemma4 multi-GPU CUDA OOM are unrelated problems." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting and slow import behavior are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Both mention DeepSpeed, but one is Qwen3 MoE weight conversion during loading and the other is a ZeRO3 deque error; different code paths." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "GlmMoeDsa stale indexer cache on second forward pass is unrelated to Gemma4 mm_token_type_ids defaults." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Different model families and failures: SAM3 video output attribute error vs Qwen3OmniMoe video-processing ValueError." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Qwen3-Next tied-weights warning and patchtsmixer post_init allowance are unrelated." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 Zero3 from_pretrained failure and a duplicated optimizer step under DeepSpeed are different bugs." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and ESM2 being broken are not the same underlying issue." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both concern tied-embedding behavior, but one is serialization of lm_head.weight and the other is resize_token_embeddings not updating decoder.embed_tokens; different concrete failures." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale indexer cache crash in GlmMoeDsa and flash-attention s_aux=None AttributeError are unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "A tied-word-embeddings warning for Qwen3.5 fine-tuning is unrelated to a stale num_return_sequences warning in paged generate()." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Both involve Qwen3.5, but one is a configuration warning and the other is a flash-attention generation failure; not the same bug." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Chunked-prefill cache missing and /v1/responses KV-cache continuation indexing are different generation bugs." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error and removed Sam3LiteText config references are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and a tied-embeddings warning are unrelated." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Missing image_utils import and hidden tokenizer decode errors when protobuf is absent are different import-path issues." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper timestamp decode crash and Kimi-K2.5 tokenizer regression are distinct tokenizer/decoding problems." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Tokenizer save_pretrained writing the wrong tokenizer_class and processor.save_pretrained missing files are related to saving, but not the same concrete bug." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both are generation/cache-related, but one is sync_gpus kwarg updating and the other is chunked_prefill cache availability; different fixes." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and a slowdown after upgrading transformers are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Generic custom model initialization breakage and ESM2-specific failure are not the same issue." + }, + { + "left": "issue:43673", + "right": "issue:45278", + "accept": false, + "reason": "Generation cache missing during chunked_prefill is unrelated to broad import errors after upgrading." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Processor save_pretrained missing files and duplicated DeepSpeed optimizer steps are unrelated." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "A performance regression after upgrading transformers and a duplicated optimizer step under DeepSpeed are different problems." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5, but one is a slowdown report and the other is a from_pretrained error with newer transformers; not the same bug." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure and GGUF loading failure are opposite-direction serialization/loading issues, not one bug." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "'Bug report' is too vague to match concretely, and the Gemma-4 Zero3 from_pretrained issue is specific; no evidence they are the same." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch missing ImportError for AutoModel and Sentence Transformers hanging on load 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": 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-10000-403", + "nodes": [ + "issue:30990", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43377", + "issue:43475", + "issue:43504", + "issue:43525", + "issue:43526", + "issue:43643", + "issue:43673", + "issue:43704", + "issue:43824", + "issue:43873", + "issue:43976", + "issue:44038", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44792", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45375", + "issue:45381", + "issue:45478", + "issue:45561", + "issue:45712", + "issue:45753" + ], + "soft_pairs": [ + "issue:42371|issue:45092", + "issue:44038|issue:44623", + "issue:43475|issue:43643", + "issue:43475|issue:45381", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:42994|issue:43525", + "issue:43475|issue:44661", + "issue:45375|issue:45478", + "issue:43232|issue:44188", + "issue:45310|issue:45375", + "issue:43873|issue:44945", + "issue:42673|issue:43704", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:44945|issue:45753", + "issue:44222|issue:45310", + "issue:43673|issue:44188", + "issue:42994|issue:43824", + "issue:36010|issue:41628", + "issue:42175|issue:45712", + "issue:42222|issue:45200", + "issue:43232|issue:44792", + "issue:44038|issue:45310", + "issue:43377|issue:44242", + "issue:44496|issue:45561", + "issue:43526|issue:45561", + "issue:44964|issue:45137", + "issue:43504|issue:45561", + "issue:42175|issue:44933", + "issue:42898|issue:44568", + "issue:30990|issue:35141", + "issue:43976|issue:44933" + ], + "prepared_review_unit_hash": "069a14d0d03fd11cd4a0f31762d92f43af48b6837343bc15128f0edd45c31a96", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37473, + "estimated_input_tokens": 9369, + "estimated_eval_tokens": 18994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers issues. Among the provided soft pairs, only issue:42673 / issue:43704 is a clear duplicate; the rest are conservative non-matches. No PR pairings are present.", + "confidence": 0.97, + "canonical_issue_reason": "There is no single canonical issue for the whole cluster because the items cover many unrelated bugs. The only true duplicate subcluster in the provided soft pairs is the Qwen3ForCausalLM VRAM leak report, where issue:42673 is the best representative and issue:43704 is its duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42673 is the best canonical issue candidate because it is the earlier, fuller report for the exact Qwen3ForCausalLM multi-dataloader-thread VRAM leak, and issue:43704 repeats the same bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "Different bugs: TF32 API guidance versus a meta-initialization incompatibility in old InternVL2 remote code." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Different code paths and symptoms: Qwen3-VL-Moe loading error versus processor.save_pretrained missing files." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "Different failures: missing Sam3VisionEncoderOutput attribute versus AutoConfig losing fields under trust_remote_code." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Related vision models, but not the same bug: SAM 3 attribute error versus qwen2.5-vl position-id issue." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but they involve different missing symbols and different modules." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Different crash sites: Mistral tokenizer regex patching versus auto-docstring kwargs processing." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Unrelated problems: quantized model saving failure versus Llama4Config missing pad_token_id." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Different bugs: SAM output attribute issue versus add-new-model-like failing in TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same model family, but different concrete issues: missing deepstack_visual_indexes versus a from_pretrained error." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Different generation bugs: sync_gpus update behavior versus attention-kernel divergence under torch.compile." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Both involve Qwen3.5-related models, but one is a from_pretrained error and the other is a missing vision config field." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Different problem areas: quantization/offloading behavior versus incorrect pipeline-parallel LLM output." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact same reported bug and symptom: Qwen3ForCausalLM VRAM leak when used across multiple dataloader threads." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports: AutoImageProcessor versus HybridCache." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Different FP8 issues: accuracy regression versus save_pretrained failure for MoE." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Both are generation-related, but they concern different models and different failure modes." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Different concrete bugs: FP8 MoE save_pretrained versus Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Unrelated generation/cache bug versus a compile-time attention branching issue." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Saving quantized models and importing Qwen2_5_VLForConditionalGeneration are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different symbols and different API surfaces." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Packaging/backend dependency behavior is not the same as leftover dummy classes leaking into dir(transformers)." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Different model/component breakages: VitPose models versus Gemma 4 mm_token_type_ids defaults." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Different bugs: generation kwargs update versus a Janus image-generation test failure." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Different model variants and failures: Qwen3-VL-Moe loading bug versus Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Different sub-systems: MIMI padding-mask batching bug versus MoE load-balancing loss logic." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Model config loading failure is unrelated to the pytest-xdist file race." + }, + { + "left": "issue:43526", + "right": "issue:45561", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to the xdist race on captured_info.txt." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Different failures: Phi-4 multimodal loading versus a DeepSpeed ZeRO3 deque error." + }, + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "Beit pretrained preset legacy-field issue is unrelated to the testing-utils race." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Dependency/backend install issue is unrelated to the missing image_utils import." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Different tokenizer regressions: cleanup-space behavior change versus add_special_tokens BOS/EOS behavior." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version compatibility issue is unrelated to the missing image_utils import." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Mostly grounded, but the summary is slightly overclaimed: among the listed soft pairs, only issue:42673/issue:43704 is an accepted duplicate. The second Qwen3.5 MoE from_pretrained pair is not one of the provided soft pairs, so calling it a true 'soft pair' duplicate is imprecise. The rest of the verdicts look conservative." + }, + "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": 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-10000-403", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30333", + "issue:33290", + "issue:34689", + "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:44079", + "issue:44188", + "issue:44190", + "issue:44206", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44448", + "issue:44484", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44869", + "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:43479|issue:44869", + "issue:43479|issue:44079", + "issue:44623|issue:45310", + "issue:43784|issue:43824", + "issue:44188|issue:44373", + "issue:43278|issue:45137", + "issue:42898|issue:45812", + "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:44295|issue:45656", + "issue:42898|issue:44448", + "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:30333|issue:34689", + "issue:44297|issue:45310", + "issue:44222|issue:44484", + "issue:43232|issue:45834", + "issue:43723|issue:44977", + "issue:28282|issue:30333" + ], + "prepared_review_unit_hash": "0addc67cd4e93fdd756b4568460ebded52120856c34163c07488f1581a2545f0", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37872, + "estimated_input_tokens": 9468, + "estimated_eval_tokens": 19192 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are mostly false positives: they connect unrelated import errors, tokenizer regressions, training issues, and config/model bugs that do not share the same concrete fix. No PRs are present in the cluster. The closest hub is the v5 tokenizer regression issue, but it is still only a loose representative, not a true duplicate anchor.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 42898 is the broadest hub among the soft edges and best matches the recurring v5 tokenizer-regression theme, even though most neighboring pairs are not true duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "42898 is the least narrow representative of the cluster because it sits at the center of several tokenizer-related soft links and has the strongest chance of being the intended anchor issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Different subsystems: multimodal config initialization vs Whisper timestamp decoding crash." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "One is config default handling; the other is ModelOutput key assignment logic." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Both involve saving/loading, but the concrete bugs are different processor files vs Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import failures in different packages and code paths." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Attention-kernel divergence under torch.compile is unrelated to a docstring typo." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Different runtime problems: dtype drift during eval vs DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they describe different concrete failures and likely different fixes." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Serve KV-cache indexing bug is unrelated to auto-docstring annotation parsing." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on failed jobs and an Adafactor+DeepSpeed OOM are unrelated bugs." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "General tokenizer loading regression is not the same as mdeberta special-token behavior." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Different multimodal loading failures with different root causes." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and behaviors." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Tied-weights warning bug is unrelated to missing tensor-parallel plan support." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Different tokenizer regressions affecting different models and failure modes." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "Unreleased PEFT version bump is unrelated to dummy class cleanup." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Position_ids buffer access bug is unrelated to double optimizer stepping under DeepSpeed." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Both mention v4/v5 output changes, but they do not point to the same concrete defect." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Missing image_utils import and dummy-class leakage are separate API-surface issues." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "Different save_pretrained bugs: FP8 MoE serialization vs tokenizer config mismatch." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch is unrelated to DeepSpeed optimizer stepping." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Different example scripts and different failures." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Config None-handling is unrelated to non-persistent buffer initialization." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Both are save_pretrained-related, but on different objects and different bugs." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FP8 accuracy drift is unrelated to missing processor save files." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature extractor argument regression is unrelated to auto-docstring annotation handling." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Two separate import errors from different modules and different missing symbols." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Different import errors caused by different missing dependencies/modules." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLflow reporting on failure is unrelated to CustomTrainer.compute_loss signature mismatch." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "Training-job reporting and Llama model loading regression are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer save_pretrained metadata bug is unrelated to Qwen3.5 MoE loading failure." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE serialization bug is unrelated to max_shard_size default behavior." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation KV-cache update bug is unrelated to long-ocr indexing in Kosmos2.5." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression is unrelated to flash-attention generation failure." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "AutoModel missing PyTorch and MLflow job reporting 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": 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-10000-403", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:35141", + "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:44261", + "issue:44263", + "issue:44295", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44521", + "issue:44568", + "issue:44623", + "issue:44829", + "issue:44871", + "issue:44913", + "issue:44991", + "issue:45092", + "issue:45103", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45593", + "issue:45753", + "issue:46002" + ], + "soft_pairs": [ + "issue:30333|issue:35141", + "issue:44263|issue:45092", + "issue:44373|issue:44485", + "issue:44263|issue:44360", + "issue:44295|issue:44623", + "issue:44514|issue:45103", + "issue:44483|issue:45406", + "issue:44261|issue:45092", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:43723|issue:44991", + "issue:30990|issue:38175", + "issue:44829|issue:46002", + "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" + ], + "prepared_review_unit_hash": "4bf002b9695d4cdc9486247621a88f7c6f630b34ed35c765c7f8fbca9cf42ac5", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35590, + "estimated_input_tokens": 8898, + "estimated_eval_tokens": 18052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are unrelated bug reports spanning tokenizer loading, model config, generation, serving, and training. I do not see a single duplicate family that safely unifies the whole set.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out; the items are mostly distinct defects in different code paths and models, so forcing one duplicate target would be misleading.", + "canonical_pr_reason": "No PRs are present in the provided items.", + "best_issue_reason": "Issue 43723 is the closest thing to a hub only because it is a broad tokenizer-loading regression in v5, but it is still too general to serve as a true canonical for this mixed set.", + "best_pr_reason": "No PRs are present in the provided items.", + "soft_edge_verdicts": [ + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Training-job MLflow reporting and embedding reinitialization are unrelated bugs." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "DSA torch.split behavior and InternVL2 meta-init incompatibility affect different code paths." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "A wrong docstring and a RoPE implementation bug are not the same underlying issue." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA/indexer, but one is a torch.split bug and the other is a missing ReLU; different defects." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Reading registered position_ids buffers and processor.save_pretrained file omission are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Multimodal chat-template batching and auto_docstring future-annotations crashes are separate problems." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "API request validation failure and Gemma4Processor missing _tokenizer are different failures." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "Layernorm epsilon precision mismatch and remote-code meta-init incompatibility are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Generic tokenizer-loading regression and Gemma eos_token_id mismatch are different bugs." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "InternVL2 meta-init incompatibility and Qwen3.5 save_pretrained key corruption do not share the same code path." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": false, + "reason": "Both concern tokenizers in v5, but they describe different model-specific loading failures; not enough to merge." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence-transformers loading stalls and SigLIP2 zero probabilities are unrelated." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "Flash-attention training degeneration and NaNs after checkout/init are different training-path defects." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "AutoTokenizer generic loading regression and FastSpeech2ConformerTokenizer failure are not clearly the same root cause." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Missing AutoImageProcessor and missing Qwen2_5_VLForConditionalGeneration are distinct import errors." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Default vision/audio config initialization and rotary_pct reload behavior are unrelated config bugs." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy and Qwen3.5 from_pretrained errors are different issues." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "A runtime torch.split bug and a docstring mistake are not duplicates." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Wrong offset_mapping and missing BOS/EOS insertion are different tokenizer behaviors." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "FP8 accuracy regression and Qwen3-VL-Moe bug reports are unrelated." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "A specific missing import from huggingface_hub and a broad 'many import errors' report are not the same concrete bug." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline cache tokenizer loading and quantized model saving are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs update and D-FINE auxiliary-loss behavior are separate code paths." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Smollm3 RoPE layer count and Qwen3-Next tied-weights warning are different model-definition bugs." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Broken env command and sentence-transformers import NameError are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FP8 accuracy regression and Qwen3_5 infinite-loop behavior are different failures." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline tokenizer cache loading and wrong tokenizer decoder type are different tokenizer issues." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Tokenization drift across versions and multimodal assistant_mask output are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings API guidance and a torch.split return-value bug are not duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:30990", + "issue:33357", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42907", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43646", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44117", + "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:45200", + "issue:45216", + "issue:45278", + "issue:45290", + "issue:45478", + "issue:45600", + "issue:46002" + ], + "soft_pairs": [ + "issue:44117|issue:44704", + "issue:22355|issue:28218", + "issue:43646|issue:46002", + "issue:30990|issue:33357", + "issue:44295|issue:44297", + "issue:43232|issue:44743", + "issue:44704|issue:45290", + "issue:42907|issue:44945", + "issue:43122|issue:44514", + "issue:41628|issue:45278", + "issue:43976|issue:44945", + "issue:44261|issue:44373", + "issue:43784|issue:45600", + "issue:39401|issue:44488", + "issue:42907|issue:43937", + "issue:43408|issue:43475", + "issue:44360|issue:44485", + "issue:39401|issue:44521", + "issue:43116|issue:45200", + "issue:44625|issue:44829", + "issue:44038|issue:44297", + "issue:42907|issue:44964", + "issue:29127|issue:30990", + "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" + ], + "prepared_review_unit_hash": "5dec8af14112048f5fd271ee1c5b94f6279cf3b4a6be1b9a9563bca6c315a449", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36572, + "estimated_input_tokens": 9143, + "estimated_eval_tokens": 18542 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues across tokenization, imports, generation, multimodal models, and training/runtime regressions. The soft links are largely lexical/topic similarity rather than the same concrete bug, so I reject all soft edges.", + "confidence": 0.9, + "canonical_issue_reason": "45278 is the broadest umbrella regression in the set (multiple import errors after upgrading), so it is the best representative issue for this heterogeneous cluster, though the cluster is not a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "45278 is the most generic and representative issue here; it best summarizes the cluster\u2019s broad \u201cimport breakage after upgrade\u201d theme even if it does not match the other issues exactly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Different failure modes: tokenizer mapping fallback vs AutoProcessor kwargs not reaching cached_file. Same API surface, but not the same bug." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "One is a missing module import, the other is tokenization spacing after added tokens. No shared underlying code-path." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Custom model initialization breakage and NaNs in classification heads are distinct training/runtime problems." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Both are loading-related, but one is a hang and the other is a Mac bus error with CLIP; different root causes." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Position_ids buffer access and tokenizer_class metadata mismatch are unrelated save/load behaviors." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/cache, but one is sync_gpus bookkeeping and the other is recurrent state reset with seq_len>1." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "cached_file argument forwarding is unrelated to chat template crashes on tool-call assistant messages." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized Ministral/Devstral models and incorrect output under pipeline parallelism are different bugs." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer-version drift and apply_chat_template batching/padding failure are different tokenization paths." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Both are import errors, but 41628 is a specific missing symbol while 45278 is a broad upgrade breakage report; not the same concrete issue." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version compatibility and pipeline-parallel wrong output are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A model config precision bug and a wrong docstring are not the same underlying problem." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Sentence-transformers import failure and broken auto_mappings references in CI are separate breakages." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping errors and loading cjvt/sleng-bert are different tokenizer/model-loading issues." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Save_pretrained failure for dequantized models and invalid GenerationConfig for GLM-5 are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Both are SAM3-related, but a model-type warning and a missing output attribute are distinct bugs." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA indexer activation and GLM-5 RoPE implementation are unrelated subsystems." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Wrong offset mappings and all-zero assistant masks are different tokenizer/chat-template bugs." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Multi-label classification returning empty results and mm_token_type_ids defaults are not the same issue." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and flash_attention_3 degenerate training are unrelated classification/modeling problems." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe loading and tokenizer_class metadata mismatch do not share a concrete code-path." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Dequantized save_pretrained issues and failing to load Phi-4 multimodal instruct are separate model lifecycle bugs." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and Sentence Transformers loading hang are not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer behavior drift in v5 and Deepseek tokenizer incorrect results are different tokenizer regressions." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Qwen3-VL-Moe bug and position_ids buffer read error are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor parallel training bug and example-script multi-label classification empty outputs are different problems." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models and gguf_file breaking from_pretrained are unrelated load/save bugs." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Missing Qwen2.5-VL export and missing HybridCache export are both import errors but not the same symbol or fix." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe loading and FP8 moe save_pretrained are distinct model-format issues." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3.5 save_pretrained regression and Qwen3.5 Moe from_pretrained error may be adjacent, but the titles point to different concrete failures and code-paths." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports from different packages; only the surface symptom matches." + } + ] + }, + "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-10000-403", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42907", + "issue:43064", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43278", + "issue:43441", + "issue:43493", + "issue:43611", + "issue:43673", + "issue:43784", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44222", + "issue:44466", + "issue:44485", + "issue:44704", + "issue:44779", + "issue:44936", + "issue:44945", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45278", + "issue:45357", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753", + "issue:46002" + ], + "soft_pairs": [ + "issue:43278|issue:44945", + "issue:43493|issue:45753", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43784|issue:45446", + "issue:43992|issue:44704", + "issue:43066|issue:44779", + "issue:38617|issue:45278", + "issue:42673|issue:45072", + "issue:43937|issue:44485", + "issue:22355|issue:29127", + "issue:43611|issue:46002", + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:42222|issue:43441", + "issue:43064|issue:43673", + "issue:43116|issue:43493", + "issue:44075|issue:44936", + "issue:45357|issue:45478", + "issue:44038|issue:45478", + "issue:43116|issue:43825", + "issue:45083|issue:45446", + "issue:43937|issue:45563", + "issue:44117|issue:45588", + "issue:33453|issue:39401", + "issue:39401|issue:44779", + "issue:43827|issue:45446", + "issue:44466|issue:46002", + "issue:43937|issue:44977", + "issue:42673|issue:43906" + ], + "prepared_review_unit_hash": "b01498f2c2861769f30faffbbdc8b8e00a88a128deb1a56cd5229d5665be984b", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 35734, + "estimated_input_tokens": 8934, + "estimated_eval_tokens": 18124 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is thematically similar but not duplicate-level: most items are distinct v5-era regressions or compatibility issues across tokenization, loading, training, serialization, and model-specific code paths. No soft pair looks safe to merge; 45278 is only a broad umbrella, not a true canonical duplicate.", + "confidence": 0.67, + "canonical_issue_reason": "Issue 45278 is the broadest representative of the cluster\u2019s shared v5 compatibility breakage theme (import failures after upgrade), but the rest are not the same underlying bug, so this is only a loose umbrella choice.", + "canonical_pr_reason": null, + "best_issue_reason": "45278 is the best single issue to stand in for the cluster because it is the most general and cross-cutting regression report, even though the cluster should not be collapsed into one duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Different failures: dtype drift between train/eval vs incorrect outputs under pipeline parallelism. No shared code-path." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Different models and symptoms: SigLIP2 implementation mismatch vs Qwen3_5 image-specific infinite loop." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both concern save_pretrained, but one is dequantized Ministral/Devstrals and the other FP8 MoE; not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Both are tokenization-related regressions, but one is version-to-version tokenization drift and the other is a flash-attention generation failure." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Import error in sentence-transformers vs a PyTorch version check bug in flex_attention; unrelated code paths." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embedding weights in UMT5 loading vs AutoProcessor kwargs forwarding; different loader layers and symptoms." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both involve tokenizers, but one is decoder type selection and the other is Deepseek tokenization correctness; not the same concrete defect." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "45278 is a broad import-regression report, but 38617 is a specific missing symbol import; too general to treat as the same bug." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM threaded dataloaders vs dtype mismatch CI issue; different problems." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GenerationConfig validation error vs RoPE implementation discussion; not the same failure mode." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Module import failure vs LayoutLMv3 error-message clarity; unrelated." + }, + { + "left": "issue:43611", + "right": "issue:46002", + "accept": false, + "reason": "Model loading with base_model_prefix vs NaNs in classification heads after checkout/init; different code paths." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 behavior API message vs missing image-patch helper on GLM46V; unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility bug vs flex_attention version-check bug; different issues." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "VitPose model breakage vs Ministral FlashAttention failure; different model families and causes." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Wrong optimizer states under FSDP2/PEFT loading vs missing generation cache in chunked prefill; not the same bug." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example script multi-label output issue vs SigLIP2 implementation discrepancy; different domains." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "SGD argument handling vs trainer.evaluate after train; unrelated trainer behaviors." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is save_pretrained key serialization and the other is from_pretrained loading failure; distinct defects." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5/MoE, but one is a broader v5/Qwen3-VL-Moe bug and the other is a specific from_pretrained error; not enough to merge." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Classification example empty results vs stale pipeline translation error message; unrelated." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "qwen3_omni_moe feature-length helper behavior vs flex_attention import/version check; different components." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig invalid vs stale warning for num_return_sequences; different generation issues." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer mapping fallback bug vs flash_attention crash on s_aux=None; unrelated." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "General tokenizer loading regression vs Qwen3 offset_mapping bug; overlapping area but not the same underlying defect." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer correctness issues, but they affect different models and behaviors (offset mapping vs generation tokenization)." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing removed pipeline API vs flex_attention import/version check; documentation vs runtime bug." + }, + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "Serialization of tied lm_head weights vs NaNs on init/checkout; different symptoms and code paths." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig validation error vs Qwen3.5 flash-attention generation failure; not the same bug." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "VRAM leak in multi-threaded Qwen3ForCausalLM use vs isolated reproduction of another issue; no concrete shared 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": 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-10000-403", + "nodes": [ + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42490", + "issue:42617", + "issue:42673", + "issue:42831", + "issue:43012", + "issue:43066", + "issue:43122", + "issue:43408", + "issue:43421", + "issue:43450", + "issue:43577", + "issue:43582", + "issue:43673", + "issue:43742", + "issue:43874", + "issue:43937", + "issue:43986", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44291", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44496", + "issue:44829", + "issue:44933", + "issue:45071", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45405", + "issue:45446", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45561", + "issue:45656" + ], + "soft_pairs": [ + "issue:43450|issue:43986", + "issue:44291|issue:45071", + "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:44829|issue:45216", + "issue:44484|issue:45310", + "issue:42371|issue:44261", + "issue:43408|issue:43742", + "issue:42673|issue:43582", + "issue:42617|issue:45341", + "issue:42222|issue:45542", + "issue:44933|issue:45278", + "issue:42490|issue:42673", + "issue:42175|issue:42222", + "issue:43937|issue:44496", + "issue:38617|issue:44220", + "issue:42371|issue:42831", + "issue:43066|issue:43122", + "issue:44483|issue:45464", + "issue:44075|issue:45656", + "issue:43673|issue:45341", + "issue:43012|issue:43577", + "issue:43874|issue:44261", + "issue:44484|issue:45478", + "issue:44410|issue:45478" + ], + "prepared_review_unit_hash": "6c4da4618f6640e8e4de47ed70e777ed40d417aa61b07524db031227d629cf31", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35629, + "estimated_input_tokens": 8908, + "estimated_eval_tokens": 18072 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is largely heterogeneous: several tokenizer/import/version-regression reports overlap superficially, but they do not appear to be the same underlying bug. No soft pair looks mergeable into a single issue or PR.", + "confidence": 0.86, + "canonical_issue_reason": "Issue 45278 is the closest umbrella candidate because it broadly covers import regressions after upgrading to 5.5.0, but the cluster is too mixed for a strong true canonical duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45278 is the most representative broad regression report in the set, but only as a loose umbrella; it is not a true duplicate of the other items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Both touch video-processing flows, but one is a shape bug and the other is a crash from missing torchvision; different failure modes and code paths." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "Both are v5 loading/type-related regressions, but one is an init_empty_weights argument issue and the other is a PreTrainedConfig type-checking break." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Unrelated problems: a released-version dependency pin vs a PyTorch version check for flex_attention import." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Both mention testing utils, but one is a small bug and the other is an xdist race on captured_info.txt; not the same defect." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizer internals, but one is a mapping lookup returning None and the other is a Mistral regex patch crash." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and likely different API breakages." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Both are tokenizer behavior issues, but one is wrong offset mappings and the other is runtime special-token/post-processor sync." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Different Qwen-family issues: missing projections in qwen3next vs a from_pretrained error in Qwen3.5 MoE." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "One is a training degradation with flash_attention_3, the other is a save_pretrained checkpoint regression; different code paths." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "A max_shard_size question is unrelated to a Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API guidance and an rms_norm_eps precision bug are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Different model-loading failures: a model-type mismatch warning vs a key error for a specific model." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "A VRAM leak in multithreaded Qwen3 inference and an Apple Silicon TypeError in caching_allocator_warmup are distinct issues." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "A 3d_parallel.py execution problem and a testing_utils bug are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "A broken VitPose model family and a backend detection issue with tensorboard-only installs do not share the same root cause." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related, but 45278 is a broad upgrade regression while 44933 is a specific missing image_utils export." + }, + { + "left": "issue:42490", + "right": "issue:42673", + "accept": false, + "reason": "A trailing-slash local-path import warning and a VRAM leak in Qwen3 multithreaded use are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Package/backend installation coverage and a broken VitPose model are different problems." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "One is a missing method on a vision processor fast class; the other is an unrecognized model/config issue." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "Both are generic framework bugs, but one is an import error and the other is an audio feature-extraction failure." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 configuration messaging and FineGrainedFP8 accuracy are not the same bug." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both are tokenizer/version regressions, but one is a wrong decoder type and the other is changed tokenization output." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both involve chat/completions, but one is a general request rejection and the other is a streaming inference failure on a specific model." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "Both involve optimizers, but one says SGD args are ignored while the other says optimizer.step is called twice under deepspeed." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "A generation cache regression and a testing_utils bug are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Both mention dtype/precision, but one is a compile-time warning and the other is incorrect model dtype propagation on load." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "One is a missing image-patch-count method in a GLM vision processor, the other is an rms_norm_eps precision issue." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "A save_pretrained shard-size question is unrelated to a Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen-family failures: missing layer projections vs a from_pretrained error." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 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-10000-403", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42222", + "issue:42757", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43502", + "issue:43531", + "issue:43824", + "issue:43873", + "issue:43874", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44704", + "issue:44829", + "issue:44987", + "issue:45003", + "issue:45071", + "issue:45103", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45459", + "issue:45542", + "issue:45588" + ], + "soft_pairs": [ + "issue:44263|issue:44485", + "issue:43097|issue:44493", + "issue:42222|issue:45459", + "issue:41628|issue:45071", + "issue:43012|issue:43408", + "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", + "issue:43986|issue:44484", + "issue:44117|issue:44987", + "issue:43874|issue:44263", + "issue:43408|issue:44368", + "issue:43976|issue:45071", + "issue:43986|issue:45372", + "issue:43531|issue:45341", + "issue:38617|issue:42757", + "issue:44261|issue:44485", + "issue:43064|issue:44315", + "issue:44062|issue:44117", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "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" + ], + "prepared_review_unit_hash": "d1e3d1b36efb4acdc062cacd6d6adeec10755af6fbf94bb94ba4e6edcf70d78b", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37683, + "estimated_input_tokens": 9421, + "estimated_eval_tokens": 19098 + }, + "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 regressions: import errors, model-specific loading failures, config/warning regressions, and a few training/runtime bugs. None of the soft pairs look like the same underlying issue, so all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43097 is the broadest v5 compatibility regression in the set and the closest thing to a cluster hub; it has cross-references and reflects a general API break rather than a model-specific symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43097 is the best representative issue here because it captures generic Transformers v5 breakage with broader impact, while the others are narrower model- or dependency-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "Both are GLM-related, but one is a torch.split indexing bug and the other is a RoPE implementation issue; different code paths." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Both are v5 regressions, but one is a missing config flag warning and the other is an unexpected position_id key; not the same bug." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "Completely different symbols and dependencies: vitpose model breakage vs tokenizer protobuf error handling." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Top-level import/type issues, but AutoImageProcessor import failure and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Both mention warnings, but a bfloat16 precision warning and a sam3_video/sam3_tracker type mismatch are distinct." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "FlashAttention is common, but one is a load-time failure and the other is a training-quality regression; not mergeable as one fix." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "No concrete overlap beyond being runtime regressions." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Same broad Qwen/VL family, but weight-shape mismatch and missing projection layers are different model bugs." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "Different scope: SwitchTransformers sparse-layer construction vs config type checking." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Both concern Qwen3-VL, but a load mismatch and a Qwen3-VL-Moe issue are different concrete failures." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated internals: sys.modules access vs a testing utility bug." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Both affect v5 loading, but gguf_file handling and a removed config option are distinct paths." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Video-model processor crash and testing_utils bug have no shared code path." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "Different features: torchvision-dependent processor loading vs shard-size documentation/behavior." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None and physical-intelligence/fast loading failure are not the same underlying bug." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Both GLM-related, but one is an image patch counter method missing and the other is torch.split return handling." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Different model families and warnings." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "Python-version compatibility vs config type checking; unrelated." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Processor-loading crash due to missing torchvision vs mistral_common import error; different dependencies and failures." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Sliding-window MoE behavior vs testing_utils bug; unrelated." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are ImportErrors from internal symbols, but they refer to different missing names/modules and likely different release breakages." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Both touch GLM-5-ish internals, but RMS epsilon config and RoPE implementation are separate numeric issues." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Training/FSDP optimizer-state bug vs Liger-kernel application bug; different integration paths." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken argument duplication and tokenizer mapping None are separate tokenizer loader issues." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen config/model problems, but missing projections and a dropped vision-index config field are different concrete bugs." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Both are import failures, but layer_type_validation and HybridCache are unrelated symbols." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Both are Qwen3-VL/MoE related, but the reported failures are different model defects." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Processor kwargs forwarding and auto_docstring annotation handling are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "local_files_only networking bug vs missing embed_tokens weight loading are different issues." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Processor/vision dependency crash vs tokenizer mapping bug; unrelated." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Offloading/quantization behavior and tie_embeddings removal are different regressions." + }, + { + "left": "issue:43824", + "right": "issue:43986", + "accept": false, + "reason": "Qwen2.5-VL import error and video processor torchvision failure are different model/dependency paths." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "A tokenizer decoder-type regression and an isolated reproduction of another issue are not enough to treat as the same bug." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "Config warning removal and docs behavior mismatch 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": 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-10000-403", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43381", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43550", + "issue:43582", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43901", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44077", + "issue:44222", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45290", + "issue:45381", + "issue:45478", + "issue:45479", + "issue:45753" + ], + "soft_pairs": [ + "issue:43825|issue:44655", + "issue:43992|issue:44484", + "issue:43208|issue:43550", + "issue:43012|issue:44368", + "issue:43352|issue:44380", + "issue:42886|issue:43381", + "issue:43012|issue:43550", + "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:36683|issue:43582", + "issue:44483|issue:44514", + "issue:44222|issue:45478", + "issue:42490|issue:43012", + "issue:43012|issue:44683", + "issue:43618|issue:43761", + "issue:42757|issue:43824", + "issue:43618|issue:44380", + "issue:38617|issue:43502", + "issue:44038|issue:44230", + "issue:44483|issue:45290", + "issue:43756|issue:44485", + "issue:43299|issue:43867", + "issue:44483|issue:45381", + "issue:43901|issue:44655", + "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:36010|issue:42757" + ], + "prepared_review_unit_hash": "1616aab27087dc3e2747f880a093122185c0e7150b8fa6936ccd816f8c849dc2", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37361, + "estimated_input_tokens": 9341, + "estimated_eval_tokens": 18938 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is very heterogeneous: it mixes unrelated import errors, model-specific regressions, saving/loading bugs, and backend-specific behavior changes. None of the soft pairs look like true duplicates or mergeable into a single fix.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 43825 is the least ambiguous, self-contained user-facing regression in the set, but the cluster is too mixed for a strong canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "43825 is the best available representative, but only because no other issue meaningfully spans the cluster; this is not a strong duplicate hub.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Different failures: a v5 pipeline error-message regression vs saving Pipeline objects." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Unrelated bugs: missing embed_tokens.weight in UMT5 loading vs save_pretrained shard-size behavior." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different models and paths: xLSTM training blockers vs Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both are warnings, but about different causes and models; not the same code-path problem." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Different concrete issues: unsupported Flash Attention in Nemotron vs GPT2 attention scaling ignored under SDPA/FA." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading bug vs gradient checkpointing in eval mode; unrelated behaviors." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "Precision warning during compile is unrelated to Bamba SDPA compilation failure." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized models is unrelated to a Qwen3.5 image-generation infinite-loop report." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Model dequantization save bug vs saving Pipeline objects are different save paths." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention-scaling backend bug is unrelated to the zero-loss classification bug." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Flash-Attention support error vs Python version support regression; different problems." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to GPT2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training blockers vs BeitImageProcessorFast reduce_labels returning one label; different components." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Gemma3Config missing vocab_size is unrelated to Apple Silicon caching_allocator_warmup TypeError." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Chat-completions request rejection vs batched apply_chat_template crash are different API paths." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 MoE/FP8, but one is save_pretrained and the other from_pretrained; not the same concrete bug." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Local-path trailing-slash warning is unrelated to a bfloat16 compile warning." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "PyTorch precision warning is unrelated to compiled flex_attention failure on torch>=2.9." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP regressions, but one loses attentions and the other loses hidden_states; not the same fix." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Different import errors from different modules: huggingface_hub vs transformers Qwen2.5-VL class." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP output regression is unrelated to GPT2 attention scaling backend behavior." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Importing layer_type_validation is unrelated to local_files_only still making API requests." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Qwen3-VL-Moe loading regression vs FP8 infer support request; not the same bug." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Both are chat/template issues, but one is a v5 chat-completions request failure and the other is a tool-call template crash." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "RoPE layer mismatch in Smollm3 is unrelated to GLM-5 RoPE implementation discussion." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-Moe loading regression vs state_dict-sorted load error are different concrete failures." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "Chat completions rejection is unrelated to Qwen2.5-VL video vision_position_ids being wrong." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mentioning return_all_scores do not match saving Pipeline objects." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model save failure is different from Pipeline.save_pretrained failure." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config vocab_size missing is unrelated to SAM 3 vision encoder output missing fpn_position_embeddings." + }, + { + "left": "issue:44222", + "right": "issue:45479", + "accept": false, + "reason": "FP8 MoE save/load bug is unrelated to a zero-loss classification bug across models." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Trailing-slash import warning is unrelated to bfloat16 compile precision warnings." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "Precision warning during compile is unrelated to flex_attention compilation failure." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Two different CLIP output regressions with different missing fields; not one duplicate." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Different import paths and missing symbols; no shared underlying bug." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Configuration import error is unrelated to unwanted network requests under local_files_only." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Model-loading regression and FP8 inference support are not the same change." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Both touch chat APIs, but they are distinct failures in different code paths." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Different RoPE-related issues in different models; no clear shared fix." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Different load/save failures; no evidence of one underlying bug." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model saving and Pipeline.save_pretrained are different save mechanisms." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Flash Attention support error is unrelated to invalid GenerationConfig handling." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "patchtsmixer post_init validation is unrelated to GPT2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "State_dict-sorted load error and v5.4.0 checkpoint corruption are related by loading/saving, but not the same concrete bug." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Different import failures from different packages and symbols; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 44, + "review_unit_count": 47, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-403", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42490", + "issue:42890", + "issue:42898", + "issue:43010", + "issue:43064", + "issue:43066", + "issue:43352", + "issue:43525", + "issue:43575", + "issue:43611", + "issue:43618", + "issue:43867", + "issue:43931", + "issue:43976", + "issue:43992", + "issue:44075", + "issue:44077", + "issue:44188", + "issue:44242", + "issue:44246", + "issue:44263", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44484", + "issue:44492", + "issue:44655", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44977", + "issue:45071", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45561", + "issue:45593", + "issue:45850" + ], + "soft_pairs": [ + "issue:42898|issue:43066", + "issue:36683|issue:44077", + "issue:43611|issue:44655", + "issue:43976|issue:44938", + "issue:36683|issue:43525", + "issue:43352|issue:45593", + "issue:43618|issue:45216", + "issue:44263|issue:45440", + "issue:36683|issue:44242", + "issue:44188|issue:44380", + "issue:43064|issue:44492", + "issue:43352|issue:43931", + "issue:43992|issue:45310", + "issue:43010|issue:45278", + "issue:43867|issue:45375", + "issue:41669|issue:44246", + "issue:44355|issue:44855", + "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" + ], + "prepared_review_unit_hash": "3aea0afb79d4415ca791cd63fdd2b996a98669e303975976408185eba7cc3431", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37070, + "estimated_input_tokens": 9268, + "estimated_eval_tokens": 18792 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of Transformers v5 regression reports: import/load failures, model-specific config/key mismatches, tokenizer behavior changes, and a few performance/parallelism issues. The only plausible duplicate edge is the import-time slowdown pair.", + "confidence": 0.58, + "canonical_issue_reason": "issue:45278 is the broadest representative of the shared v5 breakage/import-regression theme across the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most representative issue because it captures the broad version-upgrade regression pattern rather than a single model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42898", + "right": "issue:43066", + "accept": false, + "reason": "Both are tokenizer-related v5 changes, but one is about clean-up spacing behavior and the other about decoder type; different bugs." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Missing Gemma3 config attrs and patchtsmixer post_init gating are unrelated model-specific issues." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "Base-model-prefix loading breakage and Pipeline save_pretrained failure affect different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both concern Python-version compatibility, but they report different failures and likely different causes." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3 missing vocab_size and Llama4 missing pad_token_id are separate config omissions." + }, + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "Flash Attention support error for Nemotron is unrelated to D-FINE auxiliary-loss handling." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIPOutput attentions assignment and Qwen3.5 save_pretrained checkpoint corruption are different bugs." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "GlmMoeDsaIndexer torch.split behavior and DeepseekV3MoE divergence are different model implementation issues." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Missing Gemma3Config vocab_size and missing load-balancing loss with output_router_logits=False are unrelated." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "Both mention attention behavior, but one is a compile-time branching issue and the other is backend scaling config handling." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption is unrelated to a cache-strategy typo." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Nemotron Flash Attention support and Qwen3-VL weight-shape mismatch are unrelated model-specific failures." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Both involve from_pretrained errors, but for different models and different missing-state behavior." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Cache update no_grad decoration is unrelated to broad import-error regressions." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "A sorted-state_dict load error and a missing Qwen3_5MoeVisionConfig field are different issues." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both point to the same import-time slowdown problem; one explicitly identifies wildcard imports in models as the cause." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Running compiled Python files and TorchScript parse/IndentationError on Python 3.13 are different failure modes." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Config attribute absence and FSDP2/PEFT optimizer-state mismatch are unrelated." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Seed-related flaky tests and xdist race on captured_info.txt are different testing issues." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Python 3.14 import failure and PretrainedConfig type-checking regression are different problems." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "These are both save/load regressions, but one is a generic state_dict ordering issue and the other is Qwen3.5 visual-key corruption." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "No-grad cache updates and a generic complaint that v5 breaks too many models are not the same bug." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Both are from_pretrained errors, but they target different Qwen variants and different symptoms." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache update semantics and Python-version compatibility are unrelated." + }, + { + "left": "issue:44938", + "right": "issue:45381", + "accept": false, + "reason": "Python 3.14 load failure and Qwen2.5-VL video vision_position_ids bug are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "CLIPOutput attentions regression and patchtsmixer post_init policy are different issues." + }, + { + "left": "issue:42490", + "right": "issue:44075", + "accept": false, + "reason": "Local-path import warning and SGD optimizer args not being used are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug and Qwen2-57B-A14B-Instruct OOM are different scaling problems." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer ReLU discussion and DeepseekV3MoE divergence are unrelated implementation issues." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "AutoModel missing PyTorch and tokenizer loading regression are different loading failures." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Generic model-loading error and max_shard_size behavior/question are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "CLIP attentions regression and LwDetrImageLoss AMP crash are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "CLIP attentions assignment and Qwen3.5 flash-attention generation failure are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the cluster does look like a mix of v5 regression reports spanning import/load failures, tokenizer changes, config/key mismatches, and a few performance/parallelism issues. The canonical issue choice is reasonable as a broad representative, and the one accepted soft-edge pair (41669/44246) is a plausible duplicate on import-time slowdown. The rejected pairs are mostly conservative and do not overclaim sameness based on weak title similarity alone." + }, + "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": 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-10000-403", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43065", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43576", + "issue:43673", + "issue:43723", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:44062", + "issue:44112", + "issue:44222", + "issue:44230", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44387", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44655", + "issue:44749", + "issue:44908", + "issue:44938", + "issue:44961", + "issue:44964", + "issue:45071", + "issue:45125", + "issue:45341", + "issue:45375", + "issue:45468", + "issue:45478", + "issue:45600" + ], + "soft_pairs": [ + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43723|issue:44556", + "issue:44222|issue:45125", + "issue:44387|issue:44556", + "issue:42890|issue:45341", + "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:43502|issue:44222", + "issue:42831|issue:43874", + "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:45071", + "issue:43576|issue:43824", + "issue:31795|issue:38617", + "issue:41628|issue:42548", + "issue:44961|issue:45468", + "issue:38617|issue:43576", + "issue:43576|issue:44938", + "issue:43673|issue:44492", + "issue:44908|issue:44961", + "issue:44485|issue:44961" + ], + "prepared_review_unit_hash": "dd0001691f318a3e65fce21d50a06beffabcb49b697492f2d1ca72f8bad9a163", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 40, + "serialized_chars": 39022, + "estimated_input_tokens": 9756, + "estimated_eval_tokens": 19768 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is noisy and spans many unrelated Transformers issues: import errors, model-loading regressions, test flakiness, docs, FP8/quantization, and other model-specific bugs. None of the proposed soft pairs look like the same underlying defect.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue stands out: the items are not duplicates of one another and cover several distinct bug classes.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a good global canonical representative because the cluster is heterogeneous rather than one concrete bug family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "SamHQ integration-test flakiness is unrelated to a Phi-4 multimodal model-loading failure." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Different failures: missing set_seed in SamHQ tests vs a GraniteSpeech CI device-override issue." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "SamHQ test nondeterminism is not the same as stale auto_mappings references to removed Sam3LiteText configs." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "A local_files_only network leak and an AddedToken keyword collision are unrelated code paths." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Both mention loading, but one is AutoTokenizer loading in v5 and the other is checkpoint reload after a version upgrade; not the same bug." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained for MoE and a missing tensor-parallel plan are distinct issues." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization OOM and checkpoint reload incompatibility are different regressions." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "A SamHQ flaky test is not the same as a generic testing_utils bug." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Missing PreTrainedModel import and missing HybridCache import are separate symbol-export problems." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Cache update no_grad behavior and a dummy Conv2d in Sam3PixelDecoder are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Local-files-only network requests do not match a GLM-5 RoPE implementation bug." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file load errors and a training/filtering slowdown after upgrade are different symptoms." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "A missing _tp_plan for tensor parallelism is not the same as a Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence Transformers getting stuck loading is unrelated to documentation confusion in model.forward." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Decorating cache update methods with no_grad is a different change than fixing generation kwargs after sync_gpus." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Tensor-parallel planning and a missing config field silently dropped by @strict are different bugs." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLFlow failure reporting and a tokenizer-loading regression are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Qwen3VL MoE loading in v5.0.0.dev0 and reload failure after upgrading to v5.2/v5.3 are not the same concrete issue." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "A local_files_only API leak is unrelated to FP8 save_pretrained for MoE models." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "An FP8 accuracy issue and a missing image-processor method are different defects." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel not applied via model_init has nothing to do with the DSA indexer ReLU discussion." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "A real loading/network regression and an unrelated placeholder issue titled 'racoon' are not duplicates." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled Python file errors and v5.4.0 PretrainedConfig type-checking breakage are different problems." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLFlow job status reporting and tensor-parallel training bugs are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled-file loading errors and inability to save Pipeline objects are different code paths." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still referencing pipeline() and an unrelated 'racoon' issue are not the same bug." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both mention FP8/MoE, but one is about saving pretrained weights and the other about inference support." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading breakage are different concrete failures." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "An import error from huggingface_hub is not the same as the transformers env command breaking in v5." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Broken transformers env command and PretrainedConfig type-checking regression are different issues." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "The env command bug and AutoTokenizer/AutoImageProcessor import failures are not the same underlying defect." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion in model.forward is unrelated to a missing layer_type_validation import." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "AutoImageProcessor import failure and PreTrainedModel import failure are separate symbol export regressions." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "The placeholder 'racoon' issue is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "Missing layer_type_validation import and the v5 env-command failure are different bugs." + }, + { + "left": "issue:43576", + "right": "issue:44938", + "accept": false, + "reason": "Broken env command and Python 3.14 load failure are distinct issues." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked-prefill GenerationMixin cache missing and a cache-strategy typo are not the same defect." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling is unrelated to the placeholder issue titled 'racoon'." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to the placeholder issue titled 'racoon'." + } + ] + }, + "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-10000-403", + "nodes": [ + "issue:36296", + "issue:41628", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44246", + "issue:44261", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44393", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44704", + "issue:44861", + "issue:44908", + "issue:44945", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45341", + "issue:45362", + "issue:45478", + "issue:45542", + "issue:45753", + "issue:45850" + ], + "soft_pairs": [ + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "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:44393|issue:45753", + "issue:44038|issue:45125", + "issue:43576|issue:44556", + "issue:44393|issue:45071", + "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" + ], + "prepared_review_unit_hash": "f5b0bd2f43c28a53d29a269fba5c9a8b1a00ab8f74f6bd919d79c19c6a1d6ab1", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 36, + "serialized_chars": 37285, + "estimated_input_tokens": 9322, + "estimated_eval_tokens": 18900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated issues, with a loose theme of v5 migration regressions and model-specific breakages, but no soft pair looks like a true duplicate. There are no PRs in the cluster.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45850 is the broadest umbrella in the set and best matches the cluster\u2019s general theme of widespread v5 breakage, though it is very vague.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most useful representative because it is concrete about upgrade-induced breakage while still capturing the broader regression pattern.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Different problems: tensor parallel training vs a docs mismatch for text classification." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Import/export failure for AutoImageProcessor is unrelated to compiled Python file errors." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training and BEiT image processor label reduction are unrelated code paths." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Specific Qwen3.5 chat crash is not the same as a broad complaint about many models breaking." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "Different subsystems: MLA layernorm config precision vs DSA indexer activation logic." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "One is a specific processor save_pretrained bug; the other is an unspecific placeholder report." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading behavior is unrelated to the TensorFlow backend/tensorboard installation issue." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Both touch loading/import mechanics, but not the same concrete bug or failure mode." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Different model-family visual bugs: bbox hallucination vs infinite loop on a specific image." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "General Qwen3-VL bug is not the same as missing tensor-parallel plan metadata." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "v5 env-command breakage and checkpoint reload incompatibility are separate failures." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "A vision-model bbox output issue does not match a PretrainedConfig typing regression." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "A missing pad_token_id on Llama4Config is a specific config bug, not the same as a broad v5 complaint." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star performance issues and missing generation cache are different code-path problems." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both involve model loading after version changes, but the underlying failures differ." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "A typo in cache strategies is not the same as a generic report that many models break." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "StableLmConfig missing pad_token_idx is a specific config regression, not the broad v5 breakage claim." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API guidance and a cache-strategy typo are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "Both mention kwargs, but one is processor loading and the other is scheduler behavior." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "A flaky integration test is unrelated to scheduler kwargs handling." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Both are broad v5 regressions, but one is about import errors and the other about many models breaking; not the same bug." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import slowness is not the same as a lazy-loading malfunction." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Model-type warning and Liger Kernel application in model_init are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility and a Qwen3-VL output bug are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention support for NemotronH is unrelated to Qwen3-VL bounding-box errors." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save metadata mismatch is not the same as an unspecific bug report." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Position_ids buffer access error is a distinct model-state bug." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are separate issues." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star cleanup/performance is unrelated to missing HybridCache exports." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "A model import-star issue is not the same as a testing_utils bug." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache strategy typo and pipeline-parallelism output errors are unrelated." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "Missing a model method in GLM46V is a specific implementation bug, not a broad v5 breakage report." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen bugs affecting different models and behaviors." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "Optional post_init policy and tied-weight key crashes are not the same underlying bug." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() is unrelated to inverse_sqrt scheduler kwargs 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": 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-10000-403", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:37428", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43606", + "issue:43618", + "issue:43704", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44315", + "issue:44360", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45230", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45850" + ], + "soft_pairs": [ + "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", + "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:44492|issue:44998", + "issue:44861|issue:45290", + "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": "3d8ea24ce17851162fea502cf03773ee5ee3996a059a72bcf0186c62cca178c9", + "component_budget": { + "node_count": 403, + "item_count": 403, + "soft_pair_count": 1509, + "serialized_chars": 778296, + "estimated_input_tokens": 194574, + "estimated_eval_tokens": 389404 + }, + "budget": { + "node_count": 42, + "item_count": 42, + "soft_pair_count": 40, + "serialized_chars": 35533, + "estimated_input_tokens": 8884, + "estimated_eval_tokens": 18024 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is still mostly heterogeneous. The tokenizer pair (42913/43066) is clearly related and likely stems from the same v5 tokenizer transition, but with only title-level evidence it should be treated as possibly related rather than a definite duplicate. The rest of the soft edges remain conservative rejections across different code paths or features.", + "confidence": 0.78, + "canonical_issue_reason": "issue:42913 is the broadest tokenizer-v5 regression report in the set; issue:43066 looks closely related, but the available evidence is not strong enough to treat them as the same bug with high confidence.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42913 is the best overall issue candidate because it captures the broader user-visible tokenizer behavior change, making it the most useful umbrella if the pair later proves to be the same underlying regression.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Different problems: documentation confusion vs tokenizer loading regression." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Unrelated: import-star cleanup/perf issue vs scheduler kwarg handling." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Both are training-related, but they describe different failure modes and code paths." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Different features: env command breakage vs lazy loading behavior." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving pipeline objects is unrelated to tied-weight key crash handling." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer activation issue vs Gemma-4 audio positional encoding bug." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report vs a specific Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading and inverse_sqrt scheduler kwargs are different subsystems." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp bug vs GLM-5 RoPE implementation issue." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "No shared code path: processor timestamp math vs scheduler configuration." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star refactor/perf discussion is unrelated to VRAM leakage in multi-threaded loading." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion is not the same as a model-loading regression for a specific checkpoint." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Different surfaces: model.forward docs vs flash-attention import error." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Both touch model creation/loading, but the concrete incompatibilities differ." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Different model architectures and different implementation bugs." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in threaded inference is unrelated to RoPE math." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 settings API change is unrelated to the dataloader-thread VRAM leak." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "Local-files-only network access bug is unrelated to processor timestamp calculation." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Processor timestamp bug and save_pretrained missing files are different code paths." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Processor timestamp logic vs multi-thread VRAM leak are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "Different low-level math/indexing issues in different models." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to Gemma-4 positional encoding." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Precision/config epsilon issue is not the same as Gemma-4 audio encoding bug." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Highly related tokenizer-v5 reports, but title-level evidence is not enough to call them a definite duplicate or the same regression." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs bug is unrelated to an unemployment placeholder issue." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "Typo in cache strategy naming is unrelated to the placeholder issue." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight-key crash and chat-template tool-call crash are different failure points." + }, + { + "left": "issue:44998", + "right": "issue:45850", + "accept": false, + "reason": "Placeholder/unemployment issue is unrelated to a broad v5 breakage complaint." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to the placeholder issue." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "Unemployment placeholder is unrelated to a testing_utils bug." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config is unrelated to tied-weight key handling." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is unrelated to tied-weight key extraction." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Checkpoint loading slowness and missing import errors are different issues." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support request is unrelated to processor save_pretrained file omissions." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow reporting on failed training jobs is unrelated to checkpoint loading speed." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint loading slowdown vs tensor-parallel training bug are different problems." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Loading performance issue and model.forward documentation confusion do not share the same code path." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "FP8 support request is unrelated to Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Checkpoint load slowness and tokenizer loading regression are different behaviors." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching audio support and FP8 inference support are separate feature gaps." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The analysis is mostly grounded, but it overstates the tokenizer pair: from the packet we can see strong topical similarity between issue:42913 and issue:43066, yet not enough to call them a clear duplicate or the same regression with confidence. The summary should hedge more (e.g., 'likely related' or 'possibly duplicate') unless there is body-level evidence. The rest of the soft-edge rejections are conservative." + }, + "evaluator_used": true, + "retried": true, + "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": "482c132974ebc86002c363525641bbdfcd419c87d0a5b54f721f1dcb3804d248", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2477, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2477, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The three issues do not look like duplicates of one another: one is about Tapas tokenization behavior, one about a private-model download/login error message, and one about a generic model-loading failure for bert-base-uncased.", + "confidence": 0.95, + "canonical_issue_reason": "There is no strong canonical duplicate here; the reports describe different failure modes. If forced to anchor the cluster, issue 16618 is the broadest model-loading report, but it still does not match the other two.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 16618 is the best anchor only in the sense that it is the most general and discussed model-loading complaint. It is still not a true duplicate of the Tapas tokenization or 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 different underlying problem from a bert-base-uncased model-loading failure." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Private-model download/login error message is unrelated to the generic 'can't load model' report." + } + ] + }, + "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": "c354484ed5f5b9b5cdd845c5c5aa1f7675bf1c7808b7ec5ebc4c5558e24a1def", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two unrelated feature-request issues: one for Flash Attention 2 support on more architectures, the other for GGUF support on more architectures. They share only a broad \u201ccommunity contribution\u201d framing and are not 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:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different underlying requests and code paths: Flash Attention 2 support vs GGUF support. Same broad architecture-support theme, but not the same bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "450c0ab5018b102e02fe9c93ea3087291043bb36c8a87aa00417fd6462a99c8c", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6442, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6442, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster mixes two concrete locale requests (Turkish, Spanish) with three near-identical generic template issues. The generic template issues are the best representative of the cluster, but none of the pairs are strong enough to merge as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": "issue:44365 is the cleanest representative of the near-identical generic template-style issues; the Turkish and Spanish issues are distinct locale-specific requests.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44365 best captures the cluster\u2019s shared template wording and is closest to the other generic entries.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Turkish docs translation and a generic placeholder translation issue are not the same concrete request." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Turkish locale request versus a generic template issue; different underlying task." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Concrete Turkish translation request does not match the generic placeholder issue." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Different target languages (Turkish vs Spanish) make these distinct issues." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Spanish translation request is not the same as the generic template issue." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Spanish locale request versus a generic placeholder issue; not the same underlying bug/change." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Different concrete locale requests; only broad translation theme is shared." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "These are near-identical template issues, but the evidence is insufficient to say they are the same concrete issue." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Highly similar generic wording, but no explicit evidence of one underlying issue rather than repeated template entries." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Nearly identical placeholder text, but not enough proof they refer to the same concrete task." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 5, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-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": "6a52ed0d3a7b09a51fdcaa56a1c4a79e48b8c0ffd821a2496aa43c1baa34260b", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20706, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20706, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is a collection of broadly similar model-addition requests, but the underlying models, modalities, and code paths are different. I do not see true duplicates or a single canonical issue/PR for merge triage.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "EuroBert config support vs DEIMv2 addition: different model families and likely different implementation paths." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert model config request vs Qwen3-TTS speech support; unrelated modalities and code changes." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert config vs RF-DETR object detection model; different architecture and files to touch." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are distinct vision models; same broad subsystem, but not the same underlying change." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR detector vs LFM2.5 Audio model; different modality and implementation scope." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR addition vs a sparse transformer request; unrelated model families and code paths." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR detection model vs Qwen3-ASR speech recognition; different modality and concrete change." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR detection model vs Qwen3-TTS support; not the same bug/change." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT text model request vs Qwen3-ASR speech request; different model targets." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT addition vs sparse transformer support; different architecture and likely different files." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT vs LFM2.5 Audio; text model request and audio model request are not duplicates." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are unrelated model additions across different domains." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are different model requests; only broad theme of adding a model." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture request vs Qwen3-ASR support; different model families and tasks." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 architecture vs weight-sparse transformer request; not the same concrete change." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 architecture request vs ModernVBERT models; distinct model integrations." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 architecture vs Voxtral TTS support; unrelated model/task." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 vision model request vs Qwen3-TTS speech support; different modality and code path." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT models vs Qwen3-ASR support; different model family and task." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT models vs Qwen3-TTS support; not the same underlying change." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT model addition vs broad BERT-like RoPE discussion; related theme but not a duplicate." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like RoPE architecture discussion vs Voxtral TTS support; unrelated request scope." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS vs Qwen3-ASR are related by family name but target different speech tasks and fixes." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Both are speech-related, but Qwen3-TTS and Voxtral-4B-TTS-2603 are different model integrations." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS support vs DeepSeek-OCR2 addition; different modalities and code paths." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS support vs sparse transformer request; different model class and implementation." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio are both audio-related but still distinct model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio are separate speech-model requests, not the same change." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR support vs EUPE model request; different model families and functionality." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR speech support vs sparse transformer request; unrelated code paths." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio vs SAM3-LiteText; audio model request versus vision/text model request." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Sparse transformer model request vs EUPE encoder request; distinct architectures and fixes." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR is speech recognition, while Voxtral-4B-TTS-2603 is text-to-speech; opposite tasks." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT text model request vs Voxtral TTS support; unrelated model additions." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR speech support vs DeepSeek-OCR2; different model domains and code changes." + } + ] + }, + "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": "abd24aa4ec8712eb8c481d9e4576fa44d8d857b0de0b0dfd84a082c73bbba98c", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6288, + "estimated_input_tokens": 1572, + "estimated_eval_tokens": 3400 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6288, + "estimated_input_tokens": 1572, + "estimated_eval_tokens": 3400 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are a loose similarity cluster, not a duplicate set: they cover unrelated bugs across model configs, loss plumbing, quantization typos, and tokenizer warnings. No pair looks like the same underlying fix.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Both mention normalization, but one asks about Llama4TextL2Norm semantics while the other is a ModernBERTConfig type-hint issue; different models and different defect types." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Unrelated bugs: Mask2Former ignore_value is unused, versus kwargs not being forwarded to a loss function." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Different subsystems and symptoms: Mask2Former loss parameter handling versus tokenizer regex warning behavior." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former ignore_value handling is unrelated to a typo in a quantization attribute name." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "One is a model-loss parameter bug, the other is a config type-hint mistake in a different model." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss-kwargs forwarding bug and ModernBERTConfig type annotation bug are distinct code paths and fixes." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A config type hint issue is not the same underlying problem as tokenizer regex warnings after a version change." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "ModernBERTConfig norm_eps typing and the quantization_operation typo are unrelated changes." + } + ] + }, + "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": "651d192913ec6eec67697e1ade1dd96774269597b3950612700611f589bf9bba", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated: one asks for block decoding support, the other for DeepSeek v3.2 support. They should not be deduplicated.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue; the requests target different features/problem domains.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither is a duplicate of the other. If one must represent the cluster, 'DeepSeek v3.2 support' is the clearer standalone feature request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different underlying requests: block decoding implementation vs DeepSeek v3.2 model support. They share no concrete bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "6c435e1d99eb3655afb5f87c4e82b59593e2891a8719dca43f33696443f93722", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two closed issues touch Trainer customization, but they describe different problems: one about `remove_unused_column` behavior, the other about FLOPs estimation for custom trainers. They are related in theme, not the same underlying bug.", + "confidence": 0.89, + "canonical_issue_reason": "Issue #43598 is the stronger canonical issue because it states a concrete Trainer behavior (`remove_unused_column`) and a specific customization limitation, making the scope clearer.", + "canonical_pr_reason": null, + "best_issue_reason": "#43598 is the best representative issue: it is narrowly actionable and describes an explicit Trainer setting that likely needs design/behavior changes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "The issues concern different code paths and outcomes: one is about unused-column removal in Trainer data handling, the other about FLOPs accounting for custom trainers. Shared customization context is not enough to treat them as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "f7e521b2970c2a7842af7f4234efce91d1aa4351c4b6a173b1ded8855040ba6e", + "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 different feature requests for different Qwen model families and different AutoModel heads, so they should not be clustered as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43684 is the broader request and is specifically about registering Qwen3-Omni with AutoModel and AutoModelForConditionalGeneration, which is the clearest standalone issue here.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43684 is the best representative because it names the concrete registration gap and is broader than the more specialized sequence-classification request in 44405.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model variants and different tasks: Qwen3-Omni registration for base/generation auto classes versus Qwen3.5 sequence-classification support. They do not appear to be 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": 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": "e4931f27018694fbc8f63c50aa15a21db45e1d1820b2e87bbe638a99013d98ac", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4267, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4267, + "estimated_input_tokens": 1067, + "estimated_eval_tokens": 2390 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All four issues are too under-specified to confidently deduplicate. Three share the same vague title, but there is no body/context to confirm they describe the same underlying problem; the lone different title looks unrelated.", + "confidence": 0.32, + "canonical_issue_reason": "issue:43845 is the best placeholder canonical issue because it is the earliest of the repeated 'huggingface' titles, but the cluster lacks enough detail to establish a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43845 is the strongest issue candidate only by virtue of being the earliest repeated-title report; still, the report content is too thin to be a reliable canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Titles do not match, and there is no body/detail tying 'Fett' to the 'huggingface' reports." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "No substantive evidence of the same underlying bug; titles are unrelated." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "No content links this issue to the 'huggingface' reports." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": false, + "reason": "Identical vague titles are not enough to confirm the same bug without body/context." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": false, + "reason": "Same broad title, but no description or targets to verify a shared underlying issue." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": false, + "reason": "Same repeated title, but insufficient evidence to treat them as definite duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 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": "e7553489ffd9fd8dd1946c6ae387cdb2f37296faf2f0adff2aa79a41ca7d5d28", + "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 are low-signal, likely unrelated spam/placeholder issues. Two pairs share the exact same placeholder title, but there is no evidence of a shared underlying bug or concrete change, so no soft merges are justified.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44371 is the earliest and simplest representative of the spam-like cluster, but only as a bookkeeping anchor rather than because it clearly matches a real underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44371 is the best single issue to keep as the cluster representative because it is earliest and generic, but the cluster itself does not appear to describe a real deduplicable issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Same placeholder title, but the content is too empty to establish the same underlying issue or bug." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Same placeholder title, but no concrete evidence links them to the same problem." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "These titles are not meaningfully the same issue; one is spam-like and the other is a generic documentation suggestion." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "No shared bug/change is visible; the titles are unrelated." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "Generic documentation suggestion versus spam placeholder; no same underlying issue is evident." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Generic documentation suggestion versus spam placeholder; not the same concrete problem." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Identical placeholder titles alone are not enough to confirm the same underlying bug or change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "No concrete overlap beyond low-signal similarity; the titles do not indicate the same issue." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "No concrete overlap beyond low-signal similarity; the titles do not indicate the same issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "18ff4fd5a3b447a07bf1f906b8f1152897c2896f2b36757fb50f2a162fa6d0cd", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1645, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1645, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues have identical titles and fairly similar lengths, but the packet only provides soft-similarity evidence. With no explicit links, shared targets, or body-level confirmation, this should be treated as a tentative match rather than a confirmed duplicate. The soft edge is rejected.", + "confidence": 0.71, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45145 is the best provisional issue candidate because it is earlier and already has an inbound reference, but the evidence is not strong enough to confirm a duplicate/canonical merge.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "Identical titles and soft similarity alone are not enough to confirm the same underlying issue. The packet does not show near-identical bodies, explicit links, or shared targets, and deterministic_accept is false." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports only a soft-similarity match and identical titles; it does not show the bodies are near-identical or that these are definitely duplicates. The soft-edge verdict is too strong: deterministic_accept is false in the packet, so a conservative verdict would be uncertain or tentative rather than accept." + }, + "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": "d777f1c0f728e4c2f0d9379e5a5d306a24a02001acda5f42275aa70ac42f104c", + "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": "The two issues both involve 4-bit inference behavior in the Gemma/BitsAndBytes stack, but they describe different failures: one is a torch.finfo() TypeError triggered by uint8 weights in audio modules, and the other is an AssertionError caused by llm_int8_skip_modules clearing the default lm_head exclusion. They are related by broad quantization context, not the same underlying bug.", + "confidence": 0.95, + "canonical_issue_reason": "Issue #45674 is the better canonical issue for the cluster only if one wants the broadest 4-bit BitsAndBytes inference regression bucket, but the reports are not duplicates and should stay separate. #45672 is more specific to Gemma4 audio-module dtype handling; #45674 is a distinct configuration/skip-modules bug.", + "canonical_pr_reason": null, + "best_issue_reason": "#45674 is the stronger standalone issue for a generic 4-bit inference regression because it includes a clear configuration trigger and an AssertionError tied to BitsAndBytesConfig behavior. #45672 is narrower and tied to a specific model/module path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different root causes and different failure modes: torch.finfo(TypeError) on uint8 weights in audio modules versus AssertionError from llm_int8_skip_modules removing the default lm_head exclusion. Shared 4-bit inference context is too broad to treat as 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": 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": "f6e1eb981b2d5914e3cebc0d8c22d011bb9afd6544ba674821e33e8d38a9649d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster contains two extremely sparse issue reports with unrelated personal-name-and-date titles. They do not look like duplicate bug reports; they look more like low-signal/spam entries.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45762 is the earliest issue and is no less representative than the other, but there is no evidence these two are the same underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45762 is the best cluster representative only because it is earlier; the pair does not appear to be a true duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Reject: the titles are different names/dates with no shared bug description, code path, or explicit linkage; they do not appear to be the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "b21478d066a696f4f8d33b987830cc99e3cb128ee2e394a1af77d7ad1e3f0fb7", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1481, + "estimated_input_tokens": 371, + "estimated_eval_tokens": 998 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1481, + "estimated_input_tokens": 371, + "estimated_eval_tokens": 998 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues are low-signal, name/date-only entries and do not describe the same bug, feature, or change. They should not be treated as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "The titles are different personal-name/date placeholders with no shared problem statement or code context, so they do not appear to represent 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": "6d7a66659b142f6dbae83a3964a0288c04d876e311248cbcd76da525026fd505", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5726, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5726, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster is not one single duplicate set: it splits into two exact-duplicate issue pairs (45870/45871 and 45872/45873). Issue 45869 is only loosely related by topic and does not look like a duplicate of either pair.", + "confidence": 0.93, + "canonical_issue_reason": "45870 is the clearest representative of the 'Example: Financial time series prediction with DataForge' thread because it is an exact duplicate of 45871 and has the strongest direct match in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "45870 is the best single issue to keep as the representative for one duplicate thread; it is an exact duplicate pair with 45871 and is more central than the loosely related dataset request in 45869.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Related financial/data topic, but the dataset bundle request and the DataForge example are different underlying issues." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Same as 45869 vs 45870: related theme, but not the same issue." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Same title and same apparent content; this looks like a direct duplicate." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Both mention financial time series/DataForge, but one is an example request and the other is a scraping-service/project request; not the same concrete issue." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Related broad topic, but different request and likely different underlying change." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Different issue themes; no sign they describe the same change or bug." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Different issue themes; only broad topical overlap." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Same title and same apparent content; this looks like a direct duplicate." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: 45870/45871 share the same title and metadata, as do 45872/45873, while 45869 is only topically similar. The conservative non-duplicate calls for the cross-pair comparisons are reasonable, and the representative selection of 45870 is supported by the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-13", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:45795" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:41855|pull_request:43424", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:44827", + "pull_request:43995|pull_request:45213", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:45795", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43823|pull_request:45795", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "2c866de12382430c951b6cadfa7bc35cb039a1b6b01e180f7db511fdf6119abf", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35205, + "estimated_input_tokens": 8802, + "estimated_eval_tokens": 17860 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 19, + "serialized_chars": 35205, + "estimated_input_tokens": 8802, + "estimated_eval_tokens": 17860 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated PRs; the only clear duplicate is the pair of loss-utils fixes around `fixed_cross_entropy`. Everything else targets different models, docs, or subsystems and should stay separate.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43251 is the best canonical representative for the one real duplicate pair: it has the explicit issue link, a focused fix in `loss_utils.py`, and the companion PR 43254 is just an alternate formulation of the same `cross_entropy` kwargs change.", + "best_issue_reason": null, + "best_pr_reason": "PR 43251 is the strongest standalone PR in the set because it is a concrete bug fix with a linked issue and a narrow scope; it is also the right anchor for deduplicating 43254.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Unrelated changes: new VideoPrism model/docs vs an ExecuTorch dynamic-shape test. Same \u201cmodel tooling\u201d theme is too broad for duplicate merging." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Tokenizer-method cleanup for MistralCommon vs adding a new MobileLLM model. Different codepaths and goals." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer API addition vs ExecuTorch export test; no shared bug or mergeable fix." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor robustness changes across several model processors vs a brand-new MobileLLM model. Too broad and not the same change." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "`fixed_cross_entropy` kwargs support is unrelated to adding MobileLLM; different subsystem and code path." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Loss utility kwargs fix vs Mistral4 test/model updates; not the same underlying bug or patch." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch dynamic-shape export test vs Mistral4 test/model work; same word \u201ctest\u201d is not enough." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "ExecuTorch export coverage vs a new model addition. No shared concrete fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "New MobileLLM model implementation vs a config-resolution ordering fix in core modeling utils. Different problems." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "New MobileLLM model vs Falcon output-interface refactor; separate model families and unrelated changes." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output-collection refactor vs Mistral4 test/model changes. Same general area of model code, but not the same concrete bug/change." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon model refactor vs a model-creation skill PR. Completely different artifact types and purposes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test/model adjustments vs a `layrnorm` typo normalization fix. Not the same code-path issue." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 work vs docs for adding audio/video processor guides. Documentation-only and unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 tests/model integration vs core `cls.config` resolution ordering fix. Different defects." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 code/test fixes vs a model-creation skill PR; no shared fix or merge path." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model addition vs model-creation skill scaffolding. The skill may be related conceptually, but it is not the same underlying change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "MobileLLM model addition vs docs for audio/video processor components. Different artifacts and no shared bug." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs change `src/transformers/loss/loss_utils.py` to extend `fixed_cross_entropy` with the same `cross_entropy` kwargs support; they are two formulations of the same concrete fix and could be merged into one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted duplicate pair, 43251/43254, is a plausible single bugfix in the same file/function and the reasons do not overclaim. The other pairwise rejects are also appropriately cautious given the different files, subsystems, and purposes." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40546-2", + "nodes": [ + "pull_request:40546", + "pull_request:42781" + ], + "soft_pairs": [ + "pull_request:40546|pull_request:42781" + ], + "prepared_review_unit_hash": "143b2d09dbf2d179c236e716bd4dad6c534e94998a23957633c5ab0340a54840", + "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 pull requests, but they target different deliverables: one implements the base VibeVoice model, while the other adds VibeVoice Realtime and the acoustic tokenizer. The overlap is mostly shared integration/docs work, not the same underlying change.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 40546 is the better canonical PR for this cluster because it is the mature, non-draft base VibeVoice implementation and has substantial review activity; PR 42781 is a separate realtime extension.", + "best_issue_reason": null, + "best_pr_reason": "PR 40546 is the best representative PR: it is non-draft, broader and more stable, and represents the core VibeVoice support rather than the newer realtime variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Do not merge as duplicates: 40546 implements base VibeVoice, while 42781 adds VibeVoice Realtime plus acoustic-tokenizer-related changes. They share model-family integration files, but they are not the same concrete code-path fix/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40755-2", + "nodes": [ + "pull_request:40755", + "pull_request:41224" + ], + "soft_pairs": [ + "pull_request:40755|pull_request:41224" + ], + "prepared_review_unit_hash": "9690a074679da35a5baf8f3cb2dd353dca5edd27b304cd0ae287408a2080c480", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two pull requests are unrelated feature additions: one adds covariate forecasting to TimesFM, the other adds image-classification support for DINOv3 ViT. They do not appear to fix the same underlying bug or implement the same change.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models and different code paths: TimesFM forecasting with external covariates versus DINOv3 image-classification support. They are separate feature PRs, not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "aead1308c167b0bae6ff11bf9358340baa5e76f816618383418b505a10a9cd01", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two DEIMv2 pull requests target the same model family, but they are not the same change: PR 41356 is an early/basic model + image processor add, while PR 44339 is a much broader follow-up that adds loss code, auto-mappings, conversion tooling, modular files, and more integration work.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44339 is the more complete and representative DEIMv2 implementation; PR 41356 looks like an earlier partial version of the same model bring-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 44339 is the strongest single artifact for the cluster because it subsumes the basic model work and includes the broader integration needed for a full Transformers addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": false, + "reason": "Same model area, but not the same concrete change: 44339 expands the implementation substantially and adds new code paths beyond the basic PR 41356. They look like related iterations, not mergeable duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41797-3", + "nodes": [ + "pull_request:41797", + "pull_request:45186", + "pull_request:45630" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186", + "pull_request:45186|pull_request:45630" + ], + "prepared_review_unit_hash": "a02fd570bcd3780b5002132933c432f7820c2a1c48f31a6e58108649de6f4f62", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10408, + "estimated_input_tokens": 2602, + "estimated_eval_tokens": 5460 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10408, + "estimated_input_tokens": 2602, + "estimated_eval_tokens": 5460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition pull requests for different models (DeepSeek OCR, Isaac, Kimi2-6). They share some generic registration/documentation files, but they do not appear to fix the same underlying code path or represent mergeable duplicate changes.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "Kimi2-6 is the best single representative of this cluster because it is the broadest and most complete model-addition PR, with the most extensive auto-mapping and model integration changes plus high review activity.", + "best_issue_reason": null, + "best_pr_reason": "Kimi2-6 is the strongest PR to keep as the cluster representative: it has the largest scope and touches several core integration points, whereas the other two are separate model integrations with distinct architectures and files.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different models and different implementation targets: DeepSeek OCR vs Isaac. Shared files are generic model-registration scaffolding, not evidence of the same bug/change." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Both are model additions, but for unrelated model families (Isaac vs Kimi2-6) with distinct code paths and files. Similar auto-registration edits are too generic to treat as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42975-2", + "nodes": [ + "pull_request:42975", + "pull_request:42976" + ], + "soft_pairs": [ + "pull_request:42975|pull_request:42976" + ], + "prepared_review_unit_hash": "0c428493b254e4843c60a3ec766ebaf4495d6cd78d340966acc9261072a83712", + "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 GitHub Actions maintenance updates, but they target different action families and different upgrade goals: one is a broad Node 24 compatibility sweep, the other is a latest-version bump for Docker-related workflows. They are related in theme but not the same underlying change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #42975 is the broader workflow-actions compatibility upgrade and better represents the cluster\u2019s maintenance theme.", + "best_issue_reason": null, + "best_pr_reason": "PR #42975 is the better representative because it covers a wider set of workflow action upgrades aimed at compatibility, not just one action family.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Different underlying changes: #42975 upgrades multiple GitHub Actions for Node 24 compatibility, while #42976 updates Docker build actions to newer versions. They overlap in workflows but do not fix the same concrete problem and would not 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": 7, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-7", + "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": "8599e537014e802cd203d58d9bb8ea826c5d2d47205d6eb1bf0bb29fdba97e35", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23537, + "estimated_input_tokens": 5885, + "estimated_eval_tokens": 12026 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23537, + "estimated_input_tokens": 5885, + "estimated_eval_tokens": 12026 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is heterogeneous: several unrelated model-addition PRs (ViT NEPA, Molmo, Molmo2, Lfm2 Audio, CTSM, PP-OCRv6) plus one pipeline-parallel infrastructure PR. They share template files and auto-mapping scaffolding, but not the same underlying change or code-path.", + "confidence": 0.99, + "canonical_issue_reason": "No canonical issue: the items do not point to one shared bug or feature request; they are separate model integrations and one distributed-loading refactor.", + "canonical_pr_reason": "No canonical PR: there is no duplicate set here, only distinct PRs with similar repository boilerplate.", + "best_issue_reason": "No best issue candidate in this cluster because the artifacts are not tracking a single issue.", + "best_pr_reason": "No best PR candidate; the PRs address different models or unrelated infrastructure, so none is a representative duplicate target.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Both are new model-addition PRs, but they implement different models (ViT NEPA vs Molmo) and are not the same change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "ViT NEPA and Molmo2 are distinct model integrations with different files, configs, and tests; no shared underlying bug or feature." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "These add different models (ViT NEPA vs CTSM); similarity is only in boilerplate docs/auto-registration." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are separate model families/implementations; they are not one mergeable code-path fix." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM are unrelated model additions that only overlap on generic repository scaffolding." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are different model integrations with different architectures and tests, so not duplicates." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45838", + "accept": false, + "reason": "Lfm2 Audio is an audio model addition, while PP-OCRv6 is text-recognition; they do not fix the same code-path." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45838", + "accept": false, + "reason": "Pipeline-parallel loading support is infrastructure work, not the same as adding PP-OCRv6 model support." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45838", + "accept": false, + "reason": "CTSM and PP-OCRv6 are different model additions with separate model code and tests; shared docs/auto files are not enough to merge them." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-3", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "5fb89160d436495c1e8df74d51c48829412234c848509bf3feab23df72102875", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7091, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7091, + "estimated_input_tokens": 1773, + "estimated_eval_tokens": 3802 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates of one another. #43665 is clearly a bogus/test-only change, while #43291 is a Whisper tokenizer/test fix and #44815 is a separate FP8/dequantization fix. The best representative PR in the cluster is #44815 because it is the most substantive and complete change, but it is not the same underlying change as the others.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "#44815 is the strongest standalone PR: it contains a concrete code-path fix across loading/FP8 quantization, with supporting model and test updates, and looks like a real mergeable change rather than a test placeholder.", + "best_issue_reason": null, + "best_pr_reason": "#44815 is the best PR to represent the cluster because it is the most substantial and technically coherent fix; #43291 is narrower and #43665 is not a credible fix at all.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Whisper tokenizer/test fix vs. a dummy PR that inserts failing asserts in CLIP/ViT tests; not the same underlying bug or change." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Different subsystems and failure modes: Whisper decoding/tests versus FP8 dequant/model-loading changes. No concrete shared code-path problem." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "#43665 is test-only and intentionally failing, while #44815 is a real FP8/dequant fix. They are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 9, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-2", + "nodes": [ + "pull_request:43488", + "pull_request:43532" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532" + ], + "prepared_review_unit_hash": "2a07bf45aaa8205ffc127256a33fa2ce18819292ef28091495423d79164c9534", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open \"don't merge\" PRs are clustered only by a shared Vit test file, but their actual changes are unrelated: one is a setup/version/dependency probe, the other rewires CI/workflow/testing utilities. They should not be merged or triaged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No clear canonical PR: the two PRs target different code paths and different kinds of changes, so neither can represent the cluster cleanly.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a good global best fit because the cluster does not contain a single underlying bug/change; the shared test file is incidental.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Reject: the PRs do not fix the same concrete problem. 43488 changes setup/version/dependency metadata and a Vit test, while 43532 changes GitHub workflows, testing utilities, and notification code. The shared test file is incidental." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43612-2", + "nodes": [ + "pull_request:43612", + "pull_request:43613" + ], + "soft_pairs": [ + "pull_request:43612|pull_request:43613" + ], + "prepared_review_unit_hash": "b3e164d796d4604d736e6b76e00f76dc76fe9e7f7dc0fdf82520885d13bf027c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate feature PRs: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share some scaffolding and docs-generation files, but they target different tasks, models, and pipeline implementations.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the two pull requests implement different pipelines with different underlying models and task docs, so they are not duplicates.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a duplicate of the other; each is independently suitable for its own feature area, but there is no single best PR for this cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Different underlying features: concept segmentation vs visual segmentation. Shared documentation and metadata files are incidental and do not indicate the same code-path change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43651-2", + "nodes": [ + "pull_request:43651", + "pull_request:43663" + ], + "soft_pairs": [ + "pull_request:43651|pull_request:43663" + ], + "prepared_review_unit_hash": "a331ddd38e9a591ed9f6dfcf5e565693719aa97d64b4c5e1eeb4473a4903852a", + "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": "The two PRs both touch `trainer.py` and expose override hooks for custom trainers, but they change different code paths: one adjusts gradient-accumulation loss scaling, the other column filtering based on the model signature. They are related in theme, not duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43651 is the more self-contained trainer behavior change, centered on a specific training-step loss-scaling path; #43663 is a separate signature/column-filtering hook.", + "best_issue_reason": null, + "best_pr_reason": "PR #43651 is the stronger representative for this cluster because it makes a concrete, narrowly-scoped trainer fix with an explicit code-path change, whereas #43663 is a distinct extension point.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Reject: they modify different trainer behaviors. #43651 changes gradient accumulation loss scaling in `training_step`; #43663 changes signature-column extraction for dataset column filtering. Shared file/theme alone is not enough to treat them as the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-3", + "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": "6821dc0977996c891be054f8611885230304dc3f6448093d1a12264aadc54a4f", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The three PRs all cluster around the same `src/transformers/cli/serve.py` TypeAdapter/annotation NameError family. PR 43842 is the cleanest and most narrowly scoped fix; the other two look like broader variants of the same underlying change.", + "confidence": 0.81, + "canonical_issue_reason": null, + "canonical_pr_reason": "43842 is the most focused fix: it directly makes the `TypeAdapter` annotation safe when pydantic is absent, with minimal extra refactoring.", + "best_issue_reason": null, + "best_pr_reason": "43842 best represents the cluster because it cleanly and directly addresses the runtime `TypeAdapter` NameError in `serve.py` without pulling in unrelated typing cleanup or refactor churn.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": true, + "reason": "Both target the same `serve.py` TypeAdapter NameError in the CLI; 43656 is a broader typing cleanup, but the underlying bug and code path match." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "Both are fixes for the same `serve.py` TypeAdapter annotation/pydantic NameError. 43836 is broader, but the core change is the same and could plausibly live in one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: all three PRs touch `src/transformers/cli/serve.py` and are clearly about the same annotation/`TypeAdapter` NameError family. The soft-edge accepts are conservative enough because each pair shares the same file and bug theme, and the differences look like broader vs. narrower implementations that could reasonably be merged into one fix PR." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43779-2", + "nodes": [ + "pull_request:43779", + "pull_request:43816" + ], + "soft_pairs": [ + "pull_request:43779|pull_request:43816" + ], + "prepared_review_unit_hash": "e7c674adcc031aa8883109a5dfc678b4407fb20b10764302092e384d031ba83a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests appear to implement the same SwanLab integration change: adding run id/resume support in `integration_utils.py` for issue #43698, with one variant also expanding the docs. They are strong duplicate PR candidates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43816 is the cleaner representative: it carries the same SwanLab id/resume support plus the accompanying documentation updates, making it the more complete version of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43816 is the best global representative because it appears to include the full feature change and docs for SwanLab run id/resume support, while #43779 is the narrower implementation-focused variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43779", + "right": "pull_request:43816", + "accept": true, + "reason": "Same underlying SwanLab callback enhancement for id/resume support in the same file and same issue target; the doc differences do not change the core code-path change, so these are duplicate PRs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target issue #43698, touch the same file, and the previews indicate the same SwanLab id/resume support with #43816 adding docs. The duplicate/mergeable verdict is conservative enough given the shared target and overlapping code change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44066|pull_request:44071", + "pull_request:44018|pull_request:44068", + "pull_request:44066|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request: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:44098|pull_request:44101", + "pull_request:44059|pull_request:44722", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request: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:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", + "pull_request:44059|pull_request:44068", + "pull_request:44018|pull_request:44059", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44018", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:44018|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request: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": "92967931b730d88016831534c673a26d12c6b6402eb50aad370bed6cb3252421", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84895, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75094, + "estimated_input_tokens": 18774, + "estimated_eval_tokens": 37804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a campaign of model-specific refactors to standardized output tracing / capture_outputs. It is not one duplicate bugfix cluster; only a few PRs are true near-duplicates on the same concrete model code path (notably GPT-J/GPT-Neo).", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44066 is the best representative anchor: it is a substantial, explicit GPT-J/CodeGen output-tracing refactor with the issue link, and it sits at the center of the clearest duplicate overlap with 44722 and 44085.", + "best_issue_reason": null, + "best_pr_reason": "PR 44066 is the strongest single PR to keep: it covers the shared GPT-J/CodeGen tracing change, has the explicit tracking link, and is the cleanest duplicate target among the cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model code paths (CVT/FNet vs GPT-J); same theme, but not the same fix." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different models and different implementation paths; only the refactor theme overlaps." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Same GPT-J output-tracing refactor in the same file; 44066 is the broader earlier version and 44085 is a near-duplicate subset." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "ResNet-family vs EfficientNet; same umbrella issue target is not enough to merge these." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen refactor vs EfficientNet refactor; different models." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 vs DeBERTa v2; different concrete changes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen and MGP-STR are different model implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen vs MPT; same refactor style, different code path." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Same GPT-Neo output-tracing refactor in the same file; later PR is a near-duplicate." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen vs GPT-Neo; different model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J are related but separate model code paths and separate refactors." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated implementations." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR vs GPT-J/CodeGen; not the same underlying change." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet vs GPT-J; different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo vs ResNet; same theme only at a high level." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet vs MPT; different model code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen; not the same concrete fix." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert; unrelated model implementations." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "MPT vs MGP-STR; different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert; different models." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 vs MGP-STR; unrelated refactors." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J vs MGP-STR; different model code paths." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT vs Flaubert/XLM; same broad refactor theme only." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet vs GPT-J; not mergeable as one PR." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo vs MPT; different concrete changes." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert vs Flaubert/XLM; different model code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-2 vs MPT; different implementations." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet vs Flaubert/XLM; same theme, different code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet vs Segformer; unrelated model changes." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44056", + "accept": false, + "reason": "CVT/FNet vs MPNet; different code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT vs ImageGPT; different model implementations." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet vs Flaubert/XLM; unrelated concrete changes." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet vs LongT5; different code paths." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44068", + "accept": false, + "reason": "MPNet vs GPT-Neo; not the same underlying fix." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert; different model code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT vs GPT-J/CodeGen; unrelated changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR; different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44059", + "accept": false, + "reason": "GPT-Neo vs GPT-2; same refactor style, different model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo vs MPT; not mergeable as a single duplicate." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet vs LongT5; different implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet vs TextNet; unrelated concrete changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet vs LongT5; different model code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert vs MPT; not the same fix." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet vs LongT5; different models." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT vs Flaubert/XLM; only broad output-tracing similarity." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "VisualBert vs LongT5; separate model refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44071", + "accept": false, + "reason": "MPNet vs MPT; unrelated code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44161", + "accept": false, + "reason": "GPT-Neo vs LongT5; different model implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet vs Segformer; different model families and code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44018", + "accept": false, + "reason": "SqueezeBert vs GPT-Neo; different model changes." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44071", + "accept": false, + "reason": "Segformer vs MPT; unrelated code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "Segformer vs VisualBert; not the same underlying fix." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert vs DeBERTa v2; different models and refactors." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa v2 vs TextNet; unrelated concrete changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa v2 vs SpeechT5; same theme only at a very high level." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa v2 vs Vits; different model code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert vs VisualBert; unrelated changes." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer vs LongT5; different implementations." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert vs Flaubert/XLM; different models." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet vs MPNet; unrelated model code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-2 vs GPT-Neo; separate model refactors." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44161", + "accept": false, + "reason": "GPT-2 vs LongT5; unrelated fixes." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44101", + "accept": false, + "reason": "ResNet vs Flaubert/XLM; different concrete changes." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44086", + "accept": false, + "reason": "MPNet vs MGP-STR; different model code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT vs SpeechT5; unrelated changes." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44086", + "accept": false, + "reason": "SqueezeBert vs MGP-STR; different implementations." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44154", + "accept": false, + "reason": "TextNet vs Vits; different model code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "Segformer vs GPT-J/CodeGen; same tracking issue only." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen vs MGP-STR; not the same concrete fix." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen vs MPT; different model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo vs SpeechT5; unrelated code paths." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44154", + "accept": false, + "reason": "VisualBert vs Vits; different model refactors." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 vs MGP-STR; separate model changes." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet vs Flaubert/XLM; unrelated models." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-2 vs MPT; different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR; not the same fix." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa v2 vs Vits; different model code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa v2 vs SpeechT5; unrelated concrete changes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J/CodeGen output-tracing refactor; 44722 is a later near-duplicate/superset of the same code-path change." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both target the GPT-J output-tracing refactor on the same file; 44722 subsumes the same concrete change." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J vs SpeechT5; different model code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet vs SpeechT5; not the same fix." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa v2 vs SpeechT5; unrelated model implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa v2 vs Vits; different code paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: it correctly treats this as a set of model-specific output-tracing refactors rather than one uniform bugfix, and the few accepted pairs are limited to the same concrete code paths (GPT-J/CodeGen and GPT-Neo). The duplicate/near-duplicate claims stay conservative, and the representative PR choice is supported by the shared issue links and filename overlap." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 27, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request:44024", + "pull_request:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44129" + ], + "soft_pairs": [ + "pull_request:44024|pull_request:44076", + "pull_request:44073|pull_request:44074", + "pull_request:44056|pull_request:44073", + "pull_request:44056|pull_request:44074", + "pull_request:43997|pull_request:44010", + "pull_request:44010|pull_request:44129" + ], + "prepared_review_unit_hash": "ca166b957b69b7f2c10e6e12d04f5e9d1278d7a4a0b9d9dc0987ea8c509384c3", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84895, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17122, + "estimated_input_tokens": 4281, + "estimated_eval_tokens": 8818 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These PRs are all model-specific migrations to standardized output capture/tracing APIs, but they touch different architectures and code paths. They are related by refactor style, not true duplicates, so the soft edges should be rejected.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single duplicate PR exists here; if one representative is needed, 44129 is the strongest anchor because it ties the refactor to an explicit issue target and a concrete SpeechT5 output-capture change.", + "best_issue_reason": null, + "best_pr_reason": "44129 is the best representative of the cluster because it is explicitly scoped to one model, references an issue, and shows the standardized output-capture migration clearly without being overly broad.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Both are output-capture refactors, but they affect different models (FocalNet vs ImageGPT) and different hook wiring. Same migration theme, not the same underlying change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "VisualBert and TextNet are separate model implementations with distinct forward paths; this is a shared refactor pattern, not one mergeable duplicate PR." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet and VisualBert each update their own model-specific output tracing logic. They are not fixing the same concrete bug or code path." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "These are separate per-model standardized-output refactors in different files and architectures, so they should not be treated as duplicates." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated model code paths; the shared wording around standardized outputs is too broad to merge as one PR." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 both mention output tracing, but they change different modules and mechanisms. They are not the same underlying bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "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": "c0c449d51ddb5cc027f0511b4b96d91f7fd186dec97325fcc2d2e237b35ec7a3", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40161, + "estimated_input_tokens": 10041, + "estimated_eval_tokens": 20338 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40161, + "estimated_input_tokens": 10041, + "estimated_eval_tokens": 20338 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "A broad similarity cluster of model-specific output-tracing refactors. The PRs share a naming/template pattern, but they touch different architectures and code paths, so none look like true duplicates.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: these are separate model-specific output-tracing refactors, not duplicates.", + "best_issue_reason": null, + "best_pr_reason": "PR #44025 is the strongest representative of the pattern because it updates two closely related depth-anything files and clearly applies the can_return_tuple refactor, but it still is not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families and files (timm_backbone vs upernet); only the refactor style matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Different code paths in unrelated architectures (timm_backbone vs vision_text_dual_encoder)." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "timm_backbone and univnet are unrelated implementations; same output-tracing theme only." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Distinct model stacks (timm_backbone vs mamba/falcon_mamba); not the same bug or change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "timm_backbone and rwkv are different code paths; similarity is only in refactor pattern." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "mobilenet_v1 and univnet are unrelated model implementations." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Different architectures and filenames; no shared concrete fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "mobilenet_v1 vs depth_anything are separate model families, not one duplicate change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Different wrapper/model code paths (mobilenet_v1 vs vision_encoder_decoder)." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "mobilenet_v1 and speech_encoder_decoder are unrelated; only the refactor template overlaps." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "vision_text_dual_encoder and univnet fix different modules and behaviors." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model code paths (vision_text_dual_encoder vs upernet)." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "vision_text_dual_encoder is not the same subsystem as mamba/falcon_mamba." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "vision_text_dual_encoder and codegen are separate model families; no shared concrete bug." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Different architectures and files; same output-tracing refactor only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "univnet and upernet are unrelated models with different forward paths." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "univnet is separate from the mamba/falcon_mamba code path." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "univnet vs depth_anything: different model families, not one mergeable fix." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "upernet and mamba/falcon_mamba are unrelated subsystems." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "mamba/falcon_mamba and superpoint are different model implementations." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "mamba/falcon_mamba and codegen do not share the same concrete code path." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "timm_backbone and codegen are unrelated; only the refactor motif overlaps." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "univnet and codegen touch different model stacks and behaviors." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "upernet vs codegen is a broad theme match only, not a duplicate fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "depth_anything and vision_encoder_decoder are separate code paths; same tracing refactor pattern only." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "depth_anything and speech_encoder_decoder are unrelated models." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "depth_anything vs superpoint: different architectures and files." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "depth_anything and rwkv are separate model families." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "depth_anything and DPR do not appear to address the same underlying change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "vision_encoder_decoder and speech_encoder_decoder are different wrapper models with distinct code paths." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "vision_encoder_decoder vs superpoint is not the same bug or refactor target." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "vision_encoder_decoder and rwkv are unrelated implementations." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "vision_encoder_decoder and DPR fix different model paths; no duplicate evidence." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "speech_encoder_decoder and superpoint are different models with no shared concrete code path." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "speech_encoder_decoder vs rwkv is only superficially similar." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "speech_encoder_decoder and DPR are unrelated model wrappers." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "superpoint and rwkv are different architectures; not mergeable as one PR." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "superpoint and DPR touch different subsystems and fixes." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "rwkv and DPR are separate model families; shared theme is too broad." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44662-3", + "nodes": [ + "pull_request:44662", + "pull_request:45075", + "pull_request:45401" + ], + "soft_pairs": [ + "pull_request:44662|pull_request:45401", + "pull_request:44662|pull_request:45075", + "pull_request:45075|pull_request:45401" + ], + "prepared_review_unit_hash": "5798c6c949682eb10ebd90b6c158b13566ffebd924fb8b31088291dea8e3c449", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10911, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10911, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-implementation PRs, not duplicates. Their overlap is limited to shared Transformers boilerplate such as docs, auto-mapping, and registry updates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: PenguinVL, DeepSeek-OCR-2, and Voxtral TTS are different model families with different codepaths and assets; the shared files are generic integration boilerplate.", + "best_issue_reason": null, + "best_pr_reason": "No single PR is a better representative of the others because each adds a distinct model implementation rather than the same change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "PenguinVL and Voxtral TTS are unrelated model additions; they only share registry/docs scaffolding, not the same fix or code path." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 are different models with different implementation files and targets; overlap is just boilerplate integration work." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model adds, not the same underlying bug/change, despite similar auto-registration edits." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44979-2", + "nodes": [ + "pull_request:44979", + "pull_request:45363" + ], + "soft_pairs": [ + "pull_request:44979|pull_request:45363" + ], + "prepared_review_unit_hash": "13f8ce690cf9d377542f6eecdb0176d09666983a2b42fec4d16093d04d38ae20", + "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 are related only at a high level (both mention fusion), but they target different abstractions and code paths: one introduces a generic module-fusion API, the other adds KernelConfig-based n-to-1 kernel fusion integration. They should not be deduplicated.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45363 is the broader, more concrete implementation: it wires fusion into model loading and runtime behavior via KernelConfig and integration changes, with an example demonstrating end-to-end use.", + "best_issue_reason": null, + "best_pr_reason": "PR #45363 is the better representative of the cluster because it has the clearer user-facing change and more specific implementation surface; PR #44979 is a separate generic API proposal rather than the same change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Both involve fusion, but #44979 adds a generic module-fusion API layer while #45363 implements KernelConfig-driven kernel fusion for models. They do not appear to fix the same concrete problem or be mergeable into one PR without mixing distinct features." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45086-2", + "nodes": [ + "pull_request:45086", + "pull_request:45317" + ], + "soft_pairs": [ + "pull_request:45086|pull_request:45317" + ], + "prepared_review_unit_hash": "e0c0c0c4ef2e6f8fc425e62610c9d954c10b0533509edc59aa4d7cf360a66a33", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same Mistral regex AttributeError in the same code path; PR 45317 is the more complete variant because it includes the fix plus tests.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45317 is the better canonical PR because it fixes the same bug as 45086 but also adds test coverage, making it the more complete change set.", + "best_issue_reason": null, + "best_pr_reason": "PR 45317 is the best overall representative: same underlying AttributeError fix, same target file/issue, and it includes accompanying tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same underlying AttributeError in _patch_mistral_regex, same file and issue target, and the changes are directly compatible as 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": 19, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45115-2", + "nodes": [ + "pull_request:45115", + "pull_request:45569" + ], + "soft_pairs": [ + "pull_request:45115|pull_request:45569" + ], + "prepared_review_unit_hash": "1710a959541fbc879a60bda82a6e51c2cdcc00e33cccb3134594347c93fae2ec", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are related to NemotronH, but they are not duplicates: one is a narrow conversion-mapping refactor, while the other is a much broader split/cleanup that introduces NemotronH Dense and Sparse model families. They do not appear to fix the same concrete code-path problem.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45569 is the better canonical PR because it is the larger, more complete architectural change: it introduces the Dense/Sparse model split, updates auto mappings/docs/tests, and rewires the NemotronH packaging. PR 45115 is a narrower conversion-mapping follow-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 45569 is the best overall representative of the cluster because it covers the main refactor rather than just a supporting conversion-mapping update.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Both touch NemotronH, but 45115 is limited to checkpoint conversion key renames while 45569 is a broader model-architecture and docs/test refactor. They are not the same underlying change and would not plausibly merge into one PR without conflating distinct work." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 20, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45332-2", + "nodes": [ + "pull_request:45332", + "pull_request:45333" + ], + "soft_pairs": [ + "pull_request:45332|pull_request:45333" + ], + "prepared_review_unit_hash": "0a8b80624263d0f1dfbffb04fab0be63e0e857b9a93c8d866a92900d6cee3bf6", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related but distinct PRs: one introduces heterogeneous per-layer config support, while the other adds broader heterogeneous modeling/cache/masking changes. They share foundation code, but they do not look like the same underlying change and should not be merged as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader, more representative change: it covers the actual heterogeneous model support path and includes the config work plus downstream modeling/cache updates.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the best single PR for the cluster because it subsumes the config-only groundwork and reflects the larger end-to-end feature work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature area, but not the same concrete code-path change. #45333 is config-only per-layer support; #45332 is a wider modeling/cache implementation that could not be safely collapsed into the same PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45415-2", + "nodes": [ + "pull_request:45415", + "pull_request:45425" + ], + "soft_pairs": [ + "pull_request:45415|pull_request:45425" + ], + "prepared_review_unit_hash": "20e61d369bc72585296ed200cb92af4e444de2d68a8291adddcbcbafe644340d", + "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 are both typing-related, but they are not the same change: one is a broad type-checking sweep across many files, while the other adds specific typing protocols/helpers around modeling_utils and PEFT integration. I would not merge them as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45425 is the more focused, self-contained typing update; PR 45415 is a broad repository-wide type-checking sweep.", + "best_issue_reason": null, + "best_pr_reason": "PR 45425 has a tighter scope and a clearer concrete change than the sweeping type-checking pass in 45415.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Both are typing-oriented, but they address different underlying work: 45415 broadly enables type checking across many files, while 45425 adds specific typing protocols/helpers for modeling_utils/PEFT. They do not fix the same concrete code-path and are not safely 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": 22, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45487-6", + "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": "cc07df82d9c420fc26e1ea3d022baf33f2cb12f0c1dba903a851deeb3d048ab9", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 6, + "serialized_chars": 14720, + "estimated_input_tokens": 3680, + "estimated_eval_tokens": 7616 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 6, + "serialized_chars": 14720, + "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 loosely related by model-parallel/XPU themes, but they are not duplicates: they target different models and different code paths, and several are just test expectation updates. The only substantive code fix in the set is the Gemma4 parallel bug fix; the rest are model-specific and should stay separate.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45817 is the strongest standalone change: it fixes a concrete model-parallel device-placement bug in Gemma4 code, rather than only adjusting expectations. It is the best representative if one PR must be chosen, though the cluster is not a true duplicate set.", + "best_issue_reason": null, + "best_pr_reason": "PR #45817 is the best candidate for global relevance because it addresses an actual runtime bug in a production code path and has the broadest substantive fix among the candidates. The others are narrower, model-specific, or test-only updates.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Different models and different bug surfaces: AltCLIP/ChineseCLIP device placement vs Deimv2 model-parallel cleanup. Same general theme, but not the same underlying fix." + }, + { + "left": "pull_request:45487", + "right": "pull_request:45926", + "accept": false, + "reason": "AltCLIP/ChineseCLIP parallel bug fix vs HyperCLOvax XPU test expectations. These are unrelated model-specific changes." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel related, but they fix different models and different code paths: Gemma4 vs Deimv2." + }, + { + "left": "pull_request:45858", + "right": "pull_request:45890", + "accept": false, + "reason": "Both are XPU expectation updates, but for different models and tests. Test-only expectation changes for separate models are not duplicates." + }, + { + "left": "pull_request:45858", + "right": "pull_request:45926", + "accept": false, + "reason": "Hy_v3 XPU expectations and HyperCLOvax XPU expectations are separate model test updates, not one underlying bug or change." + }, + { + "left": "pull_request:45890", + "right": "pull_request:45926", + "accept": false, + "reason": "Different models and different expected outputs; these are independent CI/test expectation tweaks, not duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "f146f2afe94c6ded07abb0734397157881e94dbdbbeda33768f3be961573c4a2", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs concern expert parallelism loading, but they fix different code paths: one is about serializing `distributed_config` and exposing `has_ep` for accelerate/ZeRO-3 loading, while the other prevents expert parameters from being overwritten during FSDP2/rank-0 broadcast. They are related, but not duplicates.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45662 is the better canonical representative because it targets a concrete loading corruption bug in the parameter assignment path and its fix is tightly scoped to the overwrite mechanism.", + "best_issue_reason": null, + "best_pr_reason": "PR #45662 is the strongest standalone PR in the cluster: it addresses a specific, well-defined failure mode with direct code-path changes across loading and MoE integration.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "They share the broad EP/loading theme, but fix different underlying bugs: #45548 adds `distributed_config` serialization and `has_ep` for accelerate launch + ZeRO-3, while #45662 fixes expert tensors being overwritten by rank-0 broadcast in FSDP2. Not the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 24, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45639-2", + "nodes": [ + "pull_request:45639", + "pull_request:45645" + ], + "soft_pairs": [ + "pull_request:45639|pull_request:45645" + ], + "prepared_review_unit_hash": "a47ec3f2f9b39738fa2f8a145c7e328dc9e2780094e79e916cf0944a0f967d95", + "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 problem in testing_utils; 45645 looks like a broader follow-up that subsumes the core fix from 45639 and adds CI artifact handling.", + "confidence": 0.82, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the better canonical representative because it includes the core testing_utils xdist-safe change plus the surrounding CI/log-capture updates and tests.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 best represents the cluster since it addresses the same captured_info collision issue more completely than the narrower 45639 fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Both PRs fix the same captured_info xdist collision path; 45645 expands the same fix with CI artifact handling, so they belong to the same 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": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-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": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 27, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45975-2", + "nodes": [ + "pull_request:45975", + "pull_request:45977" + ], + "soft_pairs": [ + "pull_request:45975|pull_request:45977" + ], + "prepared_review_unit_hash": "e593e013e862586428bc362889057b3a199d1c12a63db05dfafd2d013d8f1c6d", + "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": "Two open PRs share a GGUF/Apple Silicon/kernels-community theme, but they implement different features on different code paths: one adds an optional serving-side Metal dequant fast path, the other adds a new GGUF linear-matmul integration with tests. They are related, but not duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45977 is the more central, self-contained implementation PR: it introduces the new GGUF linear path and accompanying quantizer/modeling integration, whereas PR 45975 is a narrower optional fast-path/configuration change for serving.", + "best_issue_reason": null, + "best_pr_reason": "PR 45977 looks like the stronger standalone PR for the cluster because it contains the core new code and validation coverage; PR 45975 is more of an adjacent enhancement to serving/help text and fast-path selection.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45975", + "right": "pull_request:45977", + "accept": false, + "reason": "Same broad GGUF/Metal/kernels-community area, but not the same concrete change: 45975 is about an optional serving-time dequant fast path and CLI/model-manager plumbing, while 45977 adds a new GgufLinear matmul implementation plus quantizer/modeling integration. Different code paths and merge scopes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/manifest.json b/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..08720a7c5b4a09a9c092fba0b763b2eff857cbd1 --- /dev/null +++ b/snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260516t120032z", + "artifacts": { + "hybrid": "snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-16T12:09:08Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260516T120032Z", + "variant": "hybrid" +} diff --git a/snapshots/20260516T120032Z/manifest.json b/snapshots/20260516T120032Z/manifest.json index b4261b8e5b8cfdb8f7f99e42ee59d656ec32fbab..04ff34fad7e35b8dc3f6e370cad303a161866202 100644 --- a/snapshots/20260516T120032Z/manifest.json +++ b/snapshots/20260516T120032Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 509 }, "extracted_at": "2026-05-16T12:00:32Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260516t120032z", + "runs": { + "hybrid-model-20260516t120032z": { + "analysis_id": "hybrid-model-20260516t120032z", + "artifacts": { + "hybrid": "snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260516T120032Z/analysis-runs/hybrid-model-20260516t120032z/manifest.json", + "model": null, + "published_at": "2026-05-16T12:09:08Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260516T120032Z", "watermark": {