diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index f5eda7d1a044a858465787cb3327a2a70f7372db..704867e84142c34cee8a60f8072f61522fc9078e 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": "20260526T120027Z", - "generated_at": "2026-05-26T12:14:03Z", + "snapshot_id": "20260526T180028Z", + "generated_at": "2026-05-26T18:20:10Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1755,6 +1755,64 @@ } ] }, + { + "cluster_id": "cluster-44001-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44004, + "issue_numbers": [], + "pr_numbers": [ + 44001, + 44004 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44001, + "right_pr_number": 44004, + "code_similarity": 0.087, + "size_similarity": 0.237, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.262, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "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.", @@ -2086,6 +2144,24 @@ "target_issue_number": 43979, "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." }, + { + "cluster_id": "cluster-44001-2", + "canonical_pr_number": 44004, + "duplicate_pr_numbers": [ + 44001 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44001-2 are treated as duplicates because they share 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 bcea7d1543c411f4fd2252321cbe8d13fd1a0679..592f1db6f598797ef818ef42a9cb17dc116fcec3 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": "20260526T120027Z", - "generated_at": "2026-05-26T12:14:03Z", + "snapshot_id": "20260526T180028Z", + "generated_at": "2026-05-26T18:20:10Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -16,7 +16,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:24643", "issue:30277", @@ -128,8 +128,8 @@ "issue:43039|issue:44805", "issue:41762|issue:43596", "issue:39290|issue:41720", - "issue:43901|issue:44512", "issue:45237|issue:45901", + "issue:43901|issue:44512", "issue:44841|issue:45823", "issue:43039|issue:44560", "issue:43975|issue:46015", @@ -138,364 +138,418 @@ "issue:43866|issue:44863", "issue:44292|issue:46015" ], - "prepared_review_unit_hash": "104455d95fac3691ee93543a2b57e7f7838dca6572c1fe44d13cdd596cb0f895", + "prepared_review_unit_hash": "7fc1927efed8da07ce1eeaba26f2c3e797e909d72fec4f71c0e48257c2c83bc9", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 69, - "serialized_chars": 48407, - "estimated_input_tokens": 12102, - "estimated_eval_tokens": 24460 + "serialized_chars": 48404, + "estimated_input_tokens": 12101, + "estimated_eval_tokens": 24458 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly noisy lexical similarity across unrelated issues. The only clear duplicate pockets are the DeepSpeed ZeRO-3 zero-sized-tensor index error reports and the AutoTokenizer wrong-token-ID regression; the rest should stay separate.", - "confidence": 0.78, - "canonical_issue_reason": "issue:43596 is the best representative of the genuine duplicate pocket: it states the generic DeepSpeed ZeRO-3 zero-sized-tensor IndexError clearly, and the near-identical 43638 plus related 41762 reports orbit the same failure mode.", + "summary": "Mostly unrelated issues, with two small duplicate clusters: a DeepSpeed ZeRO-3 empty-tensor/index-0 failure cluster and an AutoTokenizer wrong-token-IDs regression cluster. Most other pairs are only superficially similar and should stay separate.", + "confidence": 0.69, + "canonical_issue_reason": "issue:43596 is the clearest representative of the ZeRO-3 empty-tensor / index-0 failure cluster: it is concise, model-agnostic, and matches the near-identical follow-up issue 43638.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43596 is the strongest overall anchor for triage because it captures the core ZeRO-3 loading bug in the most general form, with the closest true duplicate nearby; most other items in the cluster are only superficially similar by error wording.", + "best_issue_reason": "issue:43596 is the best overall issue candidate because it describes the underlying failure mode most generally and cleanly, making it the strongest anchor for duplicate triage.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different model/config attribute error vs streaming API failure; only broad Qwen similarity." + "reason": "Different bugs: one is a config attribute error, the other is a streaming chat/completions failure." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Different hardware backends and failures (AMD GPU vs MPS histogram op); not the same bug." + "reason": "Both touch GPU/MoE behavior, but the failures are different (AMD GPU support vs MPS histogram op missing)." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Different models and symptoms: dtype mismatch in preprocessing vs AMD GPU execution failure." + "reason": "Both involve model/runtime compatibility, but one is image preprocessor dtype mismatch and the other is AMD GPU execution failure." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Both are runtime failures, but the model, backend, and error class differ." + "reason": "Different dtype/autocast bug versus GPU backend incompatibility; same broad area only." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Different MoE/runtime problems; no shared concrete code path." + "reason": "Different model families and different failure modes; not the same concrete bug." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Both involve Qwen/GPT-OSS style models, but the reported failures are unrelated." + "reason": "Both are Qwen-3 related, but the reported runtime errors and code paths are different." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch is unrelated to ModernBERT ONNX export." + "reason": "Both are model/runtime errors, but one is DeepSpeed collective mismatch and the other is ONNX export failure." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "ONNX export error and FineGrainedFP8 failure are separate model/tooling issues." + "reason": "Different model/export issue versus fine-grained FP8 failure; no concrete shared bug." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "ModernBERT export and Qwen3 auto device mapping are unrelated." + "reason": "ONNX export and CUDA assert under auto device map are unrelated failures." }, { "left": "issue:45901", "right": "issue:46015", "accept": false, - "reason": "Table QA crash and RAG docs cleanup are not the same underlying issue." + "reason": "Both are task/example related, but one is a task crash and the other is outdated RAG examples." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are v5 docs problems, but they cover different outdated examples and should be tracked separately." + "reason": "Both are docs cleanup for v5 removals, but they reference different removed content and likely different edits." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "ONNX export error vs import error for GenerationMixin; different code paths." + "reason": "ONNX export error and GenerationMixin import error are separate regressions." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Mask/index shape mismatch is unrelated to Gemma4 device_map forward mismatch." + "reason": "Both mention device/mask style errors, but the concrete errors and models differ." }, { "left": "issue:44918", "right": "issue:46165", "accept": false, - "reason": "TRl SFT embedding unpacking and resume-training/trust-remote-code are different training workflows." + "reason": "Different training failures: embedding unpacking with TRL versus resume-training with trust-remote-code." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Similar IndexError wording, but one is ZeRO-3/Bert loading and the other is a mask-shape mismatch." + "reason": "Same general IndexError family, but 44805 is a different mask-shape mismatch and not the same bug." + }, + { + "left": "issue:43596", + "right": "issue:46165", + "accept": false, + "reason": "ZeRO-3 empty-index failure and resume-training/trust-remote-code are unrelated." }, { "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different underlying errors: empty parameter/index-0 versus mask/tensor shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different bugs: mask shape mismatch versus tensor-parallel-only failure on GPT-OSS MoE." + }, + { + "left": "issue:44560", "right": "issue:46165", "accept": false, - "reason": "Both mention training/loading, but the actual failures are unrelated." + "reason": "Different model/task failures with no shared code-path evidence." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Both are tensor-shape related, but the failures occur in different parts of the stack and are not clearly the same bug." }, { "left": "issue:43572", "right": "issue:46165", "accept": false, - "reason": "StableLmConfig pad token regression is unrelated to resume-training behavior." + "reason": "Config field regression versus training resume issue; unrelated." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "BarkProcessor voice_preset issue has nothing to do with ONNX export." + "reason": "Processor preset bug and ONNX export bug are unrelated." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Both involve DeepSpeed, but the collective mismatch and ZeRO-3 IndexError are different bugs." + "reason": "Both involve DeepSpeed, but one is collective mismatch and the other is an index-0 empty-tensor failure." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3 IndexError on zero-sized tensors during Bert loading; wording differs, failure mode is the same." + "reason": "Same ZeRO-3 empty-parameter/index-0 failure during BertModel loading/training; only wording and model-pretraining context differ." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger cross-entropy invocation and GPT-OSS tensor-parallel failure are different issues." + "reason": "Liger Kernel cross-entropy dispatch and GPT-OSS tensor-parallel failure are different problems." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Incorrect detokenization and LoRA save/reload mismatch are separate regressions." + "reason": "Tokenizer detokenization bug and LoRA merge/save mismatch are unrelated." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "NVFP4 runtime error and LoRA round-trip mismatch do not share a concrete bug." + "reason": "Different model/runtime issues; no common underlying bug." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "Both are tensor-shape-related, but they involve different training stacks and error mechanisms." + "reason": "Activation checkpointing/FSDP tensor recomputation issue is not the same as the mask shape mismatch." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "DeepSpeed weight dimension error and collective mismatch are not the same underlying bug." + "reason": "Both are DeepSpeed training errors, but the concrete failures are different (weight rank error vs collective mismatch)." }, { "left": "issue:45859", "right": "issue:45902", "accept": false, - "reason": "Same class name, but CPU-offload incompatibility vs uninitialized-memory after meta materialization are distinct failures." + "reason": "Same model component, but one is CPU-offload incompatibility and the other is uninitialized-memory after materialization; not clearly one bug." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "ZeRO-3 Bert loading and GPT-OSS tensor-parallel behavior are unrelated." + "reason": "DeepSpeed ZeRO-3 index-0 failure and GPT-OSS tensor-parallel failure are unrelated." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "Activation-checkpointing tensor-size mismatch and compute_loss signature change are unrelated." + "reason": "Different training-stack regressions: activation checkpointing/FSDP vs custom compute_loss signature." }, { "left": "issue:43596", "right": "issue:45161", "accept": false, - "reason": "ZeRO-3 Bert IndexError is unrelated to GPT-OSS tensor-parallel failure." + "reason": "Different model-parallel failures with no shared concrete bug." }, { "left": "issue:43716", "right": "issue:45507", "accept": false, - "reason": "Different model families and different dtype/method errors." + "reason": "Different model-specific failures: dtype mismatch in preprocessing vs invalid method call in GraniteMoEHybrid." }, { "left": "issue:39290", "right": "issue:45081", "accept": false, - "reason": "Gemma3 config attribute missing and Mistral tokenizer regex patch crash are unrelated." + "reason": "Different compatibility bugs: vLLM config attribute missing vs Mistral tokenizer regex patch crash." }, { "left": "issue:45823", "right": "issue:45874", "accept": false, - "reason": "Device placement mismatch and expensive reverse embedding lookup are different forward-path problems." + "reason": "Both are Gemma4 issues, but one is device-map mismatch and the other is expensive reverse-embedding lookup." }, { "left": "issue:43425", "right": "issue:44292", "accept": false, - "reason": "Torch version incompatibility and NVFP4 runtime error are not the same bug." + "reason": "Torch version compatibility and Qwen running error are not the same bug." }, { "left": "issue:34928", "right": "issue:41720", "accept": false, - "reason": "FSDP checkpointing mismatch and Qwen3 auto device mapping failure are unrelated." + "reason": "FSDP/checkpointing recompute mismatch and CUDA assert on auto device mapping are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch and tensor-parallel-only failure are different code paths." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "Different bugs: TRL SFT embedding unpacking versus GPT-OSS TP failure." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Both are Qwen-related runtime issues, but the specific failures differ and do not look like one fix." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Different MoE implementation problems on different backends; not the same underlying defect." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy call and TRL SFT embedding unpacking are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Same DeepSpeed ZeRO-3 size-0/index-0 failure pattern; only the affected model differs." }, { "left": "issue:43827", "right": "issue:44512", "accept": false, - "reason": "Both are docs-related, but they cover different removed commands/tasks." + "reason": "Both are documentation regressions, but they concern different removed APIs/commands and would need separate edits." }, { "left": "issue:43716", "right": "issue:44560", "accept": false, - "reason": "Mistral image dtype mismatch and Qwen3-VL video StopIteration are different model-processing failures." + "reason": "Different model bugs: dtype mismatch in preprocessing versus StopIteration in video embedding." }, { "left": "issue:43828", "right": "issue:45685", "accept": false, - "reason": "Autocast dtype mismatch and MPS histogram op not implemented are different backend issues." + "reason": "Autocast dtype mismatch and MPS histogram op missing are different failures." }, { "left": "issue:44918", "right": "issue:45685", "accept": false, - "reason": "SFT trainer embedding unpacking and MPS MoE histogram failure are unrelated." + "reason": "TRL embedding unpacking and MPS histogram issue are unrelated." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Cross-entropy being called via Liger and Phi-tiny-MoE autocast mismatch are different code paths." + "reason": "Both involve tensor computations, but one is Liger Kernel cross-entropy dispatch and the other is autocast dtype mismatch." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "Collective mismatch in ZeRO-3 and compute_loss signature breakage are unrelated." + "reason": "DeepSpeed collective mismatch and custom trainer signature breakage are unrelated." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "Checkpointing/FSDP tensor mismatch and GenerationMixin import breakage are unrelated." + "reason": "Activation checkpointing/FSDP error and GenerationMixin import error are separate regressions." }, { "left": "issue:45237", "right": "issue:46015", "accept": false, - "reason": "AMD GPU execution failure and outdated RAG docs are unrelated." + "reason": "Model GPU compatibility bug and outdated RAG docs are unrelated." }, { "left": "issue:43039", - "right": "issue:44805", + "right": "issue:44560", "accept": false, - "reason": "Liger cross-entropy call and generic mask-shape IndexError are not the same bug." + "reason": "Liger Kernel cross-entropy issue and video StopIteration are different bugs." }, { "left": "issue:41762", "right": "issue:43596", "accept": true, - "reason": "Same ZeRO-3 zero-sized-tensor IndexError during loading; Gemma3 and Bert are model-specific manifestations of the same failure." + "reason": "Same ZeRO-3 empty-tensor/index-0 bug; different model names only." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Missing config attribute for vLLM and CUDA assert under auto device mapping are unrelated." - }, - { - "left": "issue:43901", - "right": "issue:44512", - "accept": false, - "reason": "TextClassificationPipeline docs and removed run-command docs are separate documentation issues." + "reason": "Different issues: missing config attribute for vLLM vs CUDA assert in auto device mapping." }, { "left": "issue:45237", "right": "issue:45901", "accept": false, - "reason": "AMD GPU model failure and table-question-answering crash are unrelated." + "reason": "Both affect Qwen-3 family areas, but the concrete crash modes are different." }, { - "left": "issue:44841", - "right": "issue:45823", + "left": "issue:43901", + "right": "issue:44512", "accept": false, - "reason": "Processor failure for Voxtral and Gemma4 device mismatch are different issues." + "reason": "Different docs drift: TextClassificationPipeline return_all_scores versus transformers run command removal." }, { - "left": "issue:43039", - "right": "issue:44560", + "left": "issue:44841", + "right": "issue:45823", "accept": false, - "reason": "Liger kernel cross-entropy path and Qwen3-VL video StopIteration are unrelated." + "reason": "Processor failure for Voxtral and Gemma4 device mismatch are unrelated." }, { "left": "issue:43975", "right": "issue:46015", "accept": false, - "reason": "Detokenization regression and RAG docs staleness are unrelated." + "reason": "Tokenizer detokenization bug and outdated RAG examples are unrelated." }, { "left": "issue:45812", "right": "issue:45920", "accept": true, - "reason": "Same AutoTokenizer wrong-token-ID regression across different model families; titles point to the same tokenizer bug." + "reason": "Same AutoTokenizer wrong-token-IDs v5 regression across model families; 45920 is the broader manifestation of the same bug." }, { "left": "issue:44863", "right": "issue:46015", "accept": false, - "reason": "NemotronH checkpoint loading and RAG docs are unrelated." + "reason": "NemotronH checkpoint loading failure and outdated examples are unrelated." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Checkpoint corruption and checkpoint loading implementation failure are different problems." + "reason": "Corrupted checkpoint versus model-loading implementation problem are not the same bug." }, { "left": "issue:44292", "right": "issue:46015", "accept": false, - "reason": "Qwen-3 NVFP4 runtime error and RAG docs cleanup are unrelated." + "reason": "Qwen-3 runtime error and outdated RAG docs are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet. The two accepted duplicate pockets are supported by the titles and soft-pair evidence: the DeepSpeed ZeRO-3 zero-sized-tensor IndexError reports (43596/43638/41762) and the AutoTokenizer wrong-token-ID regression (45812/45920). The false soft-edge rejections are conservative and the reasons mostly distinguish different error classes, models, or code paths without overstating evidence." + "feedback": "The summary is well grounded in the packet: it identifies the two supported duplicate clusters (ZeRO-3 index-0/empty-tensor and AutoTokenizer wrong-token-IDs) and treats the rest as unrelated. The soft-edge verdicts are generally conservative, and the accepted pairs are backed by nearly identical titles/error patterns." }, "evaluator_used": true, "retried": false, @@ -514,7 +568,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36010", "issue:39186", @@ -567,8 +621,8 @@ ], "soft_pairs": [ "issue:39290|issue:43531", - "issue:43854|issue:43866", "issue:43792|issue:45901", + "issue:43854|issue:43866", "issue:41093|issue:43638", "issue:43425|issue:45070", "issue:43596|issue:45800", @@ -585,8 +639,8 @@ "issue:36010|issue:39290", "issue:45800|issue:45823", "issue:41093|issue:41762", - "issue:43296|issue:43366", "issue:43572|issue:45070", + "issue:43296|issue:43366", "issue:43541|issue:45161", "issue:44387|issue:45005", "issue:43828|issue:45464", @@ -606,265 +660,277 @@ "issue:43645|issue:45399", "issue:43404|issue:45005" ], - "prepared_review_unit_hash": "8cbde3b4a90ad0a27117859a33b3783e37858211c7834e571f5c56158a9aae4e", + "prepared_review_unit_hash": "c80ba2c97484a5344cd5a5f483fd828a234dd5a2d74f8b16de77c9f2a35a981c", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 39, - "serialized_chars": 39133, - "estimated_input_tokens": 9784, - "estimated_eval_tokens": 19824 + "serialized_chars": 39131, + "estimated_input_tokens": 9783, + "estimated_eval_tokens": 19822 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a collection of unrelated Transformers bug reports with a few broad theme overlaps (sliding-window configs, ZeRO-3, dtype mismatches, Qwen/Gemma variants). Only one pair looks like a likely true duplicate: the two SigLIP2 issues reporting bad/garbled outputs. No PRs are present.", - "confidence": 0.83, - "canonical_issue_reason": null, + "summary": "Mostly heterogeneous cluster with a few real duplicate pockets. The main correction is to reject 39290 vs 43531: they both mention sliding_window, but the model families and failure contexts differ too much. A couple of tighter matches remain, especially SigLIP2 and custom-module loading.", + "confidence": 0.69, + "canonical_issue_reason": "Issue 39290 is still the strongest single anchor among the near-duplicate pockets, but only as a local representative; the cluster overall is too diverse for a strong global canonical.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43994 is the best representative of the only likely duplicate area: it is broader and more directly describes the user-facing SigLIP2 failure across AutoModel/pipeline.", + "best_issue_reason": "If one issue must stand in for the cluster, 39290 is the best representative because it is the clearest specific bug report with the strongest nearby duplicate signal, though the overall set is not one bug family.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Both mention sliding_window, but they are different models and different failure modes (Gemma3 config field vs Qwen3-MoE behavior)." + "reason": "Same keyword, but Gemma3TextConfig/vLLM and Qwen3-MoE point to different model-specific failures; not enough evidence for one bug." }, { - "left": "issue:43854", - "right": "issue:43866", + "left": "issue:43792", + "right": "issue:45901", "accept": false, - "reason": "Unrelated model-loading failure vs corrupted checkpoint report; no shared concrete bug path." + "reason": "Whisper runtime failure and table QA crash are unrelated code paths and symptoms." }, { - "left": "issue:43792", - "right": "issue:45901", + "left": "issue:43854", + "right": "issue:43866", "accept": false, - "reason": "Whisper loading/runtime issue is unrelated to table-question-answering crashes." + "reason": "Model-loading test failure vs corrupted checkpoint; different underlying problems." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Both involve index/shape errors, but one is a mask mismatch and the other is a ZeRO-3 index-out-of-bounds on a different model path." + "reason": "Both are index errors, but the models, shapes, and triggers differ." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch version incompatibility and a pydantic PretrainedConfig regression are different bugs." + "reason": "Torch version incompatibility and PretrainedConfig/pydantic regression are separate issues." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "Both mention environment/deepspeed-ish pain, but one is a ZeRO-3 Bert index error and the other is a torch/transformers version incompatibility." + "reason": "ZeRO-3/Bert index error is unrelated to torch/transformers version incompatibility." }, { "left": "issue:43975", "right": "issue:45901", "accept": false, - "reason": "Detokenization bug in DeepSeek code is unrelated to table-question-answering task crashes." + "reason": "Detokenization bug and table-question-answering crash are not the same bug." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "Whisper runtime failure is unrelated to the pydantic/config regression." + "reason": "Whisper runtime failure is unrelated to the pydantic field regression." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Both are Qwen3.5 chat-related, but one is a crash in transformers chat and the other is a streaming chat/completions API failure; not the same concrete bug." + "reason": "Both involve Qwen3.5/chat, but the concrete failures differ too much to merge." }, { "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "NVFP4 runtime failure is unrelated to the table QA crash." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Different model families and symptoms: sliding_window/vLLM versus Gemma4 device-mapping." + }, + { + "left": "issue:45464", "right": "issue:45685", "accept": false, - "reason": "Qwen-3-8B NVFP4 runtime error is unrelated to an MPS histogram kernel missing for MoE." + "reason": "Streaming chat failure and MPS Int histogram error are unrelated." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Tied lm_head weights in Mistral3 is unrelated to a corrupted Ovis2 checkpoint." + "reason": "Untied weights in Mistral3 and a corrupted checkpoint are different causes." }, { "left": "issue:43541", "right": "issue:45685", "accept": false, - "reason": "Grouped_mm tracing failure in Mixtral is a different code path than the MPS Int histogram issue." + "reason": "Grouped_mm tracing error and MPS histogram error are distinct failure paths." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Both are dtype/runtime issues, but they affect different models and different execution paths (dynamo tracing vs autocast)." + "reason": "Different models and different runtime errors; not the same bug." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Processor failure for Voxtral is unrelated to a template-node compilation error." + "reason": "Processor failure and template compilation error are unrelated." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "ImportError for GenerationMixin is unrelated to sliding-window config issues." + "reason": "GenerationMixin import error is unrelated to the sliding_window bug." }, { "left": "issue:45800", "right": "issue:45823", "accept": false, - "reason": "Version incompatibility is not the same bug as a Gemma4 device mismatch during forward." + "reason": "Torch/transformers incompatibility and Gemma4 PLE device mismatch are not the same issue." }, { "left": "issue:41093", "right": "issue:41762", "accept": false, - "reason": "Both are zero/shape index errors, but one is a mask-length mismatch and the other is a loading-time size-0 index error on Gemma3; too different to treat as the same bug." + "reason": "Both are index errors around loading, but the model paths and exact failures differ." }, { - "left": "issue:43296", - "right": "issue:43366", + "left": "issue:43572", + "right": "issue:45070", "accept": false, - "reason": "PaddleOCR-VL loading in vLLM and GGUF gpt-oss support are separate model-format issues." + "reason": "StableLm pad_token_idx regression is unrelated to the PretrainedConfig/pydantic issue." }, { - "left": "issue:43572", - "right": "issue:45070", + "left": "issue:43296", + "right": "issue:43366", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is unrelated to the pydantic PretrainedConfig regression." + "reason": "PaddleOCR-VL loading and GGUF gpt-oss support are different problems." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Mixtral torch-dynamo tracing failure and GPT-OSS tensor-parallel support are different problems." + "reason": "Torch dynamo grouped_mm tracing failure and TP-not-working are not the same underlying bug." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "Int4 memory/OOM regression is unrelated to tied weights in translation models." + "reason": "Int4 OOM regression and tied-weights translation bug are unrelated." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "Phi-tiny-MoE autocast dtype mismatch is unrelated to Qwen3.5 streaming chat failures." + "reason": "Autocast dtype mismatch and chat streaming failure are different code paths." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different bug than the pydantic field break." + "reason": "init_empty_weights argument handling is unrelated to the pydantic field regression." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "GPT-OSS GGUF support and Qwen3.5 chat streaming are different code paths." + "reason": "GGUF gpt-oss support and Qwen3.5 streaming inference are unrelated." }, { "left": "issue:45020", "right": "issue:45800", "accept": false, - "reason": "Remote_code breakage and a torch/transformers version incompatibility are not the same underlying bug." + "reason": "Remote_code breakage and torch/transformers incompatibility are not the same bug." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to the pydantic config regression." + "reason": "Qwen3-MoE sliding_window and PretrainedConfig/pydantic breakage are unrelated." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Grouped_mm tracing failure and missing Float8 storage support are different runtime issues." + "reason": "Grouped_mm tracing failure and Float8 storage lookup error are different issues." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Both are index errors under ZeRO-3, but they involve different models and different failure shapes." + "reason": "Both are index errors, but the affected scenarios and tensors differ." }, { "left": "issue:43054", "right": "issue:43994", "accept": true, - "reason": "Both report SigLIP2 producing bad/garbled outputs; same underlying model quality/implementation problem across different entry points." + "reason": "Both concern SigLIP2 producing bad outputs on the same model family; this looks like the same underlying issue." }, { "left": "issue:45759", "right": "issue:45902", "accept": false, - "reason": "Composite Qwen config unwrapping and uninitialized rotary embedding memory are distinct Qwen3.5 issues." + "reason": "Composite config unwrapping and uninitialized rotary memory are unrelated." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "TensorBoard-without-TensorFlow backend error is unrelated to the torch/transformers incompatibility." + "reason": "TensorBoard-without-TF backend error is unrelated to torch/transformers incompatibility." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP 2-D weight error and TRL input-embedding unpacking failure are unrelated." + "reason": "FSDP weight-shape error and Qwen3.5 embedding unpacking are different bugs." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Mistral3 image-preprocessor dtype mismatch is unrelated to Qwen3.5 embedding unpacking." + "reason": "Mistral dtype mismatch and Qwen3.5 SFT unpacking are unrelated." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "High perplexity on gpt-oss-20b and GLM5 are different model-specific issues." + "reason": "High perplexity on gpt-oss-20b and GLM5 are different reports with no shared failure mode." }, { "left": "issue:45632", "right": "issue:45698", - "accept": false, - "reason": "Both involve remote_code/custom-module loading, but one is a leaf-directory cache collision and the other is a wrong-module load after save_pretrained; not clearly the same concrete bug." + "accept": true, + "reason": "Both point to wrong custom-module resolution after save/load; same dynamic-module path bug." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Custom models in Jupyter and fallback to flash-attn2 being blocked are unrelated." + "reason": "Jupyter custom-model initialization and flash-attn fallback blocking are unrelated." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Specific tied-weight bug in Mistral3 is not the same as the broader translation-model tied-weights report." + "reason": "Mistral3 tied-weight bug and translation-model tied-weight regressions are different model families and fixes." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft pair, issue:43054 vs issue:43994, is reasonably supported by the titles/body summaries as a likely SigLIP2 duplicate area. The other verdicts are appropriately cautious and do not overclaim. No PR pair issues are present." + "accept": false, + "feedback": "The cluster-level summary is mostly grounded, but one soft-edge acceptance is too strong: issue:39290 vs issue:43531. They share a sliding_window keyword, but the packet shows different model families and different failure contexts (Gemma3TextConfig/vLLM vs Qwen3-MoE), so calling them the same bug overstates the evidence. For a conservative review, that pair should be marked false or at most tentative. The other accepted pairs are more plausible, but this single overconfident accept is enough to reject." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -880,7 +946,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36331", "issue:38175", @@ -938,8 +1004,8 @@ "issue:44863|issue:45005", "issue:44360|issue:44512", "issue:44918|issue:45507", - "issue:44492|issue:44512", "issue:43975|issue:44292", + "issue:44492|issue:44512", "issue:44292|issue:45507", "issue:43950|issue:44534", "issue:43644|issue:43950", @@ -967,226 +1033,244 @@ "issue:43881|issue:43883", "issue:45685|issue:45823" ], - "prepared_review_unit_hash": "b813b2861095e130a357b2e6a92620d90dd67c93565871530e803f060013445c", + "prepared_review_unit_hash": "9ae4db3ea942906e931f9fda13dc770f42ce24e3cf87a12b852c7d2c71ca4b7e", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37575, - "estimated_input_tokens": 9394, - "estimated_eval_tokens": 19044 + "serialized_chars": 37578, + "estimated_input_tokens": 9395, + "estimated_eval_tokens": 19046 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous. The only clear duplicate family is the Transformers v5 non-persistent-buffer regression; most other pairs are merely same-subsystem or same-model-family similarities, not the same concrete bug.", - "confidence": 0.95, - "canonical_issue_reason": "issue:43950 is the clearest anchor for the shared v5 non-persistent-buffer regression: it states the core bug plainly, is broadly applicable, and matches the accepted duplicate follow-up issues.", + "summary": "Mostly unrelated issue set, with a few small duplicate clusters around non-persistent buffer corruption, remote_code regressions, and SigLIP2 discrepancy/quality problems. No PRs are present.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43950 is the clearest broad regression report in the cluster: it describes the underlying non-persistent-buffer corruption bug directly, and it has the strongest duplicate-style overlap with issue:44534 (plus likely the related 45902 symptom).", "canonical_pr_reason": null, - "best_issue_reason": "issue:43950 is the best overall representative because it captures the underlying loader/materialization regression more precisely than the narrower follow-up reports.", + "best_issue_reason": "issue:43950 is the best global anchor because it states a concrete Transformers 5.x regression with a clear code-path focus and likely absorbs the closest duplicate reports in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42915", "right": "issue:45399", "accept": false, - "reason": "Both involve loading/runtime checks, but one is Qwen3 MoE FP8 and the other is flash-attn2 fallback gating; not the same bug." + "reason": "Different problems: Qwen3Moe FP8 config failure vs flash-attn2 fallback being blocked by checks." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "PagedAttentionCache crash on Qwen3.5 is unrelated to tied-weights handling in translation models." + "reason": "Different code paths: Qwen3.5 PagedAttentionCache crash vs tied-weights handling on translation models." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Quantized offloading behavior is a different code path from tied-weights/v5 translation-model issues." + "reason": "Quantization/offloading behavior is unrelated to tied-weights regressions." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is not the same as tied-weights regressions." + "reason": "Checkpoint-loading failure for NemotronH is not the same as tied-weights handling." }, { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "DSA indexer ReLU discussion and a docs typo are unrelated." + "reason": "Unrelated: DSA indexer ReLU discussion vs a docs typo about a removed command." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "TRL SFT embedding unpacking and GraniteMoEHybrid invalid method are different failures." + "reason": "Different failures in different models/subsystems; no shared concrete bug." }, { - "left": "issue:44492", - "right": "issue:44512", + "left": "issue:43975", + "right": "issue:44292", "accept": false, - "reason": "Cache-strategy typo is documentation-only and unrelated to removed run-command docs." + "reason": "Different symptoms: detokenization bug vs Qwen-3 NVFP4 runtime error." }, { - "left": "issue:43975", - "right": "issue:44292", + "left": "issue:44492", + "right": "issue:44512", "accept": false, - "reason": "Detokenization regression and Qwen-3-8B-NVFP4 runtime error are different concrete bugs." + "reason": "A cache-strategy typo is unrelated to old docs mentioning the removed run command." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "NVFP4 runtime failure and GraniteMoEHybrid invalid method do not share a concrete code path." + "reason": "No common underlying bug; they affect different models and failure modes." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Both describe the same v5 non-persistent-buffer regression: buffers are corrupted/junk-filled during loading/materialization." + "reason": "Both describe the same Transformers 5.x non-persistent-buffer corruption regression." }, { - "left": "issue:43643", + "left": "issue:43644", "right": "issue:43950", "accept": false, - "reason": "Missing fields in trust_remote_code config output is a different symptom from non-persistent-buffer corruption." + "reason": "AutoConfig remote_code field loss is a different bug than buffer corruption." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "SigLIP2 docs example errors are not the same as poorer text embeddings." + "reason": "Both mention SigLIP2, but one is a docs/example issue and the other is a model quality discrepancy." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Autocast dtype mismatch and TRL SFT embedding unpacking are different failures." + "reason": "Different training/runtime issues: autocast dtype mismatch vs Qwen3.5 RLHF gradient explosion." }, { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "Trainer compute_loss signature mismatch and Gemma3 ZeRO-3 loading error are unrelated." + "reason": "Trainer API mismatch and ZeRO-3 load failure are unrelated." }, { "left": "issue:41628", "right": "issue:45800", "accept": false, - "reason": "AutoImageProcessor import failure and torch/transformers version incompatibility are distinct issues." + "reason": "Import/export API issue is unrelated to torch/transformers version incompatibility." }, { "left": "issue:43950", "right": "issue:45902", "accept": true, - "reason": "The Qwen3_5Moe inv_freq uninitialized-memory report is a model-specific manifestation of the same non-persistent-buffer materialization regression." + "reason": "Same non-persistent-buffer materialization bug; 45902 is a model-specific manifestation after meta\u2192to_empty(cuda)." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "bitsandbytes Int8Params keyword incompatibility and Float8 storage lookup failure are different compatibility bugs." + "reason": "Different low-level compatibility problems: bitsandbytes kwarg mismatch vs missing Float8 storage." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Corrupted checkpoint and generic loading noise are not the same underlying issue." + "reason": "Corrupted checkpoint vs noisy loading behavior are not the same bug." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "SigLIP2 embedding quality and tokenization changes are not the same bug." + "reason": "SigLIP2 embedding quality and tokenization changes are different problems." }, { "left": "issue:41553", "right": "issue:43883", "accept": false, - "reason": "Bad AutoTokenizer error message for Voxtral and Molmo missing all_tied_weights_keys are unrelated." + "reason": "Bad AutoTokenizer error messaging vs missing all_tied_weights_keys attribute are unrelated." }, { "left": "issue:38175", "right": "issue:43054", "accept": false, - "reason": "Both are SigLIP2-related, but zero probabilities and worse text embeddings are not clearly the same concrete defect." + "reason": "Both concern SigLIP2 outputs, but the observed failures are too different to treat as the same bug." }, { "left": "issue:45663", "right": "issue:45902", "accept": false, - "reason": "Gemma4 FSDP2 shared_kv_states rebuilding and Qwen3_5Moe inv_freq memory initialization are unrelated." + "reason": "Gemma4 FSDP2 shared_kv_states issue is unrelated to non-persistent buffer initialization." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "Qwen3.5 FlashAttention position_ids crash and CPU-offload incompatibility are different bugs." + "reason": "Flash-attn packed-sequence misinterpretation is different from CPU-offload incompatibility in rotary embedding." }, { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "Voxtral AutoTokenizer error messaging and glm-4v-9b loading failure are unrelated." + "reason": "Different models and different failure layers; no shared root cause." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "LoRA gradient checkpointing ineffectiveness and int4 quantization OOM are different memory issues." + "reason": "Gradient checkpointing inefficiency and int4 memory blowup are different optimization issues." }, { "left": "issue:43054", "right": "issue:43493", - "accept": false, - "reason": "Both concern SigLIP2 quality, but one is embedding quality and the other is HF-vs-JAX discrepancy; not enough to treat as the same bug." + "accept": true, + "reason": "Both point to the same SigLIP2 implementation discrepancy/quality regression versus the expected/original behavior." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "Generic loading noise and a specific model load failure are not the same underlying issue." + "reason": "General loading noise is not the same as failing to load a specific model." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Detokenization bug and AMD GPU compatibility failure are unrelated." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Generic loading noise and another model-specific load failure are not the same bug." + "reason": "Noisy loading messages are unrelated to the specific model-load failure." }, { "left": "issue:43643", "right": "issue:45020", + "accept": true, + "reason": "Same remote_code regression family; 43643 is a concrete AutoConfig missing-fields symptom of the broader breakage." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "LoRA checkpointing behavior and Qwen3 MoE memory usage are different issues." + }, + { + "left": "issue:41762", + "right": "issue:42915", "accept": false, - "reason": "Remote-code config field loss is related in theme, but too different in concrete failure from broad remote_code breakage." + "reason": "ZeRO-3 load indexing error and FP8 config failure are unrelated." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "Both are load failures, but they point to different models and different failure modes." + "reason": "GLM-4V loading failure is not the same as the Molmo tied-weights attribute bug." }, { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "MPS histogram dtype error in MoE and Gemma4 device mismatch are unrelated." + "reason": "MPS int histogram support and Gemma4 device mismatch are different runtime problems." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded overall. The summary stays conservative: 43950/44534 are clearly the same non-persistent-buffer regression, and 45902 is a plausible model-specific manifestation of that same bug. The remaining pairs are appropriately rejected as different concrete failures rather than the same issue." + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The accepted soft-edge pairs are supported by the issue titles and the provided soft-pair evidence, and the rejections do not overclaim shared root causes. No PRs are present, so the anchor choice is reasonable." }, "evaluator_used": true, "retried": false, @@ -1205,7 +1289,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:24643", "issue:30064", @@ -1264,12 +1348,12 @@ "issue:44661|issue:45020", "issue:43828|issue:45823", "issue:45081|issue:45399", - "issue:45020|issue:45356", "issue:43742|issue:45399", - "issue:43827|issue:44509", + "issue:45020|issue:45356", "issue:43404|issue:43950", "issue:43638|issue:45823", "issue:42915|issue:45020", + "issue:43827|issue:44509", "issue:43872|issue:44291", "issue:43257|issue:43866", "issue:43792|issue:44220", @@ -1289,232 +1373,232 @@ "issue:24643|issue:30064", "issue:43366|issue:43828" ], - "prepared_review_unit_hash": "f23e573b746e9226d625d89d680de8705663d82ecb8cc7bd562bf4ef5dd4743d", + "prepared_review_unit_hash": "fd3079dccae342689c5c53338d250c89a63f0ea14141903d017d30e301516ec7", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 37042, - "estimated_input_tokens": 9261, - "estimated_eval_tokens": 18778 + "serialized_chars": 37048, + "estimated_input_tokens": 9262, + "estimated_eval_tokens": 18780 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a set of unrelated regression reports; only two pairs look like true duplicates: the v5 docs/pipeline cleanup and the `_is_hf_initialized` init/loading incompatibility. Everything else is too model- or code-path-specific to merge together.", - "confidence": 0.58, - "canonical_issue_reason": "44509 is the clearest canonical issue for the docs/pipeline-removal bug: it is broader and more explicit than 43827, which is the narrower variant of the same documentation problem.", + "summary": "This cluster is mostly heterogeneous: only a few pairs look like true duplicates, mainly doc typos/regressions and a couple of same-error code-path bugs. Most soft-similar pairs share only broad subsystem/theme overlap, not the same underlying issue.", + "confidence": 0.94, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "44509 is the best issue to keep as the representative of the only clear duplicate group in this set.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Different models and failure modes; one is Qwen3VL weight-only loading, the other is a GLM5 model request." + "reason": "Different models and failures: Qwen3VL from_pretrained weight_only error vs a generic GLM5 model-loading issue." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading failure vs flash-attn fallback gating; different bugs." + "reason": "Tokenizer-loading regression vs flash-attn fallback gating; unrelated code paths." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "ImportError for a missing class vs bitsandbytes Int8Params kwarg incompatibility." + "reason": "ImportError for Qwen2.5-VL class name vs bitsandbytes Int8Params kwarg incompatibility; not the same bug." }, { "left": "issue:42491", "right": "issue:44368", "accept": false, - "reason": "LoRA/Qwen3 MoE compatibility problem vs a gradient-checkpointing warning; not the same bug." + "reason": "Different LoRA/tie_word_embeddings warning issue, not the same HF4.x to HF5.x Qwen3 MoE loading failure." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "Broad remote_code breakage vs a Gemma4 device_map forward mismatch." + "reason": "Remote_code regressions broadly vs a Gemma4 device_map forward mismatch; no shared concrete bug." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Tokenizer mapping/model registration issue vs remote_code regressions; different code paths." + "reason": "Model-like addition failing in tokenizer mapping vs remote_code regressions; overlapping theme only." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Autocast dtype mismatch vs device placement mismatch; not the same failure." + "reason": "Autocast dtype mismatch in Phi-tiny-MoE vs Gemma4 PLE device mismatch; distinct failures." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Tokenizer regex patch crash vs flash-attn fallback logic; unrelated." - }, - { - "left": "issue:45020", - "right": "issue:45356", - "accept": false, - "reason": "General remote_code breakage vs a specific Kimi-K2.5 tokenizer/codec regression." + "reason": "Mistral regex patch crash vs flash-attn fallback blocking; unrelated bugs." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "KeyError while loading a model vs flash-attn fallback checks; unrelated." + "reason": "MobileLLM key error while loading vs flash-attn install/fallback checks; different code paths." }, { - "left": "issue:43827", - "right": "issue:44509", - "accept": true, - "reason": "Same v5 docs cleanup for removed summarization/translation pipeline tasks." + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "General remote_code breakage vs Kimi-K2.5 tokenizer codec regression; not the same issue." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Tied lm_head bug vs non-persistent buffer corruption; different issues." + "reason": "lm_head tying bug vs non-persistent buffer corruption on from_pretrained; separate loading semantics." }, { "left": "issue:43638", "right": "issue:45823", "accept": false, - "reason": "Zero-3 index error on a Bert model vs Gemma4 PLE device mismatch." + "reason": "Deepspeed ZeRO-3 index error on non-pretrained Bert vs Gemma4 device mismatch; unrelated." }, { "left": "issue:42915", "right": "issue:45020", "accept": false, - "reason": "FP8/Qwen3 MoE failure vs broad remote_code regressions; not the same bug." + "reason": "FineGrainedFP8 Qwen3 MoE failure vs remote_code regression broadly; too different." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Same doc regression: both note removed v5 pipeline tasks (summarization/translation/text2text) still referenced in docs." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Both report the same `_is_hf_initialized` incompatibility during model initialization/loading." + "reason": "Same underlying `_is_hf_initialized` / `Int8Params.__new__` incompatibility when loading models with init_empty_weights or bitsandbytes." }, { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed vs a corrupted Ovis2 checkpoint." + "reason": "Qwen3 MoE weight conversion with accelerate+deepspeed vs corrupted Ovis2 checkpoint; unrelated model issues." }, { "left": "issue:43792", "right": "issue:44220", - "accept": false, - "reason": "Whisper runtime failure vs a generic fbank feature extraction issue; too indirect to treat as duplicate." + "accept": true, + "reason": "Both point to the Whisper audio feature-extraction path failing; `_torch_extract_fbank_features()` is the likely root cause of 'can't run'." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "Different root causes: FP8 config failure vs bitsandbytes/init kwarg mismatch." + "reason": "Qwen3 MoE FP8 failure vs bitsandbytes/init_empty_weights kwarg issue; different subsystems." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "Bad AutoTokenizer error message for Voxtral vs tokenizer loading failure for a specific model." + "reason": "Bad AutoTokenizer error message for Voxtral vs tokenizer loading failure for est-roberta; not the same bug." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Unexpected compute_loss kwarg vs tensor mask shape mismatch; unrelated." + "reason": "Trainer compute_loss signature change vs mask/tensor shape mismatch; unrelated errors." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "Weights not converted in Qwen3 MoE loading vs gradient averaging under DeepSpeed." + "reason": "DeepSpeed weight-conversion failure vs gradient averaging with GAS/model_accepts_loss_kwargs; different training bugs." }, { "left": "issue:42947", "right": "issue:45923", "accept": false, - "reason": "LoRA gradient checkpointing ineffective vs missing supports_gradient_checkpointing flag; related theme but different bug." + "reason": "PEFT LoRA gradient checkpointing ineffective vs missing supports_gradient_checkpointing flag on a remote-code variant." }, { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Different Qwen variants and different ZeRO-3 load failures; not clearly the same concrete bug." + "reason": "Both are ZeRO-3 weight-loading failures, but on different Qwen families and with different symptoms; not clearly the same defect." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "Model-loading failure in unit tests vs NemotronH checkpoint-loading failure; different models." + "reason": "GLM-4.7-Flash test loading failure vs NemotronH checkpoint loading failure; distinct models and failure modes." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "RLHF gradient explosion/NaN issue vs flash_attention.py crash on s_aux=None." + "reason": "Qwen3.5 RLHF NaN/SDPA fallback issue vs flash_attention.py s_aux=None crash; unrelated." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "bitsandbytes init kwarg incompatibility vs CLIPTokenizer max length bug." + "reason": "bitsandbytes kwarg incompatibility vs CLIPTokenizer max_length sentinel value; no shared root cause." }, { "left": "issue:41093", "right": "issue:44805", - "accept": false, - "reason": "Both are IndexErrors, but the mask mismatch and the generic shape mismatch are different bugs." + "accept": true, + "reason": "Same mask/index shape mismatch error pattern; the later report is the same underlying IndexError with different tensor sizes." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Voxtral tokenizer error messaging vs a specific model loading failure." + "reason": "Different tokenizer-loading failures on different models; one is an error-message issue, the other a load failure." }, { "left": "issue:44479", "right": "issue:44560", - "accept": false, - "reason": "Related video-input regressions, but the impacted models and failure details are different enough to keep separate." + "accept": true, + "reason": "Both describe the same Qwen video-input regression in v5.3.0, with StopIteration being a concrete symptom of the broader video pipeline breakage." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "Qwen3.5 PagedAttention crash vs NemotronH checkpoint loading; unrelated." + "reason": "PagedAttentionCache linear_attention crash vs NemotronH checkpoint loading failure; separate bugs." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "DeepSpeed training weight-dimension error vs void segmentation-map preprocessing; unrelated." + "reason": "DeepSpeed training weight dimension error vs void segmentation map processing failure; unrelated." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF architecture support request vs autocast dtype mismatch; not the same issue." + "reason": "GGUF gpt-oss support request vs Phi-tiny-MoE autocast dtype mismatch; no common code-path bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The verdicts are grounded and conservative. The two accepted pairs are well supported by the packet: 43827/44509 are the same v5 docs pipeline-removal cleanup, and 43872/44291 are the same `_is_hf_initialized` loading incompatibility. The rejections generally stay within the evidence and avoid overclaiming duplicates." + "feedback": "The summary is grounded in the packet and stays conservative: it describes the cluster as mostly heterogeneous while calling out only a few plausible duplicate pairs. The accepted soft-edge verdicts are defensible from the issue titles/body context, and the rejected ones avoid overclaiming shared root causes." }, "evaluator_used": true, "retried": false, @@ -1533,7 +1617,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36010", "issue:38175", @@ -1595,8 +1679,8 @@ "issue:43645|issue:43646", "issue:42915|issue:43957", "issue:43366|issue:44589", - "issue:42617|issue:43366", "issue:44560|issue:44918", + "issue:42617|issue:43366", "issue:36010|issue:42915", "issue:44661|issue:45823", "issue:44560|issue:44805", @@ -1617,20 +1701,20 @@ "issue:45313|issue:45357", "issue:42491|issue:45276" ], - "prepared_review_unit_hash": "11bb5cf7a432dd1d7b343b408584ac953985b0311e3a3642602b27199accccc8", + "prepared_review_unit_hash": "521c103eb31bd9fa102759c9a3b13f0ce9636d713aa69ed23056a619f3a99db6", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 36682, + "serialized_chars": 36684, "estimated_input_tokens": 9171, "estimated_eval_tokens": 18598 }, @@ -1639,204 +1723,198 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose mixed cluster: a few genuine duplicates around Transformers v5 regressions, but most items are unrelated model-specific bugs. I only accepted the clearly same-root-cause pairs.", - "confidence": 0.62, - "canonical_issue_reason": "43646 is the broadest, clearest regression report in the set: it captures the core Transformers v5 custom-model initialization breakage that best represents the small duplicate-heavy subset.", + "summary": "Most items are unrelated model-specific regressions; only a few soft pairs look like true duplicates. The clearest duplicate groups are the non-persistent-buffer regression, the custom-model init regression, and the SigLIP2 wrong-output reports.", + "confidence": 0.74, + "canonical_issue_reason": "issue:43644 is the best anchor for the non-persistent-buffer regression: it is the earlier, more fully specified report, and issue:44534 is essentially the same bug phrased later.", "canonical_pr_reason": null, - "best_issue_reason": "It is the most representative issue for the cluster\u2019s regression-heavy subset and is cleaner than the highly model-specific reports.", + "best_issue_reason": "issue:43644 is the strongest single issue to keep as canonical because it is concrete, well-scoped, and has a clear near-duplicate; it is easier to triage than the more model-specific or ambiguous reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45325", "right": "issue:45902", "accept": false, - "reason": "Different bugs and different model families: Qwen2.5-VL rope scaling vs Qwen3.5-MoE inv_freq materialization." + "reason": "Different models and different failure modes: rope scaling bug vs uninitialized-memory rotary embedding issue." }, { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Both are Gemma4, but one is an FSDP2 shared_kv_states KeyError and the other is a device_map forward mismatch; not the same code-path." + "reason": "Same model family, but distinct code paths: FSDP2 shared_kv_states KeyError vs device_map auto device mismatch." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "GGUF GPT-OSS support and Qwen3-MoE sliding_window are unrelated changes." + "reason": "Unrelated topics: GGUF architecture support vs Qwen3-MoE sliding_window behavior." }, { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "AudioFlamingo3 track-leak batching bug vs Whisper empty-transcription failure; different models and failures." + "reason": "Different inference bugs in different pipelines; no shared concrete code path." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "Non-persistent buffer corruption is unrelated to Kosmos2.5 long-OCR index errors." + "reason": "Non-persistent buffer corruption vs OCR long-input index error are not the same bug." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Qwen3-VL video StopIteration and MoE MPS histogram dtype error are unrelated." + "reason": "Video StopIteration issue and MPS histogram Int limitation are unrelated." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Missing Qwen2_5_VL import and generic meta-device loading breakage are different issues." + "reason": "Import error for a missing class vs meta-device loading regression; not the same issue." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Bamba torch.compile+SDPA crash is unrelated to Qwen3.5 flash-attention 3D position_ids handling." + "reason": "Different concrete failures: torch.compile with SDPA vs flash-attention crash on Qwen3.5 position_ids." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "Both report the same Transformers v5 custom model initialization regression; the notebook wording in 43645 is just a context variant." + "reason": "These are the same custom-model initialization regression; one is just a notebook-specific phrasing of the other." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3-MoE FP8 failure and meta-device loading failures are different bugs." + "reason": "Qwen3MoE FineGrainedFP8Config failure is unrelated to meta-device loading bugs." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "GGUF GPT-OSS support is unrelated to the Float8 storage lookup error." + "reason": "GGUF support request and Float8 storage TypeError are different problems." }, { - "left": "issue:42617", - "right": "issue:43366", + "left": "issue:44560", + "right": "issue:44918", "accept": false, - "reason": "3d_parallel.py runtime failure and GGUF GPT-OSS support are unrelated." + "reason": "Video StopIteration vs unpacking embeddings in TRL SFT trainer are different code paths." }, { - "left": "issue:44560", - "right": "issue:44918", + "left": "issue:42617", + "right": "issue:43366", "accept": false, - "reason": "Different Qwen3.5/Qwen3-VL audio-video embedding issues; not the same underlying bug." + "reason": "A script runtime failure and GGUF model support are unrelated." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "GenerationMixin import error and Qwen3-MoE FP8 failure are unrelated." + "reason": "GenerationMixin import error is unrelated to Qwen3MoE FP8 loading." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer-mapping-related add-new-model-like failure is unrelated to Gemma4 device mismatch." + "reason": "Tokenizer-mapping/model-like failure and Gemma4 device mismatch are different bugs." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Qwen3-VL video StopIteration and generic mask-shape IndexError are unrelated." + "reason": "Different symptoms and likely different tensor-shape issues; not enough to treat as duplicates." }, { "left": "issue:43632", "right": "issue:45834", "accept": false, - "reason": "_is_hf_initialized flag regression and Kosmos2.5 OCR index error are different issues." + "reason": "_is_hf_initialized flag regression is unrelated to the long OCR index error." }, { "left": "issue:38175", "right": "issue:43994", "accept": true, - "reason": "Both are reports of the same SigLIP2 base model producing broken/zeroed outputs through normal loading/inference paths." + "reason": "Both report incorrect SigLIP2 outputs for the same model family; the later one is essentially the same underlying inference bug." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "Zero3 BERT index error and tokenizer-mapping add-new-model-like failure are different code paths." + "reason": "Deepspeed ZeRO-3 Bert initialization failure is unrelated to add-new-model-like tokenizer mapping behavior." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Zero3 BertModel initialization failure and tokenizer-mapping failure are unrelated." - }, - { - "left": "issue:44661", - "right": "issue:44805", - "accept": false, - "reason": "Tokenizer mapping validation and mask/tensor shape mismatch are unrelated." + "reason": "Zero3 Bert index error is a different bug from the tokenizer-mapping/model-like issue." }, { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Both mention stricter config handling, but the model families and failure modes differ; not enough evidence of one underlying bug." + "reason": "Both involve config loading, but the model-specific failures are not the same concrete bug." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "gpu+cpu offload dequantized loading failure and Strix Halo mmap OOM are different loading/memory issues." + "reason": "device_map dequantized-model offload failure and mmap OOM on Strix Halo are different issues." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "Same non-persistent-buffer junk regression in Transformers v5; 44534 is a later duplicate of 43644." + "reason": "Exact duplicate regression: both say transformers v5 fills non-persistent buffers with junk." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "Same SigLIP2 family, but one is zero probabilities while the other is a doc example/model-processor/quantization error; not the same concrete bug." + "reason": "SigLIP2 wrong outputs and docs-example mismatches/quantization failures are related only by model family, not the same bug." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Qwen3 MoE LoRA compatibility regression and BitNet packed-weight loading bug are unrelated." + "reason": "Qwen3_moe LoRA hf4.x/hf5.x compatibility and BitNet packed-weight loading are unrelated." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Qwen3 auto device-mapping CUDA assert and Qwen3-MoE FP8 failure are distinct failures." + "reason": "Auto device mapping CUDA assert and FineGrainedFP8Config failure are different Qwen issues." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "GLM5 and Qwen3.5 flash-attention issues are unrelated." + "reason": "GLM5 issue and Qwen3.5 flash-attention generation bug are unrelated." }, { "left": "issue:44451", "right": "issue:44488", "accept": false, - "reason": "Both are BERT loading failures, but they reference different models and lack evidence of one shared root cause." + "reason": "Both are BERT loading failures, but the titles do not establish the same concrete underlying bug." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "ZeRO-3 language_model loading and save_pretrained visual-encoder key serialization are different bugs." + "reason": "ZeRO-3 weight loading and incorrect save_pretrained visual encoder keys are different Qwen3.5 regressions." }, { "left": "issue:42491", "right": "issue:45276", "accept": false, - "reason": "Qwen3 MoE LoRA incompatibility and Gemma4 resize_token_embeddings behavior are unrelated." + "reason": "Qwen3_moe LoRA compatibility on hf5.x and Gemma4 resize_token_embeddings behavior are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet, and the accepted soft pairs are conservative. The duplicate calls around 43644/44534 and 43645/43646 are well supported, and the broader cluster description stays appropriately cautious about the many unrelated model-specific issues." + "feedback": "The summary is grounded in the packet and the duplicate judgments stay conservative overall. The canonical non-persistent-buffer pair is well supported by the titles, and the accepted soft pairs are plausibly same-bug matches without overclaiming beyond the available evidence. No pair is forced together on weak evidence, and the rejected pairs are explained in a cautious way." }, "evaluator_used": true, "retried": false, @@ -1855,7 +1933,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36010", "issue:39404", @@ -1925,8 +2003,8 @@ "issue:45276|issue:45335", "issue:36010|issue:39404", "issue:43404|issue:43454", - "issue:41720|issue:44155", "issue:43425|issue:43957", + "issue:41720|issue:44155", "issue:39692|issue:44960", "issue:44402|issue:44488", "issue:42947|issue:45704", @@ -1943,20 +2021,20 @@ "issue:45276|issue:45292", "issue:44164|issue:44756" ], - "prepared_review_unit_hash": "638c884d5c32dd2d49d75e97c16b9d2d2c0c629d485f0a6671604064161cf1cc", + "prepared_review_unit_hash": "c7771e78b7b4192731d92935b995cd8b50f4c107943c00197fa0c5edc3527706", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 38298, + "serialized_chars": 38299, "estimated_input_tokens": 9575, "estimated_eval_tokens": 19406 }, @@ -1965,108 +2043,108 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most items are separate Transformers regressions across different models and subsystems. Only the resize_token_embeddings reports for Gemma4/generic output embeddings look like a plausible duplicate pair.", - "confidence": 0.67, - "canonical_issue_reason": "issue:45292 is the most generic description of the shared resize_token_embeddings regression; issue:45276 reads like a Gemma4-specific manifestation with extra affected modules.", + "summary": "This cluster is mostly a set of unrelated issue reports. The only soft edge that looks like the same underlying bug is the resize_token_embeddings/output_embeddings pair; all other candidates are too model-/path-specific to merge confidently.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 45292 is the cleanest canonical for the shared resize_token_embeddings bug: it states the core generic symptom on output_embeddings, while 45276 is a broader Gemma4-specific manifestation of the same failure.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45292 is the cleanest representative of the only likely duplicate pair and has the broadest, most reusable title.", + "best_issue_reason": "Issue 45292 is the best representative because it describes the common root symptom without extra model-specific detail, making it the most reusable target for deduplication.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Different areas: checkpoint resume step math vs SGD optimizer args being ignored." + "reason": "Different training/runtime bugs: checkpoint resume/max_steps accounting vs optimizer arguments being ignored." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "One is non-persistent buffer initialization junk; the other is Jupyter custom-model initialization, which is unrelated." + "reason": "Both mention Transformers 5.0.0, but one is about non-persistent buffers and the other about custom model initialization in Jupyter; different problems." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading failures, but for different models and likely different root causes." + "reason": "Both are tokenizer-loading failures, but for different models and likely different root causes; not the same bug." }, { "left": "issue:43854", "right": "issue:43931", "accept": false, - "reason": "Different models and symptoms: GLM-4.7 unit-test load issue vs Qwen3-VL weight-shape mismatch." + "reason": "Different model-loading failures for different architectures; no clear shared code-path bug." }, { "left": "issue:45488", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and are not the same concrete bug." + "reason": "Tokenizer regressions in v5, but one is LlamaTokenizer pre-tokenizer handling and the other is AutoTokenizer token IDs for Granite; not the same change." }, { "left": "issue:39692", "right": "issue:43994", "accept": false, - "reason": "Same model family, but one is a doc-example/quantization mismatch and the other is bad inference results in AutoModel/pipeline." + "reason": "Same model family, but one is a documentation/example issue plus quantization failure; the other is a runtime nonsensical-results report. Too different to merge confidently." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Different failures: Qwen3 MoE weight conversion under accelerate/deepspeed vs GLM-4.7 loading in tests." + "reason": "Qwen3 MoE weight conversion/offload behavior vs GLM-4.7-Flash loading in tests; unrelated." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Both touch quantization/offloading, but the reported failure modes and likely code paths differ." + "reason": "Different resource problems: Qwen3 MoE training memory usage vs quantized offloading behavior." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Unrelated issues: Qwen3 MoE LoRA compatibility on hf5.x vs Qwen3-VL load shape mismatch." + "reason": "A LoRA compatibility regression across branches is unrelated to a Qwen3-VL weight-shape mismatch." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both mention memory/OOM under quantization, but they are distinct bugs with different symptoms and causes." + "reason": "Both involve memory, but one is MoE training memory usage and the other is int4 quantization reserved-memory/OOM; different issues." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Different model-specific crashes: Qwen3.5 chat vs Gemma4Processor missing _tokenizer in serve." + "reason": "Different models and failures: Qwen3.5 chat crash vs Gemma4Processor missing _tokenizer in serve." }, { "left": "issue:44960", "right": "issue:46050", "accept": false, - "reason": "GLM5 loading vs sinq save/load corruption are separate issues." + "reason": "GLM5 loading and sinq save/load corruption are unrelated." }, { "left": "issue:42491", "right": "issue:45292", "accept": false, - "reason": "LoRA/Qwen3 MoE compatibility is unrelated to the resize_token_embeddings regression." + "reason": "LoRA hf4.x/hf5.x compatibility has no overlap with resize_token_embeddings behavior." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Different load/save failures: extra_state handling vs init_empty_weights/_is_hf_initialized argument mismatch." + "reason": "Both are loading/saving related, but extra_state handling and init_empty_weights _is_hf_initialized are distinct bugs." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both are flash_attention crashes, but one is a packed-sequence misinterpretation on Qwen3.5 and the other is s_aux=None handling." + "reason": "Both hit flash_attention paths, but one is a packed-sequence/position_ids crash and the other is an s_aux=None AttributeError; different code paths." }, { "left": "issue:45276", "right": "issue:45335", "accept": false, - "reason": "Similar wording, but different model families and embedding surfaces; not clearly the same concrete bug." + "reason": "Similar symptom, but model-specific implementations differ (Gemma4 vs T5Gemma) and the reports do not establish a single shared root cause." }, { "left": "issue:36010", @@ -2078,115 +2156,115 @@ "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both are lm_head tying problems, but they are model-specific reports rather than the same concrete fix." + "reason": "Both mention untied lm_head weights, but they are different model families and the evidence is not enough to treat them as the same bug." }, { - "left": "issue:41720", - "right": "issue:44155", + "left": "issue:43425", + "right": "issue:43957", "accept": false, - "reason": "Different problems: Qwen3 auto device-map crash vs AudioFlamingo3 batched inference leakage." + "reason": "Torch 2.10 compatibility and meta-device model loading are different incompatibility reports." }, { - "left": "issue:43425", - "right": "issue:43957", + "left": "issue:41720", + "right": "issue:44155", "accept": false, - "reason": "Torch version incompatibility is a different issue from meta-device loading failures." + "reason": "Qwen3 auto device mapping CUDA assert is unrelated to AudioFlamingo3 track-to-track leakage." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "Unrelated model families and failure modes: SigLIP2 docs/inference vs GLM5 loading." + "reason": "Different models and failures; no shared underlying bug." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Both involve tokenizer/model loading, but the specific failures and affected models are different." + "reason": "Tokenizer vocab-size mismatch is unrelated to failing to load a specific model." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Gradient checkpointing with PEFT LoRA is unrelated to the apex.FusedRMSNorm memory leak." + "reason": "Gradient checkpointing/PEFT and apex RMSNorm memory leak are unrelated." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "Different composite-model bugs: FSDP2 shared_kv_states handling vs text_config unwrapping in from_config." + "reason": "Gemma4 FSDP2 attention state rebuilding and Qwen multimodal text_config unwrapping are different model-architecture bugs." }, { "left": "issue:43873", "right": "issue:44387", "accept": false, - "reason": "Both are memory issues under quantization, but one is offloading behavior and the other is reserved-memory growth/OOM." + "reason": "Quantization offloading vs int4 reserved-memory growth are related broadly to memory, but not the same concrete bug." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "TypeError from init_empty_weights is unrelated to mmap/OOM on Strix Halo." + "reason": "init_empty_weights argument handling is unrelated to mmap/OOM on Strix Halo." }, { "left": "issue:45663", "right": "issue:45859", "accept": false, - "reason": "Different code paths: Gemma4 FSDP2 attention state vs Qwen3 MoE rotary embedding CPU-offload compatibility." + "reason": "Different Gemma4 vs Qwen3.5 MoE offload issues; not mergeable as one fix." }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "AudioFlamingo3 batch leakage and Gemma4 device-mapping mismatch are unrelated." + "reason": "Different models and failures: embedding/token leakage vs PLE device mismatch." }, { "left": "issue:43335", "right": "issue:45663", "accept": false, - "reason": "Different model/config bugs: sparse-layer creation in SwitchTransformers vs Gemma4 FSDP2 attention state." + "reason": "SwitchTransformers sparse-layer construction and Gemma4 FSDP2 attention state are unrelated." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Both are quantization-related load failures, but they are for different models and likely different causes." + "reason": "Different quantized-model loading problems for different models/quantization formats." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "OOM under int4 quantization is not the same as disabling mmap for Strix Halo memory pressure." + "reason": "Different memory/OOM reports with no shared code-path evidence." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "Meta-device loading regressions are distinct from the Strix Halo mmap/OOM workaround." + "reason": "Meta-device loading failures and disabling mmap for Strix Halo are different issues." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Both mention gradient checkpointing, but one is PEFT LoRA ineffectiveness and the other is eval-mode incompatibility." + "reason": "Gradient checkpointing in eval mode is unrelated to PEFT LoRA checkpointing effectiveness." }, { "left": "issue:45276", "right": "issue:45292", "accept": true, - "reason": "Same underlying bug: resize_token_embeddings does not propagate to output embeddings; 45276 is just Gemma4-specific." + "reason": "Both describe the same resize_token_embeddings failure to update output_embeddings; 45276 is the broader model-specific instance, while 45292 is the generic core report." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "Save/from_pretrained extra_state handling is unrelated to mmap-induced OOM on Strix Halo." + "reason": "save/from_pretrained extra_state handling is unrelated to mmap/OOM on Strix Halo." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary stays grounded in the packet and the only accepted soft-edge pair is conservative: 45276 and 45292 both describe the same resize_token_embeddings/output_embeddings regression, with 45276 adding Gemma4-specific detail. The rest of the verdicts appropriately avoid overclaiming duplicates across distinct model families or failure modes." + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft edge, issue:45276 \u2194 issue:45292, is well supported by the titles and the shared resize_token_embeddings/output_embeddings symptom. The rejected pairs are phrased cautiously and do not overstate evidence. No PR-pair mergeability concerns apply here." }, "evaluator_used": true, "retried": false, @@ -2205,7 +2283,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36032", "issue:39404", @@ -2259,8 +2337,8 @@ "soft_pairs": [ "issue:43854|issue:45216", "issue:43381|issue:44928", - "issue:45684|issue:45698", "issue:44479|issue:44877", + "issue:45684|issue:45698", "issue:45588|issue:45663", "issue:43646|issue:43708", "issue:43645|issue:44164", @@ -2276,32 +2354,32 @@ "issue:43611|issue:43645", "issue:43425|issue:43716", "issue:44530|issue:45084", - "issue:43906|issue:44530", "issue:39404|issue:44912", + "issue:43906|issue:44530", "issue:44265|issue:44898", "issue:44479|issue:44805", - "issue:43901|issue:44509", "issue:43994|issue:44079", "issue:43425|issue:44918", + "issue:43901|issue:44509", "issue:44589|issue:45084", "issue:43299|issue:43931", "issue:44164|issue:45759", "issue:36032|issue:43452" ], - "prepared_review_unit_hash": "22d601de719e104dac5564e55a56ad9acd71aaac6a84a0098ac2a6d7cc4f80a0", + "prepared_review_unit_hash": "e44fba1572dce3fbf5b76a47c515c65fcaf1232fff60a035d44c2b67aa14e082", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36816, + "serialized_chars": 36815, "estimated_input_tokens": 9204, "estimated_eval_tokens": 18664 }, @@ -2310,180 +2388,180 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most of the cluster is heterogeneous. The resize_token_embeddings pair is a solid duplicate, but the Qwen3-VL MoE/loading pair is only superficially similar and should not be merged as the same bug.", - "confidence": 0.8, - "canonical_issue_reason": "issue:45292 is the broadest, most reusable statement of the resize_token_embeddings bug; issue:45335 is the t5gemma-specific manifestation of the same missing propagation.", + "summary": "The cluster is mostly heterogeneous Transformers bug reports. Only one soft edge looks like a true duplicate pair: the `resize_token_embeddings` regression in 45292/45335, where the general bug and the T5Gemma-specific symptom match the same underlying API issue.", + "confidence": 0.86, + "canonical_issue_reason": "Issue 45292 is the broader, model-agnostic report: `resize_token_embeddings` does not update the affected embeddings. Issue 45335 appears to be the T5Gemma-specific manifestation of the same bug, so 45292 is the better canonical anchor.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45292 is the best representative issue in this set because it captures a concrete, generalizable bug pattern with a clear duplicate counterpart.", + "best_issue_reason": "45292 is the best representative issue because it describes the root regression in general terms, while 45335 is a narrower model-specific reproduction.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Both are model-loading regressions, but they involve different models and different failure modes." + "reason": "Different bugs: one is a model load/save corruption case, the other is a Qwen3.5 checkpoint save_pretrained regression." }, { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Unrelated bugs: gradient checkpointing in eval mode versus Qwen3.5 RLHF NaNs from position_ids/SDPA behavior." + "reason": "Different failure modes: gradient checkpointing in eval mode vs RLHF NaNs from Qwen3.5 position_ids/SDPA behavior." }, { - "left": "issue:45684", - "right": "issue:45698", + "left": "issue:44479", + "right": "issue:44877", "accept": false, - "reason": "Both touch save/load workflows, but one is about file permissions and the other about loading the wrong custom module." + "reason": "Both are loading regressions, but on different model/config paths (video-input Qwen VL vs granite_speech strict config)." }, { - "left": "issue:44479", - "right": "issue:44877", + "left": "issue:45684", + "right": "issue:45698", "accept": false, - "reason": "Different model families and different regressions; only broad loading/config similarity." + "reason": "Distinct issues: read-only permission propagation during save_pretrained vs loading the wrong custom module after save_pretrained." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "Different code paths: flash_attention sink handling versus Gemma4 FSDP2 shared_kv_states reconstruction." + "reason": "Different code paths: flash_attention crash on sink-less models vs Gemma4 FSDP2 shared_kv_states rebuild KeyError." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom model initialization in notebooks is unrelated to Trainer resume_from_checkpoint max_steps math." + "reason": "Custom model initialization vs Trainer resume_from_checkpoint max_steps calculation are unrelated regressions." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Both involve custom-model workflows, but notebook initialization and extra_state save/load handling are different bugs." + "reason": "Notebook custom-model init failure is not the same bug as extra_state not being handled by save/from_pretrained." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Different causes and symptoms: autocast dtype mismatch for Phi-tiny-MoE versus meta-device loading regressions." + "reason": "Different root causes: autocast dtype mismatch in Phi-tiny-MoE vs meta-device loading breakage in some models." }, { "left": "issue:45292", "right": "issue:45335", "accept": true, - "reason": "Same underlying resize_token_embeddings bug: 45335 is the t5gemma-specific instance of the output embedding not being updated." + "reason": "Same underlying API regression: `resize_token_embeddings` does not propagate to the relevant output/decoder embeddings; 45335 is the T5Gemma-specific reproduction." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch version compatibility and a model-specific autocast dtype mismatch are not the same bug." + "reason": "Torch version compatibility is a different problem from the Phi-tiny-MoE autocast dtype mismatch." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "The titles suggest related loading trouble, but there is not enough evidence that they share the same tokenizer/vocab mismatch." + "reason": "Both involve tokenizer/model loading, but the specific failures differ (vocab-size mismatch vs inability to load a particular model)." }, { "left": "issue:43257", "right": "issue:44863", "accept": false, - "reason": "Both are load failures, but for different model families and different loading pipelines." + "reason": "Separate model-loading bugs affecting different architectures and mechanisms." }, { "left": "issue:44589", "right": "issue:44756", "accept": false, - "reason": "A Float8 storage TypeError and an mmap OOM workaround are unrelated failure modes." + "reason": "Unrelated issues: missing Float8 storage object vs mmap-induced OOM on Strix Halo." }, { "left": "issue:39404", "right": "issue:45701", "accept": false, - "reason": "Whisper pipeline return_language regression is unrelated to a version-induced tokenization change in general." + "reason": "Whisper pipeline return_language regression is unrelated to a broad tokenization-change report." }, { "left": "issue:44683", "right": "issue:45823", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device-map forward mismatch are different problems." + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device_map mismatches are different failures." }, { "left": "issue:43425", "right": "issue:45823", "accept": false, - "reason": "Torch compatibility and Gemma4 PLE device mismatch are not the same underlying bug." + "reason": "Torch 2.10 incompatibility is not the same bug as Gemma4 PLE device placement mismatch." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "base_model_prefix loading failures and notebook-defined custom model initialization failures are different issues." + "reason": "Loading models with base_model_prefix is a different regression from Jupyter notebook custom-model initialization." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch compatibility is unrelated to Mistral-3 image preprocessor/model dtype mismatch." + "reason": "Torch compatibility problems are unrelated to the Mistral-3 image preprocessor dtype mismatch." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "PagedAttentionCache linear_attention crash is unrelated to the non-template-node compile error." + "reason": "Different failures: PagedAttentionCache linear_attention crash vs a template-node compilation TypeError." }, { - "left": "issue:43906", - "right": "issue:44530", + "left": "issue:39404", + "right": "issue:44912", "accept": false, - "reason": "No clear shared bug beyond broad runtime-regression similarity." + "reason": "Whisper pipeline behavior and MXFP4 quantization fallback are unrelated." }, { - "left": "issue:39404", - "right": "issue:44912", + "left": "issue:43906", + "right": "issue:44530", "accept": false, - "reason": "Whisper pipeline language return and MXFP4 quantization fallback are different issues." + "reason": "No clear evidence they are the same underlying bug; the titles point to different reproduction contexts and failure modes." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "torch.export failures with torch_compilable_check are not the same as Perceiver interpolation failures." + "reason": "torch.export/torch_compilable_check and Perceiver interpolation are different code paths." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Video-input regression in Qwen VL models is unrelated to the mask/tensor shape IndexError." - }, - { - "left": "issue:43901", - "right": "issue:44509", - "accept": false, - "reason": "Both are docs issues, but they refer to different deprecations and should not be merged." + "reason": "Video-input regression in Qwen VL models is unrelated to the mask-shape IndexError." }, { "left": "issue:43994", "right": "issue:44079", "accept": false, - "reason": "A bad model output regression and ModelOutput key assignment behavior are distinct bugs." + "reason": "SigLIP2 inference quality issue is not the same as ModelOutput key assignment behavior." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch 2.10 incompatibility is unrelated to Qwen3.5 input-embedding unpacking in TRL SFT." + "reason": "Torch compatibility is unrelated to the Qwen3.5 embedding unpacking issue in TRL SFTTrainer." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but they cover different removed/changed pipeline behaviors and are not the same issue." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "Different failures: missing Float8 storage object versus compile-time rejection of non-template nodes." + "reason": "Missing Float8 storage object and non-template-node compilation are unrelated." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "This is only supported by shared Qwen3-VL/model-family/title similarity; the packet does not show enough evidence of the same concrete bug or code path." + "reason": "Both mention Qwen3-VL loading, but the concrete failures differ too much to merge confidently." }, { "left": "issue:44164", @@ -2495,16 +2573,16 @@ "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "T5 tokenizer add_special_tokens conflict and gguf_file breaking from_pretrained are unrelated loading failures." + "reason": "T5 tokenizer add_special_tokens conflict is unrelated to gguf_file breaking from_pretrained for tokenizer/model loading." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is mostly grounded, but one soft-edge verdict is too strong for the packet: issue:43299 vs issue:43931 is only supported by shared model family/title similarity, not clear evidence of the same underlying bug. Calling it the same loading problem overstates what the packet shows. The resize_token_embeddings pair (45292/45335) looks conservative and well-supported, but the Qwen3-VL pair should be treated as merely plausible, not accepted as a duplicate." + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The only accepted duplicate pair, 45292/45335, is a reasonable merge candidate from the titles alone: both report `resize_token_embeddings` failing to update downstream embeddings, with 45335 being the T5Gemma-specific manifestation. The remaining pairwise rejections do not overclaim sameness and are phrased cautiously enough for the available evidence." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -2520,7 +2598,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:32090", "issue:34567", @@ -2578,8 +2656,8 @@ "issue:44991|issue:45081", "issue:43856|issue:44756", "issue:44164|issue:44479", - "issue:32090|issue:39404", "issue:44737|issue:45859", + "issue:32090|issue:39404", "issue:43582|issue:43632", "issue:44661|issue:44683", "issue:44488|issue:45081", @@ -2605,236 +2683,233 @@ "issue:44849|issue:45325", "issue:44987|issue:44991" ], - "prepared_review_unit_hash": "0e3e6332b3dbb2637b15432ab57bc959f1c045393a6a94dfefd340eeff2cc456", + "prepared_review_unit_hash": "eb9d4803d52350f448dd896917dd93483ffc3f05dca020db179711655aea898c", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37234, - "estimated_input_tokens": 9309, - "estimated_eval_tokens": 18874 + "serialized_chars": 37231, + "estimated_input_tokens": 9308, + "estimated_eval_tokens": 18872 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of loosely related Transformers v5 regression reports. I only see one clear duplicate pair: the audio feature-extraction/fbank crash. The rest are thematically similar at best, but not the same concrete bug.", - "confidence": 0.67, - "canonical_issue_reason": "issue:44206 is the better umbrella report for the fbank/feature-extraction crash; issue:44220 looks like the same code path expressed through the helper-level failure.", + "summary": "The cluster is mostly heterogeneous; the soft matches are high-similarity false positives across different models, tokenizers, and regression types. I did not find any pair that looks like the same concrete bug/change.", + "confidence": 0.81, + "canonical_issue_reason": "Issue 43646 is the broadest v5 regression among the set and best represents the cluster\u2019s general model-initialization breakage theme, though it is not a true duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44206 is the most representative and concrete issue in the only clear duplicate pair, with the broadest description of the underlying audio regression.", + "best_issue_reason": "Issue 43646 is the most general and central issue, with the widest scope among the candidates.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "Different failures: deepspeed/zero3 index error in BertModel vs a torch 2.9 flex_attention compile regression." + "reason": "Different failures in different subsystems: deepspeed/BertModel broadcast vs compiled flex_attention on newer torch." }, { "left": "issue:44671", "right": "issue:44991", "accept": false, - "reason": "Both are loading-related, but one is a CamemBERT prediction regression and the other is a tokenizer loading failure for a different model." + "reason": "Both are v5-era loading regressions, but one is CamemBERT masked-LM output quality and the other is tokenizer loading for a different model." }, { "left": "issue:39404", "right": "issue:44671", "accept": false, - "reason": "Whisper pipeline return_language regression vs CamemBERT masked-LM output bug; unrelated code paths." + "reason": "Whisper pipeline language return bug is unrelated to CamemBERT masked-LM prediction regression." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Both touch tokenizer loading, but the models and failure modes differ; no evidence of the same underlying bug." + "reason": "Both involve tokenizer loading, but they hit different models and distinct code paths (_patch_mistral_regex vs generic tokenizer load failure)." }, { "left": "issue:43856", "right": "issue:44756", "accept": false, - "reason": "Qwen3 MoE training memory usage vs Strix Halo mmap OOM; same general theme, different causes." + "reason": "Both mention memory/OOM, but one is Qwen3 MoE training memory usage and the other is mmap behavior on Strix Halo." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "Model save/load extra_state handling vs a video-input regression; not the same bug." + "reason": "Save/from_pretrained extra_state handling and Qwen VL video-input regression are separate bugs." }, { - "left": "issue:32090", - "right": "issue:39404", + "left": "issue:44737", + "right": "issue:45859", "accept": false, - "reason": "Trainer GPU broadcast NoneType error and Whisper return_language pipeline failure are unrelated." + "reason": "Both are device-placement issues, but they affect different models and code paths (XLNet relative positions vs Qwen3.5 MoE rotary embedding)." }, { - "left": "issue:44737", - "right": "issue:45859", + "left": "issue:32090", + "right": "issue:39404", "accept": false, - "reason": "Both involve device placement, but they affect different models and different forward paths." + "reason": "Trainer gpu_broadcast NoneType crash is unrelated to Whisper return_language behavior." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError vs _is_hf_initialized flag regression; no shared concrete bug." + "reason": "AppleSilicon allocator TypeError and _is_hf_initialized regression are unrelated." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "Tokenizer mapping/model-addition logic vs compiled flex_attention tracing; unrelated." + "reason": "Tokenizer mapping lookup failure and torch >=2.9 flex_attention compilation failure are unrelated." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Both are tokenizer-loading complaints, but about different models and different breakages." + "reason": "Both are tokenizer-loading reports, but they concern different models and different breakages." }, { "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Two different model-loading failures; only a broad transformer-version theme is shared." + "reason": "Both are loading regressions, but one is a specific model load failure and the other is a different model's tokenizer load failure." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer initialization." + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer junk are distinct initialization bugs." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "Perplexity regression and tokenizer post-processor update bug are different issues." + "reason": "High perplexity on gpt-oss and runtime special-token post-processor updates are unrelated." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Image preprocessor dtype mismatch vs template compilation TypeError; unrelated." + "reason": "Image preprocessor dtype mismatch and template-node compilation error are unrelated." }, { "left": "issue:44206", "right": "issue:44220", - "accept": true, - "reason": "Same audio feature-extraction path: one reports the unsupported center arg crash, the other reports the downstream _torch_extract_fbank_features failure." + "accept": false, + "reason": "Both touch audio features, but the reported crashes and APIs differ; not the same concrete bug." }, { "left": "issue:36032", "right": "issue:42915", "accept": false, - "reason": "T5 tokenizer add_special_tokens conflict vs Qwen3Moe FineGrainedFP8Config failure; unrelated." + "reason": "T5 tokenizer add_special_tokens conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." }, { "left": "issue:43883", "right": "issue:44488", "accept": false, - "reason": "Missing all_tied_weights_keys on Molmo vs a model-loading regression for a different repository." + "reason": "Molmo tied-weights metadata error is unrelated to loading cjvt/sleng-bert." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "AutoConfig trust_remote_code field loss vs Qwen3.5 cache group-type crash; different code paths." + "reason": "AutoConfig trust_remote_code field loss is unrelated to Qwen3.5 PagedAttentionCache group-type crash." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "TrainerState token counter not updating vs Qwen2.5-VL iterable-dataset multi-image finetuning failure." + "reason": "TrainerState token-count tracking and Qwen2.5-VL multi-image IterableDataset failure are unrelated." }, { "left": "issue:42175", "right": "issue:46178", "accept": false, - "reason": "Both are backend-installation complaints, but tensorflow missing from torch extras and tensorflow_text backend mapping are distinct issues." + "reason": "Both involve backend handling, but one is install extras coverage and the other is a missing BACKENDS_MAPPING entry for tensorflow_text." }, { "left": "issue:44811", "right": "issue:45584", "accept": false, - "reason": "Both involve Whisper special-token behavior, but one is batch_decode skipping tokens and the other is empty-transcription generation after alignment." + "reason": "Both are Whisper-related, but batch_decode skip_special_tokens handling and empty-transcription generation after align_special_tokens are different bugs." }, { "left": "issue:43541", "right": "issue:45084", "accept": false, - "reason": "Torch dynamo grouped_mm tracing error vs template-node compilation error; not the same bug." + "reason": "Mixtral grouped_mm tracing failure and template-node compilation failure are unrelated." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Different model-loading failures; no concrete shared code-path shown." + "reason": "Different model-loading failures for different artifacts; not the same underlying bug." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "Qwen3Moe FP8 config failure vs Qwen3.5 PagedAttentionCache group-type crash; related model family, different bugs." + "reason": "Qwen3Moe FP8 config failure and Qwen3.5 linear_attention group-type crash are distinct model/runtime issues." }, { "left": "issue:43644", "right": "issue:43646", "accept": false, - "reason": "Both are v5 regressions, but one concerns buffer filling and the other custom model initialization." + "reason": "Both are v5 initialization regressions, but one is non-persistent buffers and the other is custom model initialization; separate concrete bugs." }, { "left": "issue:44464", "right": "issue:45987", "accept": false, - "reason": "Compiled chunked generation inconsistency vs StaticCache return-type contract bug; different failures." + "reason": "Chunked generation with compiled forward and StaticCache sequence-length return type are unrelated." }, { "left": "issue:43452", "right": "issue:43482", "accept": false, - "reason": "Likely both concern GGUF loading, but the titles do not show the same concrete bug/change with enough confidence." + "reason": "gguf_file path breakage and Qwen2.5-GGUF loading failure are related to GGUF loading broadly, but not the same concrete failure." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Tokenizer special-token conflict vs Jupyter custom-model initialization breakage; unrelated." + "reason": "Tokenizer method-name conflict and Jupyter custom-model initialization regression are unrelated." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "GPU+CPU offload dequantized-model load failure vs Qwen2.5-GGUF loading failure; not enough evidence of one bug." + "reason": "Dequantized-model device_map offload failure and Qwen2.5-GGUF loading failure are different loading paths." }, { "left": "issue:44849", "right": "issue:45325", "accept": false, - "reason": "Qwen3.5 hidden-states bug vs Qwen2.5-VL rope-index scaling bug; different symptoms and code paths." + "reason": "Different Qwen model families and different bugs: hidden-states output vs rope index scaling." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Both are loading regressions on different models, but the titles do not establish a shared underlying fixable bug." + "reason": "Both are transformers>=5 loading regressions, but they affect different models and failure modes." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays mostly conservative. The one accepted soft pair, issue:44206 vs issue:44220, is a reasonable duplicate call based on the shared audio/fbank feature-extraction path, and the other soft-edge rejections are cautious and supported by the titles." - }, - "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 }, @@ -2849,7 +2924,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36032", "issue:40444", @@ -2917,12 +2992,12 @@ "issue:44987|issue:45081", "issue:44220|issue:44683", "issue:42915|issue:44291", - "issue:45216|issue:45357", "issue:43632|issue:44756", + "issue:45216|issue:45357", "issue:36032|issue:43742", "issue:44062|issue:44987", - "issue:44479|issue:45325", "issue:42915|issue:44589", + "issue:44479|issue:45325", "issue:43296|issue:43531", "issue:43404|issue:45127", "issue:43531|issue:44877", @@ -2933,226 +3008,226 @@ "issue:43632|issue:44534", "issue:41553|issue:43582" ], - "prepared_review_unit_hash": "20442020b040489ed9cf611af12c6355644f6b57212beab2de63cbbb7d3627e2", + "prepared_review_unit_hash": "19c3dc1c7459266af054a56bea1389f7f7e801d8f86169a4d197eeefd109a3b9", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 36679, - "estimated_input_tokens": 9170, - "estimated_eval_tokens": 18596 + "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": "The cluster is broadly about Transformers v5-era regressions, but the individual issues span many unrelated subsystems and model families. I found no PRs, and none of the soft edges look like safe duplicates under a strict standard.", - "confidence": 0.44, - "canonical_issue_reason": "issue:43611 is the broadest, most representative loading-regression report in the set; it best fits the cluster\u2019s loose \"Transformers v5 breaks model loading\" theme, even though the cluster is heterogeneous.", + "summary": "The cluster is a loose collection of mostly unrelated Transformers bug reports, with a strong but not exact concentration around v5 model-loading/serialization regressions. None of the soft pairs look like the same concrete bug, so I rejected all of them.", + "confidence": 0.57, + "canonical_issue_reason": "Issue 43611 is the broadest, most central representative of the repeated v5 loading/initialization regressions in this set, even though the cluster overall is heterogeneous.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 is the most suitable umbrella issue among these because it is concrete, widely scoped, and closest to the recurring v5 loading failures represented here.", + "best_issue_reason": "Issue 43611 is the best issue anchor because it describes a general v5 compatibility break rather than a single model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45084", "right": "issue:45507", "accept": false, - "reason": "Different problems: template-node compilation vs an invalid method call in GraniteMoEHybrid." + "reason": "Different failures: a template compilation error versus an invalid method call in GraniteMoEHybrid. Same framework area, not the same bug." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "Unrelated failures: missing all_tied_weights_keys on Molmo vs tokenizer loading for EMBEDDIA/est-roberta." + "reason": "Both are model-loading issues, but one is a missing attribute on Molmo and the other is a tokenizer loading failure for a specific model. No concrete shared code path." }, { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Different domains and bugs: audio chat-template sampling rate vs MIMI encoder padding-mask mismatch." + "reason": "Audio chat-template sampling-rate default and MIMI batched-vs-single output mismatch are unrelated defects." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Custom model init in notebooks is not the same as non-persistent buffers being filled with junk." + "reason": "Notebook custom model initialization breakage and non-persistent buffer corruption are different v5 regressions." }, { "left": "issue:43089", "right": "issue:45987", "accept": false, - "reason": "Generation performance overhead and StaticCache return-type contract are distinct issues." + "reason": "Generation performance overhead and a cache API type-contract bug are unrelated." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Both are v5 regressions, but they concern different code paths: custom model init vs buffer serialization/init behavior." + "reason": "Custom model initialization failure versus non-persistent buffer junk values; not the same underlying bug." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Both mention tied weights, but one is missing weight tying in model init while the other is save_pretrained serialization behavior." + "reason": "Both involve tied weights/serialization, but one is a missing tie in Mistral3 conditional generation and the other is inconsistent lm_head serialization by device. Similar theme, different defect." }, { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Different model families and failure modes: Llava Next segfault vs Qwen3OmniMoe video-processing ValueError." + "reason": "Segfault on Llava Next loading and a Qwen3OmniMoe video-processing ValueError are distinct multimodal issues." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Generic loading noise is unrelated to a Mistral regex patch crash." + "reason": "Noise while loading transformers and a Mistral regex patch crash are not the same failure mode." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "Different models and symptoms: Siglip2 bad outputs vs OmDet-Turbo processor size mismatch." + "reason": "Different model families and different symptoms: bad AutoModel/pipeline outputs for SigLIP2 versus incorrect processor image size for OmDet-Turbo." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "FineGrainedFP8 model failure is unrelated to a template-node compilation TypeError." + "reason": "FP8 config failure for Qwen3Moe and template-node compilation error are unrelated." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "Both are encoder/model bugs, but the concrete failures differ: padding-mask batching vs DAC latent reconstruction." + "reason": "MIMI padding-mask batching mismatch and DAC STE mismatch are different audio-model bugs." }, { "left": "issue:44265", "right": "issue:44610", "accept": false, - "reason": "torch.export failure with torch_compilable_check is unrelated to OmDet processor input resolution." + "reason": "torch.export with torch_compilable_check and OmDet-Turbo image-size mismatch are unrelated." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "Model load failure for ScandiBERT and Mistral tokenizer regex crash are different issues." + "reason": "ScandiBERT loading failure and Mistral regex patch crash are different tokenizer/model-loading issues." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "Loading physical-intelligence/fast on v5.1.0 is a different regression from the Mistral tokenizer patch crash." + "reason": "Physical-Intelligence/fast loading regression and Mistral regex patch crash are not the same code-path problem." }, { "left": "issue:44220", "right": "issue:44683", "accept": false, - "reason": "Audio feature extraction and compiled flex_attention on torch>=2.9 are separate code paths." + "reason": "_torch_extract_fbank_features() and compiled flex_attention on torch>=2.9 concern different subsystems." }, { "left": "issue:42915", "right": "issue:44291", "accept": false, - "reason": "FP8 config failure and init_empty_weights/_is_hf_initialized argument handling are different bugs." + "reason": "Qwen3Moe FP8 failure and init_empty_weights/_is_hf_initialized argument mismatch are different initialization bugs." }, { - "left": "issue:45216", - "right": "issue:45357", + "left": "issue:43632", + "right": "issue:44756", "accept": false, - "reason": "Related theme, but not clearly the same bug: general Qwen3.5 checkpoint corruption vs visual-encoder key serialization specifically." + "reason": "_is_hf_initialized breakage and mmap OOM avoidance on Strix Halo are unrelated." }, { - "left": "issue:43632", - "right": "issue:44756", + "left": "issue:45216", + "right": "issue:45357", "accept": false, - "reason": "_is_hf_initialized breakage and mmap OOM on Strix Halo are unrelated." + "reason": "Both are Qwen3.5 save_pretrained regressions, but one is generic checkpoint correctness and the other is specifically incorrect visual encoder keys. Similar area, not clearly one bug." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "Tokenizer method conflict in T5 and a key error loading MobileLLM are not the same underlying issue." + "reason": "Tokenizer method-name conflict and MobileLLM key error are different loading failures." }, { "left": "issue:44062", "right": "issue:44987", "accept": false, - "reason": "AddedToken special-argument conflict and a model-loading regression for physical-intelligence/fast are distinct." + "reason": "AddedToken special-flag duplication and physical-intelligence/fast loading failure are unrelated tokenizer/model issues." }, { - "left": "issue:44479", - "right": "issue:45325", + "left": "issue:42915", + "right": "issue:44589", "accept": false, - "reason": "Both involve Qwen vision models, but one is a video-input regression and the other is still-image temporal position scaling." + "reason": "FP8 config failure and missing Float8 storage type are different Torch/version compatibility problems." }, { - "left": "issue:42915", - "right": "issue:44589", + "left": "issue:44479", + "right": "issue:45325", "accept": false, - "reason": "Both touch FP8-ish areas, but one is a config/load failure and the other is a missing Float8 storage type." + "reason": "Video-input regression across several Qwen models and still-image rope-index scaling in Qwen2.5-VL are different multimodal bugs." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "PaddleOCR-VL loading and Qwen3-MoE sliding_window behavior are unrelated." + "reason": "PaddleOCR-VL loading failure in vLLM and Qwen3-MoE sliding_window behavior are unrelated." }, { "left": "issue:43404", "right": "issue:45127", "accept": false, - "reason": "Both involve tied weights, but one is a model class not tying lm_head while the other is LoRA merge collapse with extended vocabulary." + "reason": "Both touch tied embeddings, but one is missing lm_head tying and the other is LoRA merge collapse with extended vocabulary. Not the same concrete bug." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Qwen3-MoE sliding_window bug and granite_speech strict-config loading failure are unrelated." + "reason": "Qwen3-MoE sliding_window and granite_speech strict-config loading are unrelated." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer loading conflict in T5 and Qwen3 auto device-mapping CUDA assert are different failures." + "reason": "T5 tokenizer add_special_tokens conflict and Qwen3 auto device mapping cuda assert are unrelated." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "IterableDataset multi-image finetuning and Qwen2.5-VL rope-index scaling are different bugs." + "reason": "Multiple-images IterableDataset failure and Qwen2.5-VL temporal position scaling are different multimodal training/inference bugs." }, { "left": "issue:43611", "right": "issue:44534", "accept": false, - "reason": "Base_model_prefix loading regression and non-persistent buffer junk are separate v5 issues." + "reason": "Both are v5 regressions, but one is a base_model_prefix loading break and the other is junk-filled non-persistent buffers. Same release, different defect." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch version incompatibility and generic loading noise are not the same bug." + "reason": "Torch 2.10 incompatibility and noisy loading logs are unrelated." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "_is_hf_initialized handling and non-persistent buffer initialization are different code paths." + "reason": "_is_hf_initialized flag handling and non-persistent buffer corruption are different v5 breakages." }, { "left": "issue:41553", "right": "issue:43582", "accept": false, - "reason": "Bad AutoTokenizer error messaging for Voxtral is unrelated to the Apple Silicon caching_allocator_warmup TypeError." + "reason": "Bad AutoTokenizer error for Voxtral and AppleSilicon caching_allocator_warmup TypeError are unrelated." } ] }, @@ -3174,7 +3249,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:33666", "issue:35707", @@ -3227,10 +3302,10 @@ ], "soft_pairs": [ "issue:40990|issue:44811", - "issue:44079|issue:45663", "issue:43792|issue:44589", - "issue:33666|issue:40444", + "issue:44079|issue:45663", "issue:44683|issue:45020", + "issue:33666|issue:40444", "issue:44403|issue:44991", "issue:43421|issue:44568", "issue:43381|issue:45923", @@ -3245,232 +3320,238 @@ "issue:44079|issue:44534", "issue:43818|issue:45357", "issue:43531|issue:44291", - "issue:43377|issue:45491", "issue:41720|issue:45081", - "issue:40444|issue:45381", + "issue:43377|issue:45491", "issue:44265|issue:45072", + "issue:40444|issue:45381", "issue:43644|issue:44079", "issue:43749|issue:44079", "issue:42175|issue:43296", - "issue:45325|issue:45381", "issue:43632|issue:45072", + "issue:45325|issue:45381", "issue:43611|issue:43646", "issue:43792|issue:43957" ], - "prepared_review_unit_hash": "60f98f8f3e0f69d4a3c5c4b0ea97015f5970f78272763cf723dbd97719939ac1", + "prepared_review_unit_hash": "da05d36dd29e3de7b5e8e2e0561e8b33d3961116e68242e06bbbeffeefdbe930", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36902, - "estimated_input_tokens": 9226, - "estimated_eval_tokens": 18708 + "serialized_chars": 36899, + "estimated_input_tokens": 9225, + "estimated_eval_tokens": 18706 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous; most soft pairs are related by broad subsystem/topic only, not the same bug. Two pairs do look like genuine duplicates: the AutoTokenizer/tokenizer.json regression and the Qwen2.5-VL position-id regression. I\u2019d use the tokenizer-loading issue as the main representative.", - "confidence": 0.61, - "canonical_issue_reason": "issue:44462 is the broadest concrete bug here: AutoTokenizer ignoring tokenizer.json. It also cleanly subsumes the Granite-specific symptom in issue:45812, making it the best umbrella issue in this set.", + "summary": "This cluster is mostly a grab bag of distinct Transformers/v5 regressions and model-specific loading/training bugs, not a tight duplicate set. Only one soft pair looks like the same underlying Qwen2.5-VL position-id bug.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45020 is the broadest umbrella in the set ('Recent transformers versions break models using `remote_code`') and best represents the overall v5 regression theme across multiple model-loading failures.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44462 is the best representative because it is a clear, root-cause tokenizer-loading regression rather than a model-specific symptom, and it matches the strongest duplicate pair in the cluster.", + "best_issue_reason": "issue:45020 is the most suitable cluster representative because it is the broadest, most reusable description of the loading/regression class, even though many other items are more specific manifestations.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:40990", "right": "issue:44811", "accept": false, - "reason": "Different problems and code paths: perplexity evaluation vs Whisper batch_decode special-token handling." - }, - { - "left": "issue:44079", - "right": "issue:45663", - "accept": false, - "reason": "ModelOutput key assignment bug vs Gemma-4 FSDP shared_kv_states rebuild; unrelated." + "reason": "Different models and failures: perplexity on GPT-OSS vs Whisper batch_decode special-token handling." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "Whisper runtime failure and Float8 storage lookup error are different failures." + "reason": "Unrelated symptoms: Whisper runtime failure vs missing Float8 storage type." }, { - "left": "issue:33666", - "right": "issue:40444", + "left": "issue:44079", + "right": "issue:45663", "accept": false, - "reason": "Both are Qwen VL training issues, but the failures are different: multi-GPU training vs iterable dataset with multiple images." + "reason": "Different code paths: ModelOutput key assignment vs Gemma4 attention shared_kv_states rebuild." }, { "left": "issue:44683", "right": "issue:45020", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and remote_code model loading regressions are unrelated." + "reason": "Different layers: torch>=2.9 flex_attention compilation vs remote_code model loading regressions." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both are Qwen2-VL/Qwen2.5-VL related, but one is multi-GPU training and the other is iterable dataset handling with multiple images per prompt." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "Generic loading noise vs tokenizer loading failure; not the same underlying bug." + "reason": "One is generic loading noise, the other is a specific tokenizer loading regression for EMBEDDIA/est-roberta." }, { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Both involve tokenizer special tokens, but one is runtime post-processor refresh and the other is BOS/EOS insertion for a specific tokenizer." + "reason": "Both involve tokenizers, but one is runtime post-processor updates and the other is add_special_tokens/BOS-EOS behavior for a specific tokenizer." }, { "left": "issue:43381", "right": "issue:45923", "accept": false, - "reason": "Eval-mode gradient checkpointing misuse is not the same as a missing supports_gradient_checkpointing flag." + "reason": "Eval-mode gradient checkpointing error is not the same as a missing supports_gradient_checkpointing flag on a remote-code model." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen VL finetuning." + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen2.5-VL iterable-dataset multi-image finetuning." }, { "left": "issue:44462", "right": "issue:45812", - "accept": true, - "reason": "Both point to the same AutoTokenizer loading regression; Granite wrong token IDs plausibly come from ignoring tokenizer.json." + "accept": false, + "reason": "Both are AutoTokenizer regressions, but one is ignoring tokenizer.json while the other is wrong token IDs for Granite models; too different to merge confidently." }, { "left": "issue:44291", "right": "issue:44589", "accept": false, - "reason": "Unexpected _is_hf_initialized argument and missing Float8 storage object are different init/load failures." + "reason": "init_empty_weights/_is_hf_initialized argument breakage is separate from the Float8 storage lookup failure." }, { "left": "issue:43482", "right": "issue:45538", "accept": false, - "reason": "Qwen2.5-GGUF loading failure and CLIPTokenizer model_max_length are unrelated tokenizer/model-loading bugs." + "reason": "GGUF loading in Transformers v5 is unrelated to CLIPTokenizer max_length semantics." }, { "left": "issue:42175", "right": "issue:45542", "accept": false, - "reason": "Both touch TensorFlow packaging, but one is missing backend in the torch extra and the other is a tf-backend detection/runtime issue." + "reason": "Both mention TF/backend packaging, but one is missing TensorFlow in a torch extra and the other is a tensorboard-only undefined backend error." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "Flash-attention-3 training degeneration and single-label num_labels=1 zero-loss are different classification bugs." + "reason": "FlashAttention-3 training degeneration is not the same bug as single-label classification with num_labels=1 yielding zero loss." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "Device-map offload loading failure and Qwen3 MoE memory inefficiency are distinct issues." + "reason": "Device-map/offload loading failure is distinct from Qwen3 MoE memory inefficiency during training." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "Different model/config failures: GGUF loading vs missing pad_token_id on Llama4Config." + "reason": "Different model-loading regressions: GGUF/Transformers v5 vs Llama4Config missing pad_token_id." }, { "left": "issue:44079", "right": "issue:44534", "accept": false, - "reason": "ModelOutput key assignment and non-persistent buffer junk are separate core regressions." + "reason": "ModelOutput key bookkeeping is unrelated to non-persistent buffer initialization." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Video-LLaVA tower weights/temporal attention issue is unrelated to Qwen3.5 save_pretrained key regression." + "reason": "Video-LLaVA architecture/weights issue is separate from Qwen3.5 save_pretrained visual-encoder key regression." }, { "left": "issue:43531", "right": "issue:44291", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE and init_empty_weights argument handling are unrelated." - }, - { - "left": "issue:43377", - "right": "issue:45491", - "accept": false, - "reason": "Both concern batching/padding, but they are different model-specific bugs with different symptoms." + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to init_empty_weights argument handling." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "Qwen3 auto device-map assert and Mistral tokenizer regex patch crash are unrelated." + "reason": "Qwen3 auto device-map CUDA assert is unrelated to Mistral tokenizer regex patch crashing." }, { - "left": "issue:40444", - "right": "issue:45381", + "left": "issue:43377", + "right": "issue:45491", "accept": false, - "reason": "Both are Qwen2.5-VL, but one is a finetuning/dataset failure and the other is a video position-id bug." + "reason": "MIMI padding-mask mismatch and Gemma3 mixed-length NaNs are both batching issues but appear to be different mechanisms and models." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "torch.export/torch_compilable_check failure and bfloat16 dtype mismatch are unrelated." + "reason": "torch.export/compilable_check failure is not the same as bfloat16 dtype mismatches in inference." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal Qwen2.5-VL issues, but one is dataset finetuning with multiple images and the other is video position-id calculation." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Non-persistent buffer junk and ModelOutput key assignment are different bugs." + "reason": "Non-persistent buffer junk and ModelOutput key assignment are different object-state bugs." }, { "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP CPU RAM efficient loading regression is unrelated to ModelOutput key assignment." + "reason": "FSDP CPU RAM efficient loading regression is unrelated to ModelOutput field handling." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "TensorFlow extra/backend packaging and PaddleOCR-VL model loading are different issues." - }, - { - "left": "issue:45325", - "right": "issue:45381", - "accept": true, - "reason": "Both describe the same Qwen2.5-VL position-id calculation regression affecting image/video paths in the same area of code." + "reason": "Packaging/backend omission in a torch install extra is not the same as PaddleOCR-VL loading failure in vLLM." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "_is_hf_initialized regression and bfloat16 dtype mismatch are unrelated." + "reason": "_is_hf_initialized regression and bfloat16 dtype mismatch are different Transformers v5 issues." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": true, + "reason": "Same Qwen2.5-VL position-id/rope-index code path; one reports still-image temporal scaling, the other video input vision_position_ids being wrong." }, { "left": "issue:43611", "right": "issue:43646", "accept": false, - "reason": "Both are transformers v5 regressions, but base_model_prefix loading and custom model initialization are not clearly the same bug." + "reason": "Both are Transformers v5 init/load regressions, but one is base_model_prefix loading and the other is custom model initialization; not clearly the same bug." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Whisper can\u2019t run and torch.device('meta') loading regressions are different failures." + "reason": "Whisper model runtime failure is not the same as meta-device loading breakage affecting other models." + }, + { + "left": "issue:45020", + "right": "issue:45381", + "accept": false, + "reason": "Remote-code loading regressions and Qwen2.5-VL video position IDs are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet overall, and the two accepted soft pairs are reasonably conservative based on the issue titles and subsystem overlap. The representative/canonical choice of issue:44462 is also defensible for this cluster." + "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The cluster is indeed heterogeneous, and the lone accepted Qwen2.5-VL position-id pair is the only clearly mergeable one. The choice of issue:45020 as a broad umbrella is defensible given the repeated v5/remote-code loading regressions in the set." }, "evaluator_used": true, "retried": false, @@ -3489,7 +3570,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:34634", "issue:35707", @@ -3546,8 +3627,8 @@ "issue:43454|issue:44466", "issue:42915|issue:43482", "issue:43296|issue:45800", - "issue:43701|issue:45325", "issue:44479|issue:45823", + "issue:43701|issue:45325", "issue:44291|issue:44877", "issue:43881|issue:44488", "issue:43606|issue:44265", @@ -3566,202 +3647,220 @@ "issue:43454|issue:45072", "issue:43572|issue:45759", "issue:43257|issue:45923", - "issue:43317|issue:43873", "issue:43377|issue:44898", + "issue:43317|issue:43873", "issue:40990|issue:42947", "issue:43526|issue:43883", "issue:43322|issue:46050" ], - "prepared_review_unit_hash": "8fda98609b42870fc40d8e0a1655411c72060335a3e06f3031b451b7ffc18eed", + "prepared_review_unit_hash": "ad4a78dd2a4e8475ab64e94a47d8bd6eec8dace9b4f2f9a3a8c5551a308b5e99", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36832, - "estimated_input_tokens": 9208, - "estimated_eval_tokens": 18672 + "serialized_chars": 36827, + "estimated_input_tokens": 9207, + "estimated_eval_tokens": 18670 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a set of largely unrelated bug reports across different models and subsystems. The soft-similarity links are mostly superficial (e.g., both mention loading, offload, device maps, or tokenization) but do not point to the same concrete bug or mergeable change set.", - "confidence": 0.96, - "canonical_issue_reason": "No clear canonical issue: the items span different models, APIs, and failure modes, so picking one as the duplicate target would be misleading.", + "summary": "The cluster is mostly a set of semantically similar but non-duplicate bug reports spanning different models and code paths. The soft pairs share broad themes like loading, offloading, quantization, or tied weights, but they are not the same underlying bug/change, so none should be merged.", + "confidence": 0.95, + "canonical_issue_reason": "issue:43873 is the broadest umbrella candidate (offloading + quantization) among the items, but the cluster is too heterogeneous for a true canonical duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "No single best issue for deduplication; the cluster is heterogeneous, so none is a safe representative anchor.", + "best_issue_reason": "issue:43873 is the best cluster representative because it is the most general and central of the few offloading/quantization reports, though it still does not subsume the rest.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45325", "right": "issue:45834", "accept": false, - "reason": "Both are multimodal indexing bugs, but they affect different models and different code paths (Qwen2.5-VL RoPE temporal positions vs Kosmos2.5 OCR long-input indexing)." + "reason": "Different models and different failures: Qwen2.5-VL rope-index scaling vs Kosmos2.5 OCR length/index error." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "Different models and failures: SigLIP2 produces bad results via AutoModel/pipeline, while Perceiver fails on non-default image resolution and interpolation." + "reason": "Both are vision-related, but they describe different models and bugs: SigLIP2 inference mismatch vs Perceiver resolution/interpolation failure." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "Both involve tied lm_head weights, but one is a model/config tie failure and the other is a serialization inconsistency by device; not the same concrete bug." + "reason": "Both mention tied weights/lm_head, but one is an AyaVision model bug and the other is a v5 serialization inconsistency; not the same code-path problem." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Different models and loading paths: Qwen3Moe FP8 configuration failure vs Qwen2.5-GGUF loading failure under v5." + "reason": "Different quantization/loading issues on different model families (Qwen3Moe FP8 vs Qwen2.5-GGUF v5 load failure)." }, { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "Unrelated failures: PaddleOCR-VL loading in vLLM versus a torch/transformers version incompatibility." + "reason": "Unrelated compatibility reports: PaddleOCR-VL loading in vLLM vs a torch/transformers version incompatibility." }, { - "left": "issue:43701", - "right": "issue:45325", + "left": "issue:44479", + "right": "issue:45823", "accept": false, - "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL RoPE/position-id scaling." + "reason": "Both involve multimodal/device behavior, but one is a video-input regression and the other is a Gemma4 PLE device mismatch." }, { - "left": "issue:44479", - "right": "issue:45823", + "left": "issue:43701", + "right": "issue:45325", "accept": false, - "reason": "Different regressions in different models: video-input handling for Qwen VL variants versus Gemma4 PLE device mismatch during forward." + "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL rope-index scaling." }, { "left": "issue:44291", "right": "issue:44877", "accept": false, - "reason": "Different problems: init_empty_weights argument handling versus strict config rejection for granite_speech." + "reason": "Both are loading/config issues, but one is an init_empty_weights API break and the other is strict config validation for granite_speech." }, { "left": "issue:43881", "right": "issue:44488", "accept": false, - "reason": "Both are load failures, but for unrelated models and likely unrelated causes." + "reason": "Different models and symptoms: glm-4v-9b load failure vs cjvt/sleng-bert load failure." }, { "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "CPU offload device mismatch for Bark is unrelated to torch.export failure on torch_compilable_check models." + "reason": "CPU offload device mismatch in Bark is unrelated to torch.export failures in torch_compilable_check models." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Offloading/quantization behavior is unrelated to tokenization changes." + "reason": "Offloading/quantization behavior is unrelated to a tokenizer-version regression." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting has no meaningful overlap with PEFT checkpoint loading." + "reason": "Audio chat-template sampling-rate defaulting is unrelated to GraniteSpeech PEFT checkpoint loading." }, { "left": "issue:40990", "right": "issue:45584", "accept": false, - "reason": "Different domains: perplexity on a language model versus Whisper generation failing on empty transcription." + "reason": "Different tasks and bugs: perplexity on gpt-oss-20b vs Whisper empty-transcription generation failure." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "Bark voice preset bug and progressive generation with inputs_embeds/past_key_values are separate issues." + "reason": "Bark voice_preset and progressive generation with inputs_embeds/past_key_values are different code paths." }, { "left": "issue:44568", "right": "issue:45920", "accept": false, - "reason": "Both are tokenizer regressions, but they describe different symptoms and model families; no shared concrete bug is evident." + "reason": "A specific BOS/EOS tokenizer bug is not the same as the broader AutoTokenizer wrong-IDs regression." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Progressive generation with inputs_embeds is unrelated to Qwen3 device-map CUDA assertion." + "reason": "Progressive generation failure is unrelated to Qwen3 auto device mapping cudaErrorAssert." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "Tokenizer NER/padding crashes and torch.export torch_compilable_check failures are separate code paths." + "reason": "Tokenizer crashes on NER/padding are unrelated to torch.export failures with torch_compilable_check." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "Both are audio-model-related, but one is offload device mismatch and the other is DAC from_latents vs forward mismatch due to missing STE." + "reason": "Both are model-specific runtime bugs, but Bark CPU offload mismatch and DAC.from_latents STE mismatch are different problems." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Both mention device mapping, but the models and failure mechanisms differ (CUDA assert on Qwen3 vs Gemma4 PLE forward mismatch)." + "reason": "Both involve device_map auto, but the model families and failure modes differ (cudaErrorAssert vs forward device mismatch)." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "Tied-weight lm_head behavior and Bamba torch.compile SDPA failure are unrelated." + "reason": "AyaVision tied-weights issue is unrelated to Bamba torch.compile/SDPA failure." }, { "left": "issue:39692", "right": "issue:40444", "accept": false, - "reason": "Different multimodal workflows and different bugs: SigLIP2 docs/model mismatch versus Qwen2.5-VL IterableDataset multi-image finetuning failure." + "reason": "Documentation/example errors for SigLIP2 are unrelated to Qwen2.5-VL multi-image finetuning failure." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "MIMI padding-mask batching bug and OmDet-Turbo processor/model input-size mismatch are unrelated." + "reason": "MIMI padding-mask batch mismatch is unrelated to OmDet-Turbo image-size mismatch." }, { "left": "issue:43454", "right": "issue:45072", "accept": false, - "reason": "Different issues around model behavior: tied lm_head weights versus dtype mismatches in bfloat16 inference." + "reason": "Different subsystems: tied lm_head weights vs dtype mismatch in bfloat16 inference." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "A missing pad_token_idx in StableLmConfig is unrelated to AutoModelForCausalLM.from_config not unwrapping text_config." + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to composite Qwen config unwrapping." }, { "left": "issue:43257", "right": "issue:45923", "accept": false, - "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed is unrelated to a missing supports_gradient_checkpointing flag." + "reason": "Qwen3 MoE weight conversion under accelerate/deepspeed is unrelated to a missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "MIMI encoder padding-mask issue is unrelated to Perceiver non-default-resolution interpolation behavior." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "Both involve offload/quantization, but one is loading dequantized models with device_map=auto and the other is a broader offloading expectation issue; not clearly the same bug." + "reason": "Both mention offload/quantization, but one is dequantized-model loading on gpu+cpu offload and the other is a broader offloading regression." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity on a benchmark is unrelated to gradient checkpointing not taking effect with PEFT LoRA." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction is unrelated to Molmo missing all_tied_weights_keys." }, { "left": "issue:43322", "right": "issue:46050", "accept": false, - "reason": "Segmentation fault on Llava Next loading is unrelated to sinq quantized model save/load breakage." + "reason": "Llava Next loading segfault and sinq save/load quantization breakage are distinct failure modes." } ] }, @@ -3783,7 +3882,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36010", "issue:36331", @@ -3852,8 +3951,8 @@ "issue:36331|issue:42915", "issue:43404|issue:45357", "issue:43450|issue:45701", - "issue:43873|issue:44756", "issue:43550|issue:43720", + "issue:43873|issue:44756", "issue:44423|issue:45406", "issue:41720|issue:42617", "issue:45632|issue:45684", @@ -3868,226 +3967,226 @@ "issue:36010|issue:42617", "issue:44671|issue:44743" ], - "prepared_review_unit_hash": "b24425072f9083352865720ca9fa6c385311f89b6f8928a95f8b03e9c9687baa", + "prepared_review_unit_hash": "d6844e82e0aa3a14bfac0af6512ac07876fde015f299440df4e1d88bb226d1ac", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 37126, - "estimated_input_tokens": 9282, - "estimated_eval_tokens": 18820 + "serialized_chars": 37121, + "estimated_input_tokens": 9281, + "estimated_eval_tokens": 18818 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: the items cover unrelated loading, processor, quantization, multimodal, and trainer regressions. There is no strong duplicate group; at best, a few pairs share a broad subsystem, but not the same concrete bug.", - "confidence": 0.27, - "canonical_issue_reason": "issue:43873 is the broadest and most central open report in the set, covering offloading/quantization behavior that loosely overlaps several memory/offload-related items, so it is the best anchor if a canonical issue must be chosen.", + "summary": "The cluster is mostly a set of unrelated Transformers issues with only superficial overlap around loading, offloading, and model-specific regressions. I did not find any soft pair that looks like the same underlying bug or change, so all soft edges are rejected.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43873 is the best cluster anchor: it is a broad, currently open infrastructure bug about offloading/quantization with strong discussion and inbound-reference signals, while most other items are narrower model-specific regressions or API breakages.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the most generally framed and still active issue among the candidates, making it the least arbitrary representative of the cluster.", + "best_issue_reason": "Issue 43873 is the most representative and actionable issue in this set because it captures a broad class of loading/offloading failures and has the strongest evidence of ongoing impact.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43881", "right": "issue:44991", "accept": false, - "reason": "Both are model-loading failures, but one is about a specific GLM vision model and the other about tokenizer loading for a different checkpoint; no shared code-path bug is evident." + "reason": "Both are loading failures, but one is a GLM model load problem and the other is a tokenizer loading regression for a specific repo; no sign of the same bug." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "Both mention weights during loading, but one is about tying lm_head weights and the other about unpacking packed BitNet weights; different mechanisms and fixes." + "reason": "Different code paths: tied lm_head weights in a multimodal model vs packed-weight unpacking during accelerate loading." }, { "left": "issue:41720", "right": "issue:43322", "accept": false, - "reason": "Both are inference/loading failures, but the reported symptoms and model paths differ (Qwen3 auto device mapping vs Llava Next segfault)." + "reason": "Both crash during model use/loading, but they involve different models and different failure modes (cuda assert vs segfault)." }, { "left": "issue:43296", "right": "issue:44877", "accept": false, - "reason": "These are both load failures, but one is a vLLM/transformers compatibility issue and the other is strict config validation; different root causes." + "reason": "One is a vLLM/PaddleOCR-VL loading failure, the other is strict config validation blocking granite_speech; these are unrelated." }, { "left": "issue:43749", "right": "issue:44534", "accept": false, - "reason": "Both touch memory/offload behavior, but one is an FSDP CPU RAM-efficient loading regression and the other is a v5 non-persistent buffer serialization problem." + "reason": "Both touch loading/serialization, but one is FSDP CPU RAM-efficient loading and the other is non-persistent buffer initialization; not the same bug." }, { "left": "issue:44466", "right": "issue:45357", "accept": false, - "reason": "Both involve saving/serialization regressions, but one is tied weights serialization and the other is incorrect visual encoder key saving; not the same bug." + "reason": "Both are save_pretrained regressions, but one is tied lm_head serialization varying by device and the other is incorrect visual encoder keys for Qwen3.5." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "Both involve Qwen3.5-family models, but one is a device-mapping crash and the other is a flash-attention generation regression." + "reason": "Auto device-map CUDA failure and flash-attention generation issues are different bugs in different execution paths." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "Unrelated failures: a 3d_parallel.py runtime problem versus a Qwen3Moe FineGrainedFP8Config issue." + "reason": "One is a script/runtime failure for 3d_parallel.py; the other is a model/config-specific FineGrainedFP8 failure." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "Tokenizer/tokenization behavior could affect perplexity, but the reports do not describe the same underlying defect or code path." + "reason": "Tokenizer/version-related reasoning is too broad here; one reports high perplexity on a model/dataset, the other a general tokenization change across versions." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "Both are memory-related, but one is int4 quantization causing extra reserved CUDA memory and the other is an apex RMSNorm memory leak." + "reason": "Both mention memory, but one is CUDA reserved-memory growth under int4 quantization and the other is an apex FusedRMSNorm leak in T5." }, { "left": "issue:44008", "right": "issue:45823", "accept": false, - "reason": "Both are Gemma-family model bugs, but one is a variable-name collision in forward and the other is a device-mapping mismatch in a different model." + "reason": "Different Gemma model families and different symptoms: variable name collision vs device-mapping mismatch." }, { "left": "issue:36331", "right": "issue:42617", "accept": false, - "reason": "A trainer API signature change is unrelated to the 3d_parallel.py failure." + "reason": "Trainer compute_loss signature breakage is unrelated to the 3d_parallel.py execution problem." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Different subsystems entirely: tokenizer padding/truncation versus bfloat16 dtype mismatches in model inference." + "reason": "Tokenizer crash on NER/batched padding is unrelated to bfloat16 dtype mismatches in inference." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "One is a dtype-loading bug in BLIP2, the other is a resume/max_steps calculation bug in Trainer; no shared code path." + "reason": "Blip2 dtype loading bug and Trainer max_steps resume calculation are separate concerns." }, { "left": "issue:44877", "right": "issue:44991", "accept": false, - "reason": "Both are loading regressions, but one is strict config handling and the other is tokenizer loading for a specific model; not the same defect." + "reason": "Strict config validation for granite_speech is not the same as tokenizer loading for EMBEDDIA/est-roberta." }, { "left": "issue:36331", "right": "issue:42915", "accept": false, - "reason": "Trainer loss-signature handling and FP8 model loading are unrelated." + "reason": "Trainer API incompatibility and FineGrainedFP8 model failure do not share the same underlying bug." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "Both concern multimodal model internals, but one is weight tying and the other is save_pretrained key serialization; different bugs." + "reason": "Weight-tying bug in Mistral3 and incorrect visual encoder keys in Qwen3.5 are different save/serialization defects." }, { "left": "issue:43450", "right": "issue:45701", "accept": false, - "reason": "Video processor batching shape issues are unrelated to the tokenization regression claim." + "reason": "Video processor shape handling and tokenization-version changes are unrelated issues." }, { - "left": "issue:43873", - "right": "issue:44756", + "left": "issue:43550", + "right": "issue:43720", "accept": false, - "reason": "Both are memory/offload themed, but one is quantization offloading and the other is mmap-related OOM avoidance; distinct root causes." + "reason": "torch.compile with SDPA on Bamba-9B-v2 is a different code path from packed-weight loading in BitNet." }, { - "left": "issue:43550", - "right": "issue:43720", + "left": "issue:43873", + "right": "issue:44756", "accept": false, - "reason": "One is a torch.compile/SDPA failure in Bamba, the other is an accelerate loading issue for BitNet packed weights." + "reason": "Both involve memory/offload concerns, but one is quantization/offloading correctness and the other is a Strix Halo mmap OOM workaround." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Both are serve-time multimodal failures, but the specific crashes differ and point to different processor/code-path issues." + "reason": "Both crash in serve/multimodal scenarios, but they fail in different processor paths with different missing attributes." }, { "left": "issue:45632", "right": "issue:45684", "accept": false, - "reason": "Cache-path collision and read-only permission propagation are unrelated save/load concerns." + "reason": "Cache-path collisions for local trust_remote_code models and read-only permission propagation during save_pretrained are unrelated filesystem issues." }, { "left": "issue:44479", "right": "issue:44918", "accept": false, - "reason": "Both mention Qwen3.5, but one is a video-input regression and the other is TRL SFT embedding unpacking; not the same bug." + "reason": "A video-input regression across Qwen VL models is not the same as TRL SFT embedding unpacking failure." }, { "left": "issue:43550", "right": "issue:43606", "accept": false, - "reason": "Different failures: torch.compile with SDPA versus CPU offload device mismatch." + "reason": "Different model families and distinct causes: compile/SDPA failure versus CPU-offload device mismatch." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "Both are image-size/preprocessing issues, but they involve different models and different expected-input mismatches." + "reason": "Both are image preprocessing/resolution bugs, but the affected models and mechanism differ enough that they do not look like one bug." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "Tokenizer padding/NER crashes and image processor resolution mismatch are different preprocessing bugs." + "reason": "Tokenizer crash on NER inputs and processor output-size mismatch are separate issues." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "FP8 model failure and dequantized-model offload failure are related only at a very high level; they are not the same code-path problem." + "reason": "FineGrainedFP8 model failure and dequantized model loading with cpu offload are not the same underlying defect." }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "A regression around processor.tokenizer/image handling is not the same as a general tokenization-change report." + "reason": "Processor/tokenizer regression in v4.57.5 is not the same as a broad tokenization-change report." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "Different components and symptoms: BEiT label reduction versus GLM model loading." + "reason": "Label-reduction logic in BeitImageProcessorFast is unrelated to a GLM model loading failure." }, { "left": "issue:41720", "right": "issue:45161", "accept": false, - "reason": "Tensor-parallel GPT-OSS MoE issues and Qwen3 auto device mapping failures are different model/runtime problems." + "reason": "Auto device-map CUDA assert and GPT-OSS MoE tensor-parallel failure are different distributed/inference problems." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "Importing GenerationMixin is unrelated to a 3d_parallel.py execution failure." + "reason": "ImportError for GenerationMixin is unrelated to the 3d_parallel.py runtime failure." }, { "left": "issue:44671", "right": "issue:44743", "accept": false, - "reason": "CamemBERT masked-LM prediction errors and Qwen3.5 recurrent-state cache resets are unrelated model-specific bugs." + "reason": "CamemBERT masked-LM prediction regression and Qwen3.5 recurrent-state reset with cache are different model-specific bugs." } ] }, @@ -4109,7 +4208,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:29159", "issue:30064", @@ -4172,18 +4271,18 @@ "issue:29159|issue:36032", "issue:43388|issue:45059", "issue:45406|issue:45464", - "issue:33357|issue:35707", "issue:30064|issue:34634", + "issue:33357|issue:35707", "issue:43606|issue:43720", "issue:43550|issue:43653", "issue:41720|issue:43746", "issue:43873|issue:45704", "issue:43421|issue:45701", - "issue:44492|issue:44509", "issue:43606|issue:43653", "issue:43531|issue:45759", "issue:34634|issue:41720", "issue:42490|issue:43329", + "issue:44492|issue:44509", "issue:34567|issue:35707", "issue:44514|issue:44545", "issue:44625|issue:45479", @@ -4191,14 +4290,14 @@ "issue:44898|issue:45072", "issue:44451|issue:44991" ], - "prepared_review_unit_hash": "02752ac3460fa627f400bc3317b32f9cf468b4c3d7e1138853795ac26a2485fe", + "prepared_review_unit_hash": "08eb5397ce4e9e7ffffae1b8ca8d68e1c74cb9d05ec3221f4611af875c1c0bd2", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, @@ -4213,192 +4312,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly heterogeneous; the only clear duplicate is the Qwen2_5_VLProcessor batched `padding=False` crash (44514/44545). All other soft pairs share a subsystem at most, but not the same concrete bug.", - "confidence": 0.77, - "canonical_issue_reason": "Issue 44514 is the cleaner anchor for the only true duplicate pair here: it matches 44545 exactly on the same `Qwen2_5_VLProcessor.apply_chat_template` batched `padding=False` crash.", + "summary": "Only one soft pair is a true duplicate: the two Qwen2_5_VLProcessor.apply_chat_template crashes are the same bug. All other pairs are related at a broad subsystem level but describe different failures, models, or code paths, so they should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": "issue:44514 is the best canonical issue: it is the earlier, more complete report for the exact same batched-input/padding=False crash, while issue:44545 is a near-verbatim duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "44514 is the most actionable and clearly duplicated issue in the set; it best represents the one confirmed bug cluster.", + "best_issue_reason": "issue:44514 is the strongest representative overall because it has the same concrete failure mode as issue:44545 and appears to be the primary report that the later issue duplicates.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45081", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer-related, but they describe different failures: Mistral regex patching crash vs Granite token ID regression." + "reason": "Both involve tokenizer regressions, but they are different bugs: Mistral regex patching vs Granite token ID corruption." }, { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Different model/config bugs: Qwen3-MoE sliding window handling vs StableLmConfig missing `pad_token_idx`." + "reason": "Different models and different config issues; one is sliding_window handling, the other is missing pad_token_idx after v5." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Both are config discrepancies, but for different fields and models (`Gemma3TextConfig` API vs GPTNeoX `rotary_pct` reload behavior)." + "reason": "Both are config-serialization discrepancies, but they affect different fields and model families." }, { "left": "issue:43540", "right": "issue:43782", "accept": false, - "reason": "Different code paths: Qwen3OmniMoe video input processing vs Qwen3VL `from_pretrained` weight-only loading." + "reason": "Different Qwen multimodal failures with different inputs and error modes; not the same underlying bug." }, { "left": "issue:42915", "right": "issue:43322", "accept": false, - "reason": "Different failures and model families: FineGrainedFP8Config issue vs Llava Next segmentation fault on load." + "reason": "Different loading/runtime failures in different architectures; one is FP8 config, the other is Llava Next segfault." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "Both hit tokenizers, but the bugs are different: NER/batched padding crash vs MLuke task-time AttributeError." + "reason": "Tokenizer crashes on different models and tasks; not one shared defect." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Runtime special-token post-processor sync bug is not the same as Granite tokenizer returning wrong token IDs." + "reason": "Both concern tokenizer behavior after special-token changes, but one is runtime post-processor refresh and the other is a Granite token-ID regression." }, { "left": "issue:36331", "right": "issue:41720", "accept": false, - "reason": "Trainer signature mismatch and Qwen3 device-mapping CUDA assert are unrelated." + "reason": "Unrelated failures: Trainer custom loss signature vs Qwen3 device-mapping cuda assert." }, { "left": "issue:29159", "right": "issue:36032", "accept": false, - "reason": "Both involve tokenizers, but one is slow/fast inconsistency and the other is a T5 special-token name conflict on load." + "reason": "Different tokenizer problems: slow/fast inconsistency versus T5 tokenizer load-time method conflict." }, { "left": "issue:43388", "right": "issue:45059", "accept": false, - "reason": "Metric-gathering label truncation is unrelated to SAM3 text/bounding-box processing." + "reason": "Different subsystems and symptoms; metric-gathering label trimming is not related to SAM3 PCS text/bbox behavior." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Different surfaces and failures: missing `_tokenizer` in `Gemma4Processor` vs Qwen3.5 streaming chat/completions failure." + "reason": "Different runtime paths and models: Gemma4Processor missing _tokenizer vs Qwen3.5 streaming chat/completions failure." }, { - "left": "issue:33357", - "right": "issue:35707", + "left": "issue:30064", + "right": "issue:34634", "accept": false, - "reason": "A MacOS CLIP bus error is not the same bug as progressive generation with `inputs_embeds`/`past_key_values`." + "reason": "Different processor bugs affecting different modalities; segmentation-map handling is unrelated to Bark voice_preset." }, { - "left": "issue:30064", - "right": "issue:34634", + "left": "issue:33357", + "right": "issue:35707", "accept": false, - "reason": "Image processor segmentation-map handling and Bark voice_preset behavior are unrelated." + "reason": "Completely different issues: MacOS bus error on CLIP vs generation with inputs_embeds/past_key_values." }, { "left": "issue:43606", "right": "issue:43720", "accept": false, - "reason": "Both touch loading/offload paths, but one is CPU-offload device mismatch and the other is BitNet packed-weight unpacking." + "reason": "Both are CI/offload-related, but one is a CPU-offload device mismatch and the other is packed-weight unpacking in accelerate loading." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "Different model/paths: torch.compile + SDPA failure vs tokenizer special-token registration bug." + "reason": "Different bugs in different areas: torch.compile/SDPA vs tokenizer special-token registration." }, { "left": "issue:41720", "right": "issue:43746", "accept": false, - "reason": "CUDA assert during auto device mapping is unrelated to GraniteSpeech PEFT local-checkpoint loading." + "reason": "Different loading problems: auto device mapping crash vs PEFT adapter local-checkpoint loading." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Quantized offloading behavior and T5 Apex RMSNorm memory leak are separate issues." + "reason": "Different features and failure modes: quantization offloading vs T5/apex RMSNorm memory leak." }, { "left": "issue:43421", "right": "issue:45701", "accept": false, - "reason": "Special-token post-processor refresh is not the same as a general tokenization regression across versions." - }, - { - "left": "issue:44492", - "right": "issue:44509", - "accept": false, - "reason": "A cache-strategy typo and stale docs about removed pipeline tasks are unrelated." + "reason": "One is a specific TokenizersBackend post-processor update bug; the other is a broader tokenization-version-change report." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "Same project area, but different concrete bugs: CPU-offload mismatch vs BigBird tokenizer mask token registration." + "reason": "Different bug classes: offload device mismatch vs tokenizer special-token decode behavior." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "Both involve Qwen3.5/Qwen3-MoE config handling, but one is sliding-window behavior and the other is `from_config` text_config unwrapping." + "reason": "Different model/config issues; sliding_window in Qwen3-MoE is unrelated to AutoModelForCausalLM unwrapping text_config in Qwen 3.5/3.6." }, { "left": "issue:34634", "right": "issue:41720", "accept": false, - "reason": "BarkProcessor voice preset and Qwen3 auto device mapping are unrelated." + "reason": "Different symptom and subsystem: BarkProcessor voice_preset vs Qwen3 auto device mapping crash." }, { "left": "issue:42490", "right": "issue:43329", "accept": false, - "reason": "Import-path slash warning is unrelated to undefined video-token helper variables in multimodal processors." + "reason": "Both involve loading-related behavior, but one is path parsing/import warning and the other is a multimodal token-counting bug." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "Unrelated docs/typo issues: cache strategy typo vs pipeline docs mentioning removed tasks." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "Trainer token-count tracking and progressive generation are different bugs." + "reason": "TrainerState token-count tracking is unrelated to progressive generation with inputs_embeds and past_key_values." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Same exact bug report and same crash condition: `Qwen2_5_VLProcessor.apply_chat_template` on batched input with `padding=False`." + "reason": "Same exact crash report: Qwen2_5_VLProcessor.apply_chat_template fails on batched input when padding=False; 44545 is a duplicate of 44514." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Both concern classification labels, but one is config propagation and the other is a degenerate loss formulation with `num_labels=1`." + "reason": "Different classification bugs: config propagation in Qwen3.5 vs degenerate zero loss across sequence-classification models." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Runtime special-token post-processor updates are a different bug from DiaConfig losing custom token IDs after save/load." + "reason": "Both are tokenizer/config state issues, but one is post-processor refresh and the other is DiaConfig persistence of custom token IDs." }, { "left": "issue:44898", "right": "issue:45072", "accept": false, - "reason": "Image-resolution interpolation failure is unrelated to dtype mismatch in bf16 inference." + "reason": "Different model/runtime failures: Perceiver non-default resolution vs dtype mismatch in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading regressions, but they affect different models and do not look like the same underlying defect." + "reason": "Different tokenizer load failures for different models; no evidence of the same underlying bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet: the 44514/44545 pair is an exact title-level duplicate with the same `Qwen2_5_VLProcessor.apply_chat_template` batched `padding=False` crash, and the other soft pairs are handled conservatively without overstating evidence. No mergeability issues are apparent." + "feedback": "The summary is well grounded in the packet and stays conservative on the soft-edge pairs. The accepted duplicate pair, issue:44514/issue:44545, is strongly supported by matching titles and closely aligned failure descriptions, with 44514 appearing to be the earlier and fuller report. I don\u2019t see any overstatement in the other pair judgments based on the provided evidence." }, "evaluator_used": true, "retried": false, @@ -4417,7 +4516,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:30064", "issue:36010", @@ -4478,8 +4577,8 @@ "issue:44368|issue:45357", "issue:39692|issue:44610", "issue:43746|issue:46050", - "issue:45704|issue:45923", "issue:44918|issue:44936", + "issue:45704|issue:45923", "issue:43421|issue:43653", "issue:45663|issue:45923", "issue:43381|issue:43844", @@ -4500,230 +4599,227 @@ "issue:44220|issue:44661", "issue:43653|issue:43720" ], - "prepared_review_unit_hash": "4a9c0e53199f851dce4bf3c287d9888061b53b55ea916e3e47ceb13063eb368d", + "prepared_review_unit_hash": "0067a6f5ed62946114e3b99c12f3a10c08c63da3b58aa98e5b2e2adaba0ef8f0", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 31, - "serialized_chars": 36774, - "estimated_input_tokens": 9194, - "estimated_eval_tokens": 18644 + "serialized_chars": 36772, + "estimated_input_tokens": 9193, + "estimated_eval_tokens": 18642 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous and only one soft edge looks like a true duplicate: the offline tokenizer/cache regression around HF_HUB_OFFLINE. The rest are distinct bugs across unrelated model, tokenizer, training, and quantization paths.", - "confidence": 0.31, - "canonical_issue_reason": "Issue 44843 is the clearest root-cause-style report in the cluster and appears to subsume the offline tokenizer/cache failure described in 42886 via the _patch_mistral_regex/model_info path.", + "summary": "No duplicates or mergeable equivalents stand out here. The soft pairs mostly share broad areas like tokenizers, multimodal models, offloading, or training, but each describes a different concrete failure mode or root cause, so all edges should be rejected.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 44843 is the strongest representative because it isolates a specific failing code path rather than only a symptom, but the overall cluster is not a single coherent duplicate set.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45759", "right": "issue:45859", "accept": false, - "reason": "Different bugs: composite-config unwrapping in from_config vs CPU-offload incompatibility in rotary embedding." + "reason": "Different bugs: one is config unwrapping for composite Qwen multimodal models, the other is CPU offload incompatibility in rotary embedding forward." }, { "left": "issue:44077", "right": "issue:44625", "accept": false, - "reason": "Unrelated model/config issues; one is a patchtsmixer post_init policy change, the other is Qwen3.5 num_labels propagation." + "reason": "Unrelated failures: optional post_init policy in patchtsmixer vs num_labels propagation in Qwen3.5 config." }, { "left": "issue:43531", "right": "issue:44589", "accept": false, - "reason": "Different subsystems and failures: Qwen3-MoE sliding window vs missing Float8 storage type." + "reason": "Different subsystems and symptoms: Qwen3-MoE sliding window handling vs missing Float8 storage type on load." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen-VL related, but one is weight_only loading and the other is video vision_position_ids; not the same bug." + "reason": "Both are Qwen/VL-related, but one is a weight_only loading error and the other is a video vision_position_ids bug; not the same defect." }, { "left": "issue:44987", "right": "issue:45042", "accept": false, - "reason": "Different issues: model loading regression for one package vs PIL image processors wrongly requiring torchvision." + "reason": "Separate problems: loading a specific model fails vs PIL image processors incorrectly requiring torchvision." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "Flash-attention sink-less model crash is unrelated to Qwen composite config unwrapping." + "reason": "Different code paths: flash_attention sink-less s_aux handling vs from_config not unwrapping text_config." }, { "left": "issue:44062", "right": "issue:44451", "accept": false, - "reason": "Different failure modes: AddedToken special-arg TypeError vs a model load failure for ScandiBERT." + "reason": "No shared bug: AddedToken keyword duplication error vs a model loading failure for ScandiBERT." }, { "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "One is a tie_word_embeddings warning, the other is incorrect visual-encoder key saving; not the same code path." + "reason": "Distinct Qwen issues: warning about tie_word_embeddings vs incorrect visual encoder keys during save_pretrained." }, { "left": "issue:39692", "right": "issue:44610", "accept": false, - "reason": "Both mention vision models, but one is a SigLIP2 doc/example mismatch and the other is an OmDet-Turbo processor size bug." + "reason": "Different model/docs problems: SigLIP2 example errors vs OmDet-Turbo processor/model input-size mismatch." }, { "left": "issue:43746", "right": "issue:46050", "accept": false, - "reason": "Different checkpoint/loading problems: PEFT adapter local load vs sinq quantized save/load corruption." + "reason": "Not the same issue: local PEFT checkpoint loading for GraniteSpeech vs quantized sinq save/load corruption." }, { - "left": "issue:45704", - "right": "issue:45923", + "left": "issue:44918", + "right": "issue:44936", "accept": false, - "reason": "T5 RMSNorm memory leak is unrelated to Nemotron gradient-checkpointing flag support." + "reason": "Different failures: SFT trainer input embedding unpacking vs trainer.evaluate() breaking after train()." }, { - "left": "issue:44918", - "right": "issue:44936", + "left": "issue:45704", + "right": "issue:45923", "accept": false, - "reason": "Different training failures: Qwen3.5 embedding unpacking in TRL SFT vs trainer.evaluate() after trainer.train()." + "reason": "Unrelated: apex FusedRMSNorm memory leak in T5 vs missing supports_gradient_checkpointing flag." }, { "left": "issue:43421", "right": "issue:43653", "accept": false, - "reason": "Related to special tokens, but not the same bug: runtime post-processor updates vs BigBirdTokenizer mask-token registration/decode output." + "reason": "Different tokenizer bugs: runtime special-token post-processor refresh vs BigBird mask token registration/decode output." }, { "left": "issue:45663", "right": "issue:45923", "accept": false, - "reason": "Gemma-4 FSDP2 shared_kv_states KeyError is unrelated to gradient-checkpointing flag metadata." + "reason": "Distinct issues: FSDP2 shared_kv_states rebuilding per layer vs trust_remote_code gradient-checkpointing flag missing." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Eval-mode gradient checkpointing limitation is unrelated to a ZeRO-3 gradient blow-up." + "reason": "Both involve training behavior, but one is eval-mode gradient checkpointing support and the other is gradient explosion under ZeRO-3." }, { "left": "issue:42886", "right": "issue:44843", - "accept": true, - "reason": "Same underlying offline tokenizer/cache regression; 44843 identifies the culprit (_patch_mistral_regex calling model_info unconditionally) behind 42886's HF_HUB_OFFLINE failure." + "accept": false, + "reason": "Related to offline tokenizer loading, but not the same bug: one is generic cache/offline failure, the other is a specific _patch_mistral_regex model_info call." }, { "left": "issue:45704", "right": "issue:45859", "accept": false, - "reason": "Different issues: T5 RMSNorm memory leak vs Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." + "reason": "Different models and symptoms: memory leak from fused norm use vs CPU offload incompatibility in Qwen rotary embedding." }, { "left": "issue:43531", "right": "issue:43645", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to Jupyter custom-model initialization in Transformers 5.0.0." + "reason": "Distinct regressions: sliding_window handling in Qwen3-MoE vs Jupyter custom model definition/initialization in Transformers 5." }, { "left": "issue:41720", "right": "issue:45704", "accept": false, - "reason": "CUDA assert from auto device mapping is unrelated to the T5 apex RMSNorm memory leak." + "reason": "No overlap beyond being model-runtime bugs: cudaErrorAssert on Qwen3 auto device mapping vs T5 fused RMSNorm memory leak." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Special-token post-processor behavior is unrelated to LayoutLMv2Tokenizer NER/padding crashes." + "reason": "Different tokenizer paths: special-token post-processor update issue vs LayoutLMv2Tokenizer crashes on NER/padding." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different model families and bugs: SigLIP2 inference regression vs CamemBERT masked-LM prediction regression." + "reason": "Separate model correctness bugs: SigLIP2 AutoModel/pipeline output regression vs CamemBERT masked LM predictions in v5." }, { "left": "issue:43746", "right": "issue:43873", "accept": false, - "reason": "Local checkpoint loading with PEFT adapters is unrelated to quantization offloading behavior." + "reason": "Different areas: PEFT local checkpoint loading vs quantization/offloading behavior." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "Doc/example errors for SigLIP2 are unrelated to quantization/offloading behavior." + "reason": "One is a documentation/example mismatch, the other is a quantization offloading issue; not the same bug." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Both involve tokenizer regex fixes, but one is a hard crash loading Mistral tokens and the other is a codec-handling regression in Kimi-K2.5; not clearly the same bug." + "reason": "Both touch mistral regex logic, but one is a crash on fix_mistral_regex and the other is a Kimi tokenizer regression with codec handling/warning." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "Different low-level runtime errors: DeepSpeed ZeRO-3/BertModel index error vs _torch_extract_fbank_features issue." + "reason": "Different runtime errors in different components: ZeRO-3/BertModel indexing vs audio fbank feature extraction." }, { "left": "issue:40444", "right": "issue:43746", "accept": false, - "reason": "Multimodal iterable dataset fine-tuning failure is unrelated to PEFT local checkpoint loading." + "reason": "Unrelated multimodal training failure vs local checkpoint loading with PEFT adapters." }, { "left": "issue:45356", "right": "issue:45907", "accept": false, - "reason": "Tokenizer codec/regex regression is unrelated to list_repo_files not forwarding revision." + "reason": "Completely different: tokenizer regression vs hub API list_repo_files not forwarding revision." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Completely different topics: void segmentation map processing vs GenerationMixin import error." + "reason": "Different domains entirely: image processor segmentation-map handling vs GenerationMixin import error." }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "Different numerical/model bugs: packed-weight loading vs DAC.from_latents missing STE mismatch." + "reason": "Separate bugs: packed BitNet weights not unpacked on accelerate load vs DAC.from_latents not matching forward pass without STE." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio feature extraction bug is unrelated to add-new-model-like failing for TOKENIZER_MAPPING_NAMES." + "reason": "Different code paths: torch fbank feature extraction vs add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." }, { "left": "issue:43653", "right": "issue:43720", "accept": false, - "reason": "BigBird special-token decode issue is unrelated to BitNet packed-weight loading." + "reason": "No shared underlying defect: BigBird special-token decode bug vs BitNet packed-weight loading." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The only likely duplicate edge called out (42886 \u2194 44843) is supported by the issue titles and the shared _patch_mistral_regex/model_info path, while the rest of the soft-edge rejections are plausibly distinct bugs. No clear overstatement beyond the cautious wording already used." - }, - "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 }, @@ -4738,7 +4834,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:30064", "issue:36331", @@ -4804,8 +4900,8 @@ "issue:44186|issue:44898", "issue:43653|issue:43819", "issue:43531|issue:43643", - "issue:43643|issue:44877", "issue:43950|issue:45987", + "issue:43643|issue:44877", "issue:44843|issue:45081", "issue:30064|issue:36331", "issue:43540|issue:45381", @@ -4815,206 +4911,206 @@ "issue:39692|issue:45834", "issue:43577|issue:43818", "issue:43782|issue:44977", - "issue:45584|issue:45834", "issue:44821|issue:45084", + "issue:45584|issue:45834", "issue:44186|issue:44442" ], - "prepared_review_unit_hash": "53ec5b1d296865e1d3fa27dd7e381108dd19a9c322ce8055d21c4186ff074185", + "prepared_review_unit_hash": "17ca86f12c6443af6d5748b803825e884b962b795653e5cfb7be2b99641f824e", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36507, - "estimated_input_tokens": 9127, - "estimated_eval_tokens": 18510 + "serialized_chars": 36510, + "estimated_input_tokens": 9128, + "estimated_eval_tokens": 18512 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the soft pairs share broad Transformers themes but not the same concrete bug or fix path, so I would not deduplicate any of them.", - "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue stands out because the cluster mixes unrelated regressions across models, tokenizers, processors, cache logic, and training utilities; if forced to pick one anchor, issue 44843 is the clearest core-loading regression, but it does not represent the rest.", + "summary": "This cluster is mostly a loose grab-bag of unrelated Transformers issues across tokenizers, multimodal models, generation, and cache logic. None of the soft pairs looks like the same concrete bug; the closest is the two Mistral regex issues, but they describe different failure modes.", + "confidence": 0.93, + "canonical_issue_reason": "No strong canonical issue: the items are heterogeneous and do not form a single duplicate set. If one must be chosen as an anchor, issue 44843 is the closest because it is the most specific and directly tied to the Mistral tokenizer patch path.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44843 is the most concrete and broadly actionable regression in the set, with a clear failure mode and code path, though it is not a true representative of the whole cluster.", + "best_issue_reason": "Issue 44843 is the best representative only in a weak sense: it is specific, reproducible, and the only item in a near-related soft pair, but it still does not unify the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43540", "right": "issue:44008", "accept": false, - "reason": "Different models and root causes: Qwen3OmniMoe video-processing ValueError vs Gemma 3n audio_mel_mask attribute collision." + "reason": "Different models and failure modes: Qwen3OmniMoe video input validation vs Gemma 3n attribute collision in forward()." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "Both are model output regressions, but one is missing CLIP attentions and the other is RTDetrV2 producing different outputs; not the same bug." + "reason": "Both are regressions, but on different models/code paths: CLIP attentions assignment vs RTDetrV2 output drift." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "Distinct code paths and failures: Bamba torch.compile/SDPA issue vs SwitchTransformers/TimmWrapperModel dtype mismatch." + "reason": "Unrelated bugs: torch.compile+SDPA on Bamba vs dtype mismatch in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:45183", "right": "issue:45479", "accept": false, - "reason": "One is input validation/error-message logic; the other is zero-loss behavior in single-label classification. Different bugs." + "reason": "Different core problems: input validation XOR logic vs degenerate single-label classification loss." }, { "left": "issue:43295", "right": "issue:45834", "accept": false, - "reason": "Both involve model loading/processing, but the regression in processor.tokenizer access is unrelated to Kosmos2.5's long-OCR index error." + "reason": "One is a processor/tokenizer regression; the other is a long-ocr index error in Kosmos2.5." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "Unrelated failures: torch.compile with SDPA in Bamba vs DAC.from_latents not matching forward pass due to missing STE." + "reason": "Different models and bugs: SDPA/compile failure vs DAC forward/from_latents mismatch." }, { "left": "issue:43388", "right": "issue:46032", "accept": false, - "reason": "Different areas: gather_for_metrics last-batch label handling vs Mamba2Mixer cache correctness for seq_len > 1." + "reason": "Different training/runtime paths: gather_for_metrics batching vs Mamba2 cache correctness." }, { "left": "issue:44062", "right": "issue:44488", "accept": false, - "reason": "Tokenizer construction bug with AddedToken kwargs vs failure to load a specific model tokenizer; no shared root cause." + "reason": "Both involve tokenizer loading, but one is an AddedToken keyword conflict and the other is a model-specific load failure." }, { "left": "issue:43716", "right": "issue:44008", "accept": false, - "reason": "Different models and modalities: Blip2 image preprocessor dtype mismatch vs Gemma 3n variable-name collision in audio forward pass." + "reason": "Different subsystems: dtype mismatch in image preprocessing vs Gemma 3n audio mask name collision." }, { "left": "issue:43335", "right": "issue:43756", "accept": false, - "reason": "Different model/config bugs: sparse layer creation with zero layers vs Smollm3 RoPE layer count mismatch." + "reason": "Distinct model/config bugs: sparse-layer construction vs RoPE layer dropping." }, { "left": "issue:43322", "right": "issue:45685", "accept": false, - "reason": "Llava Next loading segfault and MPS histogram-not-implemented are separate platform/runtime issues." + "reason": "No shared code path: Llava Next loading segfault vs MPS histogram not implemented for Int." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "Tokenizer crash on NER padding/truncation vs Perceiver image-classification failure at non-default resolution." + "reason": "Different model families and symptoms: LayoutLMv2 tokenizer crashes vs Perceiver interpolation failure." }, { "left": "issue:43653", "right": "issue:43819", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug vs DAC.from_latents/forward mismatch; different subsystems." + "reason": "Tokenizer special-token registration bug vs DAC STE mismatch; unrelated." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to AutoConfig trust_remote_code missing fields." + "reason": "Different areas: Qwen3-MoE sliding window vs AutoConfig trust_remote_code field loss." }, { - "left": "issue:43643", - "right": "issue:44877", + "left": "issue:43950", + "right": "issue:45987", "accept": false, - "reason": "Both are config-loading issues, but one is missing fields from trust_remote_code and the other is strict config rejecting granite_speech; different causes." + "reason": "Both are cache/state-related regressions, but one corrupts non-persistent buffers and the other violates get_seq_length return type." }, { - "left": "issue:43950", - "right": "issue:45987", + "left": "issue:43643", + "right": "issue:44877", "accept": false, - "reason": "Non-persistent buffer corruption in from_pretrained is unrelated to StaticCache.get_seq_length returning the wrong type." + "reason": "Both are config-loading issues, but they concern different mechanisms and model families." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Both touch Mistral regex patching, but one is an offline hub call in _patch_mistral_regex while the other is an AttributeError on backend_tokenizer; different failure points." + "reason": "Both mention _patch_mistral_regex, but the failures differ: offline model_info access vs missing backend_tokenizer attribute." }, { "left": "issue:30064", "right": "issue:36331", "accept": false, - "reason": "Image segmentation-map processing and CustomTrainer.compute_loss signature mismatch are unrelated." + "reason": "Completely unrelated: image segmentation-map processing vs CustomTrainer loss signature mismatch." }, { "left": "issue:43540", "right": "issue:45381", "accept": false, - "reason": "Same broad Qwen multimodal area, but different models and bugs: Qwen3OmniMoe video input handling vs qwen2.5-vl vision_position_ids." + "reason": "Both involve Qwen variants, but the bugs are different: video input handling vs flash-attention generation behavior." }, { "left": "issue:44448", "right": "issue:44671", "accept": false, - "reason": "Different models and regressions: Pegasus output changes across versions vs CamemBERT masked-LM prediction errors." + "reason": "Separate model regressions with different outputs and different tasks: summarization vs masked LM." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Both concern token/processor special-token behavior, but one is runtime post-processor updates and the other is Whisper batch_decode skipping special tokens." + "reason": "Related to tokenization/special tokens in a broad sense, but the concrete bugs are different: runtime post-processor refresh vs Whisper batch_decode skip_special_tokens handling." }, { "left": "issue:41720", "right": "issue:44991", "accept": false, - "reason": "Different domains: Qwen3 auto device-mapping CUDA assert on A800 vs tokenizer loading failure for EMBEDDIA/est-roberta." + "reason": "Unrelated failures: Qwen3 device-mapping cuda assert vs tokenizer load failure for est-roberta." }, { "left": "issue:39692", "right": "issue:45834", "accept": false, - "reason": "Documentation/example errors for SigLIP2 are not the same as Kosmos2.5's runtime index error on long OCR input." + "reason": "Different multimodal/documentation issues: SigLIP2 example problems vs Kosmos2.5 OCR index error." }, { "left": "issue:43577", "right": "issue:43818", "accept": false, - "reason": "Different models and bug classes: Blip2 dtype mismatch vs Video-LLaVA missing temporal attention/shared weights." + "reason": "Different model loading bugs: BLIP2 dtype propagation vs Video-LLaVA video_tower/temporal-attention issue." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Related model family, but one is a weight_only loading error and the other is a flash-attention generation bug; not mergeable as one fix." + "reason": "Different Qwen model families and failures: weight_only load error vs flash-attention generation problem." }, { - "left": "issue:45584", - "right": "issue:45834", + "left": "issue:44821", + "right": "issue:45084", "accept": false, - "reason": "Whisper empty-transcription generation after align_special_tokens is unrelated to Kosmos2.5 long-input indexing." + "reason": "No shared underlying bug: AutoImageProcessor-from-URL loading vs template-node compilation error." }, { - "left": "issue:44821", - "right": "issue:45084", + "left": "issue:45584", + "right": "issue:45834", "accept": false, - "reason": "AutoImageProcessor URL loading and TypeError compiling non-template nodes are unrelated code paths." + "reason": "Different input domains and failure modes: Whisper empty transcription after token alignment vs Kosmos2.5 long OCR index error." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "LayoutLMv2 tokenizer crash and AutoTokenizer failing to load FastSpeech2ConformerTokenizer are different tokenizer/loading bugs." + "reason": "Different tokenizer bugs affecting different models and APIs; not the same underlying issue." } ] }, @@ -5036,7 +5132,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:28218", "issue:29159", @@ -5096,13 +5192,13 @@ "issue:43577|issue:43582", "issue:43825|issue:43994", "issue:44805|issue:44936", - "issue:44485|issue:44509", "issue:45987|issue:46192", - "issue:43825|issue:43827", "issue:44671|issue:45701", - "issue:28218|issue:29159", + "issue:44485|issue:44509", "issue:44610|issue:45072", + "issue:28218|issue:29159", "issue:43720|issue:45072", + "issue:43825|issue:43827", "issue:43782|issue:45325", "issue:43906|issue:46209", "issue:42175|issue:45081", @@ -5118,215 +5214,218 @@ "issue:43742|issue:45020", "issue:43526|issue:44554" ], - "prepared_review_unit_hash": "bcba21316dbae4e5fcea5ca8bd0ecd74e4889e4b5e35f707f4ff09bb9f8f6386", + "prepared_review_unit_hash": "15a17dbba50b445dff34ac4f6c746368c730b9a88e82671d3935e780e1100d6a", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36609, - "estimated_input_tokens": 9153, - "estimated_eval_tokens": 18562 + "serialized_chars": 36600, + "estimated_input_tokens": 9150, + "estimated_eval_tokens": 18556 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous cluster with several distinct bug families (tokenizer behavior, pipeline/v5 docs, remote_code regressions, model-specific loading/inference bugs, and training/runtime errors). None of the soft pairs look like true duplicates; most are only thematically similar.", - "confidence": 0.84, - "canonical_issue_reason": "No single canonical issue cleanly represents the whole cluster. If one must be chosen, issue 43825 is the most concrete representative of the small pipeline/v5 subset, but the cluster is too mixed for a strong canonical.", + "summary": "Mostly unrelated issue mix; only the tokenizer added-token spacing reports look like the same underlying bug. The rest are similar at a subsystem level but not concrete duplicates.", + "confidence": 0.78, + "canonical_issue_reason": "issue:28218 is the clearest concrete report of the tokenizer added-token spacing bug, and it best matches the one plausible duplicate in the set.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43825 is the clearest, most actionable bug report among the near-v5/pipeline items, but it still does not generalize to the unrelated tokenizer/model/training issues in the cluster.", + "best_issue_reason": "issue:28218 is the strongest representative issue: specific, self-contained, and directly tied to the duplicate tokenizer behavior.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43644", "right": "issue:43749", "accept": false, - "reason": "Different failure modes: junk non-persistent buffers during save/load vs broken FSDP CPU RAM efficient loading. Same broad loading area, not the same bug." + "reason": "Both concern model/loading behavior, but one is about non-persistent buffer initialization and the other about FSDP CPU RAM efficient loading; not the same bug." }, { "left": "issue:43606", "right": "issue:45072", "accept": false, - "reason": "Both mention device/dtype issues during inference, but they affect different models and code paths (CPU offload vs bfloat16 inference). Not the same underlying defect." + "reason": "Different models and failures: CPU offload device mismatch vs bfloat16 dtype mismatch. Same broad inference area, not the same issue." }, { "left": "issue:44479", "right": "issue:45834", "accept": false, - "reason": "Video-input regression for Qwen VL models is unrelated to Kosmos2.5 OCR index errors. Different subsystems and symptoms." + "reason": "Both are multimodal input bugs, but they affect different models and different failure modes." }, { "left": "issue:44561", "right": "issue:45020", "accept": false, - "reason": "Both involve recent v5/remote_code breakage, but one is specifically `is_torch_fx_available` removal while the other is a broad regression report. Too general to merge as duplicates." + "reason": "issue:44561 is a specific trust_remote_code regression from a removed helper; issue:45020 is a broad umbrella report. Related, but not the same concrete bug." }, { "left": "issue:34634", "right": "issue:36010", "accept": false, - "reason": "BarkProcessor voice_preset failure and GenerationMixin import error are unrelated model/API issues." + "reason": "One is a BarkProcessor preset bug, the other an import error for GenerationMixin; no duplicate evidence." }, { "left": "issue:43577", "right": "issue:43582", "accept": false, - "reason": "One is a BLIP2 dtype propagation bug; the other is an Apple Silicon allocator warmup TypeError. Same platform theme only." + "reason": "Different domains: BLIP2 dtype loading vs Apple Silicon allocator warmup TypeError." }, { "left": "issue:43825", "right": "issue:43994", "accept": false, - "reason": "Pipeline translation-task messaging and SigLIP2 nonsensical outputs are unrelated problems." + "reason": "One is a v5 pipeline error-message mismatch; the other is a bad AutoModel/pipeline result for a specific model. Not the same bug." }, { "left": "issue:44805", "right": "issue:44936", "accept": false, - "reason": "Generic mask/index shape crash versus trainer.evaluate() failing after train(). Different stack traces and code paths." - }, - { - "left": "issue:44485", - "right": "issue:44509", - "accept": false, - "reason": "GLM-5 RoPE discussion is unrelated to docs still mentioning removed pipeline tasks." + "reason": "Generic index-shape error vs trainer evaluate-after-train failure; too little concrete overlap to treat as duplicate." }, { "left": "issue:45987", "right": "issue:46192", "accept": false, - "reason": "StaticCache sequence-length contract bug and ignored return_tensors in text_kwargs are separate API issues." - }, - { - "left": "issue:43825", - "right": "issue:43827", - "accept": false, - "reason": "They are related to the v5 pipeline removals, but one is an error-message bug and the other is stale docs. Same topic, not the same bug." + "reason": "One is a StaticCache return-type contract bug, the other silently ignores return_tensors when text_kwargs is passed." }, { "left": "issue:44671", "right": "issue:45701", "accept": false, - "reason": "CamemBERT masked-LM regression and generic tokenization changes are not the same concrete defect." + "reason": "CamemBERT masked-LM regression and a general tokenization-version complaint are not the same code-path problem." }, { - "left": "issue:28218", - "right": "issue:29159", + "left": "issue:44485", + "right": "issue:44509", "accept": false, - "reason": "Both involve tokenizer behavior, but one is about an added token inserting extra space and the other is slow/fast tokenizer inconsistency more broadly. Not clearly the same bug." + "reason": "One discusses GLM-5 RoPE implementation, the other stale docs about removed pipeline tasks." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "OmDet-Turbo processor size mismatch is unrelated to SwitchTransformers/TimmWrapperModel bfloat16 dtype mismatches." + "reason": "Different processors/models and different defects: input-size mismatch vs dtype mismatch." + }, + { + "left": "issue:28218", + "right": "issue:29159", + "accept": true, + "reason": "Both describe the same tokenizer added-token spacing inconsistency, with slow/fast tokenizer behavior and an extra space after added tokens." }, { "left": "issue:43720", "right": "issue:45072", "accept": false, - "reason": "Packed-weight unpacking failure during accelerate loading is a different issue from dtype mismatches in inference." + "reason": "BitNet packed-weight loading failure is unrelated to dtype mismatch issues in other models." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Both mention v5 pipeline removals, but one is an error-message issue and the other is stale docs; different artifacts and fixes." }, { "left": "issue:43782", "right": "issue:45325", "accept": false, - "reason": "Qwen3VL weight_only loading error and Qwen2.5-VL RoPE scaling bug are separate model-specific regressions." + "reason": "Different Qwen-VL bugs: weight_only loading error vs still-image temporal position scaling." }, { "left": "issue:43906", "right": "issue:46209", "accept": false, - "reason": "A reproduction of an older issue and an FP8/B200 inference bug are unrelated." + "reason": "A reproduction of an older issue is not the same bug as an FP8/B200 inference failure." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "Backend packaging issue for `.[torch]` and a Mistral regex patch crash are unrelated." + "reason": "Packaging/backend selection issue vs tokenizer regex patch crash; unrelated." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "CPU RAM efficient loading breakage and unexpected `_is_hf_initialized` arg during init_empty_weights are distinct loading bugs." + "reason": "Both are loading-related, but one is FSDP CPU RAM efficient loading and the other is init_empty_weights argument handling; distinct failures." }, { "left": "issue:43582", "right": "issue:44857", "accept": false, - "reason": "AppleSilicon allocator warmup TypeError and CUDA float16 AMP crash in LwDetrImageLoss are different platform/runtime failures." + "reason": "Apple Silicon warmup TypeError and CUDA AMP float16 crash are different platform-specific bugs." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Tokenizer regex patch crash and Gemma4Processor missing `_tokenizer` are separate loading/processor bugs." + "reason": "Tokenizer regex patch crash and Gemma4Processor missing _tokenizer are separate component bugs." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "apply_chat_template sampling-rate default bug and DAC.from_latents mismatch are unrelated audio issues." + "reason": "Audio chat-template sampling-rate defaulting and DAC latent reconstruction mismatch are unrelated." }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "BarkProcessor voice_preset does not work and CustomTrainer.compute_loss signature breakage are unrelated." + "reason": "Processor voice_preset failure and CustomTrainer compute_loss signature mismatch do not describe the same defect." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and RTDetrV2 output regression are different model/processor defects." + "reason": "Different vision bugs: label reduction returning one label vs RTDetrV2 output drift in v5." }, { "left": "issue:43650", "right": "issue:43906", "accept": false, - "reason": "'ADD THE DATA' is not a technical bug report, and it is not the same as the referenced reproduction issue." + "reason": "No meaningful overlap; one is an empty placeholder title, the other a reproduction issue." }, { "left": "issue:44060", "right": "issue:44368", "accept": false, - "reason": "Incorrect tied-weights warning in Qwen3-Next and a Qwen3.5 LoRA warning are related only by theme, not by identical code path." + "reason": "Both involve Qwen tie-word-embedding warnings, but one is a wrong tied-weights mapping bug and the other is a user-facing warning during LoRA fine-tuning." }, { "left": "issue:43653", "right": "issue:44912", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug and MXFP4 quantization fallback are unrelated." + "reason": "Tokenizer special-token registration and MXFP4 quantization loading are unrelated." }, { "left": "issue:43742", "right": "issue:45020", "accept": false, - "reason": "KeyError loading MobileLLM-125M and broad remote_code breakage are different failures." + "reason": "A specific MobileLLM load key error is not the same underlying problem as a broad remote_code regression." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "BeitImageProcessorFast label reduction and MPS attention correctness with differing head dims are unrelated." + "reason": "BeitImageProcessorFast label reduction and MPS attention correctness are different issues." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and appropriately conservative. The summary stays within the packet evidence, and the only accepted soft-edge pair is plausibly the same tokenizer spacing bug based on the issue titles. The other pairings are correctly rejected as subsystem-level similarities rather than clear duplicates." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -5341,7 +5440,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:34567", "issue:36010", @@ -5396,16 +5495,16 @@ "issue:45084|issue:45538", "issue:43329|issue:45600", "issue:44589|issue:45042", - "issue:43746|issue:44811", "issue:43638|issue:44936", + "issue:43746|issue:44811", "issue:43452|issue:44991", "issue:44387|issue:44617", "issue:43550|issue:44912", "issue:36010|issue:43645", "issue:43819|issue:43927", "issue:43257|issue:43329", - "issue:39692|issue:44912", "issue:43854|issue:44977", + "issue:39692|issue:44912", "issue:38175|issue:44610", "issue:43720|issue:44610", "issue:45459|issue:45803", @@ -5413,30 +5512,30 @@ "issue:43454|issue:43577", "issue:43531|issue:45042", "issue:43262|issue:44811", - "issue:43257|issue:43696", "issue:43329|issue:44479", + "issue:43257|issue:43696", "issue:42490|issue:43257", "issue:43643|issue:45759", - "issue:43329|issue:43450", "issue:43606|issue:45859", + "issue:43329|issue:43450", "issue:43749|issue:44756", "issue:34567|issue:40990", "issue:44568|issue:45356" ], - "prepared_review_unit_hash": "66261d035057627a14bec6a78bf5ef57a6a2352f24533ae58a55fea168cd28fa", + "prepared_review_unit_hash": "fb0fadd3e3b2d7fa119080baef4663f42585049a6f58372a1750cae28223fc3a", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36621, + "serialized_chars": 36622, "estimated_input_tokens": 9156, "estimated_eval_tokens": 18568 }, @@ -5445,193 +5544,196 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is highly heterogeneous: the soft pairs are only superficially related by subsystem/theme, not by the same underlying bug or fix. No PRs are present.", - "confidence": 0.94, - "canonical_issue_reason": "No true canonical issue exists here; the items span many unrelated bugs (training, tokenization, multimodal/video, loading, offload, quantization, OOM), so any single issue would be a poor duplicate representative.", + "summary": "Mostly unrelated Transformer issue reports with a few thematically similar pairs. Only the Qwen video-input regression pair looks like the same underlying bug; no PRs are present.", + "confidence": 0.61, + "canonical_issue_reason": "issue:43329 is the clearest root-cause report in the set: it names the broken video branch in `_get_num_multimodal_tokens` and affects multiple VLM processors.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43749 is the strongest single anchor only because it has the most discussion/inbound references, but it still does not represent the rest of this mixed cluster.", + "best_issue_reason": "issue:43329 is the best representative because it describes a concrete, centralized multimodal-video code-path bug with broad downstream impact.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "Unrelated bugs: template-node compilation vs tokenizer max-length constant." + "reason": "Different problems: compilation/template-node errors vs tokenizer max-length behavior." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "Different code paths: multimodal video token counting vs stale auto_mappings references." + "reason": "Unrelated subsystems: multimodal video token counting vs stale auto_mappings references." }, { "left": "issue:44589", "right": "issue:45042", "accept": false, - "reason": "Different failures: missing Float8 storage vs PIL image processor torchvision requirement." + "reason": "Different failure modes: missing Float8 storage vs image processor torchvision dependency." }, { - "left": "issue:43746", - "right": "issue:44811", + "left": "issue:43638", + "right": "issue:44936", "accept": false, - "reason": "Different features and code paths: local PEFT checkpoint loading vs Whisper batch_decode behavior." + "reason": "Training/DeepSpeed index error is not the same as evaluate-after-train state failure." }, { - "left": "issue:43638", - "right": "issue:44936", + "left": "issue:43746", + "right": "issue:44811", "accept": false, - "reason": "Both are training/eval failures, but the underlying bugs are different (DeepSpeed ZeRO-3 index error vs evaluate-after-train failure)." + "reason": "Different APIs and bugs: PEFT local checkpoint loading vs Whisper batch_decode skip_special_tokens handling." }, { "left": "issue:43452", "right": "issue:44991", "accept": false, - "reason": "Different model loading problems: gguf_file handling vs tokenizer loading for a specific repo." + "reason": "Both concern loading, but different entrypoints and concrete regressions; not the same bug." }, { "left": "issue:44387", "right": "issue:44617", "accept": false, - "reason": "Both are OOM reports, but for different models and mechanisms; not the same bug." + "reason": "Both mention OOM, but one is quantization-memory regression and the other is a model-specific memory limit issue." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "Unrelated: torch.compile/SDPA crash in Bamba vs MXFP4 load fallback in gpt-oss." + "reason": "Different model/code-path failures: torch.compile+SDPA vs MXFP4 load fallback." }, { "left": "issue:36010", "right": "issue:43645", "accept": false, - "reason": "Different regressions: GenerationMixin import path vs custom model initialization in Jupyter." + "reason": "ImportError for GenerationMixin is unrelated to Jupyter custom-model initialization breakage." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "Different model bugs: DAC latent reconstruction mismatch vs DiaConfig token-id persistence." + "reason": "Unrelated bugs: DAC forward/from_latents mismatch vs config fields lost after save/load." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "Different areas: Qwen3 MoE loading under accelerate/deepspeed vs multimodal video token counting." + "reason": "Different loading/dispatch paths: Qwen3-MoE weight conversion vs multimodal token counting." }, { - "left": "issue:39692", - "right": "issue:44912", + "left": "issue:43854", + "right": "issue:44977", "accept": false, - "reason": "Different issues: SigLIP2 docs/example problems vs gpt-oss MXFP4 loading behavior." + "reason": "Different models and symptoms; both are generation-related but not the same concrete bug." }, { - "left": "issue:43854", - "right": "issue:44977", + "left": "issue:39692", + "right": "issue:44912", "accept": false, - "reason": "Different model-specific generation/load failures; not the same concrete bug." + "reason": "SigLIP2 doc-example failures are unrelated to gpt-oss MXFP4 loading." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "Different vision-model issues: zero probabilities vs processor/model input-size mismatch." + "reason": "Different vision-model issues: zero probabilities vs processor output shape/input-size mismatch." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "Different code paths: packed-weight loading vs processor output shape." + "reason": "Accelerate packed-weight unpacking bug is unrelated to OmDet processor size mismatch." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Both involve exception handling, but in different functions and with different bugs." + "reason": "Both hide errors with exceptions, but they are different functions and different root causes." }, { "left": "issue:36010", "right": "issue:36331", "accept": false, - "reason": "Both affect trainer-related APIs, but one is an import error and the other is a compute_loss signature break." + "reason": "Import-time GenerationMixin failure is unrelated to custom compute_loss keyword regression." }, { "left": "issue:43454", "right": "issue:43577", "accept": false, - "reason": "Different model loading bugs: lm_head weight tying vs dtype propagation to QFormer." + "reason": "Different multimodal model bugs: lm_head tying vs dtype propagation for BLIP2." }, { "left": "issue:43531", "right": "issue:45042", "accept": false, - "reason": "Unrelated: Qwen3-MoE sliding-window logic vs image processor torchvision dependency." + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to PIL backend torchvision requirements." }, { "left": "issue:43262", "right": "issue:44811", "accept": false, - "reason": "Both are audio/processor issues, but sampling-rate defaulting and batch_decode special-token handling are distinct." - }, - { - "left": "issue:43257", - "right": "issue:43696", - "accept": false, - "reason": "Different problems: MoE weight conversion under accelerate/deepspeed vs plain OOM on GPT-oss-20b." + "reason": "Different audio processor methods and symptoms; not the same bug." }, { "left": "issue:43329", "right": "issue:44479", + "accept": true, + "reason": "Both point to the same broken video-input path in Qwen multimodal processors; 44479 reads like the broader v5.3.0 manifestation of the helper bug in 43329." + }, + { + "left": "issue:43257", + "right": "issue:43696", "accept": false, - "reason": "Both are video-related, but one is undefined variables in token counting and the other is a broader v5.3.0 regression." + "reason": "Qwen3-MoE loading/conversion is unrelated to GPT-oss OOM." }, { "left": "issue:42490", "right": "issue:43257", "accept": false, - "reason": "Completely different topics: trailing-slash local-path warning vs Qwen3 MoE loading." + "reason": "Local-path import warning with trailing slash is unrelated to Qwen3-MoE accelerate/deepspeed weight conversion." }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "Both are config-loading issues, but one is missing fields with trust_remote_code and the other is text_config unwrapping for multimodal configs." + "reason": "Both involve config handling, but different methods and failure modes; not the same underlying bug." }, { - "left": "issue:43329", - "right": "issue:43450", + "left": "issue:43606", + "right": "issue:45859", "accept": false, - "reason": "Different video bugs: undefined helper variables vs incorrect batched processor output shape." + "reason": "Both mention CPU offload/device handling, but they are model-specific issues in different code paths." }, { - "left": "issue:43606", - "right": "issue:45859", + "left": "issue:43329", + "right": "issue:43450", "accept": false, - "reason": "Both mention CPU offload, but they are different models and failure modes." + "reason": "Video token counting bug is unrelated to batched video processor output shape." }, { "left": "issue:43749", "right": "issue:44756", "accept": false, - "reason": "Different loading/memory issues: FSDP CPU RAM efficient loading vs mmap on Strix Halo OOM." + "reason": "Different memory-loading contexts: FSDP CPU RAM efficient loading vs mmap on Strix Halo." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "Unrelated: TrainerState token counter not updating vs GPT-oss perplexity issue." + "reason": "Trainer token counter bug is unrelated to GPT-oss perplexity." }, { "left": "issue:44568", "right": "issue:45356", "accept": false, - "reason": "Both are tokenizer regressions, but for different models and different root causes." + "reason": "Both are tokenizer regressions, but they affect different models and different tokenizer code paths." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft edge (43329/44479) is reasonably supported by the overlapping Qwen video-input regression context, and the other pair rejections do not overclaim sameness. No PRs are present, so there is no mergeability issue." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -5646,7 +5748,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:24643", "issue:28282", @@ -5694,7 +5796,6 @@ "issue:45488", "issue:45538", "issue:45701", - "issue:45823", "issue:45907" ], "soft_pairs": [ @@ -5707,8 +5808,8 @@ "issue:44568|issue:45488", "issue:44987|issue:45538", "issue:43452|issue:43582", - "issue:43697|issue:45357", "issue:41720|issue:43540", + "issue:43697|issue:45357", "issue:43927|issue:44912", "issue:42915|issue:45538", "issue:44479|issue:45381", @@ -5718,256 +5819,246 @@ "issue:43540|issue:44560", "issue:43317|issue:45538", "issue:44062|issue:44991", + "issue:24643|issue:29159", "issue:45137|issue:45405", "issue:44987|issue:45907", - "issue:24643|issue:29159", "issue:28282|issue:34689", "issue:43577|issue:45072", - "issue:43257|issue:43756", "issue:43742|issue:44291", + "issue:43257|issue:43756", "issue:28282|issue:29127", "issue:42175|issue:44488", "issue:42915|issue:43749", - "issue:38175|issue:44898", "issue:43582|issue:43782", - "issue:43540|issue:45823" + "issue:38175|issue:44898" ], - "prepared_review_unit_hash": "ce942500b578f62cb2daa85ac56ab686d0914f14c747e94ce25803ec9bfad0b2", + "prepared_review_unit_hash": "427ab9fafce1a8b60dfd7648f4ae88d095bf249cdc3943a96d8a607f260c7cf7", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37558, - "estimated_input_tokens": 9390, - "estimated_eval_tokens": 19036 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36692, + "estimated_input_tokens": 9173, + "estimated_eval_tokens": 18602 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: tokenizer regressions, model-loading errors, video-input bugs, dtype/device-map issues, and a few DeepSpeed/quantization reports. I only see one plausible duplicate pair in the Qwen VL video-input regression family.", - "confidence": 0.61, - "canonical_issue_reason": "Issue 45701 is the broadest and most representative anchor here: it explicitly frames a cross-version tokenization change, which is the closest shared theme among several tokenizer-related reports in an otherwise mixed set.", + "summary": "These issues mostly share model-loading/tokenization language but describe different concrete failures. I did not find any soft pair that looks like the same underlying bug or change; they span distinct code paths such as DeepSpeed/FSDP loading, video preprocessing, tokenizer behavior, quantization, and model-specific config regressions.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45701 is the best umbrella-style issue in this set: it is broad, open, and explicitly about version-dependent tokenization changes, which makes it the closest thing to a cluster representative.", "canonical_pr_reason": null, - "best_issue_reason": "45701 is the best single issue to represent the cluster because it is generic, active, and closest to the recurring regression theme; the other items are mostly narrower or unrelated one-off failures.", + "best_issue_reason": "issue:45701 is the strongest global representative because it is broad enough to subsume related tokenizer regressions, has active inbound references, and is phrased as a general behavioral regression rather than a narrow model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Both are Qwen loading problems, but one is an MoE weight-conversion issue under accelerate+deepspeed and the other is a Qwen3-VL weight-shape mismatch; different failure modes and code paths." + "reason": "Both are Qwen3/VL-related loading bugs, but one is about MoE weight conversion under accelerate+deepspeed and the other is a weight-shape mismatch for Qwen3-VL-30B-A3B-Instruct. Different failure modes and code paths." }, { "left": "issue:29159", "right": "issue:34567", "accept": false, - "reason": "Tokenizer inconsistency and TrainerState token-count tracking are unrelated subsystems." + "reason": "Tokenizer inconsistency vs TrainerState token-count tracking. Same broad area only at a high level, but unrelated bugs." }, { "left": "issue:42915", "right": "issue:43742", "accept": false, - "reason": "Qwen3Moe FP8 loading failure vs MobileLLM key error are different model-loading bugs." + "reason": "Qwen3Moe fine-grained FP8 failure vs MobileLLM key error during model loading. Different models and different loading/quantization failures." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "Init-empty-weights argument handling and PIL/torchvision backend requirements are unrelated." + "reason": "Init-empty-weights argument handling vs PIL backend requiring torchvision. Completely different subsystems." }, { "left": "issue:42915", "right": "issue:44821", "accept": false, - "reason": "Qwen3Moe FP8 loading is not the same bug as AutoImageProcessor URL loading." + "reason": "FP8 config failure vs AutoImageProcessor URL loading. Different functionality and error classes." }, { "left": "issue:44849", "right": "issue:45701", "accept": false, - "reason": "Qwen3.5 hidden-state output bug is unrelated to the tokenization-version regression in 45701." + "reason": "Qwen3.5 output_hidden_states bug is a model-specific forward-pass regression, while 45701 is a broad tokenization/version-change complaint." }, { "left": "issue:44568", "right": "issue:45488", "accept": false, - "reason": "Both concern tokenizer behavior, but they affect different tokenizers and different mechanisms (BOS/EOS insertion vs LlamaTokenizer pre-tokenizer override)." + "reason": "mdeberta tokenizer add_special_tokens regression vs LlamaTokenizer overriding ByteLevel with Metaspace. Both tokenizer-related, but distinct tokenizer implementations and behaviors." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "Loading failure for a specific model and CLIPTokenizer max-length behavior are not the same underlying bug." + "reason": "Loading a specific model fails vs CLIPTokenizer max length bug. Not the same issue." }, { "left": "issue:43452", "right": "issue:43582", "accept": false, - "reason": "gguf_file loading breakage and Apple Silicon allocator warmup TypeError are unrelated." + "reason": "gguf_file breaks pretrained loading APIs vs Apple Silicon TypeError in caching_allocator_warmup. Unrelated." }, { - "left": "issue:43697", - "right": "issue:45357", + "left": "issue:41720", + "right": "issue:43540", "accept": false, - "reason": "RTDetr output divergence and Qwen3.5 save_pretrained key corruption are different code paths." + "reason": "Qwen3 auto device map cuda assert vs Qwen3OmniMoe video-input ValueError. Same family name, different concrete failure." }, { - "left": "issue:41720", - "right": "issue:43540", + "left": "issue:43697", + "right": "issue:45357", "accept": false, - "reason": "Auto device-mapping CUDA assert on Qwen3 is unrelated to Qwen3OmniMoe video processing." + "reason": "RTDetrV2 output mismatch in v5 vs Qwen3.5 save_pretrained saving wrong visual encoder keys. Different model behavior and different lifecycle stage." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "Custom token ID persistence and MXFP4 quantization fallback are unrelated." + "reason": "DiaConfig token IDs lost on save/load vs MXFP4 quantization fallback. Different models and unrelated bugs." }, { "left": "issue:42915", - "right": "issue:43749", + "right": "issue:45538", "accept": false, - "reason": "FP8 Qwen3Moe loading and FSDP CPU RAM efficient loading are different bugs." + "reason": "Qwen3Moe FP8 loading failure vs CLIPTokenizer model_max_length bug. No substantive overlap." }, { "left": "issue:44479", "right": "issue:45381", - "accept": true, - "reason": "Both report the same Qwen VL video-input regression in v5.3.0, centered on incorrect video-position handling; they look like the same underlying code-path issue." + "accept": false, + "reason": "Qwen2.5/Qwen3.5 video-input regression vs qwen2.5-vl vision_position_ids wrong. Related family, but one is a broad multi-model regression and the other is a specific positional-ID bug." }, { "left": "issue:33357", "right": "issue:34567", "accept": false, - "reason": "MacOS CLIP bus error and TrainerState token counting are unrelated." + "reason": "MacOS bus error with community CLIP model vs TrainerState token counter bug. Different components and symptoms." }, { "left": "issue:43540", "right": "issue:44479", "accept": false, - "reason": "Qwen3OmniMoe video ValueError and Qwen2.5/3.x VL video regression are different model families and likely different bugs." + "reason": "Qwen3OmniMoe video processing ValueError vs broader v5.3 video-input regression across several model families. Overlapping theme, but not the same concrete bug." }, { "left": "issue:42175", "right": "issue:43824", "accept": false, - "reason": "Packaging/backend dependency inclusion and missing Qwen2_5_VL import are unrelated." + "reason": "TensorFlow missing from torch install vs import error for Qwen2_5_VLForConditionalGeneration. Dependency packaging vs symbol export/import issue." }, { "left": "issue:43540", "right": "issue:44560", "accept": false, - "reason": "Both are Qwen video issues, but they describe different models and different error types." + "reason": "Qwen3OmniMoe video ValueError vs Qwen3-vl-embedding StopIteration in 5.3.0. Different model and different exception path." }, { "left": "issue:43317", "right": "issue:45538", "accept": false, - "reason": "Device-map/offload dequantization failure and CLIP tokenizer max-length behavior are unrelated." + "reason": "device_map=auto dequantized model offload failure vs CLIPTokenizer max length bug. Different code paths." }, { "left": "issue:44062", "right": "issue:44991", "accept": false, - "reason": "AddedToken special-arg duplication and tokenizer loading for est-roberta are different tokenizer bugs." + "reason": "AddedToken special-argument collision vs tokenizer loading failure for est-roberta. Same area, but not the same bug." + }, + { + "left": "issue:24643", + "right": "issue:29159", + "accept": false, + "reason": "DeepSpeed training runtime error about weight dimensionality vs tokenizer slow/fast inconsistency. Unrelated." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "DeepSpeed ZeRO3 deque error and PEFT version bump are unrelated." + "reason": "DeepSpeed ZeRO3 deque error vs PEFT minimum version bump. Completely unrelated." }, { "left": "issue:44987", "right": "issue:45907", "accept": false, - "reason": "Model loading regression and list_repo_files revision forwarding are unrelated." - }, - { - "left": "issue:24643", - "right": "issue:29159", - "accept": false, - "reason": "DeepSpeed training weight-shape error and tokenizer slow/fast inconsistency are unrelated." + "reason": "Model loading failure for physical-intelligence/fast vs list_repo_files not forwarding revision. Different APIs and failures." }, { "left": "issue:28282", "right": "issue:34689", "accept": false, - "reason": "Missing PyTorch import and Llama 3.2 Vision loading regression are different issues." + "reason": "Missing PyTorch ImportError for AutoModel vs Llama 3.2 90B Vision model loading regression. Both are load-time errors, but the causes are different." }, { "left": "issue:43577", "right": "issue:45072", "accept": false, - "reason": "Both mention dtype, but one is BLIP2 loading state and the other is CI inference mismatches in different models." + "reason": "Blip2 dtype staying float32 vs SwitchTransformers/TimmWrapperModel dtype mismatches in bf16 inference. Both dtype-related, but different models and symptoms." }, { - "left": "issue:43257", - "right": "issue:43756", + "left": "issue:43742", + "right": "issue:44291", "accept": false, - "reason": "Qwen3 MOE weight conversion and Smollm3 RoPE-layer count are unrelated." + "reason": "MobileLLM key error while loading a model vs init_empty_weights TypeError from unexpected internal argument. Not the same bug." }, { - "left": "issue:43742", - "right": "issue:44291", + "left": "issue:43257", + "right": "issue:43756", "accept": false, - "reason": "MobileLLM key error and init_empty_weights constructor mismatch are different failures." + "reason": "Qwen3 MoE weight conversion/loading issue vs Smollm3 RoPE layer count mismatch. Different model families and different bug types." }, { "left": "issue:28282", "right": "issue:29127", "accept": false, - "reason": "AutoModel missing PyTorch and LayoutLMv3 error-message clarity are unrelated." + "reason": "PyTorch missing ImportError vs LayoutLMv3 box-information error message clarity. No duplicate signal." }, { "left": "issue:42175", "right": "issue:44488", "accept": false, - "reason": "TensorFlow optional dependency packaging and a specific model-loading failure are unrelated." + "reason": "Packaging dependency omission vs failure to load cjvt/sleng-bert. Different issues." }, { "left": "issue:42915", "right": "issue:43749", "accept": false, - "reason": "Same as the earlier Qwen3Moe FP8 vs FSDP mismatch: different bugs." - }, - { - "left": "issue:38175", - "right": "issue:44898", - "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 and Perceiver image-classification resolution handling are unrelated." + "reason": "Qwen3Moe FP8 failure vs FSDP_CPU_RAM_EFFICIENT_LOADING broken. Both involve advanced loading, but distinct mechanisms and models." }, { "left": "issue:43582", "right": "issue:43782", "accept": false, - "reason": "Apple Silicon allocator TypeError and Qwen3VL weight_only loading error are unrelated." + "reason": "Apple Silicon warmup TypeError vs Qwen3VL weight_only=True error. Different backend and failure mode." }, { - "left": "issue:43540", - "right": "issue:45823", + "left": "issue:38175", + "right": "issue:44898", "accept": false, - "reason": "Qwen3OmniMoe video processing and Gemma4 PLE device mismatch are unrelated." + "reason": "Unexpected zero probabilities in a specific model vs Perceiver non-default resolution failure. Separate model behaviors, not duplicates." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative about the mostly heterogeneous cluster. The lone accepted pair (44479/45381) is plausibly the same Qwen VL video-input regression family, and the other soft-edge rejects do not overclaim duplication." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -5982,7 +6073,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:24643", "issue:29127", @@ -5994,12 +6085,11 @@ "issue:43493", "issue:43526", "issue:43531", + "issue:43540", "issue:43643", - "issue:43688", "issue:43697", "issue:43720", "issue:43742", - "issue:43749", "issue:43756", "issue:43906", "issue:43994", @@ -6028,6 +6118,7 @@ "issue:45479", "issue:45588", "issue:45600", + "issue:45823", "issue:45920", "issue:45987", "issue:46121", @@ -6035,13 +6126,14 @@ ], "soft_pairs": [ "issue:44737|issue:45588", + "issue:43540|issue:45823", "issue:43404|issue:45987", "issue:43526|issue:45479", "issue:43906|issue:45381", "issue:43493|issue:43994", "issue:34567|issue:36331", - "issue:43756|issue:45325", "issue:44291|issue:44821", + "issue:43756|issue:45325", "issue:44913|issue:46121", "issue:44062|issue:45081", "issue:44792|issue:44964", @@ -6058,200 +6150,202 @@ "issue:43697|issue:45216", "issue:43906|issue:46202", "issue:41762|issue:44936", - "issue:43688|issue:43749", "issue:44514|issue:45381" ], - "prepared_review_unit_hash": "b54cd1fabff219749c1fd7104c4fb35a6d09ed42fcba9cafd1123ba56bf47140", + "prepared_review_unit_hash": "667db3c19375eec2524434462e643aecf3f81564776b50f3075753054ac4bd45", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 26, - "serialized_chars": 35911, - "estimated_input_tokens": 8978, - "estimated_eval_tokens": 18212 + "serialized_chars": 35941, + "estimated_input_tokens": 8986, + "estimated_eval_tokens": 18228 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is heterogeneous and the soft pairs mostly share only broad subsystem names, not the same underlying defect. I would not merge any of the proposed soft edges. The most representative issue in the cluster is the broad tokenizer regression in 45920.", - "confidence": 0.24, - "canonical_issue_reason": "issue:45920 is the broadest, most cross-cutting report here: it describes a tokenizer regression affecting several model families, making it a better cluster representative than the many narrow, model-specific bugs.", + "summary": "This cluster is mostly a grab bag of unrelated closed issues across different models/components. The only plausible duplicate pair is the SigLIP2 implementation mismatch vs. user-visible nonsensical outputs; everything else looks distinct and should stay separate.", + "confidence": 0.78, + "canonical_issue_reason": "No single canonical issue fits the whole cluster; if we need one anchor, issue 43493 is the best root-cause-style report for the only likely duplicate pair (SigLIP2).", "canonical_pr_reason": null, - "best_issue_reason": "issue:45920 is the best global representative because it spans multiple affected models and points to a shared code-path regression rather than a one-off model-specific symptom.", + "best_issue_reason": "Issue 43493 is the clearest technical statement of the underlying bug, while 43994 reads more like a downstream symptom/reproduction on the same SigLIP2 path.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44737", "right": "issue:45588", "accept": false, - "reason": "XLNet device-placement work vs a flash-attention auxiliary-loss crash; unrelated code paths." + "reason": "Unrelated problems: XLNet CPU rope indexing vs flash-attention aux-state crash." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Different models and failure modes: Qwen3OmniMoe video processing vs Gemma4 device-mapping mismatch." }, { "left": "issue:43404", "right": "issue:45987", "accept": false, - "reason": "Mistral3 weight tying vs StaticCache sequence-length return type; different bugs." + "reason": "Different subsystems: Mistral3 weight tying vs StaticCache seq-length return type." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "BeitImageProcessorFast label reduction vs sequence-classification loss degeneracy; not the same defect." + "reason": "Unrelated image-label reduction bug vs sequence-classification loss degeneracy." }, { "left": "issue:43906", "right": "issue:45381", "accept": false, - "reason": "An isolated reproduction of another issue vs a Qwen2.5-VL video position-id bug; too different to treat as duplicates." + "reason": "Both involve Qwen/VL themes, but one is a reproduction of another issue and the other is a specific video position-id bug; not enough evidence of the same concrete defect." }, { "left": "issue:43493", "right": "issue:43994", - "accept": false, - "reason": "Both concern SigLIP2, but one is HF-vs-JAX parity and the other is nonsensical pipeline output; not clearly the same code-path bug." + "accept": true, + "reason": "Both point to the same SigLIP2 model correctness problem: HF/JAX discrepancy and broken/nonsensical outputs on the same model family." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "TrainerState token counting vs a custom compute_loss signature error; unrelated trainer issues." + "reason": "Trainer state token counting and custom loss signature incompatibility are different bugs." }, { - "left": "issue:43756", - "right": "issue:45325", + "left": "issue:44291", + "right": "issue:44821", "accept": false, - "reason": "Smollm3 RoPE layer dropping vs Qwen2.5-VL temporal position scaling; distinct model-specific problems." + "reason": "Different areas: init_empty_weights/_is_hf_initialized loading path vs AutoImageProcessor URL loading." }, { - "left": "issue:44291", - "right": "issue:44821", + "left": "issue:43756", + "right": "issue:45325", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized mismatch vs AutoImageProcessor URL loading; different loading paths." + "reason": "Different models and different RoPE-related bugs." }, { "left": "issue:44913", "right": "issue:46121", "accept": false, - "reason": "GPTNeoXConfig reload resetting rotary_pct vs rope-validation TypeError on JSON-loaded lists; different serialization/validation bugs." + "reason": "Config reload defaulting and rope-validation list handling are separate issues." }, { "left": "issue:44062", "right": "issue:45081", "accept": false, - "reason": "AddedToken kwarg duplication vs Mistral regex backend_tokenizer AttributeError; unrelated tokenizer failures." + "reason": "Tokenizer AddedToken argument collision is unrelated to Mistral regex patching." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "janus generation test failure vs Phi-4 multimodal model loading failure; different models and symptoms." + "reason": "Both are multimodal-related, but one is a failing test and the other is a model-loading regression for a different model." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "PIL backend torchvision dependency issue vs Mistral tokenizer regex patch crash; no shared bug." + "reason": "Image processor torchvision dependency issue is unrelated to tokenizer regex crash." }, { "left": "issue:45357", "right": "issue:45920", "accept": false, - "reason": "Qwen3.5 save_pretrained visual-key regression vs tokenizer wrong token IDs across several models; different subsystems." + "reason": "Different regression classes: save_pretrained key serialization vs incorrect token IDs from AutoTokenizer." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "MobileLLM key error vs missing Float8 storage lookup; distinct loading failures." + "reason": "Different load failures: MobileLLM key error vs missing Float8 storage type." }, { "left": "issue:43452", "right": "issue:44488", "accept": false, - "reason": "gguf_file/from_pretrained handling vs failure to load cjvt/sleng-bert; not the same code path." + "reason": "Both are loading issues, but for different models and likely different code paths." }, { "left": "issue:43531", "right": "issue:44821", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior vs AutoImageProcessor URL loading; unrelated." + "reason": "Qwen3-MoE sliding window behavior and AutoImageProcessor URL loading are unrelated." }, { "left": "issue:43643", "right": "issue:45375", "accept": false, - "reason": "Generic trust_remote_code config-field loss vs Qwen3_5MoeVisionConfig strict field dropping; different config issues." + "reason": "Both mention missing config fields, but the former is a generic trust_remote_code AutoConfig issue and the latter is a model-specific @strict field drop; not clearly the same bug." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "Dependency-version bump vs stale auto_mappings references; unrelated maintenance problems." + "reason": "Version-pin/release issue is unrelated to stale auto_mappings references." }, { "left": "issue:44625", "right": "issue:44877", "accept": false, - "reason": "num_labels propagation bug vs granite_speech config loading strictness; different config concerns." + "reason": "num_labels propagation and strict config loading are different configuration bugs." }, { - "left": "issue:43688", - "right": "issue:43749", + "left": "issue:24643", + "right": "issue:29127", "accept": false, - "reason": "Auxiliary-loss normalization vs FSDP CPU RAM efficient loading; unrelated model/training bugs." + "reason": "DeepSpeed training RuntimeError and LayoutLMv3 error-message clarity are unrelated." }, { - "left": "issue:44514", - "right": "issue:45381", + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight loading and Perceiver interpolation failure are different model-specific bugs." + }, + { + "left": "issue:43697", + "right": "issue:45216", "accept": false, - "reason": "Batched chat-template crash vs video vision_position_ids bug; distinct Qwen2.5-VL paths." + "reason": "RTDetrV2 output drift and Qwen3.5 save_pretrained checkpoint corruption are unrelated regressions." }, { "left": "issue:43906", "right": "issue:46202", "accept": false, - "reason": "Reproduction of an external issue vs Gemma pipeline roundtrip failure on a token boundary; not the same underlying bug." + "reason": "No clear shared underlying defect; one is a reproduction of an older issue, the other is a Gemma pipeline roundtrip bug." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "Gemma3 ZeRO-3 loading error vs trainer.evaluate() failing after train(); different lifecycle stages and failures." + "reason": "Gemma3 ZeRO-3 load failure and trainer.evaluate-after-train are unrelated." }, { - "left": "issue:43720", - "right": "issue:44898", - "accept": false, - "reason": "BitNet packed-weight loading bug vs Perceiver interpolation failure; unrelated." - }, - { - "left": "issue:43697", - "right": "issue:45216", - "accept": false, - "reason": "RTDetrV2 output regression vs Qwen3.5 save_pretrained regression; different models and code paths." - }, - { - "left": "issue:43906", + "left": "issue:44514", "right": "issue:45381", "accept": false, - "reason": "Reproduction issue vs Qwen2.5-VL video position-id scaling bug; not the same defect." + "reason": "Same model family, but batched chat-template padding crash is a different code path from wrong video vision_position_ids." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall: the packet is heterogeneous, and the soft-edge rejections are mostly conservative given the available titles. The only accepted pair, issue:43493 / issue:43994, is a reasonable likely duplicate on the same SigLIP2 path based on the titles alone. Minor caveat: the cluster summary says \"closed issues\" even though a few items are open, but that does not materially affect the verdict." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -6266,7 +6360,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:28282", "issue:29159", @@ -6318,24 +6412,25 @@ "issue:46178" ], "soft_pairs": [ + "issue:43688|issue:43749", "issue:45372|issue:46170", - "issue:44466|issue:45005", "issue:43452|issue:43577", + "issue:44466|issue:45005", "issue:44493|issue:46050", "issue:43819|issue:44811", - "issue:43452|issue:44843", "issue:30064|issue:33666", + "issue:43452|issue:44843", "issue:44936|issue:45823", "issue:45542|issue:46178", "issue:44484|issue:44704", - "issue:28282|issue:32090", "issue:43295|issue:45356", + "issue:28282|issue:32090", "issue:43653|issue:44361", "issue:44361|issue:44442", "issue:28282|issue:33357", "issue:44514|issue:45290", - "issue:38175|issue:43295", "issue:44464|issue:44743", + "issue:38175|issue:43295", "issue:28282|issue:35141", "issue:41720|issue:43906", "issue:43653|issue:44568", @@ -6343,214 +6438,226 @@ "issue:43688|issue:45704", "issue:44843|issue:44991", "issue:43646|issue:43749", - "issue:43688|issue:45440", - "issue:29159|issue:33357", "issue:43531|issue:43742", + "issue:29159|issue:33357", + "issue:43688|issue:45440", "issue:43688|issue:45701", "issue:43653|issue:43927" ], - "prepared_review_unit_hash": "ab4bd63918f77fb5ecb320405a4a7250cdcfbb2de872fda6065cbda30c5cb6a1", + "prepared_review_unit_hash": "413774f79871653359b4834ac934b7e853611d94b3f9b3e1aadc669efa9c5f7e", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36841, - "estimated_input_tokens": 9211, - "estimated_eval_tokens": 18678 + "soft_pair_count": 31, + "serialized_chars": 37143, + "estimated_input_tokens": 9286, + "estimated_eval_tokens": 18828 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is noisy and mostly heterogeneous: the soft pairs span unrelated tokenizer, training, model-loading, and device/runtime bugs. I would not merge any of the proposed soft edges.", - "confidence": 0.68, - "canonical_issue_reason": "issue:45701 is the broadest tokenizer-regression report here and has the strongest signal as an umbrella issue for the tokenizer-related subset of this cluster.", + "summary": "This cluster is heterogeneous: most items are distinct bugs across tokenization, loading, training, serialization, and backend detection. I would not merge any of the proposed soft edges as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 45701 is the broadest umbrella in the set, but the cluster is still too mixed to make it a safe duplicate canonical.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45701 is the best single issue to anchor the cluster because it is open, broad, and likely to subsume several tokenizer-version regression reports.", + "best_issue_reason": "Issue 45701 is the best available anchor because it is broad, open, and about tokenizer/version regressions, but it still does not represent the unrelated training/loading/model-init failures in the rest of the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:45372", - "right": "issue:46170", + "left": "issue:43688", + "right": "issue:43749", "accept": false, - "reason": "Different dependency failures: Gemma processor loading vs Windows/ROCm torch.distributed import/type issues." + "reason": "Auxiliary-loss normalization and FSDP CPU RAM loading are different bugs in different code paths." }, { - "left": "issue:44466", - "right": "issue:45005", + "left": "issue:45372", + "right": "issue:46170", "accept": false, - "reason": "Both mention tied weights in v5, but one is a specific lm_head serialization/device bug and the other is a broader translation-model report." + "reason": "Both are import/dependency failures, but they involve different packages, platforms, and root causes." }, { "left": "issue:43452", "right": "issue:43577", "accept": false, - "reason": "Unrelated problems: gguf_file loading breakage vs BLIP2 dtype propagation." + "reason": "gguf_file loading and Blip2 dtype propagation are unrelated failures." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but one is device-dependent serialization and the other is a broader translation-model behavior report; not the same concrete bug." }, { "left": "issue:44493", "right": "issue:46050", "accept": false, - "reason": "Position-id key mismatches are not the same as sinq quantization save/load breakage." + "reason": "Unexpected position-id keys and sinq quantization save/load breakage are different issues." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "Different model paths and symptoms: DAC latent reconstruction vs Whisper batch decode special-token handling." + "reason": "DAC latent mismatch and Whisper batch_decode skip_special_tokens are unrelated code paths." }, { - "left": "issue:43452", - "right": "issue:44843", + "left": "issue:30064", + "right": "issue:33666", "accept": false, - "reason": "Tokenizer/model loading failures, but one is gguf_file-related and the other is an offline mistral-regex cache lookup bug." + "reason": "Void segmentation map processing and Qwen2-VL multi-GPU training are different problems." }, { - "left": "issue:30064", - "right": "issue:33666", + "left": "issue:43452", + "right": "issue:44843", "accept": false, - "reason": "Different domains: image processor segmentation-map handling vs Qwen2-VL multi-GPU training." + "reason": "gguf_file loading and offline mistral-regex patch behavior are separate tokenizer/model-loading bugs." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "Trainer lifecycle bug vs Gemma4 device-map forward mismatch; not the same code path." + "reason": "trainer.evaluate() after train and Gemma4 device-map mismatch are unrelated training/runtime issues." }, { "left": "issue:45542", "right": "issue:46178", "accept": false, - "reason": "Both concern backend detection, but one is TensorFlow/tensorboard setup and the other is tensorflow_text mapping." + "reason": "These are different backend-detection/import problems involving different dependencies." }, { "left": "issue:44484", "right": "issue:44704", "accept": false, - "reason": "save_pretrained shard-size behavior is unrelated to AutoProcessor forwarding kwargs to cached_file." + "reason": "max_shard_size documentation/behavior and cached_file kwargs forwarding are not the same bug." }, { - "left": "issue:28282", - "right": "issue:32090", + "left": "issue:43295", + "right": "issue:45356", "accept": false, - "reason": "ImportError for missing PyTorch is unrelated to Trainer NoneType broadcast errors." + "reason": "Processor/tokenizer regression and Kimi-K2.5 codec handling are distinct tokenizer issues." }, { - "left": "issue:43295", - "right": "issue:45356", + "left": "issue:28282", + "right": "issue:32090", "accept": false, - "reason": "Both are regressions, but one is processor/tokenizer API breakage and the other is Kimi codec/regex handling." + "reason": "Missing PyTorch import and NoneType broadcast errors are unrelated failures." }, { "left": "issue:43653", "right": "issue:44361", "accept": false, - "reason": "BigBird special-token registration bug is unrelated to MLukeTokenizer AttributeError failures." + "reason": "BigBird special-token registration and MLukeTokenizer AttributeError are different tokenizer bugs." }, { "left": "issue:44361", "right": "issue:44442", "accept": false, - "reason": "Different tokenizer implementations and different failure modes; no shared concrete bug." + "reason": "These are different tokenizer-loading failures for different models." }, { "left": "issue:28282", "right": "issue:33357", "accept": false, - "reason": "PyTorch import absence and MacOS bus errors on CLIP are unrelated runtime issues." + "reason": "PyTorch import error and Mac bus error on CLIP are unrelated." }, { "left": "issue:44514", "right": "issue:45290", "accept": false, - "reason": "Both involve apply_chat_template, but the crash conditions differ: batched padding vs tool-call assistant messages." - }, - { - "left": "issue:38175", - "right": "issue:43295", - "accept": false, - "reason": "Siglip2 zero probabilities and processor.tokenizer regression are unrelated issues." + "reason": "Both are chat-template crashes, but they hit different inputs and failure modes, so they are not clearly the same bug." }, { "left": "issue:44464", "right": "issue:44743", "accept": false, - "reason": "Chunked generation with compiled forward is not the same as recurrent state reset in Qwen3-MoE cache handling." + "reason": "Compiled chunked generation inconsistency and Qwen3 modular recurrent-state reset are different generation bugs." }, { - "left": "issue:28282", - "right": "issue:33357", + "left": "issue:38175", + "right": "issue:43295", "accept": false, - "reason": "Missing PyTorch import and community-CLIP bus error are different failures with different triggers." + "reason": "Siglip2 zero probabilities and processor.tokenizer regression are unrelated." }, { - "left": "issue:29159", - "right": "issue:33357", + "left": "issue:28282", + "right": "issue:35141", "accept": false, - "reason": "Slow/fast tokenizer inconsistency is not the same as the MacOS CLIP bus error." + "reason": "Missing PyTorch import and output-embedding reinitialization after resize are different issues." }, { - "left": "issue:43531", - "right": "issue:43742", + "left": "issue:41720", + "right": "issue:43906", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to MobileLLM loading key errors." + "reason": "A device-map cudaErrorAssert and a reproduction issue are not the same concrete bug." }, { "left": "issue:43653", "right": "issue:44568", "accept": false, - "reason": "Both are tokenizer special-token issues, but they affect different models and different mechanics." + "reason": "Both involve special tokens, but they affect different tokenizers and different mechanics." }, { "left": "issue:43577", "right": "issue:43697", "accept": false, - "reason": "BLIP2 dtype casting and RTDetrV2 output divergence are different bugs." + "reason": "Blip2 dtype propagation and RTDetrV2 output divergence are unrelated." }, { "left": "issue:43688", "right": "issue:45704", "accept": false, - "reason": "Auxiliary-loss normalization and apex RMSNorm memory leak are unrelated." + "reason": "Auxiliary-loss normalization and T5 apex RMSNorm memory leak are unrelated." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading regressions, but the root causes and affected models differ." + "reason": "Offline model_info call in the mistral regex patch and tokenizer load failure for est-roberta have different root causes." }, { "left": "issue:43646", "right": "issue:43749", "accept": false, - "reason": "Custom model initialization breakage is not the same as FSDP CPU RAM efficient loading." + "reason": "Custom model initialization breakage and FSDP CPU RAM loading are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and MobileLLM-125M key errors are different model-specific bugs." + }, + { + "left": "issue:29159", + "right": "issue:33357", + "accept": false, + "reason": "Slow/fast tokenizer inconsistency and MacOS bus error are not the same failure." }, { "left": "issue:43688", "right": "issue:45440", "accept": false, - "reason": "Different model families and different failure types: auxiliary-loss math vs DeepSeekV3MoE implementation divergence." + "reason": "Auxiliary-loss normalization and DeepSeekV3 MoE divergence are unrelated model bugs." }, { "left": "issue:43688", "right": "issue:45701", "accept": false, - "reason": "Auxiliary-loss normalization is unrelated to the broad tokenization regression report." + "reason": "A specific auxiliary-loss bug and a broad tokenization-regression report do not match the same underlying issue." }, { "left": "issue:43653", "right": "issue:43927", "accept": false, - "reason": "Special-token registration and DiaConfig save/load custom token ID loss are different bugs." + "reason": "BigBird special-token registration and DiaConfig save/load token-ID loss are different persistence/tokenizer issues." } ] }, @@ -6572,7 +6679,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:28218", "issue:32090", @@ -6637,12 +6744,12 @@ "issue:43504|issue:43550", "issue:43504|issue:43720", "issue:43504|issue:44610", - "issue:44466|issue:46050", "issue:32090|issue:33666", + "issue:44466|issue:46050", "issue:33666|issue:36010", "issue:43742|issue:44821", - "issue:45823|issue:46050", "issue:43720|issue:43927", + "issue:45823|issue:46050", "issue:43606|issue:43927", "issue:43452|issue:44451", "issue:43262|issue:43295", @@ -6657,232 +6764,232 @@ "issue:43493|issue:43825", "issue:28218|issue:33357" ], - "prepared_review_unit_hash": "3fcc6c5a82c56003876caf027180d5ae02392e777fdfc632582c7b20a15799e7", + "prepared_review_unit_hash": "d9f3e1583510069040ed682b12a2b78559e6b25b19b19eb45e423a4ec2ebc44a", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 37049, - "estimated_input_tokens": 9263, - "estimated_eval_tokens": 18782 + "serialized_chars": 37046, + "estimated_input_tokens": 9262, + "estimated_eval_tokens": 18780 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster looks like a broad false-positive mix of unrelated issues: tokenizer spacing, trainer errors, model-loading regressions, dtype/device mismatches, and task-specific model bugs. None of the soft edges looks like the same underlying bug or change.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 43504 is the cleanest concrete loading-regression report to use as an anchor, though this cluster is not a real duplicate set.", + "summary": "This is not a cohesive duplicate cluster: the issues span unrelated bugs across training, loading, config serialization, multimodal processors, attention kernels, and model-specific regressions. The soft-similarity pairs mostly share only broad keywords, not the same concrete code path.", + "confidence": 0.98, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "43504 is the most self-contained and actionable issue here; it has a specific failure mode and is easier to triage than the more model-specific or symptom-only reports.", + "best_issue_reason": "issue:43550 is the strongest standalone report here: it names a specific model, a concrete failure mode (torch.compile with SDPA), and a plausible single code path to fix.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45491", "right": "issue:46002", "accept": false, - "reason": "Both mention NaNs, but one is a Gemma3 sliding-window GPU bug and the other is a classification-head checkout/init issue; different code paths." + "reason": "Both mention NaNs, but one is Gemma3 sliding-window attention on GPU and the other is classification-head NaNs after checkout/init; different symptoms and likely different causes." }, { "left": "issue:43550", "right": "issue:43927", "accept": false, - "reason": "One is a Bamba torch.compile/SDPA failure; the other is a DiaConfig save/load field-loss bug. No shared underlying defect." + "reason": "One is a Bamba torch.compile/SDPA failure; the other is a DiaConfig save/load field-loss bug. No shared code path." }, { "left": "issue:44464", "right": "issue:44977", "accept": false, - "reason": "Both are generation regressions, but they involve different models and different causes (compiled forward vs flash-attention)." + "reason": "Both affect generation, but one is chunked generation with compiled forward and the other is Qwen3.5 flash-attention inference. Too broad to merge." }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "Both touch trust_remote_code, but one is missing fields from AutoConfig and the other is a helper removal breaking remote-code models; not the same bug." + "reason": "Both involve trust_remote_code-adjacent behavior, but one is missing fields in AutoConfig output and the other is a v5 API removal breaking remote-code models. Different fixes." }, { "left": "issue:43550", "right": "issue:44361", "accept": false, - "reason": "A compile/SDPA model bug versus a tokenizer AttributeError on tasks; unrelated." + "reason": "Completely different models and failures: SDPA/compile versus tokenizer AttributeError on tasks." }, { "left": "issue:44479", "right": "issue:44625", "accept": false, - "reason": "Both are Qwen-related, but one is a video-input regression and the other is num_labels propagation." + "reason": "Both are Qwen3.5-related, but one is a video-input regression and the other is num_labels propagation into text config." }, { "left": "issue:41720", "right": "issue:44464", "accept": false, - "reason": "Qwen3 auto-device-map cudaErrorAssert and compiled-forward chunked generation inconsistency are different failures." + "reason": "A CUDA assert in Qwen3 auto device mapping is unrelated to chunked generation output inconsistency under compiled forward." }, { "left": "issue:44977", "right": "issue:46209", "accept": false, - "reason": "Qwen3.5 flash-attention generation issues versus FP8 inference on B200; different code paths." + "reason": "Both are inference bugs, but one is flash-attention behavior in Qwen3.5 and the other is FP8 inference on B200; different paths." }, { "left": "issue:43577", "right": "issue:45588", "accept": false, - "reason": "BLIP2 dtype-loading mismatch and flash_attention.py s_aux=None handling are unrelated." + "reason": "One is dtype drift in BLIP2 loading, the other is a flash_attention integration crash on s_aux=None; unrelated." }, { "left": "issue:32090", "right": "issue:34567", "accept": false, - "reason": "Trainer broadcast TypeError versus TrainerState token-counter not updating; different trainer bugs." + "reason": "Trainer broadcast TypeError and TrainerState token-count tracking are separate training bugs." }, { "left": "issue:43577", "right": "issue:44554", "accept": false, - "reason": "MPS attention correctness and BLIP2 dtype behavior are unrelated." + "reason": "BLIP2 dtype mismatch and an MPS attention correctness issue are different subsystems and failure modes." }, { "left": "issue:43504", "right": "issue:43550", "accept": false, - "reason": "Legacy-field model loading failure is not the same as the Bamba compile/SDPA regression." + "reason": "Beit legacy-field loading and Bamba compile/SDPA are unrelated model-specific bugs." }, { "left": "issue:43504", "right": "issue:43720", "accept": false, - "reason": "Both are loading regressions, but one is a legacy-field preset load issue and the other is packed-weight unpacking during accelerate loading." + "reason": "Legacy config-field loading for Beit is not the same as BitNet packed-weight handling during accelerate loading." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "Model preset loading failure and OmDet processor/model input-size mismatch are different bugs." + "reason": "Beit pretrained-load failure and OmDet processor/model size mismatch are unrelated." }, { - "left": "issue:44466", - "right": "issue:46050", + "left": "issue:32090", + "right": "issue:33666", "accept": false, - "reason": "Tied-weight serialization depending on device and quantized save/load breakage are not the same code-path problem." + "reason": "Both mention training/multi-GPU, but one is a broadcast TypeError and the other is a Qwen2-VL multi-GPU training setup issue." }, { - "left": "issue:32090", - "right": "issue:33666", + "left": "issue:44466", + "right": "issue:46050", "accept": false, - "reason": "Trainer NoneType broadcast and Qwen2-VL multi-GPU training are unrelated." + "reason": "Serialization of tied lm_head weights and sinq quantization save/load breakage are both persistence bugs, but not the same concrete bug." }, { "left": "issue:33666", "right": "issue:36010", "accept": false, - "reason": "Multi-GPU training versus GenerationMixin import failure; different subsystems." + "reason": "Qwen2-VL multi-GPU training and a GenerationMixin import error are unrelated." }, { "left": "issue:43742", "right": "issue:44821", "accept": false, - "reason": "MobileLLM load key error and AutoImageProcessor-from-URL failure are unrelated." + "reason": "MobileLLM loading key error and AutoImageProcessor-from-URL failure are different loading paths." }, { - "left": "issue:45823", - "right": "issue:46050", + "left": "issue:43720", + "right": "issue:43927", "accept": false, - "reason": "Gemma4 device mismatch with device_map='auto' is not the same as sinq quantized save/load breakage." + "reason": "BitNet packed-weight unpacking and DiaConfig custom-token-ID loss are unrelated save/load bugs." }, { - "left": "issue:43720", - "right": "issue:43927", + "left": "issue:45823", + "right": "issue:46050", "accept": false, - "reason": "Packed-weight accelerate loading bug versus DiaConfig missing fields; unrelated." + "reason": "Gemma4 device-map mismatch during forward and sinq quantized model persistence are unrelated." }, { "left": "issue:43606", "right": "issue:43927", "accept": false, - "reason": "CPU-offload device mismatch and config field loss are different bugs." + "reason": "CPU-offload device mismatch in bark-small and DiaConfig field loss after save/load are not the same bug." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "gguf_file/from_pretrained breakage and ScandiBERT load failure are too different to treat as one bug." + "reason": "GGUF loading failures for AutoTokenizer/AutoModel and a specific model load failure are too different to merge." }, { "left": "issue:43262", "right": "issue:43295", "accept": false, - "reason": "Audio apply_chat_template sampling-rate default issue versus processor.tokenizer/image passthrough regression; different APIs." + "reason": "Audio chat-template sample-rate defaulting and a processor.tokenizer/image-input regression are both processor issues but different code paths." }, { "left": "issue:44849", "right": "issue:46209", "accept": false, - "reason": "Qwen3.5 hidden-states bug and FP8 inference failure are unrelated." + "reason": "Qwen3.5 hidden-states bug and FP8 inference failure on B200 are unrelated." }, { "left": "issue:43278", "right": "issue:43688", "accept": false, - "reason": "BF16-to-FP32 dtype drift and auxiliary-loss normalization are different layers of the stack." + "reason": "Embedding dtype drift during evaluate and incorrect auxiliary-loss normalization are unrelated model-train bugs." }, { "left": "issue:43994", "right": "issue:46192", "accept": false, - "reason": "SigLIP2 output quality issue versus return_tensors being ignored with text_kwargs; not the same defect." + "reason": "SigLIP2 bad outputs and return_tensors being ignored when text_kwargs is passed are unrelated." }, { "left": "issue:43525", "right": "issue:43572", "accept": false, - "reason": "Both are missing-pad-token config regressions, but they affect different model configs and field names; no shared concrete bug is shown." + "reason": "Both are config padding-token attribute issues, but for different model configs and different missing-field names; not a single concrete bug." }, { "left": "issue:33666", "right": "issue:36331", "accept": false, - "reason": "Qwen2-VL multi-GPU training and CustomTrainer compute_loss signature mismatch are unrelated." + "reason": "Qwen2-VL multi-GPU training and CustomTrainer.compute_loss signature breakage are different training issues." }, { "left": "issue:43720", "right": "issue:44361", "accept": false, - "reason": "BitNet packed-weight loading and MLukeTokenizer task AttributeError have no common code path." + "reason": "BitNet loading/unpacking and MLukeTokenizer task AttributeError are unrelated." }, { "left": "issue:43756", "right": "issue:44913", "accept": false, - "reason": "Smollm3 RoPE layering bug and GPTNeoX rotary_pct reload bug are both config-adjacent, but not the same underlying issue." + "reason": "Smollm3 RoPE-layer mismatch and GPTNeoXConfig rotary_pct reload regression are both config-related, but not the same underlying bug." }, { "left": "issue:44625", "right": "issue:46002", "accept": false, - "reason": "num_labels propagation and NaNs in classification heads are unrelated." + "reason": "Qwen3.5 num_labels propagation and classification-head NaNs are unrelated." }, { "left": "issue:43493", "right": "issue:43825", "accept": false, - "reason": "SigLIP2 implementation discrepancy and pipeline translation-task messaging are unrelated." + "reason": "SigLIP2 implementation discrepancy and a pipeline translation error-message issue are not the same bug." }, { "left": "issue:28218", "right": "issue:33357", "accept": false, - "reason": "Tokenizer extra-space after added token and MacOS bus error on a CLIP model are unrelated." + "reason": "Tokenizer added-space behavior and a MacOS bus error in CLIP loading are completely unrelated." } ] }, @@ -6904,7 +7011,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:33357", "issue:33666", @@ -6963,12 +7070,12 @@ "issue:43540|issue:44977", "issue:43334|issue:43572", "issue:44488|issue:44843", + "issue:45200|issue:45229", "issue:43493|issue:43844", "issue:43278|issue:43844", - "issue:45200|issue:45229", - "issue:43756|issue:45083", - "issue:39692|issue:43295", "issue:43334|issue:45759", + "issue:39692|issue:43295", + "issue:43756|issue:45083", "issue:43257|issue:43299", "issue:43646|issue:44466", "issue:43824|issue:44589", @@ -6987,20 +7094,20 @@ "issue:43994|issue:44493", "issue:44423|issue:44734" ], - "prepared_review_unit_hash": "1380460df57be53af670159d95aa560322f38a4050a5e5e6ff266196cb904194", + "prepared_review_unit_hash": "1a7faf2eb776ce19006563196a7bcfb8e73f4f804bf6c9603a4d8eeb6b27e605", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36911, + "serialized_chars": 36912, "estimated_input_tokens": 9228, "estimated_eval_tokens": 18712 }, @@ -7009,198 +7116,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: many separate model-specific regressions and config/tokenizer bugs, with only loose topical similarity around Transformers 5.x compatibility and multimodal loading. I would not merge any of the soft pairs as duplicates.", - "confidence": 0.91, - "canonical_issue_reason": "issue:45812 is the broadest and most user-impacting issue here (tokenization regression across Granite models) and is the closest thing to a cluster anchor, though the surrounding issues are not true duplicates of it.", + "summary": "This is a loose, heterogeneous cluster of mostly Transformers v5 regression reports across unrelated model families (Qwen, Gemma, SigLIP, tokenizer/config loading, serving, and CI). Based on the titles alone, none of the soft-edge pairs look like the same concrete bug or change.", + "confidence": 0.69, + "canonical_issue_reason": "Issue 43646 is the broadest representative of the recurring \"v5 breaks model initialization/loading\" theme, but the cluster is too mixed to treat any single issue as a true canonical duplicate target.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45812 is the strongest global representative because it describes a concrete, high-signal regression with broad model impact and multiple references, unlike the mostly isolated model-specific bugs elsewhere in the set.", + "best_issue_reason": "Issue 43646 is the best global representative because it most directly captures the common regression pattern seen across several nearby reports, even though the cluster is not a single bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44964", "right": "issue:45405", "accept": false, - "reason": "Unrelated: model loading failure for Phi-4 multimodal vs an unreleased PEFT version bump." + "reason": "Different problems: one is a model-load failure for Phi-4 multimodal, the other is a dependency/version bump issue for PEFT." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Different bugs: Qwen3.5 hidden-states behavior vs incorrect save_pretrained visual encoder keys." + "reason": "Both involve Qwen3.5, but one is about output_hidden_states behavior and the other about save_pretrained writing wrong visual encoder keys; not the same bug path." }, { "left": "issue:39692", "right": "issue:43493", "accept": false, - "reason": "One is a broken documentation/example flow; the other is a SigLIP2 implementation mismatch vs JAX." + "reason": "SigLIP2 docs/example errors are not the same as a model-vs-JAX implementation discrepancy." }, { "left": "issue:44568", "right": "issue:45812", "accept": false, - "reason": "Both tokenizer-related, but different regressions and models: mDeBERTa special-token insertion vs Granite token IDs." + "reason": "Both concern tokenizer special-token behavior, but one is about mdeberta add_special_tokens and the other is a Granite token-ID regression; too different to merge." }, { "left": "issue:43540", "right": "issue:44977", "accept": false, - "reason": "Different failure paths: Qwen3OmniMoe video-processing ValueError vs Qwen3.5 flash-attention generation issue." + "reason": "Both are Qwen3.5-family issues, but one is a video-input ValueError in Qwen3OmniMoe and the other is flash-attention generation quality; different concrete failures." }, { "left": "issue:43334", "right": "issue:43572", "accept": false, - "reason": "Superficially similar missing config fields, but different models, attributes, and code paths." + "reason": "Both are config attribute-missing regressions, but they affect different configs and fields (pad_token_id vs pad_token_idx) with no evidence of one underlying bug." }, { "left": "issue:44488", "right": "issue:44843", "accept": false, - "reason": "Different subsystems: model loading for sleng-bert vs offline tokenizer patching via model_info()." + "reason": "sleng-bert load failure and HF_HUB_OFFLINE/Mistral regex patch are unrelated code paths." }, { - "left": "issue:43493", - "right": "issue:43844", + "left": "issue:45200", + "right": "issue:45229", "accept": false, - "reason": "SigLIP2 fidelity mismatch and DeepSpeed gradient inflation are unrelated bugs." + "reason": "One is a missing default for mm_token_type_ids, the other is a multi-GPU CUDA OOM; not the same bug." }, { - "left": "issue:43278", + "left": "issue:43493", "right": "issue:43844", "accept": false, - "reason": "Embedding dtype drift in eval vs gradient growth under ZeRO-3 are distinct training issues." + "reason": "SigLIP2 implementation mismatch and a ZeRO-3 gradient increase issue are unrelated." }, { - "left": "issue:45200", - "right": "issue:45229", + "left": "issue:43278", + "right": "issue:43844", "accept": false, - "reason": "Defaulting mm_token_type_ids to zeros is unrelated to Gemma4 multi-GPU OOM." + "reason": "Embedding dtype drift and gradient explosion under DeepSpeed are different training bugs." }, { - "left": "issue:43756", - "right": "issue:45083", + "left": "issue:43334", + "right": "issue:45759", "accept": false, - "reason": "Different models and symptoms: RoPE layer count bug vs a helper-length calculation issue." + "reason": "Qwen3-VL pad_token_id missing and AutoModelForCausalLM not unwrapping text_config are distinct model-loading issues." }, { "left": "issue:39692", "right": "issue:43295", "accept": false, - "reason": "Doc/example mistakes for SigLIP2 are not the same as the processor.tokenizer regression." + "reason": "SigLIP2 example/documentation errors do not match the processor.tokenizer regression in custom model code." }, { - "left": "issue:43334", - "right": "issue:45759", + "left": "issue:43756", + "right": "issue:45083", "accept": false, - "reason": "Both involve multimodal config handling, but one is missing pad_token_id and the other is unwrap-text_config behavior." + "reason": "RoPE-layer count mismatch and a helper-function length calculation issue in qwen3_omni_moe are not the same defect." }, { "left": "issue:43257", "right": "issue:43299", "accept": false, - "reason": "Related family, but different concrete problems: loading/weight conversion under accelerate+deepspeed vs Qwen3VL Moe loading failure." + "reason": "Both mention Qwen3 MoE loading, but one is about accelerate/deepspeed weight conversion and the other is a broader Qwen3VL MoE load failure; insufficient evidence of one code-path bug." }, { "left": "issue:43646", "right": "issue:44466", "accept": false, - "reason": "Custom model initialization breakage and device-dependent lm_head serialization are different regressions." + "reason": "Both are v5-related, but one is custom model initialization and the other is lm_head.weight serialization depending on device; not the same change." }, { "left": "issue:43824", "right": "issue:44589", "accept": false, - "reason": "Importing a missing model class and a Float8 storage lookup failure are unrelated." + "reason": "Qwen2.5-VL import error and Float8 storage lookup failure are unrelated." }, { "left": "issue:33357", "right": "issue:33666", "accept": false, - "reason": "CLIP bus error on macOS and Qwen2-VL multi-GPU training are completely different issues." + "reason": "MacOS bus error in CLIP and Qwen2-VL multi-GPU training are completely different issues." }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Different models and code paths: BEiT legacy-field loading vs bark-small CPU offload device mismatch." + "reason": "BEiT legacy-field loading and bark-small CPU offload device mismatch are unrelated." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "Same model family, but one is OOM during inference and the other is a device-placement mismatch during forward." + "reason": "Both are Gemma4 issues, but one is CUDA OOM during inference and the other is a PLE device mismatch during forward; different bugs." }, { "left": "issue:43927", "right": "issue:44361", "accept": false, - "reason": "Both tokenizer/config related, but the underlying failures and models differ." + "reason": "DiaConfig losing token IDs after save/load and MLukeTokenizer task AttributeError are unrelated." }, { "left": "issue:44589", "right": "issue:45520", "accept": false, - "reason": "Float8 storage type resolution and Python 3.13 flash_attn import metadata are unrelated." + "reason": "Float8 storage-object lookup and flash_attn import KeyError are different failure modes." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "Both are Transformers 5 compatibility problems, but one is a config field rename and the other is an unexpected constructor argument." + "reason": "StableLmConfig missing pad_token_idx and init_empty_weights receiving an unexpected argument are separate compatibility regressions." }, { "left": "issue:44464", "right": "issue:45584", "accept": false, - "reason": "Different generation bugs: compiled-forward chunking inconsistency vs empty-transcription handling in Whisper." + "reason": "Chunked generation with compiled forward and Whisper empty-transcription generation after align_special_tokens are unrelated." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "Embedding dtype drift and resume_from_checkpoint key mismatch do not share the same root cause." + "reason": "Embedding dtype drift in eval and resume_from_checkpoint key mismatch are different problems." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "A real runtime device mismatch vs a stale CI test are not the same underlying bug." + "reason": "CPU offload device mismatch and a stale GraniteSpeech CI test are not the same underlying bug." }, { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "BEiT preset loading and BigBirdTokenizer special-token registration are unrelated." + "reason": "BEiT legacy-field loading and BigBirdTokenizer special-token registration are unrelated." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "TP OOM for a large Qwen model is unrelated to the PEFT version bump issue." + "reason": "Qwen2 large-model TP OOM and a PEFT version bump issue do not share the same code path." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "A failed Janus generation test and an unreleased dependency version bump are unrelated." + "reason": "A janus test failure and a dependency version bump are unrelated." }, { "left": "issue:43994", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 producing bad outputs and widespread unexpected position-id keys are distinct regressions." + "reason": "SigLIP2 wrong outputs with AutoModel/pipeline and unexpected position-id keys are different serialization/loading issues." }, { "left": "issue:44423", "right": "issue:44734", "accept": false, - "reason": "Both are serve/runtime crashes, but one is a multimodal .to() type error and the other is KV-cache indexing; different code paths." - }, - { - "left": "issue:44843", - "right": "issue:45357", - "accept": false, - "reason": "Offline tokenizer patching and incorrect visual-encoder save keys are separate issues." + "reason": "Serve crashes with multimodal models and KV-cache continuation tensor indexing are both serving bugs, but the concrete failure modes are distinct." } ] }, @@ -7222,7 +7323,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:15354", "issue:28218", @@ -7288,9 +7389,9 @@ "issue:45084|issue:45520", "issue:15354|issue:38175", "issue:43540|issue:45200", + "issue:45200|issue:45823", "issue:45072|issue:45198", "issue:37428|issue:43957", - "issue:45200|issue:45823", "issue:43232|issue:44849", "issue:44186|issue:46192", "issue:43493|issue:43701", @@ -7304,208 +7405,208 @@ "issue:37428|issue:43824", "issue:39692|issue:46192" ], - "prepared_review_unit_hash": "89e2a9f82e740b883b1aeb94fb5cbfc79e77a143ae1a914e384ce7cc22901f06", + "prepared_review_unit_hash": "fb0168e1e8442db267d917e8de506a97b472f4317f0247e63831a13615ff8eb9", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36422, - "estimated_input_tokens": 9106, - "estimated_eval_tokens": 18468 + "serialized_chars": 36426, + "estimated_input_tokens": 9107, + "estimated_eval_tokens": 18470 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous; the soft edges are mostly title-level similarities across unrelated bugs, so none of the candidate pairs look like true duplicates or mergeable PR-equivalents.", - "confidence": 0.97, - "canonical_issue_reason": "issue:29159 is the broadest, most representative issue in the set (generic tokenizer inconsistency), but the cluster is too mixed for a strong canonical duplicate.", + "summary": "This cluster is noisy and mostly spans separate transformers bugs around tokenization/processor APIs, multimodal chat templating, generation, quantization, and model loading. None of the soft pairs look like true duplicates; the closest subtheme is apply_chat_template / multimodal tokenization.", + "confidence": 0.34, + "canonical_issue_reason": "issue:44521 is the best cluster anchor because it is a clearly reproduced, user-facing multimodal chat-template/tokenization bug and is the closest semantic match to another soft candidate (45290), while the other items are more peripheral or unrelated.", "canonical_pr_reason": null, - "best_issue_reason": "issue:29159 is the best cluster anchor because it is general and closest to the tokenizer-related subset, even though the overall cluster does not form a single bug family.", + "best_issue_reason": "issue:44521 is the strongest standalone representative of the cluster\u2019s recurring tokenizer/processor surface area, with direct impact, active discussion, and the broadest overlap to the nearby chat-template regression reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43873", "right": "issue:46050", "accept": false, - "reason": "Both mention quantization, but one is about offloading behavior and the other about persistence after save/load; different bugs." + "reason": "Both involve quantization, but one is about offloading behavior and the other about save/load corruption; not the same bug." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Flash Attention test failures and MLflow reporting on failed jobs are unrelated subsystems and failure modes." + "reason": "Unrelated failures: Flash Attention 2 tests vs MLFlow reporting after a failed training job." }, { "left": "issue:45406", "right": "issue:46121", "accept": false, - "reason": "Gemma4Processor missing _tokenizer is unrelated to rope-parameter validation TypeError." + "reason": "Different code paths: Gemma4Processor/_tokenizer regression vs rope-validation TypeError." }, { "left": "issue:45588", "right": "issue:46050", "accept": false, - "reason": "One is a flash-attention integration AttributeError; the other is quantized-model save/load breakage." + "reason": "AttributeError in flash_attention sinkless models is unrelated to quantized model save/load breakage." }, { "left": "issue:42490", "right": "issue:43696", "accept": false, - "reason": "Local-path import warnings and CUDA OOM on GPT-oss-20b are clearly different problems." + "reason": "Local-path import warning and CUDA OOM are unrelated." }, { "left": "issue:43844", "right": "issue:44964", "accept": false, - "reason": "ZeRO-3 gradient growth and Phi-4 multimodal load failure are not the same code-path bug." + "reason": "Different problems: ZeRO-3 gradient growth vs a model loading failure for Phi-4-multimodal-instruct." }, { "left": "issue:28218", "right": "issue:34567", "accept": false, - "reason": "Tokenizer spacing after added tokens is unrelated to TrainerState token-count tracking." + "reason": "Tokenizer spacing bug and TrainerState token count tracking are different features." }, { "left": "issue:29159", "right": "issue:32090", "accept": false, - "reason": "Slow/fast tokenizer inconsistency is unrelated to the Trainer _gpu_broadcast_one NoneType error." + "reason": "Tokenizer consistency issue vs trainer broadcast NoneType error are unrelated." }, { "left": "issue:44521", "right": "issue:45290", "accept": false, - "reason": "Zero assistant masks in multimodal templates and crashes on tool-call messages are different chat-template bugs." + "reason": "Same general apply_chat_template area, but different failure modes: assistant masks vs crash on tool-call messages with no content." }, { "left": "issue:43582", "right": "issue:44977", "accept": false, - "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention generation issues do not share a concrete bug." + "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention generation bug are not the same bug." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "MPS attention correctness and a PyTorch version check/import bug are unrelated." + "reason": "MPS attention correctness vs PyTorch version gating for AuxRequest import are different issues." }, { "left": "issue:45084", "right": "issue:45520", "accept": false, - "reason": "Template-node compilation failure and Python 3.13 flash_attn KeyError are different import/compile paths." + "reason": "Template compilation TypeError and flash_attn import KeyError are unrelated." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "torch.jit.script GeneratorExp export failure and unexpected zero probabilities in SigLIP2 are unrelated." + "reason": "JIT scripting/export limitation and zero-probabilities on SigLIP2 are different bugs." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Qwen3OmniMoe video-processing ValueError and Gemma4 mm_token_type_ids behavior are separate model-specific issues." + "reason": "Video-input processing error in Qwen3OmniMoe vs Gemma4 mm_token_type_ids defaulting issue." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4-related, but one is missing token-type defaults and the other is a device mismatch in forward." }, { "left": "issue:45072", "right": "issue:45198", "accept": false, - "reason": "dtype mismatch in inference and Wav2Vec2 save/tokenization failures are not the same bug." + "reason": "Different subsystems and symptoms: dtype mismatch in inference vs save_pretrained/tokenization failure." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "Flash-attention utility import error and meta-device model loading breakage are distinct loading issues." - }, - { - "left": "issue:45200", - "right": "issue:45823", - "accept": false, - "reason": "Gemma4 defaulting mm_token_type_ids and PLE device mismatch under device_map=auto are different failures." + "reason": "Flash-attention import error and meta-device loading breakage are separate runtime issues." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs after sync_gpus and Qwen3.5 output_hidden_states behavior are separate generation bugs." + "reason": "Generation kwargs update after sync_gpus is unrelated to the Qwen3.5 output_hidden_states bug." }, { "left": "issue:44186", "right": "issue:46192", "accept": false, - "reason": "LayoutLMv2Tokenizer crashes on NER/padding and return_tensors being ignored are unrelated tokenizer API issues." + "reason": "LayoutLMv2 tokenizer crash on NER/padding is not the same as return_tensors being ignored when text_kwargs is passed." }, { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "SigLIP2 implementation discrepancy and resume_from_checkpoint key mismatch are not the same code path." + "reason": "SigLIP2 implementation discrepancy and resume_from_checkpoint key mismatch do not share the same code path." }, { "left": "issue:45381", "right": "issue:46209", "accept": false, - "reason": "Qwen2.5-VL video position IDs and FP8 inference on B200 are different model/hardware problems." + "reason": "Wrong video vision_position_ids in Qwen2.5-VL is unrelated to FP8 inference failure on B200." }, { "left": "issue:45823", "right": "issue:46192", "accept": false, - "reason": "Gemma4 device placement and return_tensors handling are unrelated regressions." + "reason": "Gemma4 device placement mismatch and return_tensors precedence bug are different issues." }, { "left": "issue:43295", "right": "issue:43450", "accept": false, - "reason": "Gemma4Processor _tokenizer regression and batched video shape handling are different processor issues." + "reason": "Processor.tokenizer regression/passing images to tokenizer and batched video shape errors are distinct multimodal bugs." }, { "left": "issue:43295", "right": "issue:44610", "accept": false, - "reason": "Same as above: processor tokenizer access vs OmDet-Turbo image-size mismatch are unrelated." + "reason": "These are both processor/model mismatches, but they affect different models and different failure modes." }, { "left": "issue:43572", "right": "issue:44987", "accept": false, - "reason": "StableLmConfig missing pad_token_idx and transformers>=5.1.0 loading fast are different versioning/loading failures." + "reason": "Missing pad_token_idx in config and a model-loading regression for physical-intelligence/fast are unrelated." }, { "left": "issue:44554", "right": "issue:45356", "accept": false, - "reason": "MPS attention correctness bug and Kimi-K2.5 tokenizer regression are unrelated." + "reason": "MPS attention correctness issue and Kimi-K2.5 tokenizer regression are not the same bug." }, { "left": "issue:43572", "right": "issue:43957", "accept": false, - "reason": "Missing pad_token_idx and meta-device loading failures do not describe the same defect." + "reason": "Config default regression and meta-device loading failures are different problems." }, { "left": "issue:37428", "right": "issue:43824", "accept": false, - "reason": "A missing flash-attention import symbol and a missing Qwen model class import are distinct import errors." + "reason": "flash_attention_utils import error and Qwen2_5_VL import error are separate import regressions." }, { "left": "issue:39692", "right": "issue:46192", "accept": false, - "reason": "SigLIP2 documentation/example errors are unrelated to return_tensors being ignored when text_kwargs is passed." + "reason": "SigLIP2 docs/example errors and a generic return_tensors precedence bug are not duplicates." } ] }, @@ -7527,7 +7628,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:28218", "issue:35141", @@ -7586,9 +7687,9 @@ "issue:44898|issue:45412", "issue:44466|issue:45127", "issue:43334|issue:43525", + "issue:43450|issue:43575", "issue:44792|issue:45563", "issue:43824|issue:43975", - "issue:43450|issue:43575", "issue:41720|issue:46209", "issue:42915|issue:43824", "issue:43388|issue:43526", @@ -7601,216 +7702,198 @@ "issue:43975|issue:45520", "issue:44442|issue:45198", "issue:38175|issue:45412", - "issue:45520|issue:46170", "issue:44514|issue:44521", + "issue:45520|issue:46170", "issue:43262|issue:43450", "issue:44206|issue:45584", - "issue:43827|issue:43901", "issue:43819|issue:44112", + "issue:43827|issue:43901", "issue:44610|issue:44857" ], - "prepared_review_unit_hash": "93acfbd16f6cb607b323d2e8bfe4260f7147f40c15fbd1022929cdf37a13f6d0", + "prepared_review_unit_hash": "3df6e8d5b52176db8fbe94b0e645a12a82145efa868c4954d5a7cf2a6e1fc256", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36622, - "estimated_input_tokens": 9156, - "estimated_eval_tokens": 18568 + "serialized_chars": 36620, + "estimated_input_tokens": 9155, + "estimated_eval_tokens": 18566 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous; none of the soft pairs look like true duplicates, so I rejected all of them. The only weakly central issue is the import/backend failure around `flash_attn` (45520), but even that is just the best representative of a noisy cluster, not a real duplicate hub.", - "confidence": 0.76, - "canonical_issue_reason": "Issue 45520 is the most connected item in the set and is a concrete, reproducible bug report; it is the closest thing to a cluster anchor, though the surrounding issues are still unrelated.", + "summary": "This cluster is mostly heterogeneous single-issue reports rather than a true duplicate set. None of the soft pairs look like the same concrete bug/change, so I would not merge any of them.", + "confidence": 0.69, + "canonical_issue_reason": "Issue 44521 is the most representative issue here: it has the strongest activity/attention and is the closest to the only nearby Qwen2.5-VL processor/chat-template candidate.", "canonical_pr_reason": null, - "best_issue_reason": "45520 is the clearest and most central issue to use as a representative for this noisy cluster, but it should not be treated as a true duplicate canonical without stronger evidence.", + "best_issue_reason": "Issue 44521 is the best overall representative of the cluster because it is active, user-facing, and sits in the clearest adjacent area to one other item in the set (`apply_chat_template`/multimodal processor behavior).", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45200", "right": "issue:45325", "accept": false, - "reason": "Different bugs in different multimodal paths: Gemma 4 text-only token-type defaults vs Qwen2.5-VL temporal position scaling." + "reason": "Different bugs: Gemma 4 multimodal token-type IDs vs Qwen2.5-VL still-image rope/position scaling." }, { "left": "issue:45520", "right": "issue:46178", "accept": false, - "reason": "Both are import/backend-related, but they hit different backend symbols and different failure modes; not the same underlying bug." + "reason": "Unrelated import/backend failures in different code paths: `flash_attn` on Python 3.13 vs `tensorflow_text` backend mapping." }, { "left": "issue:43295", "right": "issue:43873", "accept": false, - "reason": "One is a processor API regression, the other is quantization/offloading behavior; too far apart." + "reason": "Processor regression around `processor.tokenizer`/image passing is unrelated to quantization offloading behavior." }, { "left": "issue:43550", "right": "issue:43844", "accept": false, - "reason": "Different code paths and symptoms: torch.compile with SDPA vs ZeRO-3 gradient blow-up." + "reason": "Different failure modes: `torch.compile` + SDPA on Bamba vs DeepSpeed ZeRO-3 gradient growth." }, { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Unrelated issues: Perceiver resize/interpolation failure vs RT-DETR memory not being freed." + "reason": "One is a Perceiver resolution/interpolation bug; the other is a memory release/GC issue for RT-DETR." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "Both mention tied weights, but one is device-dependent serialization of `lm_head.weight` and the other is LoRA merge collapse with extended vocab; not the same bug." + "reason": "Both involve tied weights, but one is device-dependent serialization of `lm_head.weight`; the other is LoRA merge collapse with extended vocab." }, { "left": "issue:43334", "right": "issue:43525", "accept": false, - "reason": "Same broad symptom (`pad_token_id` missing), but for different model configs and likely different fixes." + "reason": "Same symptom class (`pad_token_id` missing) but different models/config paths; not the same concrete bug." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batched video processor shape bug is unrelated to Qwen2-57B tensor-parallel OOM." }, { "left": "issue:44792", "right": "issue:45563", "accept": false, - "reason": "Different failures: a Janus image-generation test vs a stale paged-generate warning." + "reason": "Different subsystems: Janus image-generation test failure vs stale paged-generate warning." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "Import error for a missing model class vs detokenization regression in DeepSeek Coder; no shared code-path evidence." - }, - { - "left": "issue:43450", - "right": "issue:43575", - "accept": false, - "reason": "Video processor batching shape bug vs tensor-parallel OOM on a large model; unrelated." + "reason": "ImportError for Qwen2.5-VL class is unrelated to DeepSeek detokenization regression." }, { "left": "issue:41720", "right": "issue:46209", "accept": false, - "reason": "Both are hardware-specific inference failures, but on different models and different accelerator constraints; not mergeable as one fix." + "reason": "Both are hardware-related inference failures, but they affect different models and different failure mechanisms." }, { "left": "issue:42915", "right": "issue:43824", "accept": false, - "reason": "Qwen3MoE FP8 failure and Qwen2.5-VL import error are unrelated." + "reason": "Qwen3Moe FP8 failure is unrelated to the missing Qwen2.5-VL import." }, { "left": "issue:43388", "right": "issue:43526", "accept": false, - "reason": "Both concern labels, but one is metric gathering dropping tuple elements and the other is BeitImageProcessorFast reducing labels incorrectly; different behaviors." + "reason": "Both are label-processing issues, but one is `gather_for_metrics` dropping tuple labels and the other is `reduce_labels` returning only one label." }, { "left": "issue:42490", "right": "issue:43493", "accept": false, - "reason": "Path-trailing-slash import warning is unrelated to SigLIP2 implementation discrepancies." + "reason": "Trailing-slash import warning and SigLIP2 implementation discrepancy are unrelated." }, { "left": "issue:43278", "right": "issue:43856", "accept": false, - "reason": "Training/eval dtype mismatch vs MoE memory inefficiency; different defects." + "reason": "Embedding dtype regression in evaluation is not the same as MoE training memory inefficiency." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing after added tokens and embedding reinitialization after resize are different issues." + "reason": "Tokenizer spacing after added token and embedding reinitialization after resize are different bugs." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug vs GraniteSpeech CI test staleness; not the same bug." + "reason": "BigBirdTokenizer special-token registration bug is unrelated to a GraniteSpeech CI device-override test failure." }, { "left": "issue:38175", "right": "issue:43493", "accept": false, - "reason": "Both mention SigLIP2, but one is a specific zero-probability symptom and the other is a broader HF-vs-JAX discrepancy; insufficient evidence of one underlying bug." + "reason": "Both mention SigLIP2, but one reports zero probabilities and the other a broader HF-vs-JAX discrepancy; not enough to treat as the same bug." }, { "left": "issue:43526", "right": "issue:46192", "accept": false, - "reason": "Label reduction bug and `return_tensors` being ignored are unrelated processor issues." + "reason": "Different API bugs: `reduce_labels` truncation vs `return_tensors` being ignored when `text_kwargs` is passed." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "Detokenization regression in a model tokenizer is unrelated to the `flash_attn` import_utils KeyError." + "reason": "Detokenization regression and `flash_attn` import error are unrelated." }, { "left": "issue:44442", "right": "issue:45198", "accept": false, - "reason": "AutoTokenizer loading failure for one tokenizer and save_pretrained/tokenization failure for another are separate tokenizer bugs." - }, - { - "left": "issue:38175", - "right": "issue:45412", - "accept": false, - "reason": "SigLIP2 zero-probabilities bug vs RT-DETR memory cleanup bug; unrelated." - }, - { - "left": "issue:45520", - "right": "issue:46170", - "accept": false, - "reason": "Different dependency/import problems: `flash_attn` backend mapping vs torch.distributed on Windows/ROCm." + "reason": "Different speech-model failures: tokenizer loading vs save_pretrained/tokenization failure." }, { "left": "issue:44514", "right": "issue:44521", "accept": false, - "reason": "Both touch `apply_chat_template`, but one crashes on batched padding=False input and the other returns zero assistant masks; different concrete failures." + "reason": "Both are Qwen2.5-VL `apply_chat_template` issues, but one is a batching/padding crash and the other is incorrect all-zero assistant masks; not the same concrete bug." }, { "left": "issue:43262", "right": "issue:43450", "accept": false, - "reason": "Audio processor sample-rate defaulting and batched video processor shapes are unrelated." + "reason": "Audio chat-template sample-rate default bug is unrelated to video processor batched-shape output." }, { - "left": "issue:44206", - "right": "issue:45584", + "left": "issue:43819", + "right": "issue:44112", "accept": false, - "reason": "Feature extractor `center` arg crash and Whisper empty-transcription generation failure are different code paths." + "reason": "DAC latent/forward mismatch is unrelated to the GraniteSpeech CI test flake." }, { "left": "issue:43827", "right": "issue:43901", "accept": false, - "reason": "Both are docs regressions around pipeline deprecations, but they refer to different pages and API details; too broad to merge as one fix." - }, - { - "left": "issue:43819", - "right": "issue:44112", - "accept": false, - "reason": "DAC latent/forward mismatch is unrelated to a GraniteSpeech CI test issue." + "reason": "Both are docs-related, but one is about removed `pipeline()` references and the other about `return_all_scores`; different content." }, { "left": "issue:44610", "right": "issue:44857", "accept": false, - "reason": "Different model families and failures: OmDet-Turbo input-size mismatch vs LwDetr AMP/CUDA crash." + "reason": "Processor output resolution mismatch and AMP/CUDA loss crash are different bugs." } ] }, @@ -7832,7 +7915,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:29127", "issue:29942", @@ -7895,12 +7978,12 @@ "issue:37428|issue:44351", "issue:45290|issue:45381", "issue:45200|issue:45588", - "issue:43278|issue:43825", "issue:43335|issue:43653", "issue:43611|issue:43931", "issue:44206|issue:45823", "issue:43550|issue:44112", "issue:43819|issue:44493", + "issue:43278|issue:43825", "issue:44855|issue:45083", "issue:43335|issue:43504", "issue:45588|issue:45859", @@ -7919,238 +8002,244 @@ "issue:43606|issue:44857", "issue:34689|issue:35141" ], - "prepared_review_unit_hash": "3ed5a871e59065f61a6c0c8dbbb4af2b1be0a50e6163bfc081a226e5b14d244d", + "prepared_review_unit_hash": "48cf2da9cc5e96143b088fcb8becdaee0e06116e9e243412dd54a9c3cd249034", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 38095, - "estimated_input_tokens": 9524, - "estimated_eval_tokens": 19304 + "serialized_chars": 38091, + "estimated_input_tokens": 9523, + "estimated_eval_tokens": 19302 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated issues with only one clear duplicate pair: the Qwen3.5 Moe from_pretrained regression (#45310 and #45478). All other soft edges look like different bugs or different code paths and should be rejected.", - "confidence": 0.94, - "canonical_issue_reason": "issue:45310 is the earlier, fuller report of the only clear duplicate pair and cleanly captures the Qwen3.5 Moe from_pretrained regression.", + "summary": "This cluster is mostly a set of unrelated issues; the only clear duplicate pair is the Qwen3.5 MoE from_pretrained regression. I would keep the earlier report as canonical.", + "confidence": 0.95, + "canonical_issue_reason": "Issue 45310 is the earlier report of the same Qwen3.5 MoE from_pretrained failure as 45478, with identical title and the same concrete regression.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the best issue anchor because it is the strongest true duplicate target in the set; the rest are heterogeneous and do not form a coherent duplicate cluster.", + "best_issue_reason": "45310 is the best issue to keep as the canonical representative because it is the first report of the duplicated Qwen3.5 MoE loading bug and already captures the core failure mode.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "Different model subsystems and failure modes: DAC latents/STE mismatch vs qwen3_omni_moe feature length helper behavior." + "reason": "Different models and failures: DAC latent decoding/STE mismatch vs a Qwen3-Omni helper length computation issue." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "One is an import error for a missing symbol; the other is a broad torch version compatibility complaint." + "reason": "One is an import error for a flash-attention helper; the other is a broad Torch 2.10 compatibility issue." }, { "left": "issue:43335", "right": "issue:43550", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug vs Bamba torch.compile/SDPA failure; unrelated code paths." + "reason": "SwitchTransformers sparse-layer config bug and Bamba torch.compile/SDPA failure are unrelated code paths." }, { "left": "issue:43606", "right": "issue:45083", "accept": false, - "reason": "CPU offload device mismatch in bark-small vs a qwen3_omni_moe helper-function behavior issue." + "reason": "CPU offload device mismatch in Bark-small is unrelated to the Qwen3-Omni output-length helper bug." }, { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "Float16 AMP crash in LwDetrImageLoss is unrelated to D-FINE missing auxiliary losses." + "reason": "Float16 AMP crash in LwDetrImageLoss is not the same bug as D-FINE skipping auxiliary losses." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention 2 test failures vs Trainer/_gpu_broadcast_one NoneType error are different bugs." + "reason": "Flash Attention 2 test failures and a Trainer NoneType broadcast error are different failures." }, { "left": "issue:44448", "right": "issue:44743", "accept": false, - "reason": "Pegasus output regression across versions vs recurrent state reset in qwen3 modular code; different mechanisms." + "reason": "Pegasus v4/v5 output differences and Qwen3 recurrent-state reset are separate model-specific regressions." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA/extended-vocab collapse is unrelated to the 2^24 category limit error." + "reason": "LoRA/vocab merge collapse and category-count overflow are unrelated problems." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Both are import-related, but they involve different missing symbols and different breakages." + "reason": "Both are import-related, but they concern different missing symbols and different breakages." }, { "left": "issue:45290", "right": "issue:45381", "accept": false, - "reason": "Chat template tool-call crash vs qwen2.5-vl video vision_position_ids mismatch; not the same bug." + "reason": "Chat-template tool-call crash and Qwen2.5-VL vision position-id bug are unrelated." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma4 mm_token_type_ids defaulting issue is unrelated to flash_attention s_aux=None crashes." - }, - { - "left": "issue:43278", - "right": "issue:43825", - "accept": false, - "reason": "Embedding dtype drift during eval vs pipeline translation-task warning; different API surfaces." + "reason": "Gemma4 text-only mm_token_type_ids handling and flash_attention sink-less s_aux handling are different code paths." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "Sparse layer misconfiguration in SwitchTransformers vs BigBirdTokenizer special-token registration problem." + "reason": "SwitchTransformers sparse-layer config and BigBirdTokenizer special-token registration are unrelated." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "Base model prefix loading regression is unrelated to Qwen3-VL weight-shape mismatch." + "reason": "base_model_prefix loading breakage and Qwen3-VL weight-shape mismatch are different model-loading issues." }, { "left": "issue:44206", "right": "issue:45823", "accept": false, - "reason": "LaserFeatureExtractor center-arg regression vs Gemma4 PLE device mismatch; different failures." + "reason": "Unsupported center arg in an audio feature extractor is unrelated to Gemma4 PLE device mismatch." }, { "left": "issue:43550", "right": "issue:44112", "accept": false, - "reason": "Bamba torch.compile SDPA bug vs GraniteSpeech stale device-override CI failure are unrelated." + "reason": "Bamba torch.compile/SDPA failure and GraniteSpeech stale device-override test are not the same bug." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "DAC forward/from_latents mismatch is not the same as unexpected position-id key warnings." + "reason": "DAC STE mismatch and unexpected position-id keys are different symptoms and code paths." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift in evaluate and a pipeline translation-task warning are unrelated regressions." }, { "left": "issue:44855", "right": "issue:45083", "accept": false, - "reason": "Python 3.13 IndentationError in DebertaV2 import is unrelated to qwen3_omni_moe output-length helper behavior." + "reason": "DebertaV2 Python 3.13 import parsing error and Qwen3-Omni helper behavior are unrelated." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "SwitchTransformers sparse-layer creation bug vs Beit semantic-segmentation preset loading issue; different models and causes." + "reason": "SwitchTransformers sparse-layer creation bug and BEiT legacy-field loading bug are not the same issue." }, { "left": "issue:45588", "right": "issue:45859", "accept": false, - "reason": "Both touch flash/offload behavior, but one is an AttributeError on s_aux=None and the other is CPU offload incompatibility in rotary embedding." + "reason": "Both touch offload/attention-adjacent logic, but they fail in different modules with different root causes." }, { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "LayoutLMv3 error-message clarity issue vs trainer NoneType broadcast crash; different underlying bugs." + "reason": "LayoutLMv3 error-message clarity and Trainer broadcast TypeError are unrelated." }, { "left": "issue:43335", - "right": "issue:45072", + "right": "issue:45083", "accept": false, - "reason": "SwitchTransformers sparse-layer bug vs dtype mismatches in bfloat16 inference; not the same defect." + "reason": "SwitchTransformers sparse-layer config and Qwen3-Omni feature-length helper are unrelated." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "SigLIP2 docs/example errors are unrelated to BeitImageProcessorFast reduce_labels returning the wrong labels." + "reason": "SigLIP2 doc/example problems and BeitImageProcessorFast label reduction are unrelated." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "Documentation/example failures vs position-id key regression; different artifacts and code paths." + "reason": "Documentation/model-processor mismatch and unexpected position-id keys are different issues." }, { "left": "issue:45310", "right": "issue:45478", "accept": true, - "reason": "Same title, same model family, same from_pretrained error; clear duplicate reports of the same regression." + "reason": "Same title, same model family, same from_pretrained regression, and both describe the same loading failure." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "BitNet packed-weight unpacking failure is unrelated to GraniteSpeech CI device-override staleness." + "reason": "BitNet packed-weight loading and GraniteSpeech CI device-override failures are unrelated." }, { "left": "issue:43335", "right": "issue:44112", "accept": false, - "reason": "Different areas entirely: SwitchTransformers config vs GraniteSpeech CI." + "reason": "SwitchTransformers config bug and GraniteSpeech CI failure do not share a concrete root cause." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and bfloat16 dtype mismatch in inference are unrelated." }, { "left": "issue:44448", "right": "issue:44779", "accept": false, - "reason": "Pegasus v4/v5 output change is not the same as DeepSeek tokenizer tokenization regression." + "reason": "Pegasus output change and DeepSeek tokenizer regression are different model-specific v5 regressions." }, { "left": "issue:44360", "right": "issue:44561", "accept": false, - "reason": "DSA indexer lacking ReLU vs removal of is_torch_fx_available; unrelated breakages." + "reason": "DSA indexer activation discussion and removal of is_torch_fx_available breakage are not the same bug." }, { "left": "issue:42490", "right": "issue:43854", "accept": false, - "reason": "Local-model path import warning vs failing to load GLM-4.7-Flash in unit tests; different issues." + "reason": "Local-path trailing-slash import warning and GLM-4.7-Flash unit-test loading failure are unrelated." }, { "left": "issue:45920", "right": "issue:46192", "accept": false, - "reason": "AutoTokenizer wrong token IDs across models vs return_tensors being ignored when text_kwargs is passed; similar API area but different bugs." + "reason": "Tokenizer ID regressions across many models and return_tensors being ignored with explicit text_kwargs are different issues." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "CPU offload device mismatch in Bark-small vs float16 AMP crash in LwDetrImageLoss; not the same code path." + "reason": "CPU offload device mismatch and float16 AMP loss crash are different failure modes." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Model loading regression for Llama 3.2 Vision is unrelated to embedding reinitialization after resizing." + "reason": "Llama 3.2 Vision model-loading breakage and post_init reinitializing tied embeddings are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The assessment is grounded in the packet and stays conservative on soft-edge pairs. The only clearly supported duplicate pair is issue:45310 with issue:45478, which share the same title and model-specific from_pretrained regression. The rest of the pair rejections are consistent with the titles/bodies and do not overstate the evidence." + "feedback": "The summary is grounded in the packet: the only clearly supported duplicate pair is issue:45310 and issue:45478, which share the same title and the same Qwen3.5 MoE from_pretrained regression. The soft-edge verdicts are conservative and stay within the evidence provided, mostly rejecting pairs as unrelated without overclaiming. No PR-pair mergeability concerns apply here." }, "evaluator_used": true, "retried": false, @@ -8169,7 +8258,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:10000", "issue:15354", @@ -8195,7 +8284,6 @@ "issue:43746", "issue:43873", "issue:43927", - "issue:43976", "issue:44448", "issue:44462", "issue:44493", @@ -8212,12 +8300,12 @@ "issue:45229", "issue:45372", "issue:45406", - "issue:45440", "issue:45491", "issue:45563", "issue:45588", "issue:45698", "issue:45803", + "issue:45823", "issue:46209" ], "soft_pairs": [ @@ -8225,235 +8313,241 @@ "issue:44977|issue:45229", "issue:44857|issue:45072", "issue:43746|issue:46209", - "issue:40444|issue:43526", "issue:44448|issue:44977", + "issue:40444|issue:43526", "issue:28218|issue:32090", "issue:43701|issue:45083", "issue:32090|issue:33357", "issue:29942|issue:35141", "issue:43550|issue:45083", "issue:43723|issue:44554", - "issue:44561|issue:44779", "issue:37428|issue:44987", - "issue:43927|issue:45698", + "issue:44561|issue:44779", "issue:43873|issue:45229", + "issue:43927|issue:45698", "issue:44462|issue:44561", "issue:43278|issue:43329", "issue:42490|issue:43575", "issue:10000|issue:15354", "issue:41720|issue:45229", "issue:44977|issue:45563", - "issue:44568|issue:45491", "issue:45372|issue:45588", + "issue:44568|issue:45491", "issue:44857|issue:45588", "issue:43412|issue:45588", "issue:45198|issue:45803", "issue:45372|issue:45406", "issue:43278|issue:43381", - "issue:43976|issue:45440" + "issue:45588|issue:45823" ], - "prepared_review_unit_hash": "4548fdb31031631ecb74d141f908fc81a76b4989bbbf10f1900867dadf49b5d4", + "prepared_review_unit_hash": "3501a7cbe037eb3adae7942ff13c9ceddf5677c85bb5ba052415ef00b46ff028", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36797, - "estimated_input_tokens": 9200, - "estimated_eval_tokens": 18656 + "serialized_chars": 36251, + "estimated_input_tokens": 9063, + "estimated_eval_tokens": 18382 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous: the soft-linked issues span unrelated tokenizer, model-loading, attention, quantization, export, and runtime errors. None of the soft pairs look like the same underlying bug or change.", - "confidence": 0.98, - "canonical_issue_reason": "No canonical issue: the linked issues cover different codepaths and symptoms, so there is no single representative duplicate target.", + "summary": "The soft pairs are mostly broad semantic matches rather than true duplicate bugs; I would reject all of them. The strongest standalone issue in the set looks like 43873 because it is open and has the most inbound discussion, while 45698 is the clearest self-contained bug report.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43873 is the best canonical anchor here: it is open, has the highest discussion/inbound-reference signal in the set, and describes a broadly relevant user-facing bug that can absorb related reports.", "canonical_pr_reason": null, - "best_issue_reason": "No global best issue: nothing here clearly serves as an umbrella for the cluster, because the soft edges do not indicate a shared root cause.", + "best_issue_reason": "issue:45698 is the most clearly written standalone bug report with a concrete failure mode in from_pretrained/save_pretrained, so it is the best single issue for a reader to understand and act on quickly.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "Different problems: one is model-specific zero probabilities, the other is a position-id key warning across many models." + "reason": "Both mention incorrect model outputs, but one is siglip2 zero probabilities and the other is a position-id key warning; different symptoms and likely different code paths." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Flash-attention generation failure and multi-GPU CUDA OOM are distinct runtime issues." + "reason": "Flash-attention generation failure for Qwen3.5 and multi-GPU CUDA OOM for Gemma4 are unrelated bugs." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Separate dtype/backend regressions in different models and codepaths; not the same bug." + "reason": "AMP/CUDA crash in a loss module and bfloat16 dtype mismatches in inference are distinct issues." }, { "left": "issue:43746", "right": "issue:46209", "accept": false, - "reason": "Local checkpoint loading with PEFT adapters is unrelated to FP8 inference failing on B200." + "reason": "PEFT/local checkpoint loading for GraniteSpeech and FP8 inference failure on B200 are different problems." }, { - "left": "issue:40444", - "right": "issue:43526", + "left": "issue:44448", + "right": "issue:44977", "accept": false, - "reason": "Multimodal iterable-dataset batching failure is not the same as BEiT processor label reduction." + "reason": "Version-to-version output drift for Pegasus and a flash-attention generation failure for Qwen3.5 are not the same underlying bug." }, { - "left": "issue:44448", - "right": "issue:44977", + "left": "issue:40444", + "right": "issue:43526", "accept": false, - "reason": "Pegasus v4/v5 output drift and Qwen flash-attention generation failure are different defects." + "reason": "IterableDataset multi-image finetuning failure and BeitImageProcessorFast label reduction are unrelated data-processing bugs." }, { "left": "issue:28218", "right": "issue:32090", "accept": false, - "reason": "Tokenizer spacing after added tokens has nothing to do with Trainer GPU broadcast NoneType errors." + "reason": "Tokenizer spacing after added tokens has no overlap with Trainer broadcast TypeError." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint resume key mismatch is unrelated to the qwen3_omni_moe helper-function bug." + "reason": "Checkpoint resume key mismatch and an omni-moe feature-length helper bug are different code paths." }, { "left": "issue:32090", "right": "issue:33357", "accept": false, - "reason": "Trainer broadcast NoneType and MacOS bus error on CLIP are different failure modes." + "reason": "Trainer NoneType broadcast error and MacOS bus error with a CLIP model do not describe the same failure." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "FlashAttention test failures and embedding reinitialization after resize are unrelated." + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization after resizing token embeddings." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is not the same as undefined helper names in qwen3_omni_moe." + "reason": "torch.compile SDPA failure in Bamba and a helper-function logic bug in qwen3_omni_moe are different." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "AutoTokenizer v5 loading behavior and an MPS attention correctness issue are different problems." - }, - { - "left": "issue:44561", - "right": "issue:44779", - "accept": false, - "reason": "Removal of an internal utility breaking trust_remote_code is unrelated to DeepSeek tokenizer output regression." + "reason": "AutoTokenizer v5 loading issue and MPS attention correctness on value/query head mismatch are unrelated." }, { "left": "issue:37428", "right": "issue:44987", "accept": false, - "reason": "Both are loading/import regressions, but they point to different concrete failures and codepaths." + "reason": "Missing flash-attention utility import and a model load failure for physical-intelligence/fast are both import-related at a high level, but not the same concrete bug." }, { - "left": "issue:43927", - "right": "issue:45698", + "left": "issue:44561", + "right": "issue:44779", "accept": false, - "reason": "Save/load state loss of custom token IDs is not the same as loading the wrong custom module after save_pretrained." + "reason": "Removal of is_torch_fx_available breaking trust_remote_code models and Deepseek tokenizer regression in v5 are distinct issues." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "Quantization offloading behavior and a multi-GPU OOM are different memory-management issues." + "reason": "Quantization offloading behavior and multi-GPU CUDA OOM are different root causes and would not be merged into one fix." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load flows, but one is custom token IDs being lost and the other is the wrong custom module being loaded; separate bugs." }, { "left": "issue:44462", "right": "issue:44561", "accept": false, - "reason": "Tokenizer.json handling and a missing utility function are unrelated." + "reason": "Tokenizer.json being ignored and trust_remote_code breaking after a removed helper are unrelated." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Embedding dtype drift between train/eval is not the same as undefined video-token helper names." + "reason": "BF16-to-FP32 dtype drift in evaluate is unrelated to undefined variables in the video token-count helper." }, { "left": "issue:42490", "right": "issue:43575", "accept": false, - "reason": "Import warning for trailing-slash paths and tensor-parallel OOM are unrelated." + "reason": "Trailing-slash local path import warning and tensor-parallel OOM loading Qwen2-57B are unrelated." }, { "left": "issue:10000", "right": "issue:15354", "accept": false, - "reason": "Different historical bugs: German DistilBert issue vs JIT GeneratorExp export failure." + "reason": "German DistilBertModel issue and torch.jit.script generator-expression export failure are different historical bugs." }, { "left": "issue:41720", "right": "issue:45229", "accept": false, - "reason": "Auto device-mapping CUDA assert and multi-GPU OOM are distinct failures." + "reason": "cudaErrorAssert with auto device mapping and multi-GPU OOM are separate inference failures." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Flash-attention generation malfunction and a stale warning for num_return_sequences are not the same issue." + "reason": "Flash-attention generation correctness and a stale warning for num_return_sequences are different problems." }, { - "left": "issue:44568", - "right": "issue:45491", + "left": "issue:45372", + "right": "issue:45588", "accept": false, - "reason": "Special-token insertion bug and Gemma3 NaNs under sliding-window attention are different defects." + "reason": "Gemma 4 processor loading import failure and flash_attention crash on s_aux=None are unrelated." }, { - "left": "issue:45372", - "right": "issue:45588", + "left": "issue:44568", + "right": "issue:45491", "accept": false, - "reason": "Gemma4 processor import failure is unrelated to a flash_attention AttributeError on s_aux=None." + "reason": "Tokenizer special-token insertion regression and Gemma3 NaN embeddings are different failure modes." }, { "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "Loss/AMP crash and flash_attention sink-less-model crash are different codepaths." + "reason": "AMP/CUDA loss crash and flash_attention s_aux=None AttributeError are not the same code-path issue." }, { "left": "issue:43412", "right": "issue:45588", "accept": false, - "reason": "Executorch export failures are unrelated to the flash_attention s_aux=None attribute error." + "reason": "Executorch export issues in Gemma3n and flash_attention sink-less-model crash are unrelated." }, { "left": "issue:45198", "right": "issue:45803", "accept": false, - "reason": "Wav2Vec2 save/tokenization failure and a bare-except swallowing errors in Fuyu are distinct bugs." + "reason": "Wav2Vec2 save/tokenization failure and a bare-except bug in Fuyu tensor conversion are different bugs." }, { "left": "issue:45372", "right": "issue:45406", "accept": false, - "reason": "Both touch Gemma4, but one is an import dependency issue and the other is a missing _tokenizer attribute in serve." + "reason": "ReasoningEffort import failure for Gemma 4 processors and missing _tokenizer in Gemma4Processor are distinct load-time issues." }, { - "left": "issue:43976", - "right": "issue:45440", + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype changes and gradient checkpointing in eval mode are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45823", "accept": false, - "reason": "Python version compatibility and DeepSeekV3MoE output divergence are unrelated." + "reason": "flash_attention.py crashing on s_aux=None and Gemma4 PLE device mismatch under device_map=auto are different bugs." } ] }, @@ -8475,7 +8569,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:25251", "issue:29127", @@ -8491,15 +8585,16 @@ "issue:42994", "issue:43065", "issue:43066", - "issue:43257", "issue:43278", "issue:43381", "issue:43421", + "issue:43575", "issue:43611", "issue:43653", "issue:43701", "issue:43756", "issue:43873", + "issue:43976", "issue:43994", "issue:44186", "issue:44206", @@ -8510,6 +8605,7 @@ "issue:44462", "issue:44466", "issue:44479", + "issue:44610", "issue:44743", "issue:44871", "issue:44977", @@ -8521,17 +8617,15 @@ "issue:45459", "issue:45491", "issue:45563", - "issue:45588", "issue:45712", - "issue:45823", "issue:46121" ], "soft_pairs": [ - "issue:45588|issue:45823", + "issue:43976|issue:45440", "issue:44448|issue:44466", - "issue:25251|issue:32090", "issue:45459|issue:45712", "issue:43653|issue:44743", + "issue:25251|issue:32090", "issue:45245|issue:45563", "issue:44206|issue:44479", "issue:43065|issue:43994", @@ -8540,8 +8634,8 @@ "issue:43065|issue:45412", "issue:43611|issue:46121", "issue:44871|issue:44977", - "issue:32090|issue:33290", "issue:44361|issue:45198", + "issue:32090|issue:33290", "issue:42490|issue:43873", "issue:33357|issue:39692", "issue:29942|issue:30064", @@ -8550,208 +8644,215 @@ "issue:43994|issue:45412", "issue:44265|issue:45198", "issue:43066|issue:44462", - "issue:43257|issue:43278", + "issue:43278|issue:43575", "issue:43756|issue:45440", "issue:43421|issue:45491", "issue:43381|issue:43701", - "issue:43653|issue:44442" + "issue:43653|issue:44442", + "issue:44610|issue:45412" ], - "prepared_review_unit_hash": "f79b8f677af473d96df026ffa27938c17ca92c5437efe37e9878e0142f459d1b", + "prepared_review_unit_hash": "220f151e3a5ead8f5c97ba880bb847846d0202f4cfbe3ff74eab79b21290783c", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36178, - "estimated_input_tokens": 9045, - "estimated_eval_tokens": 18346 + "soft_pair_count": 29, + "serialized_chars": 36409, + "estimated_input_tokens": 9103, + "estimated_eval_tokens": 18462 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated Transformers bug reports; the only loose common thread is tokenizer/loading regressions, and none of the soft pairs look like true duplicates. I\u2019d use 44462 as the closest canonical issue because it is the broadest user-facing loading regression in that subset.", - "confidence": 0.32, - "canonical_issue_reason": "44462 is the most broadly scoped, user-facing tokenizer-loading regression here, so it best represents the small cluster of tokenizer-related reports better than the more niche failures.", + "summary": "This set is not a true duplicate cluster: the issues span unrelated areas (tokenizers, training, quantization, vision processors, model loading, and CI). No single canonical issue or PR stands out, and all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "44462 is the best representative issue overall because it captures a common loading-path failure with wider duplicate potential than the more model-specific or one-off bugs in the set.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:45588", - "right": "issue:45823", + "left": "issue:43976", + "right": "issue:45440", "accept": false, - "reason": "Different code paths and symptoms: flash-attention handling of s_aux=None versus a Gemma4 device_map/device-placement mismatch." + "reason": "Different failures: Python version incompatibility vs DeepseekV3MoE implementation divergence." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Both are v5 regressions, but one is Pegasus generation output drift and the other is serialization of lm_head.weight; not the same concrete bug." - }, - { - "left": "issue:25251", - "right": "issue:32090", - "accept": false, - "reason": "Pipeline top_k nesting and Trainer _gpu_broadcast_one NoneType errors are unrelated failures." + "reason": "Different bugs: generation output drift vs inconsistent lm_head.weight serialization." }, { "left": "issue:45459", "right": "issue:45712", "accept": false, - "reason": "Tokenizer exception masking when protobuf is missing is unrelated to cleanup of leftover dummy classes." + "reason": "Unrelated tokenizer error masking vs leftover dummy class cleanup." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "BigBirdTokenizer special-token decode bug and Qwen recurrent-state reset logic are different subsystems and failure modes." + "reason": "BigBirdTokenizer special-token registration is unrelated to Qwen3.5 recurrent-state reset behavior." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Nested pipeline output shape change is unrelated to Trainer _gpu_broadcast_one NoneType crash." }, { "left": "issue:45245", "right": "issue:45563", "accept": false, - "reason": "Quantized-save category limit and a stale generate() warning for num_return_sequences are not the same bug." + "reason": "Category cardinality/runtime error is unrelated to stale generate() warning behavior." }, { "left": "issue:44206", "right": "issue:44479", "accept": false, - "reason": "Unsupported center arg in a feature extractor is distinct from the Qwen video-input regression." + "reason": "Unsupported center argument in LasrFeatureExtractor is unrelated to video-input regression in Qwen models." }, { "left": "issue:43065", "right": "issue:43994", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d and SigLIP2 nonsensical outputs are different concrete model issues." + "reason": "Sam3PixelDecoder dummy Conv2d is unrelated to SigLIP2 AutoModel/pipeline nonsense outputs." }, { "left": "issue:45372", "right": "issue:45459", "accept": false, - "reason": "Gemma4 processor import failure due to ReasoningEffort is unrelated to protobuf-related tokenizer error masking." + "reason": "Gemma 4 processor import failure from mistral_common is unrelated to protobuf error masking in tokenizers." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "Both involve tokenizers, but LayoutLMv2 NER/padding crashes and Wav2Vec2 save_pretrained/tokenization failures are different bugs." + "reason": "LayoutLMv2 tokenizer crashes on NER/padding are unrelated to Wav2Vec2 save_pretrained/tokenization failures." }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "A dummy layer in Sam3PixelDecoder is not the same as RT-DETR memory not being released after deletion." + "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to RT-DETR memory release problems." }, { "left": "issue:43611", "right": "issue:46121", "accept": false, - "reason": "base_model_prefix loading regression and JSON-loaded rope validation list TypeError affect different code paths." + "reason": "base_model_prefix loading breakage is unrelated to rope-parameter JSON list handling." }, { "left": "issue:44871", "right": "issue:44977", "accept": false, - "reason": "Gemma-3 eos_token_id config mismatch and Qwen3.5 flash-attention generation failure are unrelated." + "reason": "Gemma-3 eos_token_id mismatch is unrelated to Qwen3.5 flash-attention generation issues." }, { - "left": "issue:32090", - "right": "issue:33290", + "left": "issue:44361", + "right": "issue:45198", "accept": false, - "reason": "NoneType broadcast failure in Trainer is not the same as an OOM with Adafactor in DeepSpeed." + "reason": "MLukeTokenizer AttributeError is unrelated to Wav2Vec2 save/tokenization failure." }, { - "left": "issue:44361", - "right": "issue:45198", + "left": "issue:32090", + "right": "issue:33290", "accept": false, - "reason": "MLukeTokenizer AttributeError and Wav2Vec2 save/tokenization failure are different tokenizer bugs." + "reason": "Trainer NoneType broadcast crash is unrelated to Adafactor/DeepSpeed OOM." }, { "left": "issue:42490", "right": "issue:43873", "accept": false, - "reason": "Local-path trailing-slash import warning and quantization offloading failure are not the same issue." + "reason": "Trailing-slash import warning is unrelated to offloading-with-quantization behavior." }, { "left": "issue:33357", "right": "issue:39692", "accept": false, - "reason": "A MacOS bus error on a CLIP model and SigLIP2 documentation example errors are different problems." + "reason": "MacOS bus error with CLIP is unrelated to SigLIP2 doc example mistakes." }, { "left": "issue:29942", "right": "issue:30064", "accept": false, - "reason": "Flash Attention 2 test failures and void segmentation-map processing failures do not share the same root cause." + "reason": "Flash Attention 2 test failures are unrelated to void segmentation map processing." }, { "left": "issue:29127", "right": "issue:34567", "accept": false, - "reason": "LayoutLMv3 error clarity and TrainerState num_input_tokens_seen not updating are unrelated." + "reason": "LayoutLMv3 error-message clarity is unrelated to TrainerState token counter not updating." }, { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "FineGrainedFP8Config failure and quantized-model saving failure are distinct quantization bugs." + "reason": "FineGrainedFP8Config failure for Qwen3Moe is unrelated to quantized model saving." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 wrong outputs and RT-DETR memory leaks are different symptoms and code paths." + "reason": "SigLIP2 inference mismatch is unrelated to RT-DETR memory leaks." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "torch.export.export failure with torch_compilable_check is unrelated to Wav2Vec2 tokenization/save_pretrained failures." + "reason": "torch.export/torch_compilable_check failure is unrelated to Wav2Vec2 save/tokenization issues." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Both are tokenizer-loading regressions, but one is a decoder-type mismatch while the other is AutoTokenizer ignoring tokenizer.json; not the same concrete bug." + "reason": "Wrong tokenizer decoder type in v5 is unrelated to AutoTokenizer ignoring tokenizer.json." }, { - "left": "issue:43257", - "right": "issue:43278", + "left": "issue:43278", + "right": "issue:43575", "accept": false, - "reason": "Missing MOE weight conversion under accelerate+deepspeed and BF16-to-FP32 dtype drift are different issues." + "reason": "Embedding dtype drift during eval is unrelated to tp loading OOM for Qwen2-57B-A14B-Instruct." }, { "left": "issue:43756", "right": "issue:45440", "accept": false, - "reason": "Smollm3 dropping RoPE layers and DeepseekV3MoE diverging from remote implementation are architecture-specific and not the same bug." + "reason": "Smollm3 RoPE-layer mismatch is unrelated to DeepseekV3MoE implementation divergence." }, { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime post-processor updates for special tokens and Gemma3 NaN embeddings with mixed-length batching are unrelated." + "reason": "Runtime special-token post-processor updates are unrelated to Gemma3 NaN embeddings with mixed-length batching." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Eval-mode gradient checkpointing restriction and resume_from_checkpoint key mismatch are separate training-state problems." + "reason": "Gradient checkpointing in eval mode is unrelated to resume_from_checkpoint key mismatch." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "Both are tokenizer-related, but one is special-token registration/empty decode and the other is AutoTokenizer class loading; different root causes." + "reason": "BigBirdTokenizer mask-token registration is unrelated to AutoTokenizer failing to load FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR memory reclamation." } ] }, @@ -8773,11 +8874,13 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:29127", "issue:29942", + "issue:33290", "issue:33357", + "issue:34689", "issue:35141", "issue:36010", "issue:42490", @@ -8803,17 +8906,16 @@ "issue:44387", "issue:44442", "issue:44464", - "issue:44610", "issue:44625", "issue:44743", "issue:44811", "issue:44857", + "issue:44898", "issue:44977", "issue:45072", "issue:45103", "issue:45245", "issue:45372", - "issue:45412", "issue:45440", "issue:45491", "issue:45584", @@ -8824,217 +8926,224 @@ "issue:45907" ], "soft_pairs": [ - "issue:44610|issue:45412", "issue:43824|issue:44279", "issue:29127|issue:33357", - "issue:45440|issue:45593", "issue:29942|issue:36010", + "issue:45440|issue:45593", "issue:43761|issue:45859", "issue:43526|issue:45834", "issue:43526|issue:44186", "issue:45103|issue:45372", "issue:29127|issue:35141", "issue:44625|issue:45584", - "issue:44442|issue:45072", "issue:43334|issue:43531", - "issue:42915|issue:43931", + "issue:44442|issue:45072", "issue:43575|issue:43701", + "issue:42915|issue:43931", "issue:43526|issue:44857", "issue:42490|issue:43381", "issue:44977|issue:45245", "issue:43575|issue:44387", - "issue:43262|issue:44206", "issue:44464|issue:45491", + "issue:43262|issue:44206", "issue:43646|issue:44077", "issue:44743|issue:44811", "issue:43452|issue:45588", "issue:44062|issue:45907", - "issue:43761|issue:44079" + "issue:43761|issue:44079", + "issue:33290|issue:34689", + "issue:44442|issue:44898" ], - "prepared_review_unit_hash": "6629c151882e98d7a8fb5e428079005988cc3918d8f3bb7b52be1c8a01d22c2c", + "prepared_review_unit_hash": "49e63cdcda54e50d7465058e56f34643575ab7606f127b38863fd9c07b392e7f", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 26, - "serialized_chars": 34908, - "estimated_input_tokens": 8727, - "estimated_eval_tokens": 17710 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35765, + "estimated_input_tokens": 8942, + "estimated_eval_tokens": 18140 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The soft pairs are mostly unrelated issues across different models and subsystems; none look like the same underlying bug or change, so no pair should be merged as duplicates.", - "confidence": 0.9, - "canonical_issue_reason": "No single issue is a clear duplicate anchor for this set: the reports span unrelated regressions and components. If a representative must be chosen, issue 43646 is the broadest, but it is not a true canonical duplicate target.", + "summary": "These items do not form a true duplicate cluster; they span many unrelated Transformers bugs across different models, loaders, processors, and runtime paths. All proposed soft edges are reject-worthy on the available evidence.", + "confidence": 0.77, + "canonical_issue_reason": "If a representative must be chosen, issue 44279 is the broadest/most umbrella-like title, but it is still too generic to be a strong canonical for this set.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43646 is the most general, high-level regression in the set (a broad Transformers 5.0.0 initialization break), so it is the best representative bucket if one is needed, though the cluster is not actually homogeneous.", + "best_issue_reason": "44279 is the least specific issue here, but the collection is too heterogeneous for any issue to be a reliable duplicate anchor.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44610", - "right": "issue:45412", - "accept": false, - "reason": "Different failures: processor input size mismatch for OmDet-Turbo vs RT-DETR memory not being released." - }, { "left": "issue:43824", "right": "issue:44279", "accept": false, - "reason": "One is a specific missing import for Qwen2.5-VL; the other is a broad dependency issue with no concrete same bug." + "reason": "Specific Qwen2.5-VL import failure vs generic dependency issue; not the same bug." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 error messaging clarity and a MacOS bus error on CLIP are unrelated." + "reason": "LayoutLMv3 error-message clarity vs CLIP MacOS bus error; unrelated symptoms and code paths." }, { - "left": "issue:45440", - "right": "issue:45593", + "left": "issue:29942", + "right": "issue:36010", "accept": false, - "reason": "DeepSeekV3MoE implementation divergence and D-FINE auxiliary-loss behavior are different code paths." + "reason": "Flash Attention 2 test failures vs GenerationMixin import regression; different failures." }, { - "left": "issue:29942", - "right": "issue:36010", + "left": "issue:45440", + "right": "issue:45593", "accept": false, - "reason": "Flash Attention 2 test failures are not the same issue as a GenerationMixin import error." + "reason": "DeepSeekV3MoE implementation divergence vs D-FINE auxiliary-loss omission; unrelated model bugs." }, { "left": "issue:43761", "right": "issue:45859", "accept": false, - "reason": "CLIPVision hidden_states regression and Qwen3_5Moe CPU-offload incompatibility are separate bugs." + "reason": "CLIPVisionModel hidden_states regression vs Qwen3.5Moe CPU-offload incompatibility; different components." }, { "left": "issue:43526", "right": "issue:45834", "accept": false, - "reason": "BEiT FastImageProcessor label reduction and Kosmos2.5 long OCR index errors are unrelated." + "reason": "BeitImageProcessorFast label reduction bug vs Kosmos2.5 long-OCR index error; not the same issue." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "These affect different tokenizer/processor pipelines and different failure modes." + "reason": "Image processor label handling vs LayoutLMv2Tokenizer NER/padding crash; unrelated." }, { "left": "issue:45103", "right": "issue:45372", "accept": false, - "reason": "auto_docstring annotation handling and Gemma 4 loading/import issues are not the same bug." + "reason": "auto_docstring annotations crash vs mistral_common import error in Gemma processor loading; different root causes." }, { "left": "issue:29127", "right": "issue:35141", "accept": false, - "reason": "LayoutLMv3 box validation messaging and token-embedding reinitialization after resize are unrelated." + "reason": "Error-message clarity issue vs post_init reinitialization bug; not the same code path." }, { "left": "issue:44625", "right": "issue:45584", "accept": false, - "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription generation failure are different problems." - }, - { - "left": "issue:44442", - "right": "issue:45072", - "accept": false, - "reason": "FastSpeech2Conformer tokenizer loading and bfloat16 dtype mismatches are distinct issues." + "reason": "Config propagation bug vs Whisper empty-transcription generation failure; unrelated." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Missing pad_token_id for Qwen3-VL loading is not the same as Qwen3-MoE sliding-window behavior." + "reason": "Missing pad_token_id for Qwen3-VL text config vs sliding_window issue in Qwen3-MoE; different model families." }, { - "left": "issue:42915", - "right": "issue:43931", + "left": "issue:44442", + "right": "issue:45072", "accept": false, - "reason": "FineGrainedFP8Config failure for Qwen3Moe and Qwen3-VL weight-shape mismatch are different model/config bugs." + "reason": "Tokenizer loading failure vs bfloat16 dtype mismatch during inference; different concrete problems." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "Tensor-parallel OOM on Qwen2-57B is unrelated to resume_from_checkpoint key mismatch." + "reason": "Tensor-parallel OOM on model load vs checkpoint key mismatch; unrelated failures." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FineGrainedFP8Config failure vs Qwen3-VL weight-shape mismatch; different issues." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "Label reduction bug in BeitImageProcessorFast and float16 AMP crash in LwDetrImageLoss are separate." + "reason": "BeitImageProcessorFast label reduction bug vs LwDetrImageLoss AMP/CUDA crash; unrelated." }, { "left": "issue:42490", "right": "issue:43381", "accept": false, - "reason": "Trailing-slash local model loading warning is unrelated to gradient checkpointing being disallowed in eval mode." + "reason": "Path import warning vs gradient-checkpointing-in-eval restriction; not the same bug." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Flash-attention generation problems and the 2^24 category limit are unrelated." + "reason": "Qwen3.5 flash-attention generation bug vs category-count limit error; unrelated." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "Both mention OOM, but one is tensor-parallel model loading and the other is int4 quantization memory growth; different root causes." + "reason": "Both are OOM-related, but one is TP load OOM and the other is int4 memory growth; not the same concrete problem." }, { - "left": "issue:43262", - "right": "issue:44206", + "left": "issue:44464", + "right": "issue:45491", "accept": false, - "reason": "Audio chat-template sampling-rate defaults and an unsupported center argument in LasrFeatureExtractor are unrelated." + "reason": "Compiled-forward chunked generation inconsistency vs Gemma3 NaN embeddings from sliding-window padding; different bugs." }, { - "left": "issue:44464", - "right": "issue:45491", + "left": "issue:43262", + "right": "issue:44206", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency and Gemma3 NaN embeddings from sliding-window padding are different bugs." + "reason": "Chat-template sample-rate default vs feature-extractor center-arg crash; unrelated." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "Broad custom model initialization regression and a patchtsmixer post_init policy issue do not share the same concrete failure." + "reason": "Generic custom-init regression vs patchtsmixer post_init policy issue; not a shared concrete fix." }, { "left": "issue:44743", "right": "issue:44811", "accept": false, - "reason": "Qwen3.5 recurrent-state caching bug and Whisper batch_decode skip_special_tokens handling are unrelated." + "reason": "Recurrent-state reset bug vs Whisper batch_decode skip_special_tokens behavior; unrelated." }, { "left": "issue:43452", "right": "issue:45588", "accept": false, - "reason": "gguf_file loading behavior and flash_attention sink-less AttributeError are separate code paths." + "reason": "gguf_file loading regression vs flash_attention.py s_aux=None crash; different subsystems and failures." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken keyword collision vs list_repo_files revision forwarding; unrelated API bugs." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "CLIP hidden_states regression vs ModelOutput key assignment bug; different code paths." }, { - "left": "issue:44062", - "right": "issue:45907", + "left": "issue:33290", + "right": "issue:34689", "accept": false, - "reason": "AddedToken keyword duplication and list_repo_files revision forwarding are unrelated API bugs." + "reason": "Adafactor+DeepSpeed OOM vs Llama 3.2 vision model loading breakage; unrelated." }, { - "left": "issue:43761", - "right": "issue:44079", + "left": "issue:44442", + "right": "issue:44898", "accept": false, - "reason": "CLIPVision hidden_states regression and ModelOutput key assignment with None are different issues." + "reason": "Tokenizer load failure vs Perceiver non-default resolution failure; not the same bug." } ] }, @@ -9056,7 +9165,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:33290", "issue:34567", @@ -9091,7 +9200,6 @@ "issue:44743", "issue:44855", "issue:44871", - "issue:44898", "issue:44913", "issue:44987", "issue:45003", @@ -9108,29 +9216,27 @@ "issue:46209" ], "soft_pairs": [ - "issue:33290|issue:34689", - "issue:44442|issue:44898", - "issue:45003|issue:45440", "issue:33290|issue:34567", "issue:33290|issue:35141", + "issue:45003|issue:45440", "issue:43723|issue:45479", - "issue:43232|issue:43388", "issue:43381|issue:43873", - "issue:42490|issue:44743", + "issue:43232|issue:43388", "issue:43316|issue:43525", + "issue:42490|issue:44743", "issue:43761|issue:44188", "issue:34689|issue:43611", "issue:44479|issue:45290", "issue:43720|issue:44442", "issue:44987|issue:46178", - "issue:44077|issue:44479", "issue:44442|issue:45803", - "issue:43493|issue:43827", + "issue:44077|issue:44479", "issue:43931|issue:45216", + "issue:43493|issue:43827", "issue:34689|issue:36010", - "issue:42907|issue:45698", "issue:33290|issue:36331", "issue:43316|issue:45759", + "issue:42907|issue:45698", "issue:45290|issue:46209", "issue:43873|issue:44871", "issue:43749|issue:43931", @@ -9139,94 +9245,82 @@ "issue:44190|issue:44496", "issue:44855|issue:45137" ], - "prepared_review_unit_hash": "7385df6bf9cca8b91f177942b6cdbce531036e9f2138c63cc06b7bcdc290b26c", + "prepared_review_unit_hash": "a38092142cb8957161dfccba6207c799108865976f3a1ec35a6c8f85cab5209a", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36890, - "estimated_input_tokens": 9223, - "estimated_eval_tokens": 18702 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35710, + "estimated_input_tokens": 8928, + "estimated_eval_tokens": 18112 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is highly heterogeneous and the soft edges are mostly superficial title-level similarities rather than true duplicates. I would reject every proposed merge pair.", - "confidence": 0.83, - "canonical_issue_reason": "No single canonical issue stands out: these reports span unrelated bugs across loading, configs, training, generation, vision, quantization, and docs, so there is no clear duplicate anchor for the whole set.", + "summary": "No soft pair appears to describe the same underlying bug or change. The set is a grab bag of unrelated issues spanning loading, generation, training, quantization, and docs regressions, so there is no canonical duplicate to select.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43873 is the strongest standalone anchor among the set because it is currently open, detailed, and has the most discussion/inbound references, but it still is not related to most of the other items.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:33290", - "right": "issue:34689", + "right": "issue:34567", "accept": false, - "reason": "Different bugs: DeepSpeed/Adafactor OOM vs Llama 3.2 Vision model loading regression." + "reason": "OOM with Adafactor/DeepSpeed is unrelated to TrainerState.num_input_tokens_seen not updating." }, { - "left": "issue:44442", - "right": "issue:44898", + "left": "issue:33290", + "right": "issue:35141", "accept": false, - "reason": "Unrelated failures: tokenizer loading vs Perceiver image classification resize/interpolation bug." + "reason": "Different failure modes: optimizer memory blowup vs embedding reinitialization after resize." }, { "left": "issue:45003", "right": "issue:45440", "accept": false, - "reason": "Different code paths: unsafe sys.modules access vs DeepSeekV3MoE behavioral divergence." - }, - { - "left": "issue:33290", - "right": "issue:34567", - "accept": false, - "reason": "OOM in optimizer/deepspeed is unrelated to TrainerState token counter not updating." + "reason": "sys.modules access bug is unrelated to DeepSeekV3MoE implementation divergence." }, { - "left": "issue:33290", - "right": "issue:35141", + "left": "issue:43723", + "right": "issue:45479", "accept": false, - "reason": "Optimizer memory blowup is unrelated to embedding resize/post_init reinitialization." + "reason": "Tokenizer loading regression and zero-loss sequence-classification bug are unrelated." }, { - "left": "issue:43723", - "right": "issue:45479", + "left": "issue:43381", + "right": "issue:43873", "accept": false, - "reason": "Tokenizer loading regression and degenerate classification loss are different problems." + "reason": "Gradient checkpointing in eval mode and offloading/quantization are different issues." }, { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Generation sync/update bug is unrelated to metric gathering label truncation." + "reason": "Generation kwargs after sync_gpus does not match metric gathering dropping tuple labels." }, { - "left": "issue:43381", - "right": "issue:43873", + "left": "issue:43316", + "right": "issue:43525", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction is unrelated to quantization/offloading behavior." + "reason": "Different config API problems: Gemma3TextConfig discrepancy vs missing pad_token_id on Llama4Config." }, { "left": "issue:42490", "right": "issue:44743", "accept": false, - "reason": "Local-path import warning and recurrent-state cache reset are unrelated." - }, - { - "left": "issue:43316", - "right": "issue:43525", - "accept": false, - "reason": "Both mention config API issues, but different models and different missing fields." + "reason": "Trailing-slash path import warning is unrelated to Qwen recurrent-state reset with cache." }, { "left": "issue:43761", @@ -9238,115 +9332,115 @@ "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are model-loading regressions, but they concern different mechanisms and different failure modes." + "reason": "Llama 3.2 model loading break and base_model_prefix loading regression are distinct." }, { "left": "issue:44479", "right": "issue:45290", "accept": false, - "reason": "Video-input regression and chat-template tool-call crash are separate bugs." + "reason": "Video-input regression in Qwen VL models is unrelated to chat-template tool-call crashes." }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "BitNet accelerate loading issue is unrelated to tokenizer loading failure." + "reason": "BitNet packed-weight loading bug is unrelated to AutoTokenizer failing on FastSpeech2ConformerTokenizer." }, { "left": "issue:44987", "right": "issue:46178", "accept": false, - "reason": "Different symptoms and subsystems: model loading regression vs missing BACKENDS_MAPPING entry." - }, - { - "left": "issue:44077", - "right": "issue:44479", - "accept": false, - "reason": "Optional post_init contract issue is unrelated to video input regression." + "reason": "Physical-intelligence/fast load failure is unrelated to missing tensorflow_text backend mapping." }, { "left": "issue:44442", "right": "issue:45803", "accept": false, - "reason": "Tokenizer load failure and bare-except error swallowing in Fuyu are unrelated." + "reason": "Tokenizer loading failure and FuyuBatchFeature exception handling are different code paths." }, { - "left": "issue:43493", - "right": "issue:43827", + "left": "issue:44077", + "right": "issue:44479", "accept": false, - "reason": "Model implementation discrepancy and docs still referencing pipeline() are not the same bug." + "reason": "patchtsmixer post_init policy issue is unrelated to Qwen video-input regression." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Shape-mismatch load error and save_pretrained checkpoint corruption are distinct issues." + "reason": "Weight-shape mismatch on load is unrelated to a bad save_pretrained checkpoint for Qwen3.5." }, { - "left": "issue:34689", - "right": "issue:36010", + "left": "issue:43493", + "right": "issue:43827", "accept": false, - "reason": "Model loading breakage and GenerationMixin import error are different failures." + "reason": "SigLIP2 implementation mismatch is unrelated to docs still mentioning pipeline()." }, { - "left": "issue:42907", - "right": "issue:45698", + "left": "issue:34689", + "right": "issue:36010", "accept": false, - "reason": "Dequantized save failure and wrong custom module reloading are separate save/load problems." + "reason": "Model-loading failure and GenerationMixin import error are separate regressions." }, { "left": "issue:33290", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed OOM and CustomTrainer compute_loss signature mismatch are unrelated training bugs." + "reason": "DeepSpeed Adafactor OOM is unrelated to CustomTrainer.compute_loss receiving a new kwarg." }, { "left": "issue:43316", "right": "issue:45759", "accept": false, - "reason": "Config API discrepancy and AutoModelForCausalLM unwrapping behavior are different issues." + "reason": "Gemma3TextConfig API discrepancy is unrelated to composite Qwen multimodal from_config unwrapping." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals is unrelated to loading the wrong custom module after save_pretrained." }, { "left": "issue:45290", "right": "issue:46209", "accept": false, - "reason": "Chat template crash is unrelated to FP8 inference failure on B200." + "reason": "Chat-template tool-call crash is unrelated to FP8 inference failure on B200." }, { "left": "issue:43873", "right": "issue:44871", "accept": false, - "reason": "Quantization/offloading bug and Gemma eos_token_id inconsistency are unrelated." + "reason": "Quantization/offloading behavior does not match Gemma eos_token_id configuration mismatch." }, { "left": "issue:43749", "right": "issue:43931", "accept": false, - "reason": "FSDP CPU RAM efficient loading regression is not the same as Qwen3-VL shape mismatch." + "reason": "FSDP CPU RAM efficient loading and Qwen3-VL shape mismatch are different loading bugs." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "trust_remote_code missing-fields issue and rotary_pct reload regression are different config serialization bugs." + "reason": "trust_remote_code returning missing fields is unrelated to GPTNeoX rotary_pct resetting on reload." }, { "left": "issue:43650", "right": "issue:46202", "accept": false, - "reason": "Placeholder/noise issue is unrelated to Gemma pipeline roundtrip failure." + "reason": "The vague 'ADD THE DATA' issue is not the same as Gemma pipeline roundtrip failure." }, { "left": "issue:44190", "right": "issue:44496", "accept": false, - "reason": "Local dataset loading problem is unrelated to unrecognized custom model config." + "reason": "Local dataset loading script issue is unrelated to unrecognized model config loading." }, { "left": "issue:44855", "right": "issue:45137", "accept": false, - "reason": "Python 3.13 import parsing error and DeepSpeed ZeRO3 deque pop error are unrelated." + "reason": "PyTorch 3.13 decorator parsing/import error is unrelated to DeepSpeed ZeRO3 deque underflow." } ] }, @@ -9368,7 +9462,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:16998", "issue:22355", @@ -9421,8 +9515,8 @@ ], "soft_pairs": [ "issue:25251|issue:28282", - "issue:43295|issue:43825", "issue:43065|issue:44617", + "issue:43295|issue:43825", "issue:43550|issue:43701", "issue:43606|issue:43701", "issue:43316|issue:44877", @@ -9438,8 +9532,8 @@ "issue:45803|issue:46170", "issue:43295|issue:44871", "issue:43673|issue:44743", - "issue:41950|issue:43475", "issue:43761|issue:44479", + "issue:41950|issue:43475", "issue:43388|issue:43688", "issue:43452|issue:44496", "issue:43646|issue:44913", @@ -9448,20 +9542,20 @@ "issue:43572|issue:46178", "issue:32090|issue:35141" ], - "prepared_review_unit_hash": "9cb918df43bbb13c11e4be14696883a850a55d8a56b194d35689caadb0a03657", + "prepared_review_unit_hash": "865123dcf87d23c2abc168a7458f99fbbec2be29425cfc2de3e5a58e0caf8204", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 35722, + "serialized_chars": 35721, "estimated_input_tokens": 8931, "estimated_eval_tokens": 18118 }, @@ -9470,174 +9564,174 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose collection of unrelated bug reports across many subsystems; the soft-similarity pairs do not look like true duplicates or mergeable same-fix candidates. No PRs are present.", - "confidence": 0.96, - "canonical_issue_reason": "issue:43646 is the most general and high-level regression in the set (custom model initialization breaking under Transformers 5.0), so it is the closest thing to a cluster anchor, though the cluster is not a true duplicate set.", + "summary": "These are mostly unrelated transformer issues that only share broad subsystem or release-regression language; none look like true duplicates, so there is no strong canonical item.", + "confidence": 0.18, + "canonical_issue_reason": "No clear canonical duplicate exists; the set spans many different bug classes (pipelines, configs, model loading, training, multimodal/video, distributed, and checkpoints).", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the best representative issue because it describes a broad, user-facing regression with clear actionability and relatively generic impact compared with the other highly specific reports.", + "best_issue_reason": "issue:43646 is the broadest umbrella-style regression report in the set, but it still does not subsume the others and should not be treated as a duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:25251", "right": "issue:28282", "accept": false, - "reason": "Different failures: pipeline output shape change vs missing `transformers.onnx` module import." + "reason": "Pipeline output nesting bug vs missing PyTorch import are unrelated failure modes." }, { - "left": "issue:43295", - "right": "issue:43825", + "left": "issue:43065", + "right": "issue:44617", "accept": false, - "reason": "One is a processor API regression; the other is an incorrect pipeline error message about translation support." + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video OOM are different SAM3 problems." }, { - "left": "issue:43065", - "right": "issue:44617", + "left": "issue:43295", + "right": "issue:43825", "accept": false, - "reason": "`Sam3PixelDecoder` dummy layer issue is unrelated to SAM3 video CUDA OOM." + "reason": "Processor/tokenizer regression is unrelated to a pipeline error message about translation tasks." }, { "left": "issue:43550", "right": "issue:43701", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to checkpoint resume key mismatches." + "reason": "torch.compile/SDPA failure is unrelated to a checkpoint key mismatch." }, { "left": "issue:43606", "right": "issue:43701", "accept": false, - "reason": "CPU offload device mismatch does not match resume-from-checkpoint key mismatch." + "reason": "CPU offload device mismatch and resume_from_checkpoint key mismatch are different bugs." }, { "left": "issue:43316", "right": "issue:44877", "accept": false, - "reason": "Gemma3 config API discrepancy is unrelated to strict config loading for granite_speech." + "reason": "Gemma3TextConfig API discrepancy is not the same as strict config loading failure for granite_speech." }, { "left": "issue:43316", "right": "issue:43716", "accept": false, - "reason": "Config API mismatch is not the same as an image preprocessor dtype mismatch." + "reason": "Config API discrepancy and image preprocessor dtype mismatch are separate issues." }, { "left": "issue:42617", "right": "issue:43575", "accept": false, - "reason": "Failed script execution and TP OOM are different problems and code paths." + "reason": "3d_parallel.py startup failure and tp-related OOM are unrelated." }, { "left": "issue:43540", "right": "issue:44514", "accept": false, - "reason": "Qwen3OmniMoe video-processing error is separate from batched chat-template padding crash." + "reason": "Both are multimodal/video-related, but one is a Qwen3OmniMoe video input validation error and the other is a Qwen2_5_VL batching crash." }, { "left": "issue:44077", "right": "issue:44534", "accept": false, - "reason": "Optional `post_init` policy issue is unrelated to non-persistent buffer initialization bugs." + "reason": "Optional post_init policy for patchtsmixer is unrelated to non-persistent buffer junk initialization." }, { "left": "issue:44162", "right": "issue:44792", "accept": false, - "reason": "ESM2 regression and Janus image-generation test failure do not describe the same underlying bug." + "reason": "ESM2 training breakage and janus image-generation test failure do not share the same bug." }, { "left": "issue:16998", "right": "issue:22355", "accept": false, - "reason": "Model max length question is unrelated to missing ONNX submodule import." + "reason": "model_max_length question for DeBERTa-V3 is unrelated to missing transformers.onnx module import." }, { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "Gemma EOS config inconsistency is unrelated to Whisper empty-transcription generation failure." + "reason": "Gemma eos_token_id config inconsistency is not the same as Whisper empty transcription failure." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "Tensor-parallel OOM and MobileLLM config key error are different loading failures." + "reason": "OOM on large Qwen2 model loading is unrelated to a KeyError while loading MobileLLM-125M." }, { "left": "issue:43404", "right": "issue:43441", "accept": false, - "reason": "Untied `lm_head` weights and FlashAttention failure in Ministral-3 are different code-path problems." + "reason": "Mistral3 lm_head tying bug is different from a FlashAttention failure in Ministral-3." }, { "left": "issue:45803", "right": "issue:46170", "accept": false, - "reason": "Bare `except` in Fuyu tensor conversion is unrelated to Windows/ROCm distributed import issues." + "reason": "Bare except swallowing errors in tensor conversion is unrelated to Windows/ROCm torch.distributed import issues." }, { "left": "issue:43295", "right": "issue:44871", "accept": false, - "reason": "Processor/tokenizer regression is not the same as Gemma EOS token configuration mismatch." + "reason": "Processor regression and Gemma eos_token_id config mismatch are different code paths." }, { "left": "issue:43673", "right": "issue:44743", "accept": false, - "reason": "Cache missing in generation and recurrent state reset are related thematically but not the same concrete bug." + "reason": "Missing GenerationMixin cache during chunked_prefill is not the same as recurrent state reset in modular_qwen3_5.py." }, { - "left": "issue:41950", - "right": "issue:43475", + "left": "issue:43761", + "right": "issue:44479", "accept": false, - "reason": "Video-classification processor selection bug is unrelated to missing `fpn_position_embeddings` on SAM3 output." + "reason": "CLIPVisionModel hidden_states regression and Qwen video input regression are unrelated." }, { - "left": "issue:43761", - "right": "issue:44479", + "left": "issue:41950", + "right": "issue:43475", "accept": false, - "reason": "CLIP vision hidden-states regression is separate from Qwen video-input regression." + "reason": "Video-classification pipeline selecting image processors is different from a missing fpn_position_embeddings attribute in Sam3 video." }, { "left": "issue:43388", "right": "issue:43688", "accept": false, - "reason": "Metric label truncation and auxiliary-loss normalization are different training bugs." + "reason": "gather_for_metrics label truncation is unrelated to auxiliary loss normalization in OLMoE/GPT OSS." }, { "left": "issue:43452", "right": "issue:44496", "accept": false, - "reason": "GGUF loading breakage is different from missing `model_type` in config loading." + "reason": "gguf loading breaks for tokenizer/model APIs, while the other is an unrecognized model config error." }, { "left": "issue:43646", "right": "issue:44913", "accept": false, - "reason": "Custom model init regression is broader and different from GPTNeoX rotary_pct persistence on reload." + "reason": "Generic custom-model initialization breakage is not the same as GPTNeoX rotary_pct reload persistence." }, { "left": "issue:44871", "right": "issue:46050", "accept": false, - "reason": "Gemma EOS mismatch is unrelated to sinq quantization save/load breakage." + "reason": "Gemma eos_token_id mismatch is unrelated to sinq quantization save/load breakage." }, { "left": "issue:45127", "right": "issue:45200", "accept": false, - "reason": "LoRA merge collapse with extended vocab is unrelated to Gemma 4 multimodal token type defaults." + "reason": "LoRA merge collapse with tied embeddings is a different bug from missing mm_token_type_ids defaults." }, { "left": "issue:43572", "right": "issue:46178", "accept": false, - "reason": "StableLm missing config field and tensorflow_text backend mapping error are unrelated compatibility issues." + "reason": "StableLmConfig pad_token_idx regression is unrelated to tensorflow_text backend mapping errors." }, { "left": "issue:32090", "right": "issue:35141", "accept": false, - "reason": "Trainer GPU broadcast NoneType error is unrelated to embedding reinitialization after resizing." + "reason": "NoneType GPU broadcast failure and embedding reinitialization after resize are different training/model-init bugs." } ] }, @@ -9659,7 +9753,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:35141", "issue:41720", @@ -9679,7 +9773,6 @@ "issue:43994", "issue:44060", "issue:44077", - "issue:44079", "issue:44190", "issue:44242", "issue:44464", @@ -9692,6 +9785,7 @@ "issue:44737", "issue:44792", "issue:44855", + "issue:44877", "issue:44913", "issue:44933", "issue:44964", @@ -9712,8 +9806,8 @@ ], "soft_pairs": [ "issue:43504|issue:45698", - "issue:44734|issue:45406", "issue:44617|issue:45584", + "issue:44734|issue:45406", "issue:45563|issue:45584", "issue:43525|issue:43531", "issue:43761|issue:44242", @@ -9729,220 +9823,220 @@ "issue:44521|issue:45381", "issue:35141|issue:42490", "issue:41720|issue:45245", - "issue:43065|issue:44610", "issue:45803|issue:45987", + "issue:43065|issue:44610", "issue:44933|issue:45362", "issue:43335|issue:44855", "issue:43644|issue:44913", - "issue:44077|issue:44079", + "issue:44077|issue:44877", "issue:43976|issue:44855", "issue:43550|issue:44190", "issue:43540|issue:44734", "issue:45127|issue:45357", "issue:44737|issue:45803" ], - "prepared_review_unit_hash": "eebe10e693dc9a620a877971965034125b32849eb8455322da1ec319f8de7c01", + "prepared_review_unit_hash": "bf7d97444aec167c24983f713d74e949ec1daa3b58a0249f09638cb4cd3f7706", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36404, - "estimated_input_tokens": 9101, - "estimated_eval_tokens": 18458 + "serialized_chars": 36387, + "estimated_input_tokens": 9097, + "estimated_eval_tokens": 18450 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster looks heterogeneous: the soft edges are mostly topical lookalikes, not true duplicates. I\u2019d reject every pair and treat issue:44521 as the best single representative only because it has the strongest activity signal, not because it matches the others.", - "confidence": 0.84, - "canonical_issue_reason": "issue:44521 has the strongest discussion/inbound-reference signal in this set, so it is the best representative if a single issue must be chosen, even though the cluster is not a real duplicate group.", + "summary": "The soft pairs are largely heterogeneous and do not describe the same underlying bug or change. They span unrelated model-loading, multimodal preprocessing, generation, config, and docs/runtime regression issues, so none of the proposed duplicate links should be accepted.", + "confidence": 0.93, + "canonical_issue_reason": "issue:44521 is the most active/open issue in the set and has the strongest cross-referencing signal, so it is the best representative if one must be chosen; however, the overall set is not a true duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the most active and well-documented item here, making it the most suitable standalone anchor among otherwise unrelated reports.", + "best_issue_reason": "issue:44521 is the strongest global issue candidate by discussion and inbound references, but it should be treated as representative only, not as a merge target for the other unrelated issues.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43504", "right": "issue:45698", "accept": false, - "reason": "Both concern model loading/save behavior, but they describe different failures and code paths." + "reason": "BEiT legacy-field preset loading vs custom-module resolution after save/load; different subsystems and failure modes." }, { - "left": "issue:44734", - "right": "issue:45406", + "left": "issue:44617", + "right": "issue:45584", "accept": false, - "reason": "Both involve transformers serve crashes, but one is KV-cache continuation indexing and the other is a processor attribute error." + "reason": "Sam3Video CUDA OOM vs Whisper empty-transcription failure; unrelated code paths and symptoms." }, { - "left": "issue:44617", - "right": "issue:45584", + "left": "issue:44734", + "right": "issue:45406", "accept": false, - "reason": "Unrelated bugs: video-model OOM versus Whisper empty transcription after token alignment." + "reason": "KV-cache continuation tensor indexing in serve vs Gemma4Processor missing _tokenizer; distinct serve bugs." }, { "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "Different issues in generation: a stale warning versus a real failure on empty transcription." + "reason": "Paged-generate warning regression vs empty transcription after align_special_tokens; not the same bug." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "Different configs and symptoms: missing pad_token_id versus sliding-window handling in Qwen3-MoE." + "reason": "Missing pad_token_id in Llama4Config vs sliding_window handling in Qwen3-MoE; unrelated config issues." }, { "left": "issue:43761", "right": "issue:44242", "accept": false, - "reason": "One is a CLIPVisionModel regression; the other is an MoE load-balancing-loss bug." + "reason": "CLIP hidden_states regression vs MoE load-balancing loss gating; separate model behaviors." }, { "left": "issue:44792", "right": "issue:44977", "accept": false, - "reason": "A janus image-generation test failure is not the same bug as Qwen3.5 flash-attention misgeneration." + "reason": "janus image-generation test failure vs Qwen3.5 flash-attention generation bug; different failure surfaces." }, { "left": "issue:43931", "right": "issue:44060", "accept": false, - "reason": "Different model-loading failures: weight-shape mismatch versus incorrect tied-weights warning." + "reason": "Qwen3-VL weight-shape load mismatch vs incorrect tied-weights warning; not the same underlying defect." }, { "left": "issue:44479", "right": "issue:44734", "accept": false, - "reason": "Both touch generation/runtime behavior, but one is a video-input regression and the other is KV-cache continuation indexing." + "reason": "Video-input regression in Qwen VL models vs serve KV-cache indexing crash; unrelated paths." }, { "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "Non-persistent-buffer initialization and GPTNeoX rotary_pct reload are different root causes." + "reason": "Non-persistent buffer junk regression vs GPTNeoX rotary_pct reload defaulting; different config/runtime problems." }, { "left": "issue:44190", "right": "issue:44964", "accept": false, - "reason": "Local dataset loading in a trainer script is unrelated to loading a multimodal model preset." + "reason": "Example script dataset loading failure vs Phi-4 multimodal model loading error; not duplicates." }, { "left": "issue:44792", "right": "issue:45600", "accept": false, - "reason": "A failing janus generation test and stale auto_mappings references are different problems." + "reason": "Janus test failure vs removed Sam3LiteText config references in auto_mappings; unrelated CI/test issues." }, { "left": "issue:44464", "right": "issue:45563", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency is not the same as a stale num_return_sequences warning." + "reason": "Chunked generation inconsistency with compiled forward vs stale num_return_sequences warning; different generation bugs." }, { "left": "issue:43827", "right": "issue:43994", "accept": false, - "reason": "Docs still referencing removed pipeline APIs is unrelated to a broken SigLIP model output." + "reason": "Docs still referencing pipeline() vs SigLIP2 nonsensical runtime results; documentation and model behavior are separate." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Python parsing/import failure and flash_attention s_aux handling are separate defects." + "reason": "Python 3.13 import parsing error vs flash_attention s_aux=None crash; unrelated breakages." }, { "left": "issue:44521", "right": "issue:45381", "accept": false, - "reason": "Both involve multimodal chat/video behavior, but the bugs are different: assistant mask generation versus vision_position_ids." + "reason": "Both are multimodal-preprocessing bugs, but assistant_masks being zero and vision_position_ids being wrong are different code paths and fixes." }, { "left": "issue:35141", "right": "issue:42490", "accept": false, - "reason": "Token-embedding reinit after resize and a trailing-slash import warning are unrelated." + "reason": "Embedding resize reinitialization bug vs trailing-slash local-path warning; no shared underlying issue." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "Qwen3 auto device-mapping CUDA asserts are unrelated to the category-limit RuntimeError." + "reason": "Qwen3 auto device mapping cuda assert vs category-count limit error; distinct runtime failures." }, { - "left": "issue:43065", - "right": "issue:44610", + "left": "issue:45803", + "right": "issue:45987", "accept": false, - "reason": "A dummy Conv2d in Sam3PixelDecoder and a processor/model input-size mismatch are different bugs." + "reason": "Bare except swallowing errors vs StaticCache length contract mismatch; unrelated utilities." }, { - "left": "issue:45803", - "right": "issue:45987", + "left": "issue:43065", + "right": "issue:44610", "accept": false, - "reason": "Bare except in tensor conversion and StaticCache.get_seq_length() returning the wrong type are unrelated." + "reason": "Dummy Conv2d in Sam3PixelDecoder vs OmDet-Turbo processor/model size mismatch; different model-specific problems." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "Missing image_utils import and Qwen3.5 chat crashes are different code paths and symptoms." + "reason": "Missing import from image_utils vs Qwen3.5 chat crash; unrelated defects." }, { "left": "issue:43335", "right": "issue:44855", "accept": false, - "reason": "A sparse-layer config bug and a Python 3.13 import/parsing failure are not the same issue." + "reason": "SwitchTransformers sparse-layer creation bug vs Python 3.13 import parsing error; different areas." }, { "left": "issue:43644", "right": "issue:44913", "accept": false, - "reason": "The non-persistent-buffer junk regression is distinct from GPTNeoX rotary_pct being lost on reload." + "reason": "Both involve config/regression symptoms, but non-persistent buffer junk and rotary_pct reload behavior are not the same bug." }, { "left": "issue:44077", - "right": "issue:44079", + "right": "issue:44877", "accept": false, - "reason": "Optional post_init handling and ModelOutput key assignment are unrelated framework bugs." + "reason": "Optional post_init allowance vs strict config blocking granite_speech; related theme, but different concrete change and failure." }, { "left": "issue:43976", "right": "issue:44855", "accept": false, - "reason": "A Python-version compatibility issue is not the same as a DebertaV2Model indentation/parsing regression." + "reason": "Python-version compatibility issues, but one is version support failure and the other is a parser/indentation import error; not a duplicate." }, { "left": "issue:43550", "right": "issue:44190", "accept": false, - "reason": "Bamba torch.compile/SDPA failure is unrelated to dataset loading in a training script." + "reason": "Bamba torch.compile/SDPA bug vs local dataset loading in a training script; unrelated." }, { "left": "issue:43540", "right": "issue:44734", "accept": false, - "reason": "Qwen3OmniMoe video-input ValueError and serve KV-cache indexing crash are different failures." + "reason": "Qwen3OmniMoe video-input ValueError vs serve KV-cache indexing crash; different subsystems." }, { "left": "issue:45127", "right": "issue:45357", "accept": false, - "reason": "LoRA merge collapse with extended vocab and incorrect visual-encoder save keys are unrelated." + "reason": "LoRA merge with extended vocab collapsing model vs incorrect visual encoder keys saved in Qwen3.5; separate save/merge issues." }, { "left": "issue:44737", "right": "issue:45803", "accept": false, - "reason": "XLNet CPU arange device placement and a bare-except swallowing errors are different defects." + "reason": "XLNet CPU arange bug vs bare except swallowing errors; not the same code path or symptom." } ] }, @@ -9964,17 +10058,17 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36246", "issue:38175", "issue:38617", - "issue:39692", "issue:41628", "issue:41950", "issue:42175", "issue:42907", "issue:43065", + "issue:43116", "issue:43295", "issue:43335", "issue:43404", @@ -10017,10 +10111,10 @@ ], "soft_pairs": [ "issue:44112|issue:45600", - "issue:43335|issue:44190", "issue:44462|issue:45907", + "issue:43335|issue:44190", "issue:46082|issue:46121", - "issue:39692|issue:44190", + "issue:43116|issue:44190", "issue:44938|issue:45542", "issue:45276|issue:45584", "issue:43295|issue:45276", @@ -10028,9 +10122,9 @@ "issue:36246|issue:41628", "issue:45245|issue:45584", "issue:43650|issue:44220", - "issue:44186|issue:44734", - "issue:42175|issue:44279", "issue:36246|issue:38617", + "issue:42175|issue:44279", + "issue:44186|issue:44734", "issue:41950|issue:44016", "issue:44246|issue:45003", "issue:44683|issue:45446", @@ -10048,220 +10142,220 @@ "issue:42907|issue:43441", "issue:43295|issue:45335" ], - "prepared_review_unit_hash": "a4bd2e9513250d84aaab85b622c21f62e9116bcc531e94792a7bc2c27f755572", + "prepared_review_unit_hash": "20689046d7b1c35d566095ae2528820d5218de2f717cc8a13794be4c26d4ecf5", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36960, - "estimated_input_tokens": 9240, - "estimated_eval_tokens": 18736 + "serialized_chars": 36948, + "estimated_input_tokens": 9237, + "estimated_eval_tokens": 18730 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous: it mixes import/API breakages, model-specific regressions, CI/doc issues, and unrelated config/runtime bugs. No soft pair looks like the same concrete fixable bug or change.", - "confidence": 0.84, - "canonical_issue_reason": "Issue 41628 is the clearest broad, user-facing API regression in the set: a top-level import failure that fits the recurring import-breakage theme better than the narrower model/script-specific reports.", + "summary": "The cluster is very heterogeneous: it mixes import/export regressions, model-specific configuration bugs, backend/dependency problems, and notebook/script failures. None of the soft edges look like true duplicates of the same underlying bug or change.", + "confidence": 0.91, + "canonical_issue_reason": "issue:41628 is the broadest, clearest representative of the small import-regression subset in this set, but the overall cluster is too diverse to have a strong true canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 41628 is the best representative because it describes a concrete, high-impact Transformers import regression with a clear repro and wider applicability than the more specialized issues around it.", + "best_issue_reason": "issue:41628 is the best global anchor by title clarity and breadth of symptom, though it still only represents one slice of the cluster rather than the whole.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "Both are CI-related, but one is a GraniteSpeech test failure and the other is a stale auto_mappings reference; different bugs and different fixes." + "reason": "Both are CI-related, but they involve different models, different files, and different failure modes." }, { - "left": "issue:43335", - "right": "issue:44190", + "left": "issue:44462", + "right": "issue:45907", "accept": false, - "reason": "A SwitchTransformers config bug and an image-classification training script dataset-loading problem are unrelated." + "reason": "One is AutoTokenizer ignoring tokenizer.json; the other is list_repo_files not forwarding revision. Related area, different bug." }, { - "left": "issue:44462", - "right": "issue:45907", + "left": "issue:43335", + "right": "issue:44190", "accept": false, - "reason": "One is AutoTokenizer ignoring tokenizer.json, the other is list_repo_files not forwarding revision; both touch repo/file loading but not the same bug." + "reason": "SwitchTransformers config initialization is unrelated to a local-dataset loading failure in an example script." }, { "left": "issue:46082", "right": "issue:46121", "accept": false, - "reason": "Llama head_dim validation and rope-parameter JSON list handling are distinct config-validation failures." + "reason": "LlamaConfig head_dim validation and rope-param JSON list handling are separate config-validation bugs." }, { - "left": "issue:39692", + "left": "issue:43116", "right": "issue:44190", "accept": false, - "reason": "A SigLIP2 docs example error and a local dataset loading failure in a training script are not the same issue." + "reason": "Multi-label classification output logic is unrelated to dataset loading in a different example script." }, { "left": "issue:44938", "right": "issue:45542", "accept": false, - "reason": "Python 3.14 load failure and a missing TensorFlow backend when only tensorboard is installed are unrelated environment/backend problems." + "reason": "Python 3.14 import/load failure and missing TensorFlow backend wiring are different root causes." }, { "left": "issue:45276", "right": "issue:45584", "accept": false, - "reason": "Gemma4 embedding resize propagation and Whisper empty-transcription generation are different model behaviors." + "reason": "Gemma4 embedding-resize behavior is unrelated to Whisper empty-transcription generation." }, { "left": "issue:43295", "right": "issue:45276", "accept": false, - "reason": "Processor/tokenizer regression and Gemma4 token-embedding resize semantics are separate API bugs." + "reason": "Processor.tokenizer regression is a different code path from Gemma4 token-embedding resizing." }, { "left": "issue:43479", "right": "issue:45375", "accept": false, - "reason": "Default multimodal config initialization and missing deepstack_visual_indexes serialization are different config issues." + "reason": "Phi4Multimodal default sub-config initialization and missing deepstack_visual_indexes are different config bugs." }, { "left": "issue:36246", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but they are for different symbols/modules and look like separate export problems." + "reason": "Both are import errors, but one is a model-module symbol and the other is a top-level AutoImageProcessor export." }, { "left": "issue:45245", "right": "issue:45584", "accept": false, - "reason": "Category cardinality limits and Whisper generation on empty output are unrelated." + "reason": "Category cardinality limits and Whisper special-token alignment are unrelated." }, { "left": "issue:43650", "right": "issue:44220", "accept": false, - "reason": "A placeholder issue and an fbank feature extraction bug are not related." + "reason": "Generic content and fbank feature extraction are not the same bug." }, { - "left": "issue:44186", - "right": "issue:44734", + "left": "issue:36246", + "right": "issue:38617", "accept": false, - "reason": "LayoutLMv2 tokenizer crashes and serve/KV-cache tensor indexing failures affect different code paths." + "reason": "Different missing symbols from different modules; same symptom class, not the same defect." }, { "left": "issue:42175", "right": "issue:44279", "accept": false, - "reason": "Missing TensorFlow in a torch install and a vague dependency issue are not the same concrete bug." + "reason": "Pip extra/backend dependency packaging and a vague dependency issue are not concrete duplicates." }, { - "left": "issue:36246", - "right": "issue:38617", + "left": "issue:44186", + "right": "issue:44734", "accept": false, - "reason": "Both are ImportErrors, but they involve different missing symbols in different modules; the fixes would not be merged together." + "reason": "Tokenizer padding/truncation crash is unrelated to serve-time KV-cache continuation indexing." }, { "left": "issue:41950", "right": "issue:44016", "accept": false, - "reason": "A video-classification pipeline bug and a notebook syntax error are unrelated." + "reason": "Pipeline processor lookup and a notebook syntax error are completely different issues." }, { "left": "issue:44246", "right": "issue:45003", "accept": false, - "reason": "Import performance complaints and unsafe sys.modules access may be loosely related, but they are not the same underlying bug." + "reason": "Import slowness and unsafe sys.modules access may be adjacent, but the reports describe different failures." }, { "left": "issue:44683", "right": "issue:45446", "accept": false, - "reason": "Both are flex_attention-related, but one is a compiled-op failure on torch >= 2.9 and the other is a version-check/import gating bug." + "reason": "Compiled flex_attention failure on new torch and a version-check bug for AuxRequest import are not the same concrete problem." }, { "left": "issue:43404", "right": "issue:45216", "accept": false, - "reason": "Weight tying in Mistral3 and incorrect save_pretrained output for Qwen3.5 are different model serialization/training issues." + "reason": "Mistral3 lm_head tying and Qwen3.5 save_pretrained regression affect different model behaviors." }, { "left": "issue:38175", "right": "issue:43065", "accept": false, - "reason": "Zero probabilities in SigLIP2 and a dummy Conv2d in Sam3PixelDecoder are unrelated." + "reason": "Zero probabilities in SigLIP2 is unrelated to a dummy Conv2d in Sam3PixelDecoder." }, { "left": "issue:44016", "right": "issue:44220", "accept": false, - "reason": "Notebook syntax and audio feature extraction are different failures." + "reason": "Notebook syntax error and audio feature extraction are unrelated." }, { "left": "issue:43643", "right": "issue:44496", "accept": false, - "reason": "Missing fields from trust_remote_code configs and unrecognized model/type handling are different config-loading problems." + "reason": "Missing fields from trust_remote_code config loading and unrecognized-model config.json validation are different config-loader failures." }, { "left": "issue:44964", "right": "issue:45600", "accept": false, - "reason": "A Phi-4 multimodal load regression and a stale Sam3LiteText mapping reference are separate model/config issues." + "reason": "Phi-4 multimodal load failure and stale auto_mappings references to removed configs are different issues." }, { "left": "issue:44112", "right": "issue:44964", "accept": false, - "reason": "CI test flakiness in GraniteSpeech and a Phi-4 loading regression are different bugs." + "reason": "GraniteSpeech CI device override and Phi-4 multimodal model loading are unrelated." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "GLM-4.7-Flash unit-test loading failure and Phi-4 multimodal loading failure are model-specific, not the same bug." + "reason": "Both involve model loading, but they are different models with different failure contexts." }, { "left": "issue:44734", "right": "issue:45632", "accept": false, - "reason": "Serve/KV-cache tensor indexing and trust_remote_code cache-path collisions are unrelated." + "reason": "Serve KV-cache indexing and trust_remote_code cache-path collisions are unrelated." }, { "left": "issue:44561", "right": "issue:45632", "accept": false, - "reason": "A removed helper breaking trust_remote_code models and a local-model cache collision are different trust_remote_code problems." + "reason": "Removal of is_torch_fx_available breaks remote-code models; cache-path collisions are a different trust_remote_code bug." }, { "left": "issue:43976", "right": "issue:44987", "accept": false, - "reason": "Python version compatibility and loading a specific model under transformers>=5.1.0 are not the same concrete issue." + "reason": "Python version support and loading a specific model with transformers>=5.1.0 are different problems." }, { "left": "issue:43531", "right": "issue:45600", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and stale auto_mappings references are unrelated." + "reason": "Qwen3-MoE sliding_window behavior has nothing to do with stale auto_mappings references." }, { "left": "issue:42907", "right": "issue:43441", "accept": false, - "reason": "Saving dequantized Ministral/Devstral models and FlashAttention failures are different issues in the same family only by name." + "reason": "Saving dequantized models and FlashAttention failure in Ministral-3 are distinct code paths." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "Processor/tokenizer regression and decoder.embed_tokens resize propagation are distinct API behaviors." + "reason": "Processor.tokenizer regression and t5gemma embed_tokens resizing are separate model/API bugs." } ] }, @@ -10283,7 +10377,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:38175", "issue:39692", @@ -10337,9 +10431,9 @@ "soft_pairs": [ "issue:42490|issue:45632", "issue:43526|issue:43901", - "issue:43673|issue:44336", "issue:43441|issue:45588", "issue:44496|issue:45042", + "issue:43673|issue:44336", "issue:43335|issue:45593", "issue:44016|issue:44062", "issue:43824|issue:44933", @@ -10355,218 +10449,218 @@ "issue:44242|issue:45200", "issue:44521|issue:45325", "issue:43299|issue:45357", - "issue:44351|issue:45278", - "issue:43577|issue:45216", "issue:38175|issue:44617", + "issue:43577|issue:45216", + "issue:44351|issue:45278", "issue:41950|issue:45020", - "issue:39692|issue:43901", "issue:44279|issue:45405", "issue:44779|issue:45812", "issue:41950|issue:45823", + "issue:39692|issue:43901", "issue:43295|issue:44779" ], - "prepared_review_unit_hash": "c133a80a7025d31b50e5fbc1e24b25a8cfdcff66b610781a95f1b441f0b9a2a8", + "prepared_review_unit_hash": "8e4efc9ba432e1338c1b9d1d3f64a23f07997d88b2b6cf470c37fdd10bda8290", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36389, - "estimated_input_tokens": 9098, - "estimated_eval_tokens": 18452 + "serialized_chars": 36383, + "estimated_input_tokens": 9096, + "estimated_eval_tokens": 18448 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is very heterogeneous: the soft pairs mostly share broad topical language (import errors, multimodal configs, tokenizer regressions, flash-attention, docs) but not the same concrete bug. I would reject all soft edges and treat issue:45278 as only a loose import-regression anchor, not a true duplicate canonical.", - "confidence": 0.9, - "canonical_issue_reason": "No single canonical duplicate set stands out. If forced to anchor the cluster, issue:45278 is the broadest import-regression report, but the rest of the items are too diverse to justify a true canonical duplicate.", + "summary": "These items are mostly unrelated single-issue reports spanning different model families, pipelines, and regressions; I found no strong duplicate/merge candidates among the soft pairs.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45278 is the broadest representative regression report in the set, covering multiple import failures after an upgrade and plausibly subsuming narrower import-surface breakages.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best overall anchor because it is the broadest and most central of the few import-related reports; the other issues are mostly unrelated one-off bugs.", + "best_issue_reason": "issue:45278 is the best global representative because it has the clearest high-impact upgrade-regression framing and broad user reach.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42490", "right": "issue:45632", "accept": false, - "reason": "Both are path/loading-related, but one is a slash-end warning and the other is a trust_remote_code cache collision; different bugs." + "reason": "Trailing-slash local-path import warning and trust_remote_code cache-path collision are different path-handling bugs." }, { "left": "issue:43526", "right": "issue:43901", "accept": false, - "reason": "Image-label reduction bug vs pipeline docs mismatch; unrelated behavior and code paths." - }, - { - "left": "issue:43673", - "right": "issue:44336", - "accept": false, - "reason": "Generation cache issue in chunked prefill vs ANSI-color output in loading_report; no shared bug." + "reason": "A processor output bug and a documentation mismatch about return_all_scores are not the same issue." }, { "left": "issue:43441", "right": "issue:45588", "accept": false, - "reason": "Both mention FlashAttention, but one is a model loading/failure report and the other is an AttributeError on s_aux=None; too different to merge." + "reason": "Both mention flash attention, but one is model-specific Ministral-3 loading and the other is a generic sink-less s_aux=None crash." }, { "left": "issue:44496", "right": "issue:45042", "accept": false, - "reason": "Model config import failure vs PIL image processor requiring torchvision; unrelated." + "reason": "Unrecognized model config loading and PIL image processor torchvision dependency are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache lookup during chunked_prefill and ANSI color output in loading_report are unrelated." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "SwitchTransformers sparse-layer construction bug vs D-FINE auxiliary-loss omission; different models and logic." + "reason": "Sparse-layer construction with num_sparse_encoder_layers=0 is different from D-FINE auxiliary-loss handling." }, { "left": "issue:44016", "right": "issue:44062", "accept": false, - "reason": "Notebook syntax error vs tokenizer AddedToken keyword conflict; separate issues." + "reason": "A notebook syntax error and an AddedToken keyword conflict are separate bugs." }, { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "Qwen2.5-VL import failure vs nonexistent image_utils import; both are import problems but not the same module or bug." + "reason": "These are different import failures in different modules/symbols, not the same concrete bug." }, { "left": "issue:44075", "right": "issue:44368", "accept": false, - "reason": "SGD optimizer args ignored vs tie_word_embeddings warning; unrelated." + "reason": "Unused SGD args and a tie_word_embeddings warning in ms-swift are unrelated." }, { "left": "issue:43299", "right": "issue:45216", "accept": false, - "reason": "Qwen3VL model-loading regression vs Qwen3.5 save_pretrained regression; same family, different code paths and symptoms." + "reason": "One is a Qwen3VL model loading failure; the other is an incorrect save_pretrained checkpoint regression." }, { "left": "issue:43381", "right": "issue:45593", "accept": false, - "reason": "Gradient checkpointing in eval mode vs D-FINE auxiliary losses; no overlap beyond being model bugs." + "reason": "Gradient-checkpointing eval-mode behavior and D-FINE auxiliary-loss omission are different code paths." }, { "left": "issue:43901", "right": "issue:44496", "accept": false, - "reason": "Pipeline docs note vs unrecognized model/config loading error; unrelated." + "reason": "A pipeline docs mismatch and a model-import/config error are not the same issue." }, { "left": "issue:43976", "right": "issue:44279", "accept": false, - "reason": "Python version compatibility problem vs generic dependency issue; not the same bug." + "reason": "Python-version compatibility breakage and a vague dependency issue do not point to one concrete bug." }, { "left": "issue:43650", "right": "issue:46209", "accept": false, - "reason": "Placeholder/data request vs FP8 inference failure; unrelated." + "reason": "Placeholder/non-technical issue text and an FP8 B200 inference failure are unrelated." }, { "left": "issue:44496", "right": "issue:45759", "accept": false, - "reason": "Unrecognized model config vs AutoModelForCausalLM not unwrapping text_config; distinct multimodal-loading problems." + "reason": "These are different Qwen-related loading problems with different failure modes and code paths." }, { "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "Token embedding resize bug vs Whisper empty-transcription generation failure; different subsystems." + "reason": "Embedding-resize propagation and Whisper empty-transcription failure after align_special_tokens are unrelated." }, { "left": "issue:43479", "right": "issue:43525", "accept": false, - "reason": "Phi4Multimodal default-config initialization vs Llama4 missing pad_token_id; both config issues but not the same defect." + "reason": "Both are config issues, but they affect different model classes and different defaults/attributes." }, { "left": "issue:44242", "right": "issue:45200", "accept": false, - "reason": "MoE load-balancing loss gating bug vs Gemma4 mm_token_type_ids defaulting; different training behaviors." + "reason": "Missing load-balancing loss and mm_token_type_ids defaulting are separate training semantics bugs." }, { "left": "issue:44521", "right": "issue:45325", "accept": false, - "reason": "All-zero assistant mask bug vs rope-index temporal scaling bug; both multimodal but not the same underlying change." + "reason": "All-zero assistant masks and rope-index temporal scaling are different multimodal preprocessing bugs." }, { "left": "issue:43299", "right": "issue:45357", "accept": false, - "reason": "Qwen3.5/Qwen3VL load regression vs save_pretrained visual-key regression; related family, different failures." + "reason": "These are distinct save/load regressions for Qwen3.5 rather than one shared bug." }, { - "left": "issue:44351", - "right": "issue:45278", + "left": "issue:38175", + "right": "issue:44617", "accept": false, - "reason": "HybridCache import error may be one symptom of broader import regressions, but the titles are too broad/specific to confirm the same underlying bug." + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are unrelated." }, { "left": "issue:43577", "right": "issue:45216", "accept": false, - "reason": "BLIP2 dtype propagation bug vs Qwen3.5 checkpoint save regression; unrelated." + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint saving are unrelated issues." }, { - "left": "issue:38175", - "right": "issue:44617", + "left": "issue:44351", + "right": "issue:45278", "accept": false, - "reason": "SigLIP2 zero-probabilities issue vs Sam3Video OOM; completely different problems." + "reason": "HybridCache import failure may be a symptom in the broader import-regression report, but it is not clearly the same concrete bug." }, { "left": "issue:41950", "right": "issue:45020", "accept": false, - "reason": "Video-classification pipeline processor lookup bug vs remote_code breakage in recent versions; not the same issue." - }, - { - "left": "issue:39692", - "right": "issue:43901", - "accept": false, - "reason": "SigLIP2 docs example errors vs text-classification docs mismatch; both docs-related but different examples and failures." + "reason": "Video-classification processor lookup and remote_code breakage are different failures." }, { "left": "issue:44279", "right": "issue:45405", "accept": false, - "reason": "Generic dependency issue vs MIN_PEFT_VERSION bump/release problem; unrelated." + "reason": "A generic dependency issue and an unreleased MIN_PEFT_VERSION bump are not the same bug." }, { "left": "issue:44779", "right": "issue:45812", "accept": false, - "reason": "Deepseek tokenizer regression vs Granite tokenizer regression; both tokenizer bugs, but different model families and likely different fixes." + "reason": "Deepseek tokenizer regression and Granite tokenizer regression affect different model families and behaviors." }, { "left": "issue:41950", "right": "issue:45823", "accept": false, - "reason": "Video-classification processor lookup bug vs Gemma4 PLE device mismatch; unrelated." + "reason": "Video-classification processor lookup and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "These are both docs-related, but one is a SigLIP2 example error report and the other is a pipeline docs mismatch." }, { "left": "issue:43295", "right": "issue:44779", "accept": false, - "reason": "Processor/tokenizer regression with multimodal inputs vs Deepseek tokenizer wrong results; different code paths and model classes." + "reason": "Custom processor.tokenizer/images regression and Deepseek tokenizer incorrect results are different issues." } ] }, @@ -10588,7 +10682,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:33290", "issue:42175", @@ -10663,20 +10757,20 @@ "issue:43441|issue:44683", "issue:44016|issue:45823", "issue:44671|issue:44779", - "issue:42175|issue:43976", "issue:43723|issue:44162", - "issue:43901|issue:43994", + "issue:42175|issue:43976", "issue:43262|issue:44521", + "issue:43901|issue:43994", "issue:43673|issue:43761" ], - "prepared_review_unit_hash": "2d226b252c2693489c5d52387b60d993a4440c3bae14104c035adb38cd540d75", + "prepared_review_unit_hash": "50718ffb6bae847f8c2d1a390a43c4feae0a17f69f3c3d106cf9d0c606192ef1", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, @@ -10691,138 +10785,138 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The items do not form a true duplicate cluster; they span many unrelated bugs across tokenizers, model loading, processors, docs, and packaging. I would treat issue 44521 as the best representative issue, but none of the soft-edge pairs look like the same underlying bug/change.", - "confidence": 0.92, - "canonical_issue_reason": "Best representative issue here: it is a concrete, reproducible API regression in `apply_chat_template`, has multiple inbound references, and is broader/more actionable than the many model-specific or unrelated reports.", + "summary": "The set looks heterogeneous rather than one true duplicate cluster; most soft pairs are only broad topical matches (often v5/tokenizer/load/save regressions) and should be rejected. If a single issue must anchor the cluster, the tokenizer-loading regression around AutoTokenizer is the closest fit.", + "confidence": 0.43, + "canonical_issue_reason": "issue:44462 is the best provisional anchor because it is a concrete v5 tokenizer-loading regression and is the closest match to the other tokenizer-related near-duplicates in the set.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44521 is the strongest standalone issue: clear symptom, good downstream impact, active discussion, and a specific code-path to fix.", + "best_issue_reason": "issue:44462 is the most representative of the cluster\u2019s strongest theme (tokenizer loading/serialization regressions in v5), even though the overall cluster is not truly cohesive.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44683", "right": "issue:45542", "accept": false, - "reason": "Different subsystems and failure modes: compiled flex attention on new torch vs missing TensorFlow backend installation." + "reason": "Compiled flex_attention failure and TensorFlow backend installation are unrelated bugs." }, { "left": "issue:43299", "right": "issue:43854", "accept": false, - "reason": "Both are model-loading problems, but they concern different models and likely different code paths." + "reason": "Both involve model loading, but they are different model-specific failures with different underlying code paths." }, { "left": "issue:43976", "right": "issue:45405", "accept": false, - "reason": "Unrelated packaging/version regressions: Python support vs an over-bumped PEFT minimum version." + "reason": "Python version compatibility and an unreleased PEFT minimum version are separate release/dependency issues." }, { "left": "issue:43650", "right": "issue:46132", "accept": false, - "reason": "No shared bug: one is a placeholder/data issue, the other is a behavioral change in attention registration." + "reason": "A placeholder issue and an AttentionInterface behavior change do not describe the same change or bug." }, { "left": "issue:44462", "right": "issue:45081", "accept": false, - "reason": "Both involve tokenizers, but one is AutoTokenizer precedence for tokenizer.json and the other is a Mistral regex-patch crash." + "reason": "Both are tokenizer-loading regressions, but one ignores tokenizer.json while the other crashes in Mistral regex patching." }, { "left": "issue:43450", "right": "issue:44279", "accept": false, - "reason": "Completely unrelated: video processor batching shape bug vs a general dependency issue." + "reason": "Video processor shape handling and a generic dependency issue are unrelated." }, { "left": "issue:44297", "right": "issue:44462", "accept": false, - "reason": "Different bugs in tokenizer serialization vs tokenizer loading precedence; related area, not the same underlying defect." + "reason": "Tokenizer class serialization mismatch is different from AutoTokenizer ignoring tokenizer.json on load." }, { "left": "issue:44016", "right": "issue:44291", "accept": false, - "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated." + "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated failure modes." }, { "left": "issue:45081", "right": "issue:45907", "accept": false, - "reason": "Different issues: Mistral tokenizer regex patch crash vs list_repo_files revision forwarding in CI." + "reason": "Tokenizer regex patch crash and list_repo_files revision forwarding are different code paths." }, { "left": "issue:44466", "right": "issue:45276", "accept": false, - "reason": "Both touch Gemma4, but one is tied-weight serialization and the other is resize_token_embeddings behavior." + "reason": "lm_head serialization inconsistency and Gemma4 embedding resize behavior are distinct model bugs." }, { "left": "issue:43441", "right": "issue:45834", "accept": false, - "reason": "Different models and symptoms: FlashAttention failure vs OCR index error." + "reason": "FlashAttention failure on Ministral and OCR index error in Kosmos2.5 are unrelated model issues." }, { "left": "issue:45600", "right": "issue:45712", "accept": false, - "reason": "Both affect repository maintenance/CI, but they are separate file/reference problems with no shared code path." + "reason": "Removed auto-mappings entries and leftover dummy classes are separate cleanup/CI problems." }, { "left": "issue:42994", "right": "issue:43317", "accept": false, - "reason": "Both touch quantization/loading, but one is saving a quantized model and the other is dequantized offload loading." + "reason": "Quantized model saving and dequantized model loading with offload are different quantization workflows." }, { "left": "issue:43653", "right": "issue:45593", "accept": false, - "reason": "Tokenizer special-token decoding bug vs D-FINE auxiliary-loss behavior; unrelated." + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss handling are unrelated." }, { "left": "issue:33290", "right": "issue:45656", "accept": false, - "reason": "Both mention DeepSpeed/optimizer, but the concrete bugs differ: Adafactor OOM vs optimizer.step being called twice." + "reason": "OOM from Adafactor in DeepSpeed and optimizer.step being called twice are different DeepSpeed bugs." }, { "left": "issue:44623", "right": "issue:45397", "accept": false, - "reason": "Processor save-pretrained file omission and Gemma-4 zero3 from_pretrained are different regressions." + "reason": "Missing processor save files and Gemma-4 ZeRO3 from_pretrained are separate save/load issues." }, { "left": "issue:44623", "right": "issue:44749", "accept": false, - "reason": "No match: missing processor save files vs performance regression after upgrade." + "reason": "Processor saving missing files and a data-filtering slowdown are unrelated." }, { "left": "issue:43065", "right": "issue:44898", "accept": false, - "reason": "Different vision bugs in different models: dummy Conv2d placeholder vs Perceiver interpolation failure." + "reason": "A dummy Conv2d in Sam3PixelDecoder and Perceiver non-default-resolution failure are different model bugs." }, { "left": "issue:44261", "right": "issue:44263", "accept": false, - "reason": "Different model components and symptoms: missing rms_norm_eps precision drift vs torch.split return-value handling." + "reason": "Missing rms_norm_eps precision issue and torch.split return semantics are unrelated." }, { "left": "issue:44361", "right": "issue:45593", "accept": false, - "reason": "Tokenizer attribute error vs D-FINE loss behavior; unrelated." + "reason": "MLukeTokenizer AttributeError and D-FINE auxiliary-loss behavior are unrelated." }, { "left": "issue:43441", "right": "issue:44683", "accept": false, - "reason": "Different feature failures: model-specific FlashAttention regression vs compiled flex_attention failing on torch 2.9+." + "reason": "FlashAttention breakage for a specific model and compiled flex_attention failure are different attention-stack issues." }, { "left": "issue:44016", @@ -10834,37 +10928,37 @@ "left": "issue:44671", "right": "issue:44779", "accept": false, - "reason": "Both are model-specific wrong-results reports, but they concern different tokenizers/models and distinct regressions." - }, - { - "left": "issue:42175", - "right": "issue:43976", - "accept": false, - "reason": "Packaging/backend dependency mismatch vs Python version support breakage; not the same bug." + "reason": "CamemBERT masked-LM regression and Deepseek tokenizer regression are different model/tokenizer bugs." }, { "left": "issue:43723", "right": "issue:44162", "accept": false, - "reason": "AutoTokenizer loading regression and ESM2 breakage are different issues." + "reason": "Tokenizer loading regression and ESM2 model breakage are not the same underlying defect." }, { - "left": "issue:43901", - "right": "issue:43994", + "left": "issue:42175", + "right": "issue:43976", "accept": false, - "reason": "Docs mismatch for a pipeline option vs incorrect model/pipeline outputs; not the same underlying change." + "reason": "Missing TensorFlow backend after pip install and Python 3.9/3.10 compatibility are unrelated." }, { "left": "issue:43262", "right": "issue:44521", "accept": false, - "reason": "Same API name, but different modalities and symptoms: default 16kHz audio processing vs multimodal assistant mask generation." + "reason": "Default audio sampling rate and multimodal assistant mask generation are different apply_chat_template bugs." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Documentation mismatch for return_all_scores and incorrect SigLIP2 model outputs are unrelated." }, { "left": "issue:43673", "right": "issue:43761", "accept": false, - "reason": "Generation cache regression and CLIPVision hidden_states bug are unrelated." + "reason": "Generation cache missing and CLIPVision hidden_states regression are different v5 regressions." } ] }, @@ -10886,7 +10980,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36246", "issue:41628", @@ -10960,8 +11054,8 @@ "issue:42886|issue:46132", "issue:36246|issue:42757", "issue:36246|issue:44351", - "issue:44336|issue:44485", "issue:44246|issue:44871", + "issue:44336|issue:44485", "issue:45003|issue:45561", "issue:43673|issue:44561", "issue:44779|issue:45292", @@ -10970,220 +11064,220 @@ "issue:44242|issue:44857", "issue:43352|issue:45250" ], - "prepared_review_unit_hash": "ea79cb538e4fdc291f985295c7e0e9840a170a2efb34e5f2bafba8e320daa6e8", + "prepared_review_unit_hash": "185909242fa3092bcb1c4c9bf9da7f58c7b714394f2e28c277657cee525d59f3", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36692, - "estimated_input_tokens": 9173, - "estimated_eval_tokens": 18602 + "serialized_chars": 36685, + "estimated_input_tokens": 9172, + "estimated_eval_tokens": 18600 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly loose semantic similarity rather than true duplicates. I rejected all soft edges, and there are no PRs in the set. If forced to pick a representative, issue:44246 is the least-bad broad node, but it is only a weak canonical.", - "confidence": 0.66, - "canonical_issue_reason": "issue:44246 is the broadest, most generic report in the cluster and sits on multiple soft-similarity edges, so it is the best available representative despite the cluster being heterogeneous.", + "summary": "This cluster is mostly a grab bag of distinct Transformers regressions (import/export failures, model-loading issues, pipeline/config bugs). The only pair that looks like the same underlying bug is the Qwen2.5-VL import/export failure family.", + "confidence": 0.78, + "canonical_issue_reason": "issue:43824 is the clearest and most central representative of the Qwen2.5-VL import/export regression, with higher discussion and inbound references than the older sibling report.", "canonical_pr_reason": null, - "best_issue_reason": "Same as canonical: it is the most general issue and the closest thing to a central triage anchor here, though not a true duplicate hub.", + "best_issue_reason": "issue:43824 is the best standalone issue to anchor this cluster because it is specific, well-scoped, and most clearly describes a real duplicate-prone import failure.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43784", "right": "issue:45542", "accept": false, - "reason": "Both are import/backend failures, but the symbols and failure modes differ (`nn` import vs TensorBoard/TensorFlow backend)." + "reason": "Both are import-time failures, but they involve different missing backends/variables and different packages; not the same bug." }, { "left": "issue:43824", "right": "issue:43976", "accept": false, - "reason": "Missing Qwen2.5-VL export vs Python version compatibility; same package, different bugs." + "reason": "Qwen2.5-VL import failure vs Python version compatibility; unrelated problems." }, { "left": "issue:43450", "right": "issue:44617", "accept": false, - "reason": "Video processor shape bug vs SAM video OOM; different symptoms and code paths." + "reason": "Video shape bug vs CUDA OOM; different failure modes and code paths." }, { "left": "issue:44297", "right": "issue:45397", "accept": false, - "reason": "Tokenizer save config mismatch is unrelated to Gemma-4 ZeRO3 loading." + "reason": "Tokenizer save_pretrained metadata mismatch vs ZeRO3 from_pretrained loading failure; not the same issue." }, { "left": "issue:43525", "right": "issue:43881", "accept": false, - "reason": "Missing `pad_token_id` on Llama4Config is unrelated to glm-4v-9b loading failure." + "reason": "Missing pad_token_id on one model config vs a different model loading failure; too model-specific to be duplicates." }, { "left": "issue:43901", "right": "issue:44246", "accept": false, - "reason": "Docs mismatch for `return_all_scores` is not the same as intermittent import slowness." + "reason": "Docs mismatch for return_all_scores vs import slowdown; unrelated." }, { "left": "issue:43525", "right": "issue:43643", "accept": false, - "reason": "Llama4 config attribute error and `trust_remote_code` missing fields are different failures." + "reason": "Both involve config fields, but one is a specific missing attribute and the other is a trust_remote_code config hydration problem; not clearly the same bug." }, { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "Attention-kernel divergence and ANSI output in loading_report are unrelated." + "reason": "Attention-kernel divergence vs ANSI codes in a loading report; unrelated subsystems." }, { "left": "issue:41628", "right": "issue:43976", "accept": false, - "reason": "AutoImageProcessor import error is not the same as the Python 3.9/3.10 support issue." + "reason": "AutoImageProcessor import error vs Python 3.9/3.10 compatibility; different root causes." }, { "left": "issue:44589", "right": "issue:45362", "accept": false, - "reason": "Float8 storage lookup failure and Qwen3.5 chat crash are different model/runtime problems." + "reason": "Storage-object lookup failure vs chat-model crash; no concrete shared code path." }, { "left": "issue:44336", "right": "issue:44373", "accept": false, - "reason": "ANSI code leakage and a wrong docstring do not share the same underlying bug." + "reason": "Terminal formatting bug vs docstring issue; not duplicates." }, { "left": "issue:42491", "right": "issue:43299", "accept": false, - "reason": "Both mention Qwen3-MoE, but one is hf4.x/hf5.x LoRA compatibility and the other is a v5 loading regression." + "reason": "Both mention Qwen3 MoE, but one is LoRA compatibility on hf4.x/hf5.x and the other is Qwen3VL MoE loading; too different to merge as one PR." }, { "left": "issue:45561", "right": "issue:45563", "accept": false, - "reason": "A pytest-xdist race on `captured_info.txt` is unrelated to a stale `num_return_sequences` warning." + "reason": "pytest-xdist file race vs a stale generate warning; unrelated." }, { "left": "issue:44295", "right": "issue:45397", "accept": false, - "reason": "Buffered `position_ids` access and Gemma-4 ZeRO3 loading are different code paths." + "reason": "position_ids buffer access bug vs ZeRO3 from_pretrained failure; different issue." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import performance issue is unrelated to an unrecognized model/config error." + "reason": "Import slowdown vs unrecognized model/config error; not the same bug." }, { "left": "issue:44242", - "right": "issue:45593", + "right": "issue:44871", "accept": false, - "reason": "These are both auxiliary-loss omissions, but for different models and different gating flags; not one concrete bug." + "reason": "Router-logits load-balancing loss bug vs Gemma eos_token_id config inconsistency; different model behaviors." }, { "left": "issue:43531", "right": "issue:45362", "accept": false, - "reason": "Qwen3-MoE `sliding_window` behavior and Qwen3.5 chat crashes are not the same issue." + "reason": "Sliding-window bug in Qwen3-MoE vs chat crash in Qwen3.5-35B; too broad and not the same concrete failure." }, { "left": "issue:41950", "right": "issue:44220", "accept": false, - "reason": "Video-classification image-processor lookup and `_torch_extract_fbank_features()` are unrelated." + "reason": "Video-classification image-processor lookup vs fbank feature extraction; different pipelines." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "`reduce_labels` returning one label and unsafe `sys.modules` access are different bugs." + "reason": "BeitImageProcessorFast reduce_labels bug vs unsafe sys.modules access in modeling_utils; unrelated." }, { "left": "issue:42886", "right": "issue:46132", "accept": false, - "reason": "Offline cache loading and `AttentionInterface.register` behavior change are unrelated." + "reason": "Offline cache loading bug vs AttentionInterface.register behavior change; unrelated." }, { "left": "issue:36246", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different libraries." + "reason": "Qwen2.5-VL import error vs huggingface_hub offline-mode import error; both are imports, but different modules and failures." }, { "left": "issue:36246", "right": "issue:44351", "accept": false, - "reason": "Different missing `transformers` exports; same package, not the same bug." + "reason": "Different missing symbols from different namespaces; not the same regression." }, { - "left": "issue:44336", - "right": "issue:44485", + "left": "issue:44246", + "right": "issue:44871", "accept": false, - "reason": "ANSI formatting leakage and GLM-5 RoPE discussion are unrelated." + "reason": "Import performance issue vs eos_token_id inconsistency; unrelated." }, { - "left": "issue:44246", - "right": "issue:44871", + "left": "issue:44336", + "right": "issue:44485", "accept": false, - "reason": "Import slowness and Gemma eos_token_id inconsistency are different problems." + "reason": "ANSI terminal formatting bug vs GLM-5 RoPE discussion; not the same underlying problem." }, { "left": "issue:45003", "right": "issue:45561", "accept": false, - "reason": "Unsafe `sys.modules` access is unrelated to the xdist file race." + "reason": "sys.modules access bug vs xdist file race; different subsystems." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Both touch v5 remote-code breakage, but the concrete defects differ (`GenerationMixin` cache vs removed helper)." + "reason": "chunked_prefill cache issue vs trust_remote_code breakage after utility removal; different concrete failures." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "Deepseek tokenizer correctness regression and `resize_token_embeddings` not updating output embeddings are different bugs." + "reason": "DeepSeek tokenizer regression vs embedding resize mismatch; unrelated." }, { "left": "issue:36246", "right": "issue:43596", "accept": false, - "reason": "Qwen2.5-VL import error and BertModel/deepspeed IndexError are unrelated." + "reason": "Qwen2.5-VL import failure vs DeepSpeed/BertModel index error; unrelated." }, { "left": "issue:44295", "right": "issue:44749", "accept": false, - "reason": "Buffered `position_ids` handling and slower filtering after upgrade are not the same issue." + "reason": "position_ids buffer issue vs performance regression after version upgrade; different symptoms and likely code paths." }, { "left": "issue:44242", "right": "issue:44857", "accept": false, - "reason": "MoE loss gating and an AMP crash in LwDetrImageLoss are unrelated." + "reason": "Missing auxiliary loss vs AMP/CUDA crash; unrelated." }, { "left": "issue:43352", "right": "issue:45250", "accept": false, - "reason": "A model-specific Flash Attention 2 support gap is not the same as the generic Flash Attention 2 issue." + "reason": "Specific model not supporting Flash Attention 2 vs a general Flash Attention 2 topic; not the same concrete bug." } ] }, @@ -11205,7 +11299,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:42886", "issue:43065", @@ -11262,17 +11356,17 @@ "issue:44496|issue:45003", "issue:45412|issue:46123", "issue:44877|issue:45375", - "issue:43262|issue:44246", "issue:45292|issue:45584", - "issue:43257|issue:45137", + "issue:43262|issue:44246", "issue:45292|issue:45701", + "issue:43257|issue:45137", "issue:45375|issue:45759", "issue:45987|issue:46082", "issue:43232|issue:44336", "issue:44987|issue:45459", "issue:44479|issue:46170", - "issue:43065|issue:43408", "issue:44995|issue:45200", + "issue:43065|issue:43408", "issue:43475|issue:43540", "issue:44466|issue:45335", "issue:45397|issue:45656", @@ -11288,214 +11382,214 @@ "issue:44368|issue:45563", "issue:43931|issue:44368" ], - "prepared_review_unit_hash": "415d1b11b004e591ae623baad14771715efc3a5d173196de66df367e745cf206", + "prepared_review_unit_hash": "bcb8fc576507416b12cfe43829c63919cdc67ef9f0a374fe762f3b0e9032e7b0", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36748, - "estimated_input_tokens": 9187, - "estimated_eval_tokens": 18630 + "serialized_chars": 36742, + "estimated_input_tokens": 9186, + "estimated_eval_tokens": 18628 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is highly heterogeneous: the soft pairs mostly share only broad subsystem vocabulary (embeddings, config loading, deepspeed, video, tokenizers) rather than the same concrete bug. I reject all soft edges as non-duplicates.", - "confidence": 0.94, - "canonical_issue_reason": "If forced to choose one representative, issue 44466 is the closest hub because several nearby items revolve around tied-weight / embedding behavior. That said, the cluster does not form a single coherent duplicate set.", + "summary": "This cluster is a grab-bag of unrelated issues across tokenizers, multimodal configs, generation, logging, and CI; there is no single underlying bug/change tying them together.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the items cover many distinct subsystems and failure modes (tokenizer caching, model config loading, generation internals, multimodal/video handling, memory leaks, docs/CI), so they are not duplicates of one another.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44466 is the most concrete and broadly scoped among the recurring embedding/tied-weight reports, so it is the best single issue to anchor from this mixed set.", + "best_issue_reason": "No single issue is a good cluster representative because the cluster is heterogeneous rather than a duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "Different models and failures: ESM2 is broken vs Gemma4 mm_token_type_ids defaulting." + "reason": "ESM2 model breakage vs Gemma 4 mm_token_type_ids defaulting; different models and failure mechanisms." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "Docs mismatch in a pipeline vs unsafe sys.modules access in modeling_utils." + "reason": "Docs mismatch for TextClassificationPipeline vs unsafe sys.modules access in modeling_utils; unrelated subsystems." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Unrecognized model/config loading vs sys.modules access bug; unrelated code paths." + "reason": "Unrecognized model/config loading error vs sys.modules access bug; different code paths and symptoms." }, { "left": "issue:45412", "right": "issue:46123", "accept": false, - "reason": "Memory leak on RT-DETR deletion vs final-batch pipeline flag bug." + "reason": "RT-DETR memory not released vs MaskGenerationPipeline dropping final partial batch; unrelated behavior." }, { "left": "issue:44877", "right": "issue:45375", "accept": false, - "reason": "Both involve config strictness, but different models and different missing fields." + "reason": "Strict config loading for granite_speech vs missing deepstack_visual_indexes in Qwen config; different model families/config fields." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "resize_token_embeddings output embedding sync issue vs Whisper empty transcription after align_special_tokens; not the same bug." }, { "left": "issue:43262", "right": "issue:44246", "accept": false, - "reason": "Audio chat-template sampling-rate default vs slow import; no shared bug." + "reason": "Audio processor chat-template sampling-rate default vs slow import of transformers; unrelated." }, { "left": "issue:45292", - "right": "issue:45584", + "right": "issue:45701", "accept": false, - "reason": "Resize-token-embeddings/output head sync vs Whisper empty transcription after align_special_tokens." + "reason": "Embedding resize propagation vs tokenization differing by transformers version; distinct problems." }, { "left": "issue:43257", "right": "issue:45137", "accept": false, - "reason": "DeepSpeed-related, but one is weight conversion and the other is a zero3 deque crash." - }, - { - "left": "issue:45292", - "right": "issue:45701", - "accept": false, - "reason": "Embedding resize bug vs tokenization changing across versions; too broad to merge." + "reason": "Qwen3 MOE weight conversion under accelerate+deepspeed vs ZeRO3 deque pop error; different failure points." }, { "left": "issue:45375", "right": "issue:45759", "accept": false, - "reason": "Missing config field under @strict vs from_config not unwrapping text_config." + "reason": "Missing config field in Qwen3_5MoeVisionConfig vs AutoModelForCausalLM.from_config unwrapping composite multimodal configs; related area but not same concrete bug." }, { "left": "issue:45987", "right": "issue:46082", "accept": false, - "reason": "Cache-length return type bug vs LlamaConfig head_dim validation; unrelated." + "reason": "StaticCache seq length contract issue vs LlamaConfig head_dim validation; unrelated APIs." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs/sync_gpus bug vs ANSI escape output in loading_report." + "reason": "Generation kwargs after sync_gpus vs ANSI codes in loading_report; no overlap in bug or fix." }, { "left": "issue:44987", "right": "issue:45459", "accept": false, - "reason": "Model load failure in v5.1+ vs tokenizer error masking when protobuf is absent." + "reason": "Model loading failure on a specific repo/version vs tokenizer errors hidden by protobuf exception handling; different root causes." }, { "left": "issue:44479", "right": "issue:46170", "accept": false, - "reason": "Video-input regression vs Windows/ROCm distributed import failure; different stacks." - }, - { - "left": "issue:43065", - "right": "issue:43408", - "accept": false, - "reason": "SAM3 dummy Conv2d implementation vs model-type mismatch warning; not the same defect." + "reason": "Video input regression in Qwen variants vs Windows/ROCm torch.distributed import issue; different environments and code paths." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "Stale cache crash in GlmMoeDsa vs Gemma4 token-type defaults." + "reason": "Stale indexer cache on second forward pass vs Gemma 4 token type ids default; unrelated model internals." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs model type mismatch warning for sam3_video/sam3_tracker; not the same defect." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "SAM3 vision encoder attribute error vs Qwen3OmniMoe video processing ValueError." + "reason": "Missing fpn_position_embeddings on Sam3VisionEncoderOutput vs Qwen3OmniMoe video ValueError; separate model families and failures." }, { "left": "issue:44466", "right": "issue:45335", "accept": false, - "reason": "Both touch embeddings, but one is serialization inconsistency and the other is resize_token_embeddings propagation." + "reason": "v5 tied-weight serialization inconsistency vs t5gemma resize_token_embeddings not affecting decoder.embed_tokens; different layers and symptoms." }, { "left": "issue:45397", "right": "issue:45656", "accept": false, - "reason": "Gemma-4 zero3 loading vs duplicate optimizer.step under deepspeed; distinct bugs." + "reason": "Gemma-4 zero3 from_pretrained bug vs optimizer step called twice with deepspeed; unrelated training/loading issues." }, { "left": "issue:42886", "right": "issue:45229", "accept": false, - "reason": "Offline tokenizer cache load failure vs Gemma4 multi-GPU CUDA OOM." + "reason": "HF_HUB_OFFLINE tokenizer cache load issue vs Gemma4 multi-GPU CUDA OOM; completely different problems." }, { "left": "issue:44483", "right": "issue:46202", "accept": false, - "reason": "Chat/completions API rejection vs Gemma pipeline roundtrip on \u2581; unrelated symptoms." + "reason": "Chat completions request rejection vs Gemma pipeline roundtrip failure on special character; not the same underlying bug." }, { "left": "issue:44060", "right": "issue:44077", "accept": false, - "reason": "Incorrect tied-weights warning vs patchtsmixer post_init allowance; different configs." + "reason": "Wrong tied-weights warning in Qwen3-Next vs patchtsmixer post_init allowance; unrelated model/config issues." }, { "left": "issue:44188", "right": "issue:46202", "accept": false, - "reason": "torch.compile attention-kernel divergence vs token roundtrip failure; no shared code path." + "reason": "torch.compile attention-kernel divergence vs Gemma pipeline token roundtrip failure; no common code path." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "Second-forward stale cache crash vs flash_attention s_aux=None AttributeError." + "reason": "Stale cache on second forward pass vs flash_attention crash on s_aux=None; different bug surfaces." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "DeepSpeed zero3 deque underflow vs stale auto_mappings reference to removed configs." + "reason": "DeepSpeed ZeRO3 deque error vs stale Sam3LiteText references in auto_mappings; one is runtime, the other CI/import metadata." }, { "left": "issue:43653", "right": "issue:44162", "accept": false, - "reason": "Tokenizer special-token decode bug vs ESM2 model breakage." + "reason": "BigBirdTokenizer special-token registration bug vs ESM2 breakage; different tokenizer/model areas." }, { "left": "issue:44368", "right": "issue:44977", "accept": false, - "reason": "Tied-embeddings warning vs flash-attention generation regression; not the same failure." + "reason": "Tie_word_embeddings warning in Qwen3.5 LoRA fine-tuning vs flash-attention generation failure; not the same issue." }, { "left": "issue:44877", "right": "issue:46170", "accept": false, - "reason": "Config strictness issue vs Windows ROCm import/dependency issue." + "reason": "granite_speech config strictness vs Windows ROCm torch.distributed import/type error; unrelated." }, { "left": "issue:44368", "right": "issue:45563", "accept": false, - "reason": "Embedding warning vs stale num_return_sequences warning; different warnings and triggers." + "reason": "Tie-word-embeddings warning vs stale num_return_sequences warning in paged generate; different warnings and code paths." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch vs tied_word_embeddings warning; unrelated." + "reason": "Qwen3-VL weight-shape mismatch vs Qwen3.5 tie_word_embeddings warning; distinct loading vs config warning problems." } ] }, @@ -11517,7 +11611,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:28282", "issue:30990", @@ -11537,8 +11631,8 @@ "issue:43873", "issue:44038", "issue:44162", - "issue:44188", "issue:44297", + "issue:44351", "issue:44361", "issue:44530", "issue:44623", @@ -11580,12 +11674,12 @@ "issue:43232|issue:43673", "issue:44623|issue:45656", "issue:44749|issue:45656", - "issue:43673|issue:43827", "issue:43701|issue:44749", + "issue:43673|issue:43827", "issue:44871|issue:46132", "issue:45230|issue:45397", - "issue:43475|issue:45381", "issue:42994|issue:43482", + "issue:43475|issue:45381", "issue:43475|issue:43643", "issue:28282|issue:30990", "issue:44038|issue:44623", @@ -11599,222 +11693,222 @@ "issue:45081|issue:45103", "issue:45310|issue:45375", "issue:43873|issue:44945", - "issue:43232|issue:44188" + "issue:41628|issue:44351" ], - "prepared_review_unit_hash": "86466317d89bfac30aa9c0af7797f3e48649c91733898a8228a4beac43c768e3", + "prepared_review_unit_hash": "d080db09b54f121d0600490426d03eb76ac6a0a720da37f8ea7a1d28551094fb", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36879, - "estimated_input_tokens": 9220, - "estimated_eval_tokens": 18696 + "serialized_chars": 36838, + "estimated_input_tokens": 9210, + "estimated_eval_tokens": 18676 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: most items are unrelated bugs that only share broad transformer subdomains (loading, generation, tokenizers, serving, quantization). The soft edges look like thematic similarity, not true duplicate pairs.", - "confidence": 0.9, - "canonical_issue_reason": null, + "summary": "The set is mostly heterogeneous issue reports. A few are loosely related Transformers v5 loading/custom-model regressions, but none of the soft pairs are close enough to be treated as the same underlying bug or change, so I reject all soft edges. No pull requests are present. The broadest issue is the generic v5 custom-model initialization regression report.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43646 is the best umbrella candidate because it describes a broad Transformers 5.0 custom-model initialization regression that can plausibly encompass several narrower loading/meta-init failures in the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the broadest, most active report in the set, but the cluster is too mixed for it to serve as a true duplicate canonical.", + "best_issue_reason": "issue:43646 is the most generally applicable user-facing regression report among the issues here; the others are mostly model-specific or unrelated subsystems.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Different generation failures: missing cache state vs wrong tensor indexing in serve/KV continuation." + "reason": "Both involve generation/cache behavior, but they describe different concrete failures and code paths." }, { "left": "issue:44530", "right": "issue:46170", "accept": false, - "reason": "PagedAttention crash on Qwen3.5 models is unrelated to a Windows/ROCm torch.distributed import dependency issue." + "reason": "PagedAttention/Qwen3.5 cache failure is unrelated to a Windows ROCm import/dependency problem." }, { "left": "issue:43065", "right": "issue:46123", "accept": false, - "reason": "SAM3 PixelDecoder dummy Conv2d is unrelated to MaskGenerationPipeline dropping a final partial batch." + "reason": "SAM3 pixel decoder dummy layer and mask pipeline batch handling are unrelated bugs." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "Missing import from image_utils is a different bug than protobuf-related tokenizer error masking." + "reason": "One is a missing import/export, the other is tokenizer error handling when protobuf is absent; not the same bug." }, { "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "Both involve save_pretrained, but tokenizer metadata mismatch and processor missing files are different code paths." + "reason": "Both are save_pretrained regressions, but one concerns tokenizer config content while the other concerns processor file output." }, { "left": "issue:44361", "right": "issue:44749", "accept": false, - "reason": "Tokenizer AttributeError on tasks is unrelated to the Chinese performance slowdown report." + "reason": "MLukeTokenizer task AttributeError and a post-upgrade performance slowdown are different issues." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Whisper timestamp decode trailing-character crash is a different tokenizer regression than Kimi-K2.5 codec handling." + "reason": "Both mention tokenizer/codec problems, but they affect different models and failure modes." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "AutoConfig trust_remote_code missing fields is unrelated to the ESM2 breakage report." + "reason": "General custom-model init regression and ESM2 breakage are too different to merge as one bug." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "sync_gpus kwargs update bug and chunked_prefill cache-missing bug are distinct generation paths." + "reason": "Both touch generation internals, but one is sync_gpus kwargs handling and the other is chunked_prefill cache state." }, { "left": "issue:44623", "right": "issue:45656", "accept": false, - "reason": "processor.save_pretrained missing files is unrelated to deepspeed causing optimizer.step to run twice." + "reason": "Processor save output files and optimizer stepping under deepspeed are unrelated." }, { "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "Data filtering slowdown and double optimizer step are different failures." + "reason": "Training slowdown after upgrade and duplicate optimizer stepping are unrelated." }, { - "left": "issue:43673", - "right": "issue:43827", + "left": "issue:43701", + "right": "issue:44749", "accept": false, - "reason": "Generation cache regression is unrelated to docs still referencing removed pipeline APIs." + "reason": "Checkpoint key mismatch and data filtering slowdown are unrelated." }, { - "left": "issue:43701", - "right": "issue:44749", + "left": "issue:43673", + "right": "issue:43827", "accept": false, - "reason": "resume_from_checkpoint key mismatch is unrelated to the filtering slowdown." + "reason": "Generation cache regression and docs still referencing pipeline() are not the same underlying change." }, { "left": "issue:44871", "right": "issue:46132", "accept": false, - "reason": "Gemma eos_token_id mismatch is a config bug, not an AttentionInterface.register behavior change." + "reason": "Gemma eos_token_id inconsistency and AttentionInterface.register behavior change are unrelated." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "A generic bug report is not the same concrete issue as gemma-4 zero3 from_pretrained." + "reason": "The generic bug report has no evidence tying it to gemma-4 zero3 from_pretrained." }, { - "left": "issue:43475", - "right": "issue:45381", + "left": "issue:42994", + "right": "issue:43482", "accept": false, - "reason": "SAM3 video encoder missing fpn_position_embeddings is unrelated to qwen2.5-vl video position_id logic." + "reason": "Quantized model saving and GGUF loading are different code paths." }, { - "left": "issue:42994", - "right": "issue:43482", + "left": "issue:43475", + "right": "issue:45381", "accept": false, - "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are different operations and failure modes." + "reason": "Sam3 vision encoder output missing field and Qwen2.5-VL video position ids are different model bugs." }, { "left": "issue:43475", "right": "issue:43643", "accept": false, - "reason": "SAM3 VisionEncoderOutput field omission is unrelated to AutoConfig trust_remote_code missing fields." + "reason": "A missing attribute on Sam3 output and missing fields from trust_remote_code config are not the same defect." }, { "left": "issue:28282", "right": "issue:30990", "accept": false, - "reason": "PyTorch missing ImportError and Sentence Transformers hanging on load are not the same bug." + "reason": "PyTorch missing import error and sentence-transformers loading hang are unrelated." }, { "left": "issue:44038", "right": "issue:44623", "accept": false, - "reason": "Qwen3-VL-Moe breakage in transformers 5.0 is unrelated to processor.save_pretrained missing files." + "reason": "Qwen3-VL-Moe v5 bug and processor save_pretrained file omission are different issues." }, { "left": "issue:46077", "right": "issue:46123", "accept": false, - "reason": "Gemma4 attention-mask bug and MaskGenerationPipeline partial-batch bug are different code paths." + "reason": "Gemma4 attention-mask construction and MaskGenerationPipeline final-batch handling are unrelated." }, { "left": "issue:45406", "right": "issue:46202", "accept": false, - "reason": "Gemma4Processor missing _tokenizer in serve is unrelated to Gemma pipeline roundtrip failure on \u2581." + "reason": "Gemma4 processor missing _tokenizer and Gemma pipeline roundtrip on \u2581 are different bugs." }, { "left": "issue:42371", "right": "issue:45092", "accept": false, - "reason": "TF32 API guidance is unrelated to InternVL2 meta-initialization incompatibility." + "reason": "TF32 settings guidance and InternVL2 meta-init incompatibility are unrelated." }, { "left": "issue:41628", "right": "issue:44933", "accept": false, - "reason": "Cannot import AutoImageProcessor from transformers is a different import issue than a nonexistent image_utils import." + "reason": "Both are import errors, but they concern different symbols/modules and different failure mechanisms." }, { "left": "issue:43475", "right": "issue:44661", "accept": false, - "reason": "SAM3 output attribute bug is unrelated to add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." + "reason": "Sam3VisionEncoderOutput and add-new-model-like TOKENIZER_MAPPING_NAMES are unrelated." }, { "left": "issue:42994", "right": "issue:43525", "accept": false, - "reason": "Quantized saving failure is unrelated to Llama4Config missing pad_token_id." + "reason": "Quantized model saving and Llama4Config missing pad_token_id are different bugs." }, { "left": "issue:45375", "right": "issue:45478", "accept": false, - "reason": "Same model family, but config-field dropping and from_pretrained error are not the same concrete bug." + "reason": "Both mention Qwen3.5 MoE, but one is a missing strict field and the other is a from_pretrained regression; not enough to treat as the same bug." }, { "left": "issue:45081", "right": "issue:45103", "accept": false, - "reason": "Mistral regex patch crash and auto_docstring annotation crash are different AttributeErrors in different subsystems." + "reason": "Mistral regex patch tokenizer crash and auto_docstring future-annotations crash are unrelated." }, { "left": "issue:45310", "right": "issue:45375", "accept": false, - "reason": "Both mention Qwen3.5, but one is a from_pretrained error and the other is a missing config field being dropped." + "reason": "Both are Qwen3.5 MoE regressions, but one is a generic loading error and the other is a specific vision-config field drop." }, { "left": "issue:43873", "right": "issue:44945", "accept": false, - "reason": "Quantization offloading issues are unrelated to incorrect output under pipeline parallelism." + "reason": "Quantization offloading and pipeline-parallelism output correctness are different problems." }, { - "left": "issue:43232", - "right": "issue:44188", + "left": "issue:41628", + "right": "issue:44351", "accept": false, - "reason": "Generation kwargs sync bug is unrelated to attention-kernel divergence under torch.compile." + "reason": "Different missing-import issues affecting different symbols; not the same underlying fix." } ] }, @@ -11836,7 +11930,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:30333", "issue:30990", @@ -11867,7 +11961,6 @@ "issue:44188", "issue:44222", "issue:44242", - "issue:44351", "issue:44496", "issue:44568", "issue:44623", @@ -11882,22 +11975,23 @@ "issue:45137", "issue:45200", "issue:45310", + "issue:45356", "issue:45561", "issue:45712", "issue:45753", "issue:45812" ], "soft_pairs": [ - "issue:41628|issue:44351", + "issue:43232|issue:44188", "issue:42673|issue:43704", - "issue:44945|issue:45753", "issue:44964|issue:45137", + "issue:44945|issue:45753", "issue:36010|issue:41628", - "issue:42831|issue:44222", "issue:42994|issue:43824", + "issue:42831|issue:44222", "issue:44222|issue:45310", - "issue:43673|issue:44188", "issue:43232|issue:44792", + "issue:43673|issue:44188", "issue:44038|issue:45310", "issue:42175|issue:45712", "issue:43526|issue:45561", @@ -11906,8 +12000,8 @@ "issue:42175|issue:44933", "issue:43377|issue:44242", "issue:42898|issue:44568", - "issue:43976|issue:44933", "issue:42222|issue:45200", + "issue:43976|issue:44933", "issue:30990|issue:35141", "issue:43278|issue:45137", "issue:43479|issue:44869", @@ -11918,228 +12012,235 @@ "issue:43784|issue:43824", "issue:44734|issue:45103", "issue:43723|issue:44568", - "issue:42898|issue:44779" + "issue:42898|issue:44779", + "issue:42898|issue:45356" ], - "prepared_review_unit_hash": "ebb691b9a5cba425c7a93aa3884c8a71b4295484a152a3322428e0a653fa42de", + "prepared_review_unit_hash": "1099455bee87f0e63b283dca567f174fa7ffd646704ba91baa63ff9370639d9f", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36849, - "estimated_input_tokens": 9213, - "estimated_eval_tokens": 18682 + "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 distinct Transformers regressions (imports, tokenizer behavior, model loading/saving, multimodal bugs, training/runtime issues). Only one soft edge looks like a true duplicate: the two Qwen3ForCausalLM VRAM-leak reports.", + "summary": "This cluster is mostly a grab-bag of unrelated Transformers regressions (tokenizers, imports, model loading, FP8, generation, multimodal, etc.). Only the Qwen3ForCausalLM VRAM-leak reports look like a true duplicate pair; the rest are too different in code path or symptom to merge.", "confidence": 0.87, - "canonical_issue_reason": "issue:42673 is the clearest canonical issue because it is the fuller, earlier report of the same Qwen3ForCausalLM multi-dataloader-thread VRAM leak that 43704 appears to duplicate.", + "canonical_issue_reason": "issue:42673 is the earlier, fuller report of the same Qwen3ForCausalLM multi-dataloader VRAM leak; issue:43704 is a duplicate with the same title/symptom.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42673 is the best issue anchor in the cluster: it has the strongest duplicate evidence, a detailed repro, and the paired report 43704 looks like the same bug.", + "best_issue_reason": "issue:42673 is the strongest canonical issue candidate in this set because it has the clearest one-to-one duplicate match and the richer original bug report.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:41628", - "right": "issue:44351", + "left": "issue:43232", + "right": "issue:44188", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols (`AutoImageProcessor` vs `HybridCache`) and different code paths." + "reason": "Both are generation/runtime bugs, but they hit different mechanisms: sync_gpus kwargs update vs torch.compile attention-kernel branching." }, { "left": "issue:42673", "right": "issue:43704", "accept": true, - "reason": "Same title, same model, same symptom; this looks like the same Qwen3ForCausalLM VRAM-leak bug reported twice." + "reason": "Same title, same Qwen3ForCausalLM VRAM leak symptom, and the later report is clearly the same bug." }, { - "left": "issue:44945", - "right": "issue:45753", + "left": "issue:44964", + "right": "issue:45137", "accept": false, - "reason": "Different failures: incorrect LLM output under pipeline parallelism vs an infinite loop on a specific image for Qwen3_5." + "reason": "One is a Phi-4 multimodal load failure; the other is a DeepSpeed ZeRO3 deque IndexError. Different bugs." }, { - "left": "issue:44964", - "right": "issue:45137", + "left": "issue:44945", + "right": "issue:45753", "accept": false, - "reason": "Unrelated issues: Phi-4 multimodal model loading vs DeepSpeed ZeRO3 deque underflow." + "reason": "Pipeline-parallelism output corruption and Qwen3_5 image infinite loop are different model/workflow failures." }, { "left": "issue:36010", "right": "issue:41628", "accept": false, - "reason": "Both are import regressions, but they are different missing names and likely separate fixes." + "reason": "Both are import errors, but for different symbols and likely different fixes; not the same underlying bug." }, { - "left": "issue:42831", - "right": "issue:44222", + "left": "issue:42994", + "right": "issue:43824", "accept": false, - "reason": "Different bugs: FP8 accuracy drift vs FP8 `save_pretrained` failure in MoE." + "reason": "Quantized save failure and missing Qwen2.5-VL class import are unrelated." }, { - "left": "issue:42994", - "right": "issue:43824", + "left": "issue:42831", + "right": "issue:44222", "accept": false, - "reason": "Quantized model saving and missing `Qwen2_5_VLForConditionalGeneration` import are separate problems." + "reason": "FP8 accuracy drift and FP8 save_pretrained/moe serialization are different concrete issues." }, { "left": "issue:44222", "right": "issue:45310", "accept": false, - "reason": "Both mention FP8/MoE, but one is save-time behavior and the other is a `from_pretrained` load error for a different Qwen model variant." + "reason": "MoE save_pretrained failure vs Qwen3.5-MoE from_pretrained load error are not the same code path." }, { - "left": "issue:43673", - "right": "issue:44188", + "left": "issue:43232", + "right": "issue:44792", "accept": false, - "reason": "Different subsystems and symptoms: generation cache handling vs attention-kernel divergence under `torch.compile`." + "reason": "Generation kwargs/cache update bug and a janus test failure do not describe the same defect." }, { - "left": "issue:43232", - "right": "issue:44792", + "left": "issue:43673", + "right": "issue:44188", "accept": false, - "reason": "Different concrete bugs: generation kwargs after `sync_gpus` vs a janus image-generation test failure." + "reason": "Chunked-prefill GenerationMixin cache issue and torch.compile attention divergence are separate generation bugs." }, { "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Both involve Qwen MoE models, but the model variants and failure modes differ; too broad to treat as the same bug." + "reason": "Both mention Qwen3-MoE, but one is a broader v5.0 compatibility issue and the other is a specific v5.4.0 from_pretrained regression." }, { "left": "issue:42175", "right": "issue:45712", "accept": false, - "reason": "Packaging/backend-dependency issue vs leftover dummy classes leaking into the module namespace." + "reason": "TensorFlow backend packaging and leftover dummy classes in dir(transformers) are unrelated maintenance issues." }, { "left": "issue:43526", "right": "issue:45561", "accept": false, - "reason": "Image-processor label reduction bug vs xdist race on a captured-info file are unrelated." + "reason": "Beit label reduction bug and pytest-xdist file-race are unrelated." }, { "left": "issue:44496", "right": "issue:45561", "accept": false, - "reason": "Model config loading failure vs test-worker file race; no shared code path." + "reason": "Unrecognized model/config loading and captured_info.txt race are different problems." }, { "left": "issue:43504", "right": "issue:45561", "accept": false, - "reason": "Beit legacy-field load bug vs xdist test race are unrelated." + "reason": "Legacy-field pretrained loading failure and xdist file race are unrelated." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "TensorFlow extra/backend packaging issue vs a missing `image_utils` import; different failure classes." + "reason": "Packaging dependency mismatch and a missing image_utils import are unrelated." }, { "left": "issue:43377", "right": "issue:44242", "accept": false, - "reason": "MIMI padding-mask mismatch vs MoE load-balancing loss omission are different model bugs." + "reason": "Padding-mask mismatch in MIMI encoder vs missing load-balancing loss when router logits are off are distinct bugs." }, { "left": "issue:42898", "right": "issue:44568", "accept": false, - "reason": "Both are tokenizer regressions in v5, but one concerns cleanup spaces and the other special-token insertion for a specific tokenizer." + "reason": "Tokenizer cleanup-space behavior change and missing BOS/EOS insertion are different tokenizer regressions." }, { - "left": "issue:43976", - "right": "issue:44933", + "left": "issue:42222", + "right": "issue:45200", "accept": false, - "reason": "Python version compatibility problem vs missing import from `image_utils`; not the same bug." + "reason": "Broken vitpose model loading and Gemma 4 mm_token_type_ids defaulting are unrelated model/config issues." }, { - "left": "issue:42222", - "right": "issue:45200", + "left": "issue:43976", + "right": "issue:44933", "accept": false, - "reason": "Different models and symptoms: broken ViTPose models vs Gemma 4 missing default `mm_token_type_ids`." + "reason": "Python version compatibility and nonexistent import from image_utils are unrelated." }, { "left": "issue:30990", "right": "issue:35141", "accept": false, - "reason": "Sentence-Transformers loading hang and embedding reinitialization on resize are unrelated." + "reason": "Sentence-transformers loading hang and embedding reinitialization on resize are unrelated." }, { "left": "issue:43278", "right": "issue:45137", "accept": false, - "reason": "Embedding dtype drift during train/eval vs DeepSpeed ZeRO3 deque underflow are unrelated." + "reason": "Dtype drift between train/eval and a ZeRO3 deque IndexError are different failures." }, { "left": "issue:43479", "right": "issue:44869", "accept": false, - "reason": "Phi-4 multimodal config defaults vs Whisper timestamp decoding crash are different code paths." + "reason": "Default multimodal config initialization and Whisper word-timestamp decode crash are unrelated." }, { "left": "issue:43479", "right": "issue:44079", "accept": false, - "reason": "Config initialization with `None` and ModelOutput key assignment are separate abstractions and bugs." + "reason": "Default config construction and ModelOutput key assignment are different bugs." }, { "left": "issue:44623", "right": "issue:45310", "accept": false, - "reason": "Processor save-pretrained file emission and Qwen3.5 Moe load errors are different operations and likely different fixes." + "reason": "Missing processor save files and Qwen3.5-MoE from_pretrained loading error are unrelated." }, { "left": "issue:30333", "right": "issue:33290", "accept": false, - "reason": "MLflow reporting on failed training jobs vs Adafactor OOM in DeepSpeed are unrelated runtime issues." + "reason": "MLflow reporting on training failure and Adafactor OOM in DeepSpeed are unrelated." }, { "left": "issue:42898", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but the affected models and concrete breakages differ." + "reason": "Both are tokenizer regressions, but one is cleanup-space behavior and the other is wrong token IDs for Granite; different underlying issues." }, { "left": "issue:43784", "right": "issue:43824", "accept": false, - "reason": "Sentence-Transformers import failure due to `nn` vs missing export of a Qwen VL class are unrelated import problems." + "reason": "Sentence-transformers import NameError and missing Qwen2.5-VL class import are unrelated import failures." }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "Serving KV-cache indexing crash and auto-docstring annotation handling are unrelated." + "reason": "KV-cache continuation crash in serve and auto_docstring AttributeError under future annotations are unrelated." }, { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "Tokenizer loading failure in v5 vs special-token insertion regression for mdeberta-v3-base are different bugs." + "reason": "AutoTokenizer loading regression and add_special_tokens BOS/EOS regression are different tokenizer bugs." }, { "left": "issue:42898", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions, but one is a global v5 cleanup-space change and the other is a DeepSeek tokenizer correctness bug." + "reason": "Different tokenizer regressions affecting different models/symptoms; not the same bug." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Clean-up-space change and Kimi-K2.5 codec/regex regression are unrelated tokenizer issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays mostly conservative. The one accepted soft edge (issue:42673 \u2194 issue:43704) is supported by identical titles and matching symptoms. The rejected soft edges are framed cautiously and do not overclaim duplicates. One minor wording point: the packet does not explicitly prove a \u2018detailed repro,\u2019 but the fuller body length and discussion activity make the anchor choice reasonable enough here." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft pair, issue:42673 vs issue:43704, is strongly supported by identical titles and matching symptom. The remaining verdicts are appropriately cautious and do not overstate duplicate evidence." }, "evaluator_used": true, "retried": false, @@ -12158,7 +12259,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:22355", "issue:28282", @@ -12170,7 +12271,6 @@ "issue:42757", "issue:42831", "issue:42898", - "issue:43116", "issue:43122", "issue:43232", "issue:43479", @@ -12185,11 +12285,13 @@ "issue:44263", "issue:44295", "issue:44297", + "issue:44360", "issue:44373", "issue:44448", "issue:44483", "issue:44484", "issue:44485", + "issue:44514", "issue:44623", "issue:44933", "issue:44977", @@ -12199,7 +12301,6 @@ "issue:45125", "issue:45245", "issue:45310", - "issue:45356", "issue:45405", "issue:45406", "issue:45656", @@ -12210,17 +12311,15 @@ "issue:46209" ], "soft_pairs": [ - "issue:42898|issue:45356", "issue:43874|issue:45092", - "issue:45405|issue:45712", "issue:44060|issue:45125", + "issue:45405|issue:45712", "issue:42898|issue:44448", "issue:44295|issue:45656", "issue:44448|issue:46132", "issue:44933|issue:45712", "issue:44222|issue:44297", "issue:44297|issue:45656", - "issue:43116|issue:44190", "issue:43479|issue:43644", "issue:44190|issue:46082", "issue:44222|issue:44623", @@ -12229,8 +12328,8 @@ "issue:43122|issue:46209", "issue:30333|issue:36331", "issue:22355|issue:28282", - "issue:45245|issue:46132", "issue:28282|issue:30333", + "issue:45245|issue:46132", "issue:30333|issue:35141", "issue:45071|issue:46082", "issue:41628|issue:42757", @@ -12241,242 +12340,244 @@ "issue:44263|issue:45092", "issue:43761|issue:46082", "issue:44222|issue:44484", - "issue:44373|issue:44485", "issue:44295|issue:44623", - "issue:44483|issue:45406" + "issue:44373|issue:44485", + "issue:44483|issue:45406", + "issue:44514|issue:45103", + "issue:44263|issue:44360" ], - "prepared_review_unit_hash": "54dc6f678cd45e18622c9327e613bfe8eace4f9bad4ac5d8fdc95cb649560203", + "prepared_review_unit_hash": "c01abc47d7ff4f427c61f70e9fcbcee59cf06a36e584dd8e4deaa521d56bfefd", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37700, - "estimated_input_tokens": 9425, - "estimated_eval_tokens": 19106 + "serialized_chars": 37624, + "estimated_input_tokens": 9406, + "estimated_eval_tokens": 19068 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are mostly keyword-similar but substantively different issues; none of the soft pairs look like true duplicates.", + "summary": "These are mostly unrelated issue reports that only share superficial keyword overlap (imports, v5 regressions, save/load, multimodal, FP8, trainers). None of the soft pairs looks like the same underlying bug or change, so all soft edges should be rejected.", "confidence": 0.95, - "canonical_issue_reason": "No single canonical issue stands out: the set mixes unrelated import errors, model regressions, config validation bugs, and save/load edge cases.", + "canonical_issue_reason": "No single canonical issue is safe here: the items span many distinct bugs and regressions rather than one duplicate thread.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45356 is the strongest standalone report here because it has a clear regression boundary, affected model, and concrete symptom, but it still should not absorb the rest of the cluster.", + "best_issue_reason": "No issue is a strong global representative; the set is heterogeneous and the apparent matches are only lexical, not the same code-path failure.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:42898", - "right": "issue:45356", - "accept": false, - "reason": "Both are tokenizer regressions, but they describe different failures: v5 clean_up_tokenization_spaces behavior vs Kimi-K2.5 codec handling and warning text." - }, { "left": "issue:43874", "right": "issue:45092", "accept": false, - "reason": "Different multimodal bugs: one is a missing image-patch API, the other is a remote-code checkpoint/meta-init incompatibility." + "reason": "Different failures: missing image patch method in GLM46V vs meta-init incompatibility in old InternVL2 checkpoints." }, { - "left": "issue:45405", - "right": "issue:45712", + "left": "issue:44060", + "right": "issue:45125", "accept": false, - "reason": "Unrelated: one is a dependency version bump problem, the other is cleanup of leftover dummy classes." + "reason": "Both mention Qwen MoE, but one is a tied-weights warning bug and the other is a missing tensor-parallel plan." }, { - "left": "issue:44060", - "right": "issue:45125", + "left": "issue:45405", + "right": "issue:45712", "accept": false, - "reason": "Both are Qwen-related, but one is a tied-weights warning and the other is missing tensor-parallel metadata; different code paths." + "reason": "PEFT version bump mismatch and leftover dummy classes are unrelated packaging/check-repo issues." }, { "left": "issue:42898", "right": "issue:44448", "accept": false, - "reason": "Both mention v5 regressions, but they affect different models and different behavior paths." + "reason": "Tokenization-space cleanup behavior and Pegasus output differences are separate tokenizer/model-output regressions." }, { "left": "issue:44295", "right": "issue:45656", "accept": false, - "reason": "A buffer read error and a double optimizer step under DeepSpeed are unrelated bugs." + "reason": "Position_ids buffer reading error is unrelated to the deepspeed optimizer-step duplication bug." }, { "left": "issue:44448", "right": "issue:46132", "accept": false, - "reason": "Different problems: Pegasus output regression versus changed behavior in AttentionInterface.register." + "reason": "Pegasus v4/v5 output differences do not match an AttentionInterface registration behavior change." }, { "left": "issue:44933", "right": "issue:45712", "accept": false, - "reason": "Import/export failure in image_utils is unrelated to leftover dummy class cleanup." + "reason": "An image_utils import problem is not the same as stale dummy classes leaking into dir(transformers)." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "Both involve save_pretrained, but one is FP8 MoE serialization and the other is tokenizer config metadata mismatch." + "reason": "FP8 save_pretrained behavior for MoE models is unrelated to tokenizer_class mismatch on save_pretrained." }, { "left": "issue:44297", "right": "issue:45656", "accept": false, - "reason": "Tokenizer save metadata and optimizer stepping are unrelated." - }, - { - "left": "issue:43116", - "right": "issue:44190", - "accept": false, - "reason": "Both are example-script reports, but one is multi-label classification output and the other is local dataset loading." + "reason": "Tokenizer save metadata corruption and duplicated optimizer steps are unrelated bugs." }, { "left": "issue:43479", "right": "issue:43644", "accept": false, - "reason": "Different subsystems: multimodal config defaults versus non-persistent buffer initialization in v5." + "reason": "Phi4Multimodal config defaults and non-persistent buffer junk initialization are different initialization paths." }, { "left": "issue:44190", "right": "issue:46082", "accept": false, - "reason": "Example dataset loading failure is unrelated to LlamaConfig head_dim validation." + "reason": "Local dataset loading in an example script is unrelated to LlamaConfig head_dim validation." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "Both touch save_pretrained, but one is model FP8/MoE behavior and the other is processor file emission." + "reason": "MoE FP8 save_pretrained and processor.save_pretrained missing files are different save-path issues." }, { "left": "issue:30333", "right": "issue:34689", "accept": false, - "reason": "MLflow job reporting on failure is unrelated to a model-loading regression." + "reason": "MLFlow reporting on failed training jobs is unrelated to a Llama 3.2 Vision model-loading regression." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "FP8 accuracy issues and missing processor save files are different bugs." + "reason": "FineGrainedFP8 accuracy and processor save_pretrained missing files are not the same bug." }, { "left": "issue:43122", "right": "issue:46209", "accept": false, - "reason": "Tokenizer differences across versions are unrelated to FP8 inference failures on B200." + "reason": "Tokenization differences across versions and FP8 inference failure on B200 are unrelated." }, { "left": "issue:30333", "right": "issue:36331", "accept": false, - "reason": "A failed-job reporting bug and a Trainer compute_loss signature change are not the same issue." + "reason": "MLFlow job-state reporting and CustomTrainer compute_loss signature mismatch are separate trainer issues." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "Both are import errors, but one is a missing transformers.onnx module and the other is a missing PyTorch dependency." + "reason": "Missing transformers.onnx module and missing PyTorch dependency are distinct import errors." }, { - "left": "issue:45245", - "right": "issue:46132", + "left": "issue:28282", + "right": "issue:30333", "accept": false, - "reason": "Category-count runtime error and AttentionInterface.register behavior change are unrelated." + "reason": "PyTorch import requirement failure is unrelated to MLFlow reporting behavior." }, { - "left": "issue:28282", - "right": "issue:30333", + "left": "issue:45245", + "right": "issue:46132", "accept": false, - "reason": "Dependency import failure versus MLflow reporting bug; no shared underlying cause." + "reason": "Category-count runtime error and AttentionInterface registration behavior are unrelated APIs." }, { "left": "issue:30333", "right": "issue:35141", "accept": false, - "reason": "Job-status reporting and embedding reinitialization are separate problems." + "reason": "Failed training job reporting and embedding resize reinitialization are unrelated trainer/model-init bugs." }, { "left": "issue:45071", "right": "issue:46082", "accept": false, - "reason": "Both are config-related, but one is type checking regression and the other is explicit head_dim validation." + "reason": "PretrainedConfig type checking regression is unrelated to LlamaConfig head_dim validation." }, { "left": "issue:41628", "right": "issue:42757", "accept": false, - "reason": "Different import/export issues in different packages, with different fixes." + "reason": "AutoImageProcessor import failure and is_offline_mode import failure are different missing-symbol issues." }, { "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Unsupported processor argument and auto_docstring annotation crash are unrelated." + "reason": "Unsupported center argument in a feature extractor is unrelated to the auto-docstring AttributeError with future annotations." }, { "left": "issue:44297", "right": "issue:45310", "accept": false, - "reason": "Tokenizer save metadata mismatch is unrelated to Qwen3.5 MoE from_pretrained failure." + "reason": "Tokenizer save metadata mismatch and Qwen3.5 MoE from_pretrained error are different failure modes." }, { "left": "issue:43723", "right": "issue:44977", "accept": false, - "reason": "Tokenizer loading and flash-attention generation issues affect different code paths." + "reason": "Tokenizer loading in v5 and Qwen3.5 flash-attention generation problems are unrelated." }, { "left": "issue:43232", "right": "issue:45834", "accept": false, - "reason": "Generation kwargs synchronization and OCR index overflow are unrelated." + "reason": "Generation kwargs update after sync_gpus is not the same as Kosmos2.5 OCR long-input index error." }, { "left": "issue:44263", "right": "issue:45092", "accept": false, - "reason": "torch.split return handling in GlmMoeDsaIndexer is unrelated to meta-initialization incompatibility." + "reason": "torch.split return values in a GLM MoE indexer are unrelated to old InternVL2 meta-init incompatibility." }, { "left": "issue:43761", "right": "issue:46082", "accept": false, - "reason": "CLIP hidden_states regression and LlamaConfig validation are different bugs." + "reason": "CLIPVisionModel hidden_states regression is unrelated to LlamaConfig head_dim rejection." }, { "left": "issue:44222", "right": "issue:44484", "accept": false, - "reason": "FP8 save_pretrained bug and a question about max_shard_size are not duplicates." + "reason": "FP8 MoE save_pretrained bug and max_shard_size default question are not the same issue." }, { - "left": "issue:44373", - "right": "issue:44485", + "left": "issue:44295", + "right": "issue:44623", "accept": false, - "reason": "Wrong docstring and RoPE implementation discussion do not describe the same issue." + "reason": "Position_ids buffer access error does not match missing processor save_pretrained files." }, { - "left": "issue:44295", - "right": "issue:44623", + "left": "issue:44373", + "right": "issue:44485", "accept": false, - "reason": "Reading a registered buffer and missing processor save files are unrelated." + "reason": "A wrong docstring and a GLM-5 RoPE implementation discussion are not duplicate bugs." }, { "left": "issue:44483", "right": "issue:45406", "accept": false, - "reason": "Chat-completions request handling and Gemma4Processor missing _tokenizer are different failures." + "reason": "Chat completions endpoint acceptance failure is unrelated to Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched apply_chat_template crash is unrelated to the auto-docstring future-annotations AttributeError." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA/GLM, but one is a torch.split return-value bug and the other is a discussion about a missing ReLU; not the same underlying defect." } ] }, @@ -12498,11 +12599,12 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:22355", "issue:28218", "issue:30990", + "issue:33357", "issue:38175", "issue:39401", "issue:41628", @@ -12513,6 +12615,7 @@ "issue:42907", "issue:42994", "issue:43066", + "issue:43122", "issue:43232", "issue:43479", "issue:43576", @@ -12526,10 +12629,9 @@ "issue:44117", "issue:44261", "issue:44263", - "issue:44360", "issue:44373", "issue:44442", - "issue:44514", + "issue:44521", "issue:44568", "issue:44671", "issue:44704", @@ -12538,7 +12640,6 @@ "issue:44913", "issue:44991", "issue:45092", - "issue:45103", "issue:45278", "issue:45310", "issue:45357", @@ -12549,8 +12650,6 @@ "issue:46132" ], "soft_pairs": [ - "issue:44263|issue:44360", - "issue:44514|issue:45103", "issue:45092|issue:45357", "issue:43723|issue:44871", "issue:30990|issue:38175", @@ -12559,9 +12658,9 @@ "issue:43723|issue:44991", "issue:44829|issue:46002", "issue:43723|issue:44442", + "issue:43479|issue:44913", "issue:41628|issue:43824", "issue:42831|issue:45310", - "issue:43479|issue:44913", "issue:44263|issue:44373", "issue:42831|issue:44038", "issue:39401|issue:44568", @@ -12576,204 +12675,206 @@ "issue:44671|issue:46132", "issue:43576|issue:43784", "issue:43646|issue:46002", - "issue:42371|issue:44263" + "issue:43122|issue:44521", + "issue:42371|issue:44263", + "issue:30990|issue:33357" ], - "prepared_review_unit_hash": "501ad87e7f6f3f9299b96610247ce7c58513db3d00f5bfe33bb485cacbc2eb41", + "prepared_review_unit_hash": "4aaa9316b424e5e6c526ff7f468f1361eac9a8a9d301fc14f6e54af5bf933265", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 28, - "serialized_chars": 35135, - "estimated_input_tokens": 8784, - "estimated_eval_tokens": 17824 + "serialized_chars": 35096, + "estimated_input_tokens": 8774, + "estimated_eval_tokens": 17804 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a grab-bag of unrelated Transformers regressions; the soft-similarity pairs share broad themes (tokenizers, import errors, save/load, multimodal configs) but not the same concrete bug. No soft edge is safe to merge.", + "summary": "The candidate edges are mostly broad topical similarities rather than true duplicates. They span unrelated tokenizer, import, quantization, configuration, and model-specific regressions, so I would reject all soft pairs as the same underlying bug/change.", "confidence": 0.87, - "canonical_issue_reason": "issue:43723 is the best umbrella representative because it is a broad, user-facing tokenizer-loading regression in v5 and is closest to several other tokenizer/import complaints without being overly narrow.", + "canonical_issue_reason": "issue:43723 is the broadest representative of the cluster\u2019s recurring v5 tokenizer-loading regressions; several other items are narrower or model-specific variants, but none are clear duplicates of it.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43723 is the strongest global representative for the cluster: it captures the recurring tokenizer/from_pretrained failure mode that appears most central here, while the other issues are mostly narrower or unrelated variants.", + "best_issue_reason": "issue:43723 is the best overall issue representative because it captures the central failure mode repeated across multiple nearby reports: tokenizer loading breakage in Transformers v5.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44263", - "right": "issue:44360", - "accept": false, - "reason": "Different DSA-related bugs: one is about torch.split return values, the other about a missing ReLU. Same subsystem, not the same defect." - }, - { - "left": "issue:44514", - "right": "issue:45103", - "accept": false, - "reason": "Completely different code paths: Qwen2.5-VL chat template batching versus auto_docstring annotation handling." - }, { "left": "issue:45092", "right": "issue:45357", "accept": false, - "reason": "Both are multimodal model issues, but one is meta-init incompatibility for old remote-code checkpoints and the other is incorrect visual encoder keys on save_pretrained." + "reason": "Both are multimodal save/load regressions, but they affect different model families and different failure modes; not the same concrete bug." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "Tokenizer-loading regression versus an eos_token_id configuration mismatch; related area, but different bug." + "reason": "Both involve tokenizer/model loading in v5, but one is a generic AutoTokenizer loading failure and the other is an eos_token_id configuration inconsistency." }, { "left": "issue:30990", "right": "issue:38175", "accept": false, - "reason": "Different models and symptoms: loading gets stuck versus zero probabilities in SigLIP2." + "reason": "Completely different symptoms and model areas: sentence-transformers loading hang vs zero probabilities in a SigLIP model." }, { "left": "issue:42907", "right": "issue:46050", "accept": false, - "reason": "Both involve quantized model persistence, but they target different quantization flows and failure modes." + "reason": "Both concern quantized model persistence, but they target different quantization flows and different save/load failure paths." }, { "left": "issue:44261", "right": "issue:45092", "accept": false, - "reason": "Layernorm precision/config issue is unrelated to meta-initialization compatibility for remote-code checkpoints." + "reason": "Unrelated bugs: MLA layernorm precision/config issue vs remote-code meta-initialization incompatibility." }, { "left": "issue:43723", "right": "issue:44991", "accept": false, - "reason": "Both mention tokenizer loading, but the titles point to different models and likely different root causes." + "reason": "Both are tokenizer loading reports, but they concern different models and likely different tokenizer registration/mapping causes." }, { "left": "issue:44829", "right": "issue:46002", "accept": false, - "reason": "Flash-attention training degradation and NaNs in classification heads are different failures, not one bug." + "reason": "Different problems: flash_attention_3 training degeneration vs NaNs during classification-head init/checkout." }, { "left": "issue:43723", "right": "issue:44442", "accept": false, - "reason": "AutoTokenizer failing on one tokenizer class is not the same bug as the broader v5 tokenizer-loading regression." + "reason": "Both are AutoTokenizer loading failures, but for different tokenizers and likely different missing-registration issues." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Different config serialization bugs in different model families; not the same code path." }, { "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different symbols and likely different export/mapping causes." + "reason": "Both are import errors, but for different missing exports and different classes; too broad to merge." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "FineGrainedFP8 accuracy issue is unrelated to Qwen3.5 MoE from_pretrained failure." - }, - { - "left": "issue:43479", - "right": "issue:44913", - "accept": false, - "reason": "Different configuration bugs in different model families: default multimodal configs versus rotary_pct reload behavior." + "reason": "Different issues: FineGrainedFP8 accuracy regression vs Qwen3.5 MoE from_pretrained error." }, { "left": "issue:44263", "right": "issue:44373", "accept": false, - "reason": "One concerns torch.split return values, the other a docstring error; not the same bug." + "reason": "A torch.split behavior report and a docstring issue are not the same underlying bug." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "Different Qwen/FP8 versus Qwen3-VL-Moe issues with no concrete shared code-path." + "reason": "Different model/regression reports with no shared concrete failure mode." }, { "left": "issue:39401", "right": "issue:44568", "accept": false, - "reason": "Offset_mapping behavior and BOS/EOS special-token insertion are distinct tokenizer bugs." + "reason": "Both are tokenizer behavior bugs, but one is offset_mapping and the other is add_special_tokens/BOS-EOS handling; different code paths." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "Missing is_offline_mode import is not the same as a broad set of import errors after upgrading to v5.5.0." + "reason": "The second is a broad collection of import errors, not the same single bug as the specific is_offline_mode import failure." }, { "left": "issue:43232", "right": "issue:45593", "accept": false, - "reason": "Generation kwargs sync issue and D-FINE auxiliary-loss behavior are unrelated." + "reason": "Unrelated generation-state bug vs D-FINE auxiliary-loss behavior." }, { "left": "issue:42886", "right": "issue:42994", "accept": false, - "reason": "Offline tokenizer cache loading and quantized model saving are different persistence problems." + "reason": "Different persistence/loading failures: offline tokenizer cache loading vs quantized model save failure." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Both concern tokenizers, but one is offline cache loading and the other is decoder-type configuration in v5." + "reason": "Tokenizer cache offline loading and wrong tokenizer decoder type are distinct failures." }, { "left": "issue:22355", "right": "issue:28218", "accept": false, - "reason": "No module import error for transformers.onnx is unrelated to added-token spacing behavior." + "reason": "No shared concrete bug: missing module import vs tokenizer adding an extra space." }, { "left": "issue:42831", "right": "issue:45753", "accept": false, - "reason": "FP8 accuracy regression and an infinite-generation loop on a specific image are unrelated." + "reason": "Accuracy regression in FP8 training is unrelated to an infinite-loop multimodal inference bug." }, { "left": "issue:43756", "right": "issue:44060", "accept": false, - "reason": "RoPE-layer omission and tied-weights warning are different model-architecture bugs." + "reason": "Different model-specific implementation bugs: RoPE-layer dropping vs incorrect tied-weights warning behavior." }, { "left": "issue:44117", "right": "issue:44704", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES None handling and AutoProcessor kwargs propagation are separate from_pretrained issues." + "reason": "Both are loading-path issues, but one is tokenizer mapping fallback and the other is AutoProcessor kwargs forwarding." }, { "left": "issue:44671", "right": "issue:46132", "accept": false, - "reason": "CamemBERT prediction regression is unrelated to AttentionInterface.register behavior changes." + "reason": "Masked LM prediction regression and AttentionInterface.register behavior change are unrelated." }, { "left": "issue:43576", "right": "issue:43784", "accept": false, - "reason": "Broken env command and sentence-transformers import NameError are different regressions." + "reason": "A CLI/env command breakage and an import NameError in sentence-transformers are different issues." }, { "left": "issue:43646", "right": "issue:46002", "accept": false, - "reason": "Custom model initialization breakage is not the same as NaNs in classification heads." + "reason": "Different initialization regressions; no evidence they stem from the same underlying change." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Different areas: tokenization drift across versions vs multimodal assistant_mask computation." }, { "left": "issue:42371", "right": "issue:44263", "accept": false, - "reason": "TF32 settings misuse is unrelated to the DSA indexer split/ReLU bugs." + "reason": "TF32 settings guidance and a torch.split return-value report are unrelated." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Different symptoms and systems: loading hang vs macOS bus error on a CLIP model." } ] }, @@ -12795,13 +12896,12 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:22355", "issue:28218", "issue:29159", "issue:30990", - "issue:33357", "issue:36296", "issue:39401", "issue:41628", @@ -12810,6 +12910,7 @@ "issue:43116", "issue:43122", "issue:43232", + "issue:43278", "issue:43408", "issue:43452", "issue:43475", @@ -12847,26 +12948,24 @@ "issue:45600" ], "soft_pairs": [ - "issue:43122|issue:44521", - "issue:30990|issue:33357", "issue:44295|issue:44297", - "issue:44188|issue:44373", "issue:44704|issue:45290", - "issue:41628|issue:45278", + "issue:44188|issue:44373", "issue:42907|issue:44945", - "issue:44261|issue:44373", + "issue:41628|issue:45278", "issue:43232|issue:44743", "issue:43784|issue:45600", + "issue:44261|issue:44373", "issue:39401|issue:44488", "issue:43976|issue:44945", + "issue:43122|issue:44514", "issue:43408|issue:43475", "issue:42907|issue:43937", - "issue:43122|issue:44514", "issue:39401|issue:44521", - "issue:44360|issue:44485", "issue:44625|issue:44829", - "issue:42907|issue:44964", "issue:43116|issue:45200", + "issue:44360|issue:44485", + "issue:42907|issue:44964", "issue:44038|issue:44297", "issue:44038|issue:44295", "issue:28218|issue:30990", @@ -12875,232 +12974,227 @@ "issue:36296|issue:43116", "issue:43824|issue:44351", "issue:44038|issue:44222", - "issue:45216|issue:45478", "issue:43122|issue:43906", + "issue:45216|issue:45478", "issue:43784|issue:45446", "issue:42757|issue:44351", - "issue:22355|issue:29159" + "issue:22355|issue:29159", + "issue:43278|issue:44945" ], - "prepared_review_unit_hash": "6049652fbcc15fc4679699e7d40e2dbcd64c14d11ff0d5fad82717484e954248", + "prepared_review_unit_hash": "4041b766c39146bfa13c1ed876411b810ce551139676803211307530ec2d3514", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37204, - "estimated_input_tokens": 9301, - "estimated_eval_tokens": 18858 + "soft_pair_count": 32, + "serialized_chars": 36912, + "estimated_input_tokens": 9228, + "estimated_eval_tokens": 18712 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: most items are unrelated regressions or import/model issues that only share a broad subsystem. I would anchor on issue:43122 as the most representative tokenizer-regression report, but I do not see any soft pair that is clearly the same concrete bug/change.", - "confidence": 0.68, - "canonical_issue_reason": "issue:43122 is the broadest and most central tokenizer-regression report here, and it overlaps most with the other tokenizer-related items in the cluster.", + "summary": "This cluster is mostly a set of unrelated transformer issues with only superficial lexical similarity. I found no soft pair that clearly refers to the same underlying bug or change, so all candidate links are rejected.", + "confidence": 0.91, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "It is the best representative issue for the tokenizer-regression slice of this mixed cluster: specific enough to be actionable, but broad enough to cover the nearby tokenization complaints.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43122", - "right": "issue:44521", - "accept": false, - "reason": "Both involve tokenization/chat-template behavior, but one is a generic tokenizer regression and the other is multimodal assistant_mask generation; different defect." - }, - { - "left": "issue:30990", - "right": "issue:33357", - "accept": false, - "reason": "Different failures: Sentence-Transformers loading hang vs a Mac bus error in CLIP model loading." - }, { "left": "issue:44295", "right": "issue:44297", "accept": false, - "reason": "Unrelated symptoms: position_ids buffer access error vs tokenizer_class mismatch in tokenizer_config.json." - }, - { - "left": "issue:44188", - "right": "issue:44373", - "accept": false, - "reason": "Attention-kernel divergence under torch.compile is unrelated to a wrong docstring for position_ids." + "reason": "One is about reading a registered buffer; the other is about tokenizer_class metadata on save. Different failure modes and code paths." }, { "left": "issue:44704", "right": "issue:45290", "accept": false, - "reason": "Different code paths: AutoProcessor kwargs/cached_file plumbing vs apply_chat_template crashing on tool-call messages." + "reason": "AutoProcessor kwargs plumbing to cached_file is unrelated to apply_chat_template crashing on tool-call messages." }, { - "left": "issue:41628", - "right": "issue:45278", + "left": "issue:44188", + "right": "issue:44373", "accept": false, - "reason": "Both are import-related, but one is a missing AutoImageProcessor export and the other is a broader upgrade breakage; not the same bug." + "reason": "torch.compile attention divergence and a wrong docstring for position_ids are unrelated." }, { "left": "issue:42907", "right": "issue:44945", "accept": false, - "reason": "Saving dequantized models and incorrect pipeline-parallel outputs are different problems." + "reason": "Saving dequantized Ministrals/Devstrals and wrong pipeline-parallel outputs are different bugs." }, { - "left": "issue:44261", - "right": "issue:44373", + "left": "issue:41628", + "right": "issue:45278", "accept": false, - "reason": "Precision/config mismatch in MLA layernorm vs a docstring issue; no duplicate signal." + "reason": "Both mention import errors, but they concern different symbols and likely different regressions." }, { "left": "issue:43232", "right": "issue:44743", "accept": false, - "reason": "Both touch generation internals, but sync_gpus kwarg handling and Qwen3.5 recurrent-state resets are distinct defects." + "reason": "Both are generation-related, but one is sync_gpus kwargs handling and the other is cache-state reset logic." }, { "left": "issue:43784", "right": "issue:45600", "accept": false, - "reason": "Import NameError in sentence-transformers integration vs stale auto_mappings references; different breakages." + "reason": "Sentence-transformers import NameError and auto_mappings references to removed configs are not the same issue." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A precision bug in MLA layernorm config is unrelated to a docstring issue for position_ids." }, { "left": "issue:39401", "right": "issue:44488", "accept": false, - "reason": "Qwen3 offset_mapping is unrelated to a model-loading failure for cjvt/sleng-bert." + "reason": "Wrong offset_mapping for Qwen3 tokenizer and failure to load cjvt/sleng-bert are separate tokenizer problems." }, { "left": "issue:43976", "right": "issue:44945", "accept": false, - "reason": "Python version support regression is unrelated to incorrect outputs under pipeline parallelism." + "reason": "Python version compatibility and pipeline parallel output correctness are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "General tokenizer regression across versions and a batched apply_chat_template crash are different code paths." }, { "left": "issue:43408", "right": "issue:43475", "accept": false, - "reason": "Both are SAM3-related, but a model-type warning and a missing attribute on vision encoder output are not the same bug." + "reason": "Wrong model-class warning and a missing attribute on the SAM3 vision encoder output are not the same bug." }, { "left": "issue:42907", "right": "issue:43937", "accept": false, - "reason": "Dequantized save failure vs invalid GenerationConfig for GLM-5 are different issues." - }, - { - "left": "issue:43122", - "right": "issue:44514", - "accept": false, - "reason": "Tokenizer version-drift regression vs batched apply_chat_template crash with padding=False; different concrete symptoms." + "reason": "Dequantized save_pretrained failure and invalid GenerationConfig for GLM-5 are unrelated." }, { "left": "issue:39401", "right": "issue:44521", "accept": false, - "reason": "Different multimodal/tokenizer bugs: wrong offset_mapping vs assistant_masks all zero." - }, - { - "left": "issue:44360", - "right": "issue:44485", - "accept": false, - "reason": "DSA indexer/ReLU discussion is unrelated to GLM-5 RoPE implementation." + "reason": "Offset mapping errors and zero assistant masks in multimodal apply_chat_template are distinct tokenizer/template issues." }, { "left": "issue:44625", "right": "issue:44829", "accept": false, - "reason": "Qwen3.5 num_labels propagation and flash_attention_3 training degeneration are different code paths." - }, - { - "left": "issue:42907", - "right": "issue:44964", - "accept": false, - "reason": "Saving dequantized checkpoints is unrelated to a model-load failure for Phi-4 multimodal instruct." + "reason": "num_labels propagation in Qwen3.5 and flash_attention_3 training degeneration are unrelated." }, { "left": "issue:43116", "right": "issue:45200", "accept": false, - "reason": "Example-script multi-label empties and Gemma 4 mm_token_type_ids defaulting are different bugs." + "reason": "Empty multi-label example output and mm_token_type_ids defaults in Gemma 4 affect different features." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "A missing ReLU in DSA indexer is unrelated to GLM-5 RoPE implementation details." }, { "left": "issue:44038", "right": "issue:44297", "accept": false, - "reason": "Qwen3-VL-Moe issue vs tokenizer_class mismatch; no shared concrete defect." + "reason": "Qwen3-VL-Moe loading and tokenizer_class mismatch on save are different problems." }, { "left": "issue:44038", "right": "issue:44295", "accept": false, - "reason": "Qwen3-VL-Moe bug is unrelated to the position_ids buffer access problem." + "reason": "Model loading for Qwen3-VL-Moe does not match a position_ids buffer access error." }, { "left": "issue:28218", "right": "issue:30990", "accept": false, - "reason": "Tokenizer spacing bug vs Sentence-Transformers loading hang; unrelated." + "reason": "Tokenizer spacing after added token and Sentence Transformers hanging on load are unrelated." }, { "left": "issue:43122", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions in v5, but one is broad version drift and the other is Deepseek-specific; not enough evidence of the same root cause." + "reason": "Both are tokenizer regressions, but they affect different models and behaviors." }, { "left": "issue:42907", "right": "issue:43452", "accept": false, - "reason": "Dequantized save_pretrained failure vs gguf_file loading breakage are different artifacts." + "reason": "Saving dequantized models and gguf_file breakage in from_pretrained are different loading/saving paths." }, { "left": "issue:36296", "right": "issue:43116", "accept": false, - "reason": "Tensor-parallel training bug and example-script classification output bug are unrelated." + "reason": "Tensor parallel training bugs and empty multi-label example outputs are unrelated." }, { "left": "issue:43824", "right": "issue:44351", "accept": false, - "reason": "Different missing symbols: Qwen2_5_VLForConditionalGeneration vs HybridCache." + "reason": "Missing Qwen2_5_VLForConditionalGeneration and missing HybridCache are different missing-export/import errors." }, { "left": "issue:44038", "right": "issue:44222", "accept": false, - "reason": "Both mention MoE, but one is a model-specific loading/behavior issue and the other is FP8 save_pretrained; different fixes." + "reason": "Qwen3-VL-Moe loading and FP8 save_pretrained for MoE are not the same concrete bug." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "A version-to-version tokenization regression is not the same as an isolated reproduction of another issue." }, { "left": "issue:45216", "right": "issue:45478", "accept": false, - "reason": "Related Qwen3.5 family, but save_pretrained producing a bad checkpoint and from_pretrained throwing an error are not clearly the same concrete bug." + "reason": "Both involve Qwen3.5 and save/load regressions, but one is about save_pretrained checkpoints and the other about from_pretrained loading; too different to merge." }, { "left": "issue:43784", "right": "issue:45446", "accept": false, - "reason": "Importing sentence-transformers NameError and a PyTorch version check in flex_attention are unrelated." + "reason": "A missing nn import in sentence-transformers is unrelated to a PyTorch version check in flex_attention." }, { "left": "issue:42757", "right": "issue:44351", "accept": false, - "reason": "Missing is_offline_mode from huggingface_hub and missing HybridCache from transformers are different import failures." + "reason": "Missing is_offline_mode from huggingface_hub and missing HybridCache from transformers are separate import regressions." }, { "left": "issue:22355", "right": "issue:29159", "accept": false, - "reason": "No module named transformers.onnx is unrelated to slow-vs-fast tokenizer inconsistency." + "reason": "An absent transformers.onnx module and slow/fast tokenizer inconsistency are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Embedding dtype drift in evaluate is unrelated to incorrect outputs under pipeline parallelism." } ] }, @@ -13122,7 +13216,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:22355", "issue:29127", @@ -13136,8 +13230,8 @@ "issue:43064", "issue:43066", "issue:43116", - "issue:43278", "issue:43441", + "issue:43450", "issue:43493", "issue:43611", "issue:43673", @@ -13147,6 +13241,7 @@ "issue:43906", "issue:43937", "issue:43976", + "issue:43986", "issue:43992", "issue:44038", "issue:44075", @@ -13158,7 +13253,7 @@ "issue:44779", "issue:44936", "issue:44938", - "issue:44945", + "issue:44977", "issue:45071", "issue:45072", "issue:45083", @@ -13173,231 +13268,238 @@ "issue:46077" ], "soft_pairs": [ - "issue:43278|issue:44945", "issue:42175|issue:44938", "issue:42673|issue:45072", "issue:43493|issue:45753", - "issue:38617|issue:45278", "issue:43066|issue:44779", "issue:43992|issue:44704", + "issue:38617|issue:45278", "issue:22355|issue:29127", "issue:43611|issue:46002", "issue:43937|issue:44485", - "issue:43976|issue:45446", "issue:42222|issue:43441", - "issue:42371|issue:43874", + "issue:43976|issue:45446", "issue:43116|issue:43493", + "issue:42371|issue:43874", "issue:44075|issue:44936", "issue:45357|issue:45478", "issue:44038|issue:45478", "issue:43064|issue:43673", "issue:43116|issue:43825", "issue:45083|issue:45446", - "issue:43937|issue:45563", "issue:44380|issue:46077", + "issue:43937|issue:45563", "issue:44117|issue:45588", "issue:33453|issue:39401", - "issue:43827|issue:45446", "issue:39401|issue:44779", + "issue:43827|issue:45446", "issue:42673|issue:43906", - "issue:44291|issue:45071" + "issue:44291|issue:45071", + "issue:43450|issue:43986", + "issue:43937|issue:44977" ], - "prepared_review_unit_hash": "f43a8972b49992175556c075559720b0bac1bbe746631f45409a3bb8848a309a", + "prepared_review_unit_hash": "8344b9a73ae8b746df9dc4f88fed3006f03efd0956eb2f8f13237cc0fa8a8e99", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 28, - "serialized_chars": 35172, - "estimated_input_tokens": 8793, - "estimated_eval_tokens": 17842 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36033, + "estimated_input_tokens": 9009, + "estimated_eval_tokens": 18274 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is thematically noisy but mostly centers on Transformers v5 regressions, tokenizer/loading issues, and model-specific bugs. The soft pairs do not look like true duplicates under a strict code-path standard, so all candidate edges are rejected.", - "confidence": 0.84, - "canonical_issue_reason": "issue:45278 is the broadest umbrella report here: it captures widespread v5 import breakage after upgrade, making it the closest cluster anchor.", + "summary": "These items are mostly unrelated Transformers issues that only share broad themes like v5 regressions, tokenizers, or multimodal models. The soft-edge candidates are superficially similar but do not describe the same concrete bug/change, so none should be merged. No PRs are present.", + "confidence": 0.9, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best overall representative because it is the most general and high-impact regression report in the set, though it is not a safe duplicate sink for the more specific issues.", + "best_issue_reason": "issue:45278 is the broadest user-facing regression report in the set (many import errors after upgrading from 4.57.0 to 5.5.0), so it's the most representative issue if one must be chosen.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43278", - "right": "issue:44945", - "accept": false, - "reason": "Different bugs: dtype drift between train/eval vs incorrect output under pipeline parallelism." - }, { "left": "issue:42175", "right": "issue:44938", "accept": false, - "reason": "Packaging/backend dependency issue vs Python 3.14 import/load failure." + "reason": "Packaging/backend dependency mismatch vs a Python 3.14 import/load failure; different failure modes and code paths." }, { "left": "issue:42673", "right": "issue:45072", "accept": false, - "reason": "VRAM leak in threaded dataloader use vs bfloat16 dtype mismatch in inference." + "reason": "VRAM leak in Qwen3ForCausalLM threading vs dtype mismatches in inference; unrelated models and bugs." }, { "left": "issue:43493", "right": "issue:45753", "accept": false, - "reason": "SigLIP2 implementation discrepancy vs Qwen3_5 infinite loop on a specific image." - }, - { - "left": "issue:38617", - "right": "issue:45278", - "accept": false, - "reason": "Both are import-related, but one is a specific missing symbol and the other is a broad upgrade report; not the same concrete failure." + "reason": "SigLIP2 implementation discrepancy vs Qwen3.5 image-triggered infinite loop; both multimodal, but not the same defect." }, { "left": "issue:43066", "right": "issue:44779", "accept": false, - "reason": "Tokenizer decoder type regression vs Deepseek tokenizer output corruption; related area, distinct bug." + "reason": "Tokenizer decoder type regression vs Deepseek tokenizer output regression; same broad area, but distinct underlying problems." }, { "left": "issue:43992", "right": "issue:44704", "accept": false, - "reason": "Missing model weight on load vs AutoProcessor not forwarding kwargs to cached_file." + "reason": "Missing encoder weights during load vs AutoProcessor kwargs forwarding; different components and symptoms." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Single missing import symbol vs broad upgrade-caused import failures; the latter is an umbrella report, not the same concrete bug." }, { "left": "issue:22355", "right": "issue:29127", "accept": false, - "reason": "Missing module import vs LayoutLMv3 error-message clarity; unrelated." + "reason": "ONNX import failure vs a LayoutLMv3 error-message clarity issue; not the same bug." }, { "left": "issue:43611", "right": "issue:46002", "accept": false, - "reason": "Model loading breakage from base_model_prefix vs NaNs in classification heads after init/checkpoint." + "reason": "base_model_prefix loading regression vs NaNs in classification heads; different code paths and outcomes." }, { "left": "issue:43937", "right": "issue:44485", "accept": false, - "reason": "GenerationConfig validation failure vs GLM-5 RoPE implementation discussion; not the same code path." - }, - { - "left": "issue:43976", - "right": "issue:45446", - "accept": false, - "reason": "Python support/version compatibility issue vs PyTorch version guard for AuxRequest import." + "reason": "GenerationConfig validation failure vs GLM-5 RoPE implementation discussion; related model family, but not the same change or bug." }, { "left": "issue:42222", "right": "issue:43441", "accept": false, - "reason": "VitPose model breakage vs Ministral-3 FlashAttention failure; different models and failures." + "reason": "VitPose breakage vs Ministral-3 FlashAttention failure; separate models and distinct failure mechanisms." }, { - "left": "issue:42371", - "right": "issue:43874", + "left": "issue:43976", + "right": "issue:45446", "accept": false, - "reason": "TF32 behavior settings vs missing image-patch helper attribute; unrelated." + "reason": "Python version compatibility break vs PyTorch version check in flex_attention; both version-related, but not the same issue." }, { "left": "issue:43116", "right": "issue:43493", "accept": false, - "reason": "Example script returns empty multi-label results vs SigLIP2 model discrepancy." + "reason": "Example-script multi-label behavior vs SigLIP2 implementation discrepancy; unrelated functionality." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API messaging vs missing image-patch helper in GLM46V; completely different subsystems." }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "Optimizer argument handling bug vs trainer.evaluate failure after training; different subsystems." + "reason": "Optimizer arguments ignored vs train/evaluate interaction failure; different training bugs." }, { "left": "issue:45357", "right": "issue:45478", "accept": false, - "reason": "Both concern Qwen3.5, but save_pretrained key layout and from_pretrained loading are different concrete bugs." + "reason": "save_pretrained saves wrong visual encoder keys vs from_pretrained error for Qwen3.5 Moe; same family, but different concrete paths." }, { "left": "issue:44038", "right": "issue:45478", "accept": false, - "reason": "Related model family, but Qwen3-VL-Moe and Qwen3.5-Moe load failures are not the same underlying bug." + "reason": "Qwen3-VL-Moe breakage vs Qwen3.5 Moe load error; too different in model/version and symptom." }, { "left": "issue:43064", "right": "issue:43673", "accept": false, - "reason": "Distributed optimizer-state corruption vs missing GenerationMixin cache in chunked prefill." + "reason": "FSDP2/PEFT optimizer-state corruption vs missing GenerationMixin cache during chunked prefill; unrelated training vs generation bugs." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Classification example misbehavior vs pipeline translation support/error-message issue." + "reason": "Classification example output bug vs pipeline() translation-support messaging; different user flows and defects." }, { "left": "issue:45083", "right": "issue:45446", "accept": false, - "reason": "Qwen3_omni_moe helper behavior vs PyTorch version check; unrelated." + "reason": "Qwen3 Omni-MoE feature-length helper behavior vs flex_attention version gating; unrelated code paths." }, { - "left": "issue:43937", - "right": "issue:45563", + "left": "issue:44380", + "right": "issue:46077", "accept": false, - "reason": "Invalid generation config vs stale num_return_sequences warning; different generation-path defects." + "reason": "GPT2 attention scaling ignored in SDPA/FlashAttention vs Gemma4 bidirectional mask construction; both attention-related but not the same bug." }, { - "left": "issue:44380", - "right": "issue:46077", + "left": "issue:43937", + "right": "issue:45563", "accept": false, - "reason": "GPT2 attention scaling ignored vs Gemma4 bidirectional-attention mask construction; different model-specific behaviors." + "reason": "Invalid GenerationConfig vs stale warning for num_return_sequences; different generation-layer issues." }, { "left": "issue:44117", "right": "issue:45588", "accept": false, - "reason": "Tokenizer mapping None handling vs flash_attention crash on s_aux=None; unrelated code paths." + "reason": "Tokenizer mapping fallback bug vs flash_attention AttributeError on s_aux=None; unrelated components." }, { "left": "issue:33453", "right": "issue:39401", "accept": false, - "reason": "Tokenizer loading regression vs Qwen3 offset_mapping bug; both tokenizer-related but not the same failure." + "reason": "Generic tokenizer loading regression vs Qwen3 offset_mapping bug; the latter is much more specific." }, { - "left": "issue:43827", - "right": "issue:45446", + "left": "issue:39401", + "right": "issue:44779", "accept": false, - "reason": "Docs still referencing pipeline() vs a runtime version-check bug; unrelated." + "reason": "Qwen3 offset mapping bug vs Deepseek tokenizer regression; same broad area, different model-specific issues." }, { - "left": "issue:39401", - "right": "issue:44779", + "left": "issue:43827", + "right": "issue:45446", "accept": false, - "reason": "Different tokenizer bugs for different model families and symptoms; not one duplicate." + "reason": "Docs still referencing pipeline() vs PyTorch version check in flex_attention; docs cleanup is not the same as a runtime version bug." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "VRAM leak in dataloader threading vs isolated reproduction of a different issue; no concrete match." + "reason": "VRAM leak report vs isolated reproduction of another issue; not enough evidence they are the same underlying bug." }, { "left": "issue:44291", "right": "issue:45071", "accept": false, - "reason": "Unexpected init_empty_weights argument vs PretrainedConfig type-checking regression; distinct loading/type issues." + "reason": "init_empty_weights TypeError vs PretrainedConfig type-checking regression; both v5 load-time issues, but different failure points and causes." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video processor shape bug vs missing-torchvision crash when loading video model; distinct defects." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig invalid vs Qwen3.5 flash-attention generation failure; not the same bug." } ] }, @@ -13419,7 +13521,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:38617", "issue:39401", @@ -13433,16 +13535,15 @@ "issue:42831", "issue:43012", "issue:43066", + "issue:43097", "issue:43122", "issue:43408", "issue:43421", - "issue:43450", "issue:43577", "issue:43582", "issue:43673", "issue:43742", "issue:43937", - "issue:43986", "issue:44075", "issue:44117", "issue:44220", @@ -13451,10 +13552,11 @@ "issue:44466", "issue:44483", "issue:44484", + "issue:44493", "issue:44496", "issue:44829", "issue:44933", - "issue:44977", + "issue:45071", "issue:45081", "issue:45216", "issue:45278", @@ -13471,19 +13573,17 @@ "issue:46178" ], "soft_pairs": [ - "issue:43450|issue:43986", - "issue:43937|issue:44977", "issue:44466|issue:46002", "issue:45405|issue:45446", "issue:44117|issue:45081", "issue:45341|issue:45561", - "issue:38617|issue:41628", "issue:42222|issue:46178", + "issue:38617|issue:41628", "issue:44410|issue:45310", "issue:42617|issue:45341", "issue:44829|issue:45216", - "issue:39401|issue:43421", "issue:42673|issue:43582", + "issue:39401|issue:43421", "issue:42490|issue:42673", "issue:43408|issue:43742", "issue:42371|issue:44261", @@ -13497,219 +13597,224 @@ "issue:42371|issue:42831", "issue:42175|issue:42222", "issue:44075|issue:45656", - "issue:43673|issue:45341", "issue:44410|issue:45478", - "issue:43012|issue:43577" + "issue:43012|issue:43577", + "issue:43673|issue:45341", + "issue:43097|issue:44493", + "issue:41628|issue:45071" ], - "prepared_review_unit_hash": "e6d2d338ad7c6589274def7a8ad2d0bb476f8addc246a7ca4c57ac5b06e1ce31", + "prepared_review_unit_hash": "19149ae030576a3d84ed43d3e25e9c918c46fa463e232a17140962f27e8c9433", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36161, - "estimated_input_tokens": 9041, - "estimated_eval_tokens": 18338 + "serialized_chars": 36142, + "estimated_input_tokens": 9036, + "estimated_eval_tokens": 18328 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: most items are unrelated single-bug reports, and none of the soft pairs look like true duplicates or the same concrete change. I would not collapse any of the candidates together.", - "confidence": 0.94, - "canonical_issue_reason": "No single canonical issue: the cluster spans separate import/export regressions, tokenizer behavior changes, model-loading errors, backend/config problems, and optimizer/runtime bugs.", + "summary": "This cluster is mostly a grab bag of unrelated closed issues (imports, tokenizers, model loading, optimizer behavior, backend/version checks). Only one soft edge looks like a plausible duplicate: a specific import failure fitting under a broader post-upgrade import-regression report.", + "confidence": 0.39, + "canonical_issue_reason": "issue:45278 is the best umbrella representative because it explicitly describes the broader import-regression pattern after upgrading from 4.57.0 to 5.5.0.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a strong global representative because the soft pairs do not share one underlying code-path problem.", + "best_issue_reason": "issue:45278 is the most central and reusable summary of the cluster\u2019s closest shared theme: broad import errors after a version upgrade.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43450", - "right": "issue:43986", - "accept": false, - "reason": "Different bugs: batched video processor shape handling vs missing torchvision causing AutoProcessor load failure." - }, - { - "left": "issue:43937", - "right": "issue:44977", - "accept": false, - "reason": "GenerationConfig validation error and Qwen3.5 flash-attention generation failure are separate problems." - }, { "left": "issue:44466", "right": "issue:46002", "accept": false, - "reason": "Serialization/tied-weight inconsistency is unrelated to NaNs in classification heads after checkout/init." + "reason": "Different bugs: tied-weight serialization vs NaNs in classification heads." }, { "left": "issue:45405", "right": "issue:45446", "accept": false, - "reason": "A release/version pin issue for PEFT is not the same as a PyTorch version check bug in flex_attention." + "reason": "Separate dependency/version issues with different affected code paths." }, { "left": "issue:44117", "right": "issue:45081", "accept": false, - "reason": "Generic tokenizer mapping lookup failure and Mistral regex patch crash affect different code paths." + "reason": "Both involve tokenizers, but one is mapping-name handling and the other is a Mistral regex/backend attribute crash." }, { "left": "issue:45341", "right": "issue:45561", "accept": false, - "reason": "A minor testing_utils bug is not the same as an xdist race on captured_info.txt." + "reason": "The second is a specific xdist race in testing_utils; the first is too vague to treat as the same bug." }, { - "left": "issue:38617", - "right": "issue:41628", + "left": "issue:42222", + "right": "issue:46178", "accept": false, - "reason": "These are different missing-import issues for different symbols and modules." + "reason": "VitPose model breakage and a tensorflow_text backend-mapping error are unrelated." }, { - "left": "issue:42222", - "right": "issue:46178", + "left": "issue:38617", + "right": "issue:41628", "accept": false, - "reason": "Broken VitPose models and tensorflow_text backend mapping errors are unrelated." + "reason": "Both are import errors, but for different symbols and different breakages." }, { "left": "issue:44410", "right": "issue:45310", "accept": false, - "reason": "Missing Qwen3Next projections and Qwen3.5 MoE from_pretrained errors are different model-specific failures." + "reason": "Different Qwen model families and different failures." }, { "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "A script execution problem is unrelated to a testing_utils bug." + "reason": "Unrelated issues: a script runtime failure vs a testing_utils bug." }, { "left": "issue:44829", "right": "issue:45216", "accept": false, - "reason": "flash_attention_3 training degeneration and Qwen3.5 checkpoint serialization are different issues." + "reason": "Training degeneration with flash_attention_3 is not the same as a save_pretrained regression." }, { - "left": "issue:39401", - "right": "issue:43421", + "left": "issue:42673", + "right": "issue:43582", "accept": false, - "reason": "Wrong offset_mapping in Qwen3 tokenizer is not the same as post-processor not updating after runtime special-token changes." + "reason": "Both mention memory-ish symptoms, but one is a VRAM leak and the other is an Apple Silicon TypeError." }, { - "left": "issue:42673", - "right": "issue:43582", + "left": "issue:39401", + "right": "issue:43421", "accept": false, - "reason": "VRAM leak in multi-threaded dataloaders is unrelated to an Apple Silicon TypeError in caching_allocator_warmup." + "reason": "Offset-mapping bug and runtime special-token post-processor update are different tokenizer issues." }, { "left": "issue:42490", "right": "issue:42673", "accept": false, - "reason": "Local-path import warning and VRAM leak are different symptoms and code paths." + "reason": "Local-path import warning is unrelated to a Qwen3 VRAM leak." }, { "left": "issue:43408", "right": "issue:43742", "accept": false, - "reason": "sam3_video/sam3_tracker config mismatch is unrelated to the MobileLLM key error." + "reason": "Model-type warning and MobileLLM key error are different loading problems." }, { "left": "issue:42371", "right": "issue:44261", "accept": false, - "reason": "TF32 API guidance/config warning and missing rms_norm_eps precision error are distinct problems." + "reason": "TF32 API warning and missing rms_norm_eps are unrelated." }, { "left": "issue:44933", "right": "issue:45278", - "accept": false, - "reason": "A nonexistent image_utils import and broad import errors after upgrade are related in theme but not the same concrete bug." + "accept": true, + "reason": "45278 is a broad umbrella for post-upgrade import errors, and 44933 reads like one specific missing import under that same regression." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "ImportError for layer_type_validation is unrelated to the _torch_extract_fbank_features() issue." + "reason": "Different import/path vs feature-function failure; not the same underlying bug." }, { "left": "issue:44484", "right": "issue:45310", "accept": false, - "reason": "save_pretrained shard-size behavior and Qwen3.5 MoE loading error are different code paths." + "reason": "Different API/model-loading failures." }, { "left": "issue:43937", "right": "issue:44496", "accept": false, - "reason": "GenerationConfig invalidity is not the same as an unrecognized model missing model_type." + "reason": "GenerationConfig validation and unrecognized-model config errors are distinct." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Wrong decoder type in v5 and changed tokenization across versions are related to tokenizers but not the same underlying bug." + "reason": "Both are v5 tokenizer regressions, but they describe different concrete symptoms and code paths." }, { "left": "issue:42222", "right": "issue:45542", "accept": false, - "reason": "VitPose model breakage is unrelated to a backend error from installing tensorboard without TensorFlow." + "reason": "VitPose model breakage is unrelated to missing TensorFlow in a backend install." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "chat/completions request rejection and Qwen3.5 streaming failure are different failures in the API stack." + "reason": "Both mention chat/completions, but one is a general request rejection and the other is a Qwen3.5 streaming failure." }, { "left": "issue:42371", "right": "issue:42831", "accept": false, - "reason": "TF32 behavior warning is unrelated to the FineGrainedFP8 accuracy issue." + "reason": "TF32 behavior control and FineGrainedFP8 accuracy issues are unrelated." }, { "left": "issue:42175", "right": "issue:42222", "accept": false, - "reason": "TensorFlow backend missing from a torch install and broken VitPose models are unrelated." + "reason": "Backend-install packaging issue and VitPose model breakage are unrelated." }, { "left": "issue:44075", "right": "issue:45656", "accept": false, - "reason": "SGD args being ignored and optimizer.step being called twice are different optimizer bugs." + "reason": "Different optimizer bugs: SGD args ignored vs double optimizer step under deepspeed." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen model variants and different failure modes." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Compile-time warning about bfloat16 precision is not the same as Blip2 dtype fields remaining float32 on load." }, { "left": "issue:43673", "right": "issue:45341", "accept": false, - "reason": "Generation cache missing in chunked_prefill is unrelated to a small testing_utils bug." + "reason": "Generation cache/chunked_prefill bug is unrelated to a testing_utils issue." }, { - "left": "issue:44410", - "right": "issue:45478", + "left": "issue:43097", + "right": "issue:44493", "accept": false, - "reason": "Both mention Qwen3.5/Qwen3Next, but the missing projections bug and the from_pretrained error are not the same concrete failure." + "reason": "Removal of a config field and unexpected position-id keys are different issues." }, { - "left": "issue:43012", - "right": "issue:43577", + "left": "issue:41628", + "right": "issue:45071", "accept": false, - "reason": "A PyTorch compile warning on bfloat16 models is unrelated to Blip2 dtype fields remaining float32 on load." + "reason": "Importing AutoImageProcessor and PreTrainedConfig type-checking are unrelated." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The cluster does look heterogeneous, and the one accepted soft edge (44933 \u2194 45278) is a plausible umbrella-duplicate relationship based on the issue titles. The other pair verdicts are cautious and supported by the visible symptoms in the packet." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -13724,13 +13829,13 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:38617", - "issue:41628", "issue:42757", "issue:43012", "issue:43064", + "issue:43066", "issue:43097", "issue:43335", "issue:43408", @@ -13742,6 +13847,7 @@ "issue:43824", "issue:43873", "issue:43874", + "issue:43906", "issue:43931", "issue:43986", "issue:43992", @@ -13757,7 +13863,6 @@ "issue:44410", "issue:44484", "issue:44485", - "issue:44493", "issue:44704", "issue:44829", "issue:44987", @@ -13776,8 +13881,6 @@ "issue:46172" ], "soft_pairs": [ - "issue:43097|issue:44493", - "issue:41628|issue:45071", "issue:43874|issue:44261", "issue:44263|issue:44485", "issue:45071|issue:45542", @@ -13794,12 +13897,12 @@ "issue:45003|issue:45341", "issue:43986|issue:45341", "issue:44117|issue:44987", - "issue:43408|issue:44368", "issue:43874|issue:44263", + "issue:43408|issue:44368", "issue:43986|issue:44484", - "issue:45440|issue:46172", "issue:43531|issue:45341", "issue:43986|issue:45372", + "issue:45440|issue:46172", "issue:44261|issue:44485", "issue:38617|issue:42757", "issue:43097|issue:46050", @@ -13813,264 +13916,253 @@ "issue:43097|issue:43873", "issue:44704|issue:45103", "issue:43986|issue:44117", - "issue:43824|issue:43986" + "issue:43824|issue:43986", + "issue:43066|issue:43906" ], - "prepared_review_unit_hash": "f824affe9cf75f0f1992ce55c6cc1a61142bf34f0bddbb5cd72cb7283bb99527", + "prepared_review_unit_hash": "c848b961e48e457497a59c0eddde0976c45db59e8c078cec8e0c03ac6cab2cda", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 38, - "serialized_chars": 39074, - "estimated_input_tokens": 9769, - "estimated_eval_tokens": 19794 + "soft_pair_count": 37, + "serialized_chars": 38785, + "estimated_input_tokens": 9697, + "estimated_eval_tokens": 19650 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No safe duplicates stand out here: the soft pairs mostly share broad subsystem keywords (imports, Qwen, flash attention, warnings) but describe different concrete failures. I would keep issue 43873 as the best representative standalone report in the set.", - "confidence": 0.79, - "canonical_issue_reason": "issue:43873 is the strongest standalone bug report in the batch: open, detailed, and the most actively discussed/inbound-referenced item here.", + "summary": "This is not a true duplicate cluster; it mixes unrelated Transformers regressions, import/export breakages, model-family-specific bugs, and warning/typing issues. I would not merge any of the soft edges.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43986 is the most self-contained, user-facing regression in the set and the clearest anchor for a loading-path bug, but the surrounding items are too heterogeneous to treat this as a real duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 has the clearest ongoing impact and enough activity to serve as the most useful representative issue for this collection.", + "best_issue_reason": "43986 is the best representative only in the sense that it is concrete and actionable; it is still not a good umbrella for the rest of the set because most neighbors are unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43097", - "right": "issue:44493", - "accept": false, - "reason": "Both mention config/model warnings, but one is about a removed config field and the other about unexpected position-id keys; different bug reports." - }, - { - "left": "issue:41628", - "right": "issue:45071", - "accept": false, - "reason": "Different failures: missing top-level import vs. PretrainedConfig type-checking regression." - }, { "left": "issue:43874", "right": "issue:44261", "accept": false, - "reason": "Different model families and code paths: image-patch helper missing method vs. MLA layernorm epsilon precision issue." + "reason": "Different failures in different GLM-related paths: image-patch counting vs RMS norm precision config." }, { "left": "issue:44263", "right": "issue:44485", "accept": false, - "reason": "Both are GLM-related, but one is a DSA indexer split bug and the other is a RoPE implementation discussion; not the same defect." + "reason": "Same broad GLM area, but distinct bugs: DSA indexer split behavior vs RoPE implementation." }, { "left": "issue:45071", "right": "issue:45542", "accept": false, - "reason": "PretrainedConfig type checking and TensorBoard/TF backend detection are unrelated bugs." + "reason": "Unrelated regressions: PretrainedConfig type-checking vs TensorFlow backend detection when only tensorboard is installed." }, { "left": "issue:44263", "right": "issue:46172", "accept": false, - "reason": "Completely different model/code paths: GlmMoeDsaIndexer split behavior vs. DeepSeek-V4 tensor transpose logic." + "reason": "Different model families and code paths; DSA indexer split handling is unrelated to DeepSeek transpose logic." }, { "left": "issue:44360", "right": "issue:46172", "accept": false, - "reason": "A missing ReLU in one GLM indexer path is unrelated to the DeepSeek-V4 comb transpose bug." + "reason": "Distinct model/code-path bugs: missing ReLU in DSA indexer vs DeepSeek tensor conversion/transpose." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "Both are warnings, but they concern different models and different warning conditions." + "reason": "Both are warnings, but they come from different models and different mechanisms." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "Both involve flash attention, but one is a Ministral-3 load failure and the other is degenerate training in sequence classification; not mergeable as one fix." + "reason": "Both mention FlashAttention, but one is a loading failure and the other is degenerate training; not the same bug." }, { "left": "issue:44484", "right": "issue:45478", "accept": false, - "reason": "Save shard-size behavior is unrelated to the Qwen3.5-MoE from_pretrained loading error." + "reason": "A save_pretrained shard-size question is unrelated to Qwen3.5 MoE from_pretrained errors." }, { "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Both are Qwen model issues, but one is a Qwen3-VL weight-shape mismatch and the other is missing projections in qwen3next; different bugs." + "reason": "Different Qwen model problems with different symptoms and affected layers; not one concrete bug." }, { "left": "issue:43335", "right": "issue:45071", "accept": false, - "reason": "A SwitchTransformers config construction bug is unrelated to a PretrainedConfig typing regression." + "reason": "Sparse-layer creation in SwitchTransformers is unrelated to a v5 PretrainedConfig type-checking regression." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Both mention Qwen3-VL variants, but one is a specific shape mismatch and the other is a broader v5/Qwen3-VL-Moe compatibility report." + "reason": "Both are Qwen-related loading issues, but they affect different models and failure modes." }, { "left": "issue:43673", "right": "issue:46123", "accept": false, - "reason": "Generation cache missing in chunked prefill and mask pipeline final-batch dropping are different subsystems and symptoms." + "reason": "Generation cache handling during chunked prefill is unrelated to MaskGenerationPipeline batch-finalization behavior." }, { "left": "issue:43097", "right": "issue:43452", "accept": false, - "reason": "Removed config field warnings and GGUF tokenizer/model loading failures are unrelated." + "reason": "Configuration removal warning vs gguf_file/from_pretrained loading breakage; different code paths." }, { "left": "issue:45003", "right": "issue:45341", "accept": false, - "reason": "modeling_utils sys.modules access and a testing_utils bug do not describe the same failure." + "reason": "sys.modules access bug is unrelated to a testing_utils bug." }, { "left": "issue:43986", "right": "issue:45341", "accept": false, - "reason": "AutoProcessor/torchvision crash and a testing_utils issue are unrelated." + "reason": "AutoProcessor crashing without torchvision is not the same issue as the testing_utils bug." }, { "left": "issue:44117", "right": "issue:44987", "accept": false, - "reason": "A tokenizer mapping None-handling bug is not the same as a model-specific load failure for physical-intelligence/fast." - }, - { - "left": "issue:43408", - "right": "issue:44368", - "accept": false, - "reason": "Different warnings in different contexts: SAM3 model-type mismatch vs. tie_word_embeddings guidance for Qwen fine-tuning." + "reason": "Tokenizer mapping None handling is a different loading bug than the physical-intelligence/fast regression." }, { "left": "issue:43874", "right": "issue:44263", "accept": false, - "reason": "Different GLM subcomponents and different failures; no shared underlying code-path bug is evident." + "reason": "Different GLM subcomponents and different failure signatures." }, { - "left": "issue:43986", - "right": "issue:44484", + "left": "issue:43408", + "right": "issue:44368", "accept": false, - "reason": "Missing torchvision error in AutoProcessor is unrelated to shard-size behavior in save_pretrained." + "reason": "Model-type warning for sam3 is unrelated to a tie_word_embeddings warning in a Qwen fine-tuning setup." }, { - "left": "issue:45440", - "right": "issue:46172", + "left": "issue:43986", + "right": "issue:44484", "accept": false, - "reason": "Both are DeepSeek-related, but one is a model implementation divergence and the other is a specific tensor operation bug." + "reason": "Optional-dependency crash in AutoProcessor is unrelated to a save_pretrained shard-size question." }, { "left": "issue:43531", "right": "issue:45341", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and a testing_utils bug are unrelated." + "reason": "Qwen3-MoE sliding_window behavior is unrelated to the testing_utils bug." }, { "left": "issue:43986", "right": "issue:45372", "accept": false, - "reason": "Video-model loading without torchvision and Gemma 4 processor loading without ReasoningEffort are different import/runtime failures." + "reason": "Missing torchvision crash is unrelated to the mistral_common ReasoningEffort import failure." + }, + { + "left": "issue:45440", + "right": "issue:46172", + "accept": false, + "reason": "DeepSeek implementation divergence is a different problem from the comb.to(dtype).transpose(-1, -2) bug." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "Layernorm epsilon precision issue and GLM-5 RoPE implementation are not the same bug." + "reason": "Missing rms_norm_eps precision issue is unrelated to the GLM-5 RoPE implementation bug." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they are for different missing symbols in different packages and do not share a single fix." + "reason": "Both are import errors, but they concern different missing symbols in different modules and are not the same bug." }, { "left": "issue:43097", "right": "issue:46050", "accept": false, - "reason": "A removed config field warning and a quantization save/load breakage are unrelated." + "reason": "Tie-embeddings removal and quantized save/load corruption are unrelated regressions." }, { "left": "issue:43097", "right": "issue:45588", "accept": false, - "reason": "Tie-embeddings warning/reporting and flash_attention s_aux=None crash are different issues." + "reason": "Removed config flag warning and flash_attention s_aux=None crash are different code-path 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": "Distributed optimizer-state corruption is unrelated to Liger Kernel not being applied with model_init." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "AddedToken constructor argument collision and TOKENIZER_MAPPING_NAMES None-handling are different tokenizer-loading bugs." + "reason": "AddedToken constructor argument collision is unrelated to tokenizer mapping returning None." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "Different Qwen configuration problems: missing attention projections vs. a silently dropped vision config field." + "reason": "Missing attention projections in qwen3next is unrelated to a missing deepstack_visual_indexes config field." }, { "left": "issue:38617", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but for different APIs/symbols; no evidence they stem from the same regression." + "reason": "Different import failures: layer_type_validation vs HybridCache, with no shared code path." }, { "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Qwen3-VL-Moe loading trouble and qwen3next missing projections are distinct model-specific defects." + "reason": "Both are Qwen-family regressions, but they affect different models and different architectural components." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "Local-files-only network leakage and missing embed_tokens weight on UMT5 loading are unrelated." + "reason": "Ignoring local_files_only is unrelated to a missing embed_tokens.weight during UMT5Encoder loading." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "A removed config field warning is unrelated to quantization/offloading behavior." + "reason": "Config/removal behavior is unrelated to quantization offloading not working as expected." }, { "left": "issue:44704", "right": "issue:45103", "accept": false, - "reason": "AutoProcessor kwargs forwarding and _process_kwargs_parameters crashing under future annotations are different issues." + "reason": "kwargs propagation to cached_file is unrelated to the docstring annotation crash." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Video processor loading without torchvision and tokenizer mapping None-handling are unrelated." + "reason": "AutoProcessor without torchvision and TOKENIZER_MAPPING_NAMES returning None are separate loading problems." }, { "left": "issue:43824", "right": "issue:43986", "accept": false, - "reason": "Qwen2.5-VL import failure and AutoProcessor video-model crash are different symptoms and likely different fixes." + "reason": "Missing Qwen2_5_VLForConditionalGeneration export and missing torchvision in AutoProcessor are different failures." } ] }, @@ -14092,7 +14184,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36683", "issue:38617", @@ -14105,6 +14197,7 @@ "issue:43208", "issue:43299", "issue:43352", + "issue:43475", "issue:43502", "issue:43526", "issue:43550", @@ -14116,7 +14209,6 @@ "issue:43824", "issue:43825", "issue:43867", - "issue:43906", "issue:43976", "issue:43992", "issue:44038", @@ -14144,7 +14236,6 @@ "issue:46209" ], "soft_pairs": [ - "issue:43066|issue:43906", "issue:44938|issue:46178", "issue:43208|issue:43550", "issue:43992|issue:44484", @@ -14164,8 +14255,8 @@ "issue:43208|issue:43526", "issue:36683|issue:43582", "issue:44222|issue:45478", - "issue:42757|issue:43824", "issue:43012|issue:44683", + "issue:42757|issue:43824", "issue:43618|issue:43761", "issue:42490|issue:43012", "issue:45698|issue:46172", @@ -14175,222 +14266,229 @@ "issue:44483|issue:45290", "issue:43756|issue:44485", "issue:43066|issue:46209", - "issue:43299|issue:43867" + "issue:43299|issue:43867", + "issue:36683|issue:43475" ], - "prepared_review_unit_hash": "4169caf30dee068a1611f1c85d7ff5ab6c8e94c561e2ec882881deabb462c5a2", + "prepared_review_unit_hash": "058e0df70daac2a2ba0e06e81280cf75cb8f49d484fbcd355ede9089ebf02348", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 36942, - "estimated_input_tokens": 9236, - "estimated_eval_tokens": 18728 + "serialized_chars": 36948, + "estimated_input_tokens": 9237, + "estimated_eval_tokens": 18730 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a grab bag of unrelated Transformers issues; despite some superficial overlap (v5 regressions, model families, save/load paths), none of the soft-similarity pairs look like true duplicates or mergeable PR-equivalents.", - "confidence": 0.81, - "canonical_issue_reason": "issue:44483 is the most representative high-impact regression report in the set: a concrete v5 API break with clear user-facing impact and a specific endpoint involved.", + "summary": "This cluster is largely heterogeneous: the paired items share broad Transformers themes (loading, attention, FP8, chat templates, etc.) but not the same concrete defect. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.86, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:44483 is the strongest standalone issue to keep: it is specific, severe, and actionable, with a clear failure mode that is easier to triage than the more model-specific reports.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43066", - "right": "issue:43906", - "accept": false, - "reason": "Different bugs: tokenizer decoder type regression vs an isolated reproduction of another issue; no shared failing code path is evident." - }, { "left": "issue:44938", "right": "issue:46178", "accept": false, - "reason": "Python 3.14 load failure and a BACKENDS_MAPPING tensorflow_text backend error are unrelated import/config problems." + "reason": "Different failures: Python 3.14 import/load issue vs invalid backend mapping for tensorflow_text." }, { "left": "issue:43208", "right": "issue:43550", "accept": false, - "reason": "xLSTM small-model training bugs and Bamba torch.compile SDPA failure affect different models and failure modes." + "reason": "xLSTM training bugs and Bamba SDPA/torch.compile failure are unrelated code paths." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Missing embed_tokens.weight during UMT5 loading is unrelated to save_pretrained max_shard_size behavior." + "reason": "Missing embed token weight on load is not the same as save_pretrained shard-size behavior." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Pipeline task-support messaging regression and pipeline serialization failure are different code paths." + "reason": "Pipeline task warning text and saving Pipeline objects are distinct bugs." }, { "left": "issue:43012", "right": "issue:43550", "accept": false, - "reason": "A bfloat16 precision warning during compile is not the same as a model-specific torch.compile SDPA crash." + "reason": "BF16 compile warning is unrelated to Bamba SDPA compile failure." }, { "left": "issue:43012", "right": "issue:44368", "accept": false, - "reason": "PyTorch float32 warning during compile and a tie_word_embeddings config warning are different issues." + "reason": "PyTorch precision warning and Qwen3.5 LoRA warning come from different mechanisms." }, { "left": "issue:42907", "right": "issue:44655", "accept": false, - "reason": "Saving dequantized models and saving Pipeline objects involve different save_pretrained paths." + "reason": "Dequantized model save failure is not the same as generic Pipeline save_pretrained support." }, { "left": "issue:42907", "right": "issue:45753", "accept": false, - "reason": "Dequantized save failure and a Qwen3.5 image infinite loop are unrelated." + "reason": "Save/dequantization bug is unrelated to Qwen3.5 image-specific infinite loop." }, { "left": "issue:43352", "right": "issue:44380", "accept": false, - "reason": "Unsupported Flash Attention 2 warning for Nemotron is unrelated to GPT2 attention scaling being ignored." + "reason": "FlashAttention support error for Nemotron is different from GPT2 attention scaling being ignored." }, { "left": "issue:44162", "right": "issue:46172", "accept": false, - "reason": "ESM2 breakage and a DeepSeek tensor transpose bug are different model-specific defects." + "reason": "ESM2 breakage and deepseek-v4 tensor transpose issue are unrelated models and bugs." }, { "left": "issue:43352", "right": "issue:43976", "accept": false, - "reason": "A model capability warning and a Python-version compatibility/import issue are not the same underlying bug." + "reason": "FlashAttention support error is unrelated to Python version compatibility." }, { "left": "issue:44380", "right": "issue:46132", "accept": false, - "reason": "GPT2 backend scaling behavior and AttentionInterface.register side effects are distinct attention-stack changes." + "reason": "Attention scaling regression and AttentionInterface.register behavior change are separate issues." }, { "left": "issue:43792", "right": "issue:46123", "accept": false, - "reason": "Whisper load/run failure and MaskGenerationPipeline dropping the final partial batch are unrelated pipeline/model bugs." + "reason": "Whisper runtime failure and MaskGenerationPipeline partial-batch dropping are different pipelines and symptoms." }, { "left": "issue:44380", "right": "issue:45479", "accept": false, - "reason": "Attention scaling ignored in GPT2 is unrelated to a degenerate zero-loss classification bug." + "reason": "Attention backend scaling bug is unrelated to zero-loss classification behavior." }, { "left": "issue:43064", "right": "issue:44380", "accept": false, - "reason": "Distributed optimizer-state corruption in Trainer/FSDP2 is not the same as GPT2 attention-scaling behavior." + "reason": "FSDP/PEFT optimizer-state corruption is not the same as attention scaling being ignored." }, { "left": "issue:44483", "right": "issue:44514", "accept": false, - "reason": "Chat/completions request rejection and chat-template crashes on tool-call messages are different layers of the stack." + "reason": "Chat-completions API acceptance and Qwen2.5-VL chat-template crash are separate request-handling bugs." }, { "left": "issue:43208", "right": "issue:43526", "accept": false, - "reason": "xLSTM training blockers and BeitImageProcessorFast reduce_labels truncation are unrelated." + "reason": "xLSTM training bugs do not match BeitImageProcessorFast label reduction behavior." }, { "left": "issue:36683", "right": "issue:43582", "accept": false, - "reason": "Gemma3Config missing vocab_size and Apple Silicon allocator warmup TypeError are completely different failures." + "reason": "Gemma3Config missing vocab_size and Apple Silicon caching_allocator_warmup TypeError are unrelated." }, { "left": "issue:44222", "right": "issue:45478", "accept": false, - "reason": "FP8 save_pretrained problems and Qwen3.5 MoE from_pretrained loading errors are separate issues." + "reason": "Both involve MoE/FP8, but one is save_pretrained and the other from_pretrained loading; not the same concrete bug." }, { - "left": "issue:42757", - "right": "issue:43824", + "left": "issue:43012", + "right": "issue:44683", "accept": false, - "reason": "Missing is_offline_mode from huggingface_hub and missing Qwen2_5_VLForConditionalGeneration from transformers are unrelated import errors." + "reason": "BF16 warning is unrelated to compiled flex_attention failure on torch>=2.9." }, { - "left": "issue:43012", - "right": "issue:44683", + "left": "issue:42757", + "right": "issue:43824", "accept": false, - "reason": "A warning during compilation and a hard flex_attention failure on torch>=2.9 are different backend problems." + "reason": "Missing is_offline_mode import and missing Qwen2.5-VL symbol are different import regressions." }, { "left": "issue:43618", "right": "issue:43761", "accept": false, - "reason": "Both are CLIP regressions, but one is attentions missing and the other is hidden_states missing; they do not look like the same bug." + "reason": "CLIPOutput attentions assignment and CLIPVisionModel hidden_states regression are different CLIP bugs." }, { "left": "issue:42490", "right": "issue:43012", "accept": false, - "reason": "A trailing-slash local model warning is unrelated to the bfloat16 compile warning." + "reason": "Trailing-slash local model warning and bf16 compile warning are unrelated." }, { "left": "issue:45698", "right": "issue:46172", "accept": false, - "reason": "Wrong custom module restoration after save_pretrained and a DeepSeek dtype/transpose crash are different problems." + "reason": "Wrong custom module after save/load and deepseek-v4 tensor transpose are different serialization vs model-shape issues." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP attentions regression and GPT2 attention scaling regression affect different models and code paths." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "Importing a removed symbol and local_files_only still making API calls are unrelated import vs network-behavior bugs." + "reason": "Missing configuration_utils import and local_files_only network requests are unrelated." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Qwen3-VL-Moe loading regression and fp8 inference support are not the same concrete failure." + "reason": "Qwen3-VL-Moe loading bug and fp8 inference support issue are different failures." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Server request acceptance and apply_chat_template crashing on tool-call assistant messages are separate code paths." + "reason": "Generic /v1/chat/completions compatibility issue and assistant tool-call templating crash are not the same bug." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "Smollm3 RoPE layer mismatch and GLM-5 RoPE implementation discussion do not describe the same defect." + "reason": "Smollm3 RoPE layer mismatch and GLM-5 RoPE implementation discussion are related only by topic, not by defect." }, { "left": "issue:43066", "right": "issue:46209", "accept": false, - "reason": "Tokenizer decoder type regression and FP8 inference failure on B200 are unrelated." + "reason": "Tokenizer decoder type bug in v5 and FP8 inference failure on B200 are different subsystems." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Qwen3VL-Moe loading breakage and a state_dict sorting load error are different load-time bugs." + "reason": "Qwen3VL MoE loading regression and sorted-state_dict load error are different load-path failures." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config vocab_size AttributeError and SAM3 vision encoder missing fpn_position_embeddings are unrelated model classes." } ] }, @@ -14412,9 +14510,10 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:36010", + "issue:36296", "issue:36683", "issue:41669", "issue:42490", @@ -14425,8 +14524,8 @@ "issue:43064", "issue:43299", "issue:43352", - "issue:43475", "issue:43525", + "issue:43575", "issue:43611", "issue:43618", "issue:43867", @@ -14463,7 +14562,6 @@ "issue:46202" ], "soft_pairs": [ - "issue:36683|issue:43475", "issue:45276|issue:46077", "issue:42994|issue:44655", "issue:43901|issue:44655", @@ -14471,9 +14569,9 @@ "issue:43299|issue:45753", "issue:44077|issue:44380", "issue:36683|issue:44077", - "issue:43352|issue:43937", - "issue:43611|issue:44655", "issue:44625|issue:46077", + "issue:43611|issue:44655", + "issue:43352|issue:43937", "issue:43867|issue:45216", "issue:46077|issue:46082", "issue:43976|issue:44938", @@ -14495,257 +14593,270 @@ "issue:43010|issue:45850", "issue:43867|issue:45357", "issue:42490|issue:44075", - "issue:43010|issue:43976", "issue:43992|issue:45478", - "issue:43618|issue:44077" + "issue:43618|issue:44077", + "issue:43010|issue:43976", + "issue:36296|issue:43575" ], - "prepared_review_unit_hash": "08859d77dc5680a8a0c12269b755af913541fb035eb9cf584d5f1a1c52e3fe61", + "prepared_review_unit_hash": "c1f1c46e5772532056efcccff6ee6e44ddd86d2edb6e1408b3277bb24c490b33", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 37194, - "estimated_input_tokens": 9299, - "estimated_eval_tokens": 18854 + "serialized_chars": 37688, + "estimated_input_tokens": 9422, + "estimated_eval_tokens": 19100 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, - "analyst_result": { - "summary": "Mostly heterogeneous cluster, but not only one plausible duplicate edge: 41669\u219444246 is a real import-slowdown duplicate candidate, and 45310\u219445478 are an exact-title Qwen3.5 from_pretrained pair that looks duplicate-like, with nearby Qwen3.5 save/load reports forming a loose family. Even so, the rest are largely separate model/config regressions, so the cluster still fits a broad umbrella issue rather than one tight bug.", - "confidence": 0.74, - "canonical_issue_reason": "issue:45278 is still the broadest umbrella: it explicitly reports widespread import failures after a version upgrade, which best matches the cluster\u2019s general regression/import theme. It is broader than the Qwen3.5 mini-family, even though that family contains a duplicate-looking title pair.", - "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best global representative because it captures the widest, clearest user-facing regression pattern in the set. The cluster also contains a smaller Qwen3.5 save/load family and an import-slowdown duplicate pair, but they are narrower than 45278\u2019s broad import-breakage report.", - "best_pr_reason": null, - "soft_edge_verdicts": [ - { - "left": "issue:36683", - "right": "issue:43475", - "accept": false, - "reason": "Different models and different missing attributes (`vocab_size` vs `fpn_position_embeddings`); not the same bug." - }, + "analyst_result": { + "summary": "This set is mostly heterogeneous, with only a few clear duplicate/near-duplicate issue pairs. The strongest matches are the Qwen3.5 Moe from_pretrained reports, the import-time slowdown reports, and the Qwen3.5 visual-config/save_pretrained serialization reports.", + "confidence": 0.71, + "canonical_issue_reason": "No single cluster-wide canonical issue fits this mixed set; the best umbrella issue is 44246 for the import-time slowdown subcluster, while 45310/45478 is the clearest exact-duplicate subcluster.", + "canonical_pr_reason": null, + "best_issue_reason": "44246 is the best global issue anchor because it is a broad, user-visible regression with a plausible duplicate in 41669 and reads like the top-level symptom for that subcluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ { "left": "issue:45276", "right": "issue:46077", "accept": false, - "reason": "Both are Gemma4-related, but one is token-embedding resizing and the other is attention-mask construction; separate code paths." + "reason": "Different Gemma4 bugs: token embedding resize propagation vs bidirectional attention mask construction." }, { "left": "issue:42994", "right": "issue:44655", "accept": false, - "reason": "Both involve saving, but quantized-model saving and Pipeline `save_pretrained` are distinct failure modes." + "reason": "Both are save-related, but one is quantized model saving and the other is pipeline save_pretrained behavior/docs; not the same bug." }, { "left": "issue:43901", "right": "issue:44655", "accept": false, - "reason": "A docs mismatch and a pipeline serialization bug are not the same underlying issue." + "reason": "Docs mismatch for TextClassificationPipeline is unrelated to pipeline object serialization failure." }, { "left": "issue:36010", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they involve different APIs/packages and different breakages." + "reason": "Both are import errors, but for different symbols and different upstream modules." }, { "left": "issue:43299", "right": "issue:45753", "accept": false, - "reason": "Same model family, but one is a loading regression and the other is an image-specific generation loop." + "reason": "Qwen3VL model loading failure and Qwen3_5 infinite loop are different code-path problems." }, { "left": "issue:44077", "right": "issue:44380", "accept": false, - "reason": "Unrelated model/config problems; no shared concrete code path." + "reason": "Unrelated subsystems: patchtsmixer post_init validation vs GPT2 attention scaling under SDPA/FlashAttention." }, { "left": "issue:36683", "right": "issue:44077", "accept": false, - "reason": "Different model configs and different symptoms; only superficial similarity around optional config fields." + "reason": "Missing config attribute in Gemma3 is unrelated to patchtsmixer post_init constraints." }, { - "left": "issue:43352", - "right": "issue:43937", + "left": "issue:44625", + "right": "issue:46077", "accept": false, - "reason": "Flash Attention support gating and invalid `GenerationConfig` are unrelated failures." + "reason": "num_labels propagation bug is unrelated to Gemma4 bidirectional attention masks." }, { "left": "issue:43611", "right": "issue:44655", "accept": false, - "reason": "Loading with `base_model_prefix` and saving Pipeline objects are distinct serialization behaviors." + "reason": "Base_model_prefix loading regression is not the same as pipeline save_pretrained failure." }, { - "left": "issue:44625", - "right": "issue:46077", + "left": "issue:43352", + "right": "issue:43937", "accept": false, - "reason": "Different models and unrelated bugs (`num_labels` propagation vs attention-mask behavior)." + "reason": "FlashAttention-2 support error and invalid GenerationConfig are unrelated failures." }, { "left": "issue:43867", "right": "issue:45216", "accept": false, - "reason": "Both touch load/save correctness, but state-dict ordering during load and a Qwen3.5 save regression are not clearly the same bug." + "reason": "Both involve model persistence/loading, but one is generic state_dict ordering and the other is a Qwen3.5 save_pretrained regression." }, { "left": "issue:46077", "right": "issue:46082", "accept": false, - "reason": "Different Gemma4/Llama config issues with unrelated validation and masking logic." + "reason": "Different Gemma4 issues: attention mask mode vs LlamaConfig head_dim validation." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Both are Python-version compatibility complaints, but they target different versions and likely different root causes." + "reason": "Both are Python-version compatibility issues, but they target different Python releases and different failures." }, { "left": "issue:43352", "right": "issue:45593", "accept": false, - "reason": "Separate model features: Flash Attention support vs D-FINE auxiliary-loss handling." + "reason": "FlashAttention support and D-FINE auxiliary-loss behavior are unrelated." }, { "left": "issue:36683", "right": "issue:43525", "accept": false, - "reason": "Missing-config-attribute reports on different models and attributes; too generic to merge." + "reason": "Different missing config attributes in different model families; not the same bug." }, { "left": "issue:43618", "right": "issue:45216", "accept": false, - "reason": "Different regressions in different models/features; not mergeable into one fix." + "reason": "CLIPOutput attentions regression is unrelated to Qwen3.5 checkpoint saving." }, { "left": "issue:36683", "right": "issue:44242", "accept": false, - "reason": "Unrelated model/config bugs; only both mention configuration behavior." + "reason": "Gemma3 vocab_size attr error and load-balancing-loss gating are different model bugs." }, { "left": "issue:43352", "right": "issue:43931", "accept": false, - "reason": "Different model-loading problems with no shared concrete code path." + "reason": "Unsupported FlashAttention and Qwen3-VL weight-shape mismatch are unrelated." }, { "left": "issue:43064", "right": "issue:44492", "accept": false, - "reason": "Training/optimizer-state bug vs a typo in cache strategy names; no overlap beyond being in Transformers." + "reason": "FSDP/optimizer state corruption and a cache strategy typo do not share the same underlying bug." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "A cache-update decoration fix and a broad import-regression report are unrelated." + "reason": "no_grad decoration for cache update is unrelated to broad import errors after upgrading to 5.5.0." }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "Both are `from_pretrained` errors, but for different models and different missing/malformed state." + "reason": "Different models and failure modes: UMT5 missing weight vs Qwen3.5 Moe from_pretrained regression." }, { "left": "issue:43867", "right": "issue:46202", "accept": false, - "reason": "Sorted state_dict load failure and a Gemma pipeline roundtrip issue are different symptoms." + "reason": "Generic state_dict load error and Gemma pipeline roundtrip failure on a specific token are not the same bug." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "Both are import-time failures, but compiled Python files and a TorchScript parsing issue are unrelated triggers." + "reason": "Compiled-file import errors and a Python 3.13 torch.jit parsing problem are different root causes." }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "Both are Qwen3.5 checkpoint issues, but state-dict ordering and a missing vision config field are distinct bugs." + "reason": "Generic load failure via state_dict ordering is not the same as Qwen3_5 vision config field loss." }, { "left": "issue:41669", "right": "issue:44246", "accept": true, - "reason": "Both describe slow `import transformers`; one points to wildcard imports as the likely cause and the other reports the same import-time slowdown symptom." + "reason": "These look like the same import-time slowdown regression: one is the concrete diagnosis, the other is the user-facing symptom." }, { "left": "issue:36683", "right": "issue:43064", "accept": false, - "reason": "Different failure domains: model config attribute missing vs distributed training optimizer-state corruption." + "reason": "Missing Gemma3 config attribute is unrelated to the FSDP+PEFT optimizer-state bug." }, { "left": "issue:44938", "right": "issue:45071", "accept": false, - "reason": "Separate Python/runtime compatibility issues with different triggers and symptoms." + "reason": "Different breakages: Python 3.14 load failure vs PretrainedConfig type-checking regression." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Seed-related flakiness and an xdist file race are different testing bugs." + "reason": "Test flakiness from missing set_seed and pytest-xdist file races are not the same issue." }, { "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "A specific cache/layer update fix and a vague general complaint about many models breaking are not the same bug." - }, - { - "left": "issue:43992", - "right": "issue:45478", - "accept": false, - "reason": "Same broad `from_pretrained` theme, but different models and different reported missing/malformed state." + "reason": "Cache update no_grad bug is much more specific than the broad 'too many models' complaint." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Both are Qwen3.5 checkpoint issues, but one is load failure from ordering and the other is incorrect visual encoder keys on save." + "reason": "Generic load/state_dict issues are not the same as Qwen3.5 visual-encoder key serialization." }, { "left": "issue:42490", "right": "issue:44075", "accept": false, - "reason": "Different issues: local-path import warnings vs optimizer SGD arguments being ignored." + "reason": "Local-path import warning and SGD arguments being ignored are unrelated." }, { - "left": "issue:43010", - "right": "issue:43976", + "left": "issue:43992", + "right": "issue:45478", "accept": false, - "reason": "Cache-update decoration and Python-version support are unrelated." + "reason": "Both are from_pretrained/load errors, but for different model families and different failure modes." }, { "left": "issue:43618", "right": "issue:44077", "accept": false, - "reason": "Different regressions in different models/features; not mergeable into one fix." + "reason": "CLIPOutput attentions regression is unrelated to patchtsmixer post_init gating." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache no_grad behavior and Python version compatibility are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug and Qwen2-57B-A14B tp OOM are different issues despite both touching TP." + }, + { + "left": "issue:45357", + "right": "issue:45375", + "accept": true, + "reason": "Both point to the same Qwen3.5 vision/save_pretrained serialization problem: missing vision config fields causing incorrect saved keys." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Near-identical titles, same model family, same from_pretrained failure, and same version window; these are clearly the same bug." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The overall read is mostly conservative, but the summary overstates exclusivity: the packet also contains an exact-title duplicate-looking pair, issue:45310 and issue:45478, plus a small Qwen3.5 save/load family that could plausibly cluster together. Because of that, saying the import-time slowdown pair is the only plausible duplicate edge is not fully grounded in the packet." + "accept": true, + "feedback": "The summary stays within the packet evidence and the soft-edge calls are conservative. The accepted duplicate pairs are well grounded by the titles/body themes, and the rejected pairs avoid overclaiming similarity across different model families or failure modes. The umbrella/canonical language is cautious enough for this mixed cluster." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -14761,7 +14872,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:28282", "issue:30333", @@ -14770,6 +14881,7 @@ "issue:33453", "issue:34689", "issue:36296", + "issue:41628", "issue:42548", "issue:42757", "issue:42831", @@ -14779,7 +14891,6 @@ "issue:43232", "issue:43299", "issue:43502", - "issue:43575", "issue:43576", "issue:43618", "issue:43723", @@ -14813,7 +14924,6 @@ "issue:46132" ], "soft_pairs": [ - "issue:36296|issue:43575", "issue:28282|issue:33453", "issue:43618|issue:44857", "issue:44360|issue:45440", @@ -14824,10 +14934,10 @@ "issue:42890|issue:45600", "issue:43723|issue:44556", "issue:43576|issue:46132", - "issue:42548|issue:44351", "issue:44387|issue:44556", - "issue:42890|issue:45341", + "issue:42548|issue:44351", "issue:44222|issue:45125", + "issue:42890|issue:45341", "issue:43010|issue:43065", "issue:43502|issue:44485", "issue:44355|issue:44749", @@ -14849,259 +14959,266 @@ "issue:42757|issue:43576", "issue:43576|issue:45071", "issue:33453|issue:36296", + "issue:44222|issue:44230", "issue:43576|issue:43824", - "issue:44222|issue:44230" + "issue:41628|issue:42548" ], - "prepared_review_unit_hash": "f94c7a8d29b7c02c43e8e7fcdf48bd4ad4a3f40acf1eb7f98485202918003aca", + "prepared_review_unit_hash": "16a64a91c5aeefca2e53ee5ca5c5ad719362c1a3fac671b323e6b585bad220dd", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 38, - "serialized_chars": 38486, - "estimated_input_tokens": 9622, - "estimated_eval_tokens": 19500 + "serialized_chars": 38482, + "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 issues, with a loose theme around v5 loading/regression bugs and model-specific breakages. None of the soft pairs is clearly the same underlying defect, so I would keep them separate.", - "confidence": 0.34, - "canonical_issue_reason": "Issue 43723 is the cleanest representative of the cluster\u2019s common theme: a concrete, user-facing v5 loading regression with a direct API surface and broad relevance.", + "summary": "This cluster is a loose collection of mostly unrelated Transformers issues, many of them broad v5 regressions or loading/import problems. The soft pairs share superficial wording or subsystem overlap, but not the same concrete bug, so none should be merged as duplicates.", + "confidence": 0.88, + "canonical_issue_reason": "issue:33453 is the most representative standalone bug report in the set: it is a broad tokenizer-loading regression with high discussion activity and overlaps most with other loading-related reports.", "canonical_pr_reason": null, - "best_issue_reason": "43723 is the best anchor issue here because it is specific, actionable, and closest to the repeated \"loading broke in v5\" pattern seen across several items.", + "best_issue_reason": "issue:33453 is the best single issue candidate to anchor the cluster because it is broad, concrete, and central to the loading-regression theme seen here.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:36296", - "right": "issue:43575", - "accept": false, - "reason": "Both mention tensor parallelism/loading, but one is a general tensor-parallel training bug and the other is an OOM while loading a specific model. Not the same concrete failure." - }, { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "PyTorch import error versus tokenizer loading regression. Same broad loader area, but different symptoms and code paths." + "reason": "Both mention import/loading failures, but one is a missing PyTorch dependency error and the other is a tokenizer regression; different underlying bugs." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIP output attentions bug and LwDETR AMP crash are unrelated model/runtime failures." + "reason": "Different failures in different model paths; one is CLIP attentions handling, the other is an AMP/CUDA crash in LwDetrImageLoss." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "DSA indexer/ReLU discussion is unrelated to DeepSeekV3MoE implementation divergence." + "reason": "Unrelated topics: a discussion about a DSA indexer ReLU vs a DeepSeekV3MoE implementation divergence." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "Different models and failures: missing CLIP attentions versus Qwen3.5 flash-attention generation issues." + "reason": "Only broad generation/runtime context overlaps; CLIP attentions assignment and Qwen flash-attention generation are separate bugs." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "Test seeding flakiness is unrelated to a Phi-4 multimodal loading regression." + "reason": "One is a flaky test due to missing set_seed, the other is a Phi-4 multimodal model-loading regression." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "Local-files-only network leakage and AddedToken keyword collision are distinct bugs in different parts of the stack." + "reason": "Both involve loading-related code paths, but local_files_only network leakage and AddedToken argument duplication are different defects." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "One is a missing set_seed in integration tests; the other is a stale device-override CI failure. Not the same bug." + "reason": "Both are test failures, but they concern different tests and causes: missing set_seed vs a stale device override assertion." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "Test seeding issue versus auto_mappings references to removed configs; unrelated failure modes." + "reason": "A flaky SamHQ test and a CI break from removed auto_mappings entries are not the same bug." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Both are loading regressions, but one is tokenizer loading and the other is checkpoint reload after upgrade. Too broad to treat as one fix." + "reason": "Both are version-related loading complaints, but one is tokenizer loading and the other is checkpoint reload compatibility after upgrading to v5." }, { "left": "issue:43576", "right": "issue:46132", "accept": false, - "reason": "Broken env command and AttentionInterface.register behavior change are different features and failure paths." - }, - { - "left": "issue:42548", - "right": "issue:44351", - "accept": false, - "reason": "Both are import errors, but for different symbols and likely different dependency/export issues." + "reason": "Both touch Transformers internals, but one is an env command regression and the other is changed behavior in AttentionInterface.register." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 CUDA memory regression and checkpoint reload failure are not the same underlying problem." + "reason": "One is an int4 quantization memory regression; the other is a model reload compatibility issue." }, { - "left": "issue:42890", - "right": "issue:45341", + "left": "issue:42548", + "right": "issue:44351", "accept": false, - "reason": "Test utility bug is not the same as the SAM HQ seeding-related integration failure." + "reason": "Both are import errors, but they refer to different symbols and likely different API breakages." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "FP8 save_pretrained bug and missing tensor-parallel plan for Qwen3.5 MoE are separate issues." + "reason": "Both mention FP8/MoE, but one is save_pretrained behavior and the other is missing tensor-parallel metadata." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "A flaky integration test and a small testing_utils bug are not the same underlying issue." }, { "left": "issue:43010", "right": "issue:43065", "accept": false, - "reason": "Cache/layer update no_grad decoration and dummy Conv2d in Sam3PixelDecoder are unrelated." + "reason": "Different code paths: cache/layer update decoration vs a dummy Conv2d in Sam3PixelDecoder." }, { "left": "issue:43502", "right": "issue:44485", "accept": false, - "reason": "Network-request leakage on local_files_only and GLM-5 RoPE implementation are different bugs." + "reason": "local_files_only network behavior is unrelated to the GLM-5 RoPE implementation discussion." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Compiled Python file errors and a performance regression after upgrade are not the same issue." + "reason": "One concerns compiled Python file errors, the other is a data-filtering slowdown after upgrading Transformers." }, { "left": "issue:45125", "right": "issue:45478", "accept": false, - "reason": "Both involve Qwen3.5 MoE, but one is missing _tp_plan and the other is a broader from_pretrained error in v5.4.0. Not enough evidence of one concrete fix." + "reason": "Both are Qwen3.5/MoE-related, but one is tensor-parallel support metadata and the other is a from_pretrained loading error." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "MLFlow job reporting and tokenizer loading regression are unrelated." + "reason": "Training-job MLflow reporting and tokenizer loading regression are unrelated bugs." }, { "left": "issue:43010", "right": "issue:43232", "accept": false, - "reason": "Both are generation-related, but one is cache/layer update decoration and the other is sync_gpus/_update_model_kwargs_for_generation behavior." + "reason": "Both mention generation/cache internals, but they are distinct generation-state bugs." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Both are Qwen3.5 MoE-family items, but one is tensor parallelism and the other is a missing vision config field. Different bugs." + "reason": "Different model metadata issues: tensor parallel plan vs missing vision config field silently dropped by strict validation." }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "Sentence Transformers loading stall and documentation confusion around forward args are not duplicates." + "reason": "Sentence-transformers loading hang and documentation confusion around forward inputs are not the same issue." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "local_files_only network bug and FP8 save_pretrained moe bug are unrelated." + "reason": "Both are regressions, but one is unwanted API calls and the other is FP8 save_pretrained behavior." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Different loading regressions on different model families and versions; not a single concrete defect." + "reason": "A Qwen3VL MoE loading break and a generic v4-to-v5 checkpoint reload problem are different failures." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "FP8 accuracy issue and missing image-processor method causing multimodal token counting failure are distinct." + "reason": "One reports an FP8 accuracy issue; the other is a missing image-patch helper causing an AttributeError." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Documentation references to removed pipeline APIs are unrelated to the placeholder 'racoon' issue." + "reason": "Documentation referencing removed pipelines is unrelated to the 'racoon' issue." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "No relation between local_files_only networking and the 'racoon' issue." + "reason": "No real overlap beyond being bug reports; local_files_only network leakage and 'racoon' are unrelated." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled-file runtime errors and PretrainedConfig type checking regressions are different problems." + "reason": "Compiled-file errors and PretrainedConfig type-checking breakage are different regressions." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "MLFlow reporting failure and tensor-parallel training bug are unrelated." + "reason": "MLflow reporting on failed jobs and tensor-parallel training bugs are separate subsystems and failures." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Liger Kernel application with model_init and DSA indexer/ReLU discussion do not share a concrete bug." + "reason": "Liger Kernel application with model_init has nothing to do with a DSA indexer lacking ReLU." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Running compiled Python files and saving Pipeline objects are separate issues." + "reason": "Compiled Python file errors and inability to save Pipeline objects are distinct issues." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Tokenizer loading regression and Llama 3.2 Vision model loading breakage are different model/load failures." + "reason": "Both concern loading regressions, but one is tokenizer loading and the other is Llama 3.2 vision model loading under a specific version." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "Missing is_offline_mode import from huggingface_hub is not the same as a broken transformers env command." + "reason": "Both are v5-related API complaints, but one is a missing huggingface_hub import and the other is a broken env command." }, { "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "Broken env command and PretrainedConfig type-checking regression are unrelated." + "reason": "Unrelated: broken env command vs PretrainedConfig type-checking regression." }, { - "left": "issue:43576", - "right": "issue:43824", + "left": "issue:33453", + "right": "issue:36296", "accept": false, - "reason": "Env command failure and Qwen2.5-VL import error are different issues." + "reason": "Tokenizer loading regression and tensor-parallel training bug are not the same bug." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "FP8 save_pretrained bug and FP8 inference support request are related only by topic, not by the same code-path or fix." + "reason": "Both mention FP8/MoE, but one is a save_pretrained bug and the other is inference support." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Different import/loading failures: env command breakage versus missing Qwen2_5_VLForConditionalGeneration export." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import-name errors, but for different symbols and likely different package export regressions." } ] }, @@ -15123,15 +15240,13 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:31795", "issue:36296", "issue:38617", - "issue:41628", "issue:41669", "issue:42371", - "issue:42548", "issue:42890", "issue:43352", "issue:43408", @@ -15146,6 +15261,7 @@ "issue:44230", "issue:44246", "issue:44273", + "issue:44297", "issue:44315", "issue:44355", "issue:44393", @@ -15172,12 +15288,12 @@ "issue:46143", "issue:46144", "issue:46178", - "issue:46209" + "issue:46209", + "issue:46218" ], "soft_pairs": [ - "issue:41628|issue:42548", - "issue:31795|issue:38617", "issue:44961|issue:45468", + "issue:31795|issue:38617", "issue:44355|issue:46178", "issue:43576|issue:44938", "issue:44315|issue:46209", @@ -15203,221 +15319,253 @@ "issue:42371|issue:44492", "issue:44492|issue:45850", "issue:45278|issue:45850", + "issue:41669|issue:46218", "issue:44246|issue:44273", "issue:42890|issue:44908", - "issue:44704|issue:44908", "issue:43408|issue:44315", + "issue:44704|issue:44908", "issue:43976|issue:44393", + "issue:44297|issue:45230", "issue:43352|issue:44393" ], - "prepared_review_unit_hash": "4ed796aeebfa94850c87e4b03641e5694089ed24a0b05e05bd4539f3d5129604", + "prepared_review_unit_hash": "43dcc699751e024f009f28c0361e36564297c1c5e3bdb6b2353acdd88fe2caa1", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 34, - "serialized_chars": 37146, - "estimated_input_tokens": 9287, - "estimated_eval_tokens": 18830 + "soft_pair_count": 35, + "serialized_chars": 37491, + "estimated_input_tokens": 9373, + "estimated_eval_tokens": 19002 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a mix of unrelated model/feature bugs, with one dominant subtheme around v5 import/export regressions and lazy-loading/import behavior. The clearest representative issue is the broad import-regression report.", - "confidence": 0.84, - "canonical_issue_reason": "issue:45278 best captures the main cluster theme: widespread import failures after upgrading to v5.5.0, which is the most broadly representative and actionable report here.", + "summary": "This set is not a single duplicate cluster; it contains many unrelated issue reports with only loose similarity around v5 regressions, import/performance, and a few model-specific bugs. No soft edge looks like the same underlying bug/change with enough confidence to merge.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45850 is the broadest umbrella-style regression report in the set (\u201cSince 5.0 version it breaks too many models\u201d), so it is the most central issue node for loose grouping, though it is too vague to be a precise duplicate target.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the strongest umbrella issue for the import-error/lazy-loading regression subset; the other items are either narrower, model-specific, or unrelated.", + "best_issue_reason": "issue:45850 is the best global issue representative only because it is the closest catch-all v5 breakage report; it still lacks the specificity needed for strict duplicate consolidation.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:41628", - "right": "issue:42548", + "left": "issue:44961", + "right": "issue:45468", "accept": false, - "reason": "Both are import errors, but they target different symbols and there is no evidence they are the same concrete missing-export bug." + "reason": "Unrelated: a nonsense title versus a Gemma-4 audio positional-encoding bug; no shared concrete failure path." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation confusion about forward args is unrelated to an ImportError for layer_type_validation." - }, - { - "left": "issue:44961", - "right": "issue:45468", - "accept": false, - "reason": "These are completely unrelated issues; one is a placeholder title and the other is a Gemma audio positional-encoding bug." + "reason": "Documentation confusion about forward args vs an import error for a missing symbol; different problem classes." }, { "left": "issue:44355", "right": "issue:46178", "accept": false, - "reason": "Compiled Python file failures and a tensorflow_text backend mapping error are different failure modes with different code paths." + "reason": "Compiled Python file errors are not the same as a backend-mapping ValueError for tensorflow_text." }, { "left": "issue:43576", "right": "issue:44938", "accept": false, - "reason": "A broken env command and a Python 3.14 load failure are distinct issues, not the same regression." + "reason": "Both are version-related breakages, but one is the transformers env CLI and the other is Python 3.14 import/loading; too broad to be the same bug." }, { "left": "issue:44315", "right": "issue:46209", "accept": false, - "reason": "Liger Kernel application in model_init and FP8 inference on B200 are separate model/runtime problems." + "reason": "Liger Kernel not applied with model_init is unrelated to an FP8 inference failure on B200." }, { "left": "issue:46143", "right": "issue:46144", "accept": false, - "reason": "Both touch RoFormer, but one is missing kwargs propagation while the other is about using the attention interface; not the same bug." + "reason": "Both mention RoFormer, but one is kwargs propagation and the other is attention-interface usage; not the same concrete defect." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Scheduler kwargs handling is unrelated to the unrelated placeholder issue." + "reason": "Scheduler kwargs handling is unrelated to the placeholder racoon report." }, { "left": "issue:44485", "right": "issue:44961", "accept": false, - "reason": "GLM-5 RoPE implementation discussion is unrelated to the placeholder issue." + "reason": "GLM-5 RoPE implementation discussion is unrelated to the racoon issue." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor-parallel training bugs and a documentation mismatch for return_all_scores are not the same underlying problem." + "reason": "Tensor parallel training bug and TextClassificationPipeline docs mismatch are different areas and symptoms." }, { "left": "issue:43673", "right": "issue:44492", "accept": false, - "reason": "A cache-missing runtime bug and a typo in cache strategy docs/code are different issues." + "reason": "Missing GenerationMixin cache during chunked prefill is unrelated to a cache-strategy typo." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are unrelated." + "reason": "Tensor parallel training bug is unrelated to BeitImageProcessorFast label reduction behavior." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "A specific Qwen3.5-35B crash is not the same as a vague report that many models break in v5." + "reason": "A specific Qwen3.5-35B chat crash is not the same concrete issue as a generic 'many models break' regression report." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "Processor save_pretrained missing files is a concrete bug; the other is a generic, underspecified report." + "reason": "Missing processor.save_pretrained files is a concrete serialization bug, while the other report is too generic to match." }, { "left": "issue:44273", "right": "issue:45542", "accept": false, - "reason": "Lazy loading correctness and an undefined tf backend error from tensorboard-only installs are different bugs." + "reason": "Lazy loading problems are unrelated to a backend error caused by tensorboard without TensorFlow." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Qwen3-VL-Moe support and missing _tp_plan for tensor parallelism are related to the model family but not the same fixable code-path issue." + "reason": "General Qwen3-VL-Moe bugs and missing _tp_plan for tensor parallelism are related only at a model-family level, not the same bug." }, { "left": "issue:44273", "right": "issue:45003", "accept": false, - "reason": "Lazy loading failures and unsafe sys.modules access are adjacent areas, but the reported bugs are distinct." + "reason": "Lazy loading failure and unsafe sys.modules access may be adjacent, but they are not clearly the same underlying defect." }, { "left": "issue:44230", "right": "issue:46095", "accept": false, - "reason": "FP8 inference support for Qwen3-VL and a weight-conversion question for DeepSeekV4 are unrelated." + "reason": "FP8 inference support and a weight-conversion-script question are different requests/issues." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "A Qwen3-VL bounding-box output bug and a PretrainedConfig type-checking break are different problems." + "reason": "Qwen3-VL 2D box output problems are unrelated to PretrainedConfig type-checking regressions." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Broken env command behavior and checkpoint reload incompatibility across versions are separate regressions." + "reason": "Both involve v5 regressions, but one is the env command and the other is checkpoint reload compatibility; not the same bug." }, { "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 complaint that many models break." + "reason": "Llama4Config missing pad_token_id is a specific config bug, not the same as a broad v5 breakage umbrella." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "2D bounding-box output errors are not the same as an infinite-loop generation bug for a specific image." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-time slowdowns and missing GenerationMixin cache are both v5-related, but the concrete code paths differ." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both concern old checkpoints under v5, but one is general reload failure and the other is remote-code/meta-init incompatibility." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is a specific config bug, not the same as the generic v5 complaint." + "reason": "StableLmConfig pad_token_idx regression is a specific config migration bug, not the same as a generic v5 breakage report." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API migration guidance is unrelated to a cache-strategy typo." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "A cache-strategy typo is not the same underlying bug as a broad model-breakage report." + "reason": "A typo in cache-strategy docs/code is not the same as a broad statement that v5 breaks many models." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "Both are about v5 regressions, but 45278 is a concrete import-error report while 45850 is too vague to be the same specific bug." + "reason": "General import errors after upgrading to 5.5.0 are related in theme, but not the same concrete failure as the broad v5 breakage claim." + }, + { + "left": "issue:41669", + "right": "issue:46218", + "accept": false, + "reason": "Import-* performance work and an import failure for Qwen3_5ForCausalLM are different issues." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Import slowdown and broken lazy loading are different symptoms and likely different fixes." + "reason": "Slow import is not the same as lazy loading not working properly; the overlap is too broad." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Missing set_seed in tests and an inverse_sqrt scheduler kwargs bug are unrelated." + "reason": "Missing set_seed in tests is unrelated to scheduler kwargs handling." }, { - "left": "issue:44704", - "right": "issue:44908", + "left": "issue:43408", + "right": "issue:44315", "accept": false, - "reason": "AutoProcessor cached_file kwargs handling and scheduler kwargs handling are unrelated code paths." + "reason": "Model-type mismatch warning for sam3_video/tracker is unrelated to Liger Kernel application in model_init." }, { - "left": "issue:43408", - "right": "issue:44315", + "left": "issue:44704", + "right": "issue:44908", "accept": false, - "reason": "A wrong model-type warning and a Liger Kernel/model_init application bug are not the same issue." + "reason": "AutoProcessor cached_file kwargs propagation is unrelated to inverse_sqrt scheduler kwargs handling." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python-version compatibility and a Qwen3-VL output bug are unrelated." + "reason": "Python-version compatibility failure is unrelated to Qwen3-VL bounding-box output bugs." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch is a specific serialization bug, not a generic bug report." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash Attention 2 support for NemotronH and Qwen3-VL bounding-box errors are different model-specific bugs." + "reason": "Flash Attention 2 support for NemotronH is unrelated to Qwen3-VL bounding-box hallucination/error." } ] }, @@ -15439,18 +15587,18 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:31515", "issue:31795", "issue:33453", "issue:34689", - "issue:41628", "issue:41669", "issue:42371", "issue:42913", "issue:43066", "issue:43298", + "issue:43352", "issue:43502", "issue:43519", "issue:43576", @@ -15464,7 +15612,6 @@ "issue:44263", "issue:44273", "issue:44295", - "issue:44297", "issue:44315", "issue:44351", "issue:44360", @@ -15488,10 +15635,10 @@ "issue:45850", "issue:46018", "issue:46095", - "issue:46172" + "issue:46172", + "issue:46218" ], "soft_pairs": [ - "issue:44297|issue:45230", "issue:44295|issue:45230", "issue:43576|issue:44908", "issue:41669|issue:44351", @@ -15499,26 +15646,28 @@ "issue:41669|issue:45341", "issue:44492|issue:44945", "issue:43976|issue:45850", - "issue:44393|issue:45478", + "issue:43976|issue:46218", "issue:44077|issue:44861", + "issue:44393|issue:45478", "issue:43827|issue:44908", - "issue:41628|issue:41669", "issue:31795|issue:33453", "issue:44315|issue:44829", "issue:43576|issue:44273", "issue:44655|issue:44861", "issue:44360|issue:45468", "issue:45230|issue:45310", - "issue:46018|issue:46172", "issue:44273|issue:44908", + "issue:46018|issue:46172", + "issue:43576|issue:46218", "issue:43519|issue:44485", "issue:43519|issue:44908", "issue:41669|issue:43704", "issue:31795|issue:34689", "issue:31515|issue:31795", - "issue:43704|issue:44485", "issue:44485|issue:45468", + "issue:43704|issue:44485", "issue:43298|issue:46095", + "issue:45850|issue:46218", "issue:42371|issue:43704", "issue:43502|issue:43519", "issue:43519|issue:44623", @@ -15526,294 +15675,307 @@ "issue:43606|issue:45468", "issue:44263|issue:45468", "issue:44261|issue:45468", + "issue:44351|issue:46218", "issue:42913|issue:43066", + "issue:43352|issue:46218", "issue:44908|issue:44998", "issue:44492|issue:44998", "issue:43618|issue:44998", "issue:44861|issue:45290", - "issue:44998|issue:45850", - "issue:44998|issue:45341" + "issue:44998|issue:45850" ], - "prepared_review_unit_hash": "172b2082a6f6ae6dd14e3314af71ed7601d991bf6d369b4a456dcfe0c1984138", + "prepared_review_unit_hash": "8e067e079f4dd9507bfb02698cbb00a2d75b8d63e3325d87932e5eff9ce5768b", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 42, - "serialized_chars": 39485, - "estimated_input_tokens": 9872, - "estimated_eval_tokens": 20000 + "soft_pair_count": 44, + "serialized_chars": 40004, + "estimated_input_tokens": 10001, + "estimated_eval_tokens": 20258 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: most soft edges connect clearly different bugs, docs issues, or unrelated subsystems. I would keep the earliest concrete Qwen3.5 MoE from_pretrained regression as the representative issue, but I would not merge any of the soft-edge pairs.", - "confidence": 0.86, - "canonical_issue_reason": "issue:45310 is the earliest concrete report of the repeated Qwen3.5 MoE from_pretrained failure and is specific enough to represent that regression thread better than the broader or unrelated items in the cluster.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers regressions and docs issues, with some broad overlap around v5 breakages and tokenizer/model-loading problems. None of the soft pairs look like true duplicates under a strict same-bug standard.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45850 is the broadest umbrella in the set (\u201cSince 5.0 version it breaks too many models\u201d) and best matches the cluster\u2019s loose v5-regression theme, even though it is too generic to subsume the specific bugs cleanly.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the best issue to keep as the representative record: it has a concrete model-loading failure, a clear version trigger, and enough detail to be actionable.", + "best_issue_reason": "issue:45850 is the most representative cluster anchor because it describes the widest user-visible regression pattern; the other issues are narrower, model-specific, or unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44297", - "right": "issue:45230", - "accept": false, - "reason": "A tokenizer save_pretrained metadata mismatch is not the same as a generic placeholder bug report." - }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "Reading a buffer-registered position_ids tensor is a distinct bug from a generic placeholder report." + "reason": "Generic bug report versus a buffer/position_ids reading problem; no clear shared code path or concrete duplicate symptom." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "A broken env CLI command and a scheduler-kwargs regression are unrelated code paths." + "reason": "Broken env CLI and inverse_sqrt scheduler kwargs are unrelated subsystems." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Removing import * for performance is unrelated to a missing HybridCache import." + "reason": "Import-* cleanup/perf issue is unrelated to a HybridCache import failure." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs handling and PretrainedConfig type checking are different problems." + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are different bugs." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "A model import cleanup/performance issue is unrelated to a testing_utils bug." + "reason": "Model import cleanup is unrelated to a testing_utils bug." }, { "left": "issue:44492", "right": "issue:44945", "accept": false, - "reason": "A cache-strategy typo is not the same as incorrect pipeline-parallelism output." + "reason": "Cache-strategy typo and pipeline-parallelism output corruption are not the same bug." }, { "left": "issue:43976", "right": "issue:45850", "accept": false, - "reason": "Python 3.9 support breakage and a broad 'too many models break' complaint are not the same bug." + "reason": "Python-version compatibility failure is not the same concrete problem as the broad \u201cmany models break\u201d report." }, { - "left": "issue:44393", - "right": "issue:45478", + "left": "issue:43976", + "right": "issue:46218", "accept": false, - "reason": "Different models and failure modes: Qwen3-VL 2D box output versus Qwen3.5 MoE from_pretrained loading." + "reason": "Python support regression and Qwen3_5 import failure are different failure modes." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Optional post_init policy for patchtsmixer is unrelated to a tied-weights AttributeError." + "reason": "Optional post_init policy and tied-weight-key AttributeError are unrelated." }, { - "left": "issue:43827", - "right": "issue:44908", + "left": "issue:44393", + "right": "issue:45478", "accept": false, - "reason": "Docs still referencing pipeline() after removals is unrelated to inverse_sqrt scheduler kwargs." + "reason": "Different models and different symptoms; not the same underlying bug." }, { - "left": "issue:41628", - "right": "issue:41669", + "left": "issue:43827", + "right": "issue:44908", "accept": false, - "reason": "AutoImageProcessor import failures and import * cleanup/performance are different import issues." + "reason": "Docs still referencing pipeline() is unrelated to scheduler kwargs being ignored." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Forward docs confusion is not the same as a tokenizer loading regression." + "reason": "Documentation confusion in model.forward and tokenizer-loading regression are not the same issue." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Liger Kernel not applied with model_init and flash_attention_3 training degeneration are different acceleration/training bugs." + "reason": "Liger Kernel not applied via model_init and flash_attention_3 training degeneration are distinct code paths." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Broken env command and lazy loading failure are unrelated." + "reason": "CLI env command breakage and lazy-loading failure are not the same bug." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Saving Pipeline objects and tied-weight key extraction are different serialization paths." + "reason": "Saving Pipeline objects and tied-weight-key crash are unrelated." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "A DSA indexer activation issue is unrelated to Gemma-4 audio positional encoding." + "reason": "DSA indexer ReLU discussion and Gemma-4 audio positional encoding bug do not match." }, { "left": "issue:45230", "right": "issue:45310", "accept": false, - "reason": "A generic placeholder report is not the same as a concrete Qwen3.5 MoE loading regression." + "reason": "Generic bug report and Qwen3.5 MoE from_pretrained error are not sufficiently specific to be duplicates." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading malfunction and scheduler kwargs handling are unrelated." }, { "left": "issue:46018", "right": "issue:46172", "accept": false, - "reason": "DeepSeek shared-expert gating and a comb transpose bug are different model implementation issues." + "reason": "DeepSeek-V4 shared expert gating and a comb transpose issue are different model bugs." }, { - "left": "issue:44273", - "right": "issue:44908", + "left": "issue:43576", + "right": "issue:46218", "accept": false, - "reason": "Lazy loading is unrelated to scheduler argument propagation." + "reason": "Broken env CLI is unrelated to Qwen3_5 import failure." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are different numeric/model bugs." + "reason": "Timestamp calculation in Qwen3VL and GLM-5 RoPE implementation are different model-specific defects." }, { "left": "issue:43519", "right": "issue:44908", "accept": false, - "reason": "Timestamp computation in a processor is unrelated to scheduler kwargs." + "reason": "Processor timestamp math and scheduler kwargs are unrelated." }, { "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Import cleanup/performance is unrelated to a Qwen3 VRAM leak." + "reason": "Import-* cleanup/perf issue is unrelated to VRAM leakage in dataloader threads." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Documentation confusion about forward arguments is unrelated to Llama 3.2 model loading failure." + "reason": "Model.forward docs confusion and Llama 3.2 model-loading regression are not the same underlying bug." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Slow checkpoint loading and forward-doc confusion are different issues." + "reason": "Slow from_pretrained checkpoint loading and forward-API documentation confusion are unrelated." }, { - "left": "issue:43704", - "right": "issue:44485", + "left": "issue:44485", + "right": "issue:45468", "accept": false, - "reason": "A VRAM leak and a RoPE implementation discussion are different bugs." + "reason": "Different architectures and different implementation bugs; no shared concrete fix." }, { - "left": "issue:44485", - "right": "issue:45468", + "left": "issue:43704", + "right": "issue:44485", "accept": false, - "reason": "GLM-5 RoPE behavior and Gemma-4 audio positional encoding are unrelated model-specific math paths." + "reason": "VRAM leak in threaded dataloading and GLM-5 RoPE implementation are not duplicates." }, { "left": "issue:43298", "right": "issue:46095", "accept": false, - "reason": "Audio continuous batching support and a DeepSeek-V4 weight-conversion question are not the same bug." + "reason": "Continuous batching support for audio models and DeepSeek-V4 weight conversion are separate feature/question areas." + }, + { + "left": "issue:45850", + "right": "issue:46218", + "accept": false, + "reason": "Broad v5 breakage report and a specific Qwen3_5 import error are too different to merge." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 API behavior and a Qwen3 VRAM leak are unrelated." + "reason": "TF32 settings migration and dataloader-thread VRAM leak are unrelated." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "Unexpected API requests under local_files_only and Qwen3VL timestamp math are unrelated." + "reason": "local_files_only network requests and Qwen3VL timestamp calculation are unrelated bugs." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Processor timestamp calculation and processor.save_pretrained missing files are different failures." + "reason": "Processor timestamp math and missing save_pretrained files are different issues." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Processor timestamp math and a multi-thread VRAM leak are unrelated." + "reason": "Timestamp calculation and VRAM leak are unrelated." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device mismatch and Gemma-4 audio positional encoding are different problems." + "reason": "CPU offload device mismatch and Gemma-4 audio positional encoding bug are different problems." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "A torch.split return-value issue is unrelated to Gemma-4 audio positional encoding." + "reason": "torch.split return handling in GLM-MoE and Gemma-4 audio positional encoding do not match." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "Missing rms_norm_eps in MLA q_a_layernorm is unrelated to Gemma-4 audio positional encoding." + "reason": "Layernorm eps precision discussion and Gemma-4 audio positional encoding are unrelated." + }, + { + "left": "issue:44351", + "right": "issue:46218", + "accept": false, + "reason": "Both are import failures, but for different symbols and likely different export paths; not the same concrete bug." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both mention tokenizer v5 changes, but one is a broad behavior difference and the other is a specific decoder-type bug; not the same underlying defect." + "reason": "Both concern tokenizer v5 behavior, but one is a generic v4\u2192v5 behavior change and the other is a specific decoder-type bug." + }, + { + "left": "issue:43352", + "right": "issue:46218", + "accept": false, + "reason": "Unsupported Flash Attention 2.0 for NemotronH and Qwen3_5 import failure are unrelated." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "A scheduler kwargs regression is unrelated to a nonsense placeholder issue." + "reason": "Scheduler kwargs and an unrelated off-topic issue are not duplicates." }, { "left": "issue:44492", "right": "issue:44998", "accept": false, - "reason": "A cache-strategy typo is unrelated to a nonsense placeholder issue." + "reason": "Cache-strategy typo and an off-topic issue are unrelated." }, { "left": "issue:43618", "right": "issue:44998", "accept": false, - "reason": "CLIPOutput attentions regression is unrelated to a nonsense placeholder issue." + "reason": "CLIPOutput attentions regression and an off-topic issue are unrelated." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Tied-weight key extraction and chat template tool-call crashes are different code paths." + "reason": "Tied-weight-key list handling and chat template tool-call crash are different code paths." }, { "left": "issue:44998", "right": "issue:45850", "accept": false, - "reason": "A nonsense title is not the same as a broad model-breakage complaint." - }, - { - "left": "issue:44998", - "right": "issue:45341", - "accept": false, - "reason": "A nonsense placeholder issue is unrelated to a testing_utils bug." + "reason": "Off-topic issue and broad v5 regression report are not the same underlying bug." } ] }, @@ -15835,7 +15997,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-430", + "cluster_id": "cluster-10000-431", "nodes": [ "issue:30333", "issue:31515", @@ -15853,13 +16015,16 @@ "issue:43813", "issue:44031", "issue:44230", + "issue:44556", "issue:44623", "issue:44861", + "issue:44998", "issue:45310", "issue:46018", "issue:46144" ], "soft_pairs": [ + "issue:44556|issue:44998", "issue:43525|issue:44861", "issue:43572|issue:44861", "issue:31515|issue:38617", @@ -15882,160 +16047,166 @@ "issue:37934|issue:43668", "issue:42936|issue:43668" ], - "prepared_review_unit_hash": "2aa9b4d7065669e5936d6e4e47353ceac550b4cd5eae2f8325523f8cc36ea52c", + "prepared_review_unit_hash": "0de79b46faa0c6f478fa9b0f53f9de609b7d016dbf7bce54291899ccd34eb6e6", "component_budget": { - "node_count": 430, - "item_count": 430, - "soft_pair_count": 1591, - "serialized_chars": 823302, - "estimated_input_tokens": 205826, - "estimated_eval_tokens": 411908 + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 }, "budget": { - "node_count": 21, - "item_count": 21, - "soft_pair_count": 21, - "serialized_chars": 18006, - "estimated_input_tokens": 4502, - "estimated_eval_tokens": 9260 + "node_count": 23, + "item_count": 23, + "soft_pair_count": 22, + "serialized_chars": 19401, + "estimated_input_tokens": 4851, + "estimated_eval_tokens": 9958 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is over-broad and mostly driven by title similarity: it mixes unrelated issues across loading, tokenizers, configs, model internals, training, and inference. None of the suggested soft pairs look like the same underlying bug.", - "confidence": 0.93, - "canonical_issue_reason": "No single canonical issue is a good fit here\u2014the items are too heterogeneous, and the soft edges are only lexical similarity matches rather than true duplicates.", + "summary": "This is not a single duplicate cluster: the items span many unrelated bugs/features across loading, config, tokenizer, training, and model-specific behavior. All soft pairs look like loose topical similarity rather than the same underlying bug or change, so they should be rejected.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44556 is the most concrete, actionable issue in the set: it describes a specific regression boundary (v4.57 to v5.x) and a clear failure mode (checkpoint reload breaks after upgrade).", "canonical_pr_reason": null, - "best_issue_reason": "If forced to pick one representative, issue 43240 is the broadest concrete runtime-bug report in the set (loss kwargs propagation) and has the most inbound references, but it still does not duplicate the others.", + "best_issue_reason": "issue:44556 is the best single issue to anchor triage because it is specific, reproducible, and framed as a versioned regression rather than a broad or ambiguous request.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44556", + "right": "issue:44998", + "accept": false, + "reason": "Completely unrelated: checkpoint reload regression vs an unrelated low-signal title ('Unemployment')." + }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Different bugs: one is missing pad_token_id on Llama4Config, the other is an AttributeError in tied-weight key handling." + "reason": "Different bugs: missing pad_token_id on Llama4Config vs AttributeError in _get_tied_weight_keys for list handling." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "StableLm pad_token_idx regression and _tied_weights_keys list crash are separate config/runtime issues." + "reason": "Different config regression (pad_token_idx missing) vs tied-weight key crash; no shared code path." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Checkpoint loading slowness and a missing import from configuration_utils are unrelated code paths." + "reason": "One is slow from_pretrained checkpoint loading; the other is an ImportError for a missing symbol. Different failure modes." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 inference support for Qwen models is a different change from processor.save_pretrained missing files." + "reason": "Different areas: fp8 Qwen3-VL/Qwen3.5 inference support vs processor.save_pretrained missing files." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow job status reporting on failed training and slow from_pretrained checkpoint loading are unrelated." + "reason": "MLflow reporting after failed training job vs slow checkpoint loading; unrelated subsystems and symptoms." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "One is loading performance, the other is a tensor-parallel training bug; not the same defect." + "reason": "Checkpoint load performance issue vs tensor parallel training bug; not the same underlying defect." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "FP8 support request and Qwen3.5 MoE from_pretrained failure are different issues, not one duplicate bug." + "reason": "Both mention Qwen3.5, but one is fp8 inference support and the other is a from_pretrained regression after version upgrade; too different to merge as one fix." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Both involve loading, but one is slow checkpoint loading while the other is a tokenizer-loading regression." + "reason": "Slow from_pretrained checkpoint load vs tokenizer loading regression; similar theme only at a very broad level." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching for audio models and Qwen3-VL/Qwen3.5 FP8 support are different feature gaps." + "reason": "Continuous batching audio-model support vs fp8 inference support; different model classes and problem types." }, { "left": "issue:43717", "right": "issue:46144", "accept": false, - "reason": "Mamba/Mamba-2 init_weights behavior and RoFormer attention-interface usage are unrelated architecture-specific issues." + "reason": "Mamba init_weights behavior vs RoFormer attention interface usage; unrelated model-specific implementation issues." }, { "left": "issue:42936", "right": "issue:46018", "accept": false, - "reason": "Mask2Former ignore_value handling and DeepSeek-V4 shared-expert gating are different model bugs." + "reason": "Mask2Former ignore_value handling vs DeepSeek-V4 shared expert gating; different models and different logic." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "ModernBERT type-hint correctness and tokenizer regex warning behavior are unrelated." + "reason": "Incorrect type hint in ModernBERTConfig vs tokenizer regex warning regression; unrelated." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Both touch training/loss plumbing, but ignore_value not used and kwargs not passed to loss are different concrete bugs." + "reason": "Ignore_value not used in Mask2Former vs kwargs not forwarded to loss calculation; related only in the broadest sense of loss code." }, { "left": "issue:43240", "right": "issue:46144", "accept": false, - "reason": "Loss-kwargs forwarding and RoFormer attention-interface usage do not describe the same code-path problem." + "reason": "Loss kwargs propagation vs attention interface implementation; no shared concrete bug." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2Former ignore_value usage and tokenizer regex warnings are unrelated subsystems." + "reason": "Mask2Former ignore_value bug vs tokenizer regex warning after 4.57.3; different components and root causes." }, { "left": "issue:42936", "right": "issue:46144", "accept": false, - "reason": "Mask2Former loss handling and RoFormer attention implementation are not duplicates." + "reason": "Mask2Former ignore_value handling vs RoFormer attention interface issue; not the same code path." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "A model loss-parameter bug and a quantization typo are clearly different issues." + "reason": "Ignore_value usage bug vs a typo in quantization_operation text; unrelated." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Loss-function kwargs forwarding and an incorrect type hint are not the same bug." + "reason": "Missing kwargs in loss calculation vs incorrect type hint; different severity and implementation areas." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "Incorrect type annotation and a typo in a quantization attribute path are unrelated." + "reason": "Type hint error vs typo in an attribute name; only superficial similarity." }, { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "A question about RMS norm behavior and a ModernBERT type-hint issue are unrelated." + "reason": "Question about whether Llama4TextL2Norm is really RMSNorm vs a type-hint correction; unrelated." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "Mask2Former ignore_value handling and ModernBERT norm_eps typing are different model/config issues." + "reason": "Mask2Former ignore_value bug vs ModernBERTConfig type hint issue; different models and bug classes." } ] }, @@ -16068,52 +16239,52 @@ "issue:10519|issue:11005", "issue:11005|issue:11307" ], - "prepared_review_unit_hash": "3db553639ca2a85c89f00059655b735feb34b5b8dc99aa6e23e2f443dfb6000a", + "prepared_review_unit_hash": "20c772d1f593ae0dd0f578ec9c37a2b967b86c8a0dda7ae658e3fa98f4fac2cb", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 2876, - "estimated_input_tokens": 719, - "estimated_eval_tokens": 1694 + "serialized_chars": 2878, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 2876, - "estimated_input_tokens": 719, - "estimated_eval_tokens": 1694 + "serialized_chars": 2878, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The three issues are only superficially similar in wording and appear to be unrelated feature requests: truncation behavior, ReduceLROnPlateau-like scheduling, and Wav2Vec2 word time offsets. None look like duplicates of the same underlying bug or change.", - "confidence": 0.94, - "canonical_issue_reason": "Issue 10519 is the most concrete and self-contained request, with a clearly specified behavior change and scope.", - "canonical_pr_reason": null, - "best_issue_reason": "Issue 10519 is the best representative of the cluster only because it is the most specific and actionable; the other two are unrelated topics.", - "best_pr_reason": null, + "summary": "These three issues are about unrelated feature requests: tokenizer truncation behavior, learning-rate scheduling functionality, and Wav2Vec2 word time offsets. They do not appear to be duplicates or the same underlying bug/change.", + "confidence": 0.97, + "canonical_issue_reason": "No true canonical issue for this cluster; the items cover different subsystems and different requested capabilities.", + "canonical_pr_reason": "No pull requests are present in this cluster.", + "best_issue_reason": "If one issue must serve as a representative, #10519 is the most concrete and narrowly scoped request, but it is not representative of the others as a duplicate target.", + "best_pr_reason": "No pull requests are present in this cluster.", "soft_edge_verdicts": [ { "left": "issue:10519", "right": "issue:11307", "accept": false, - "reason": "Different domains and requested changes: token truncation behavior vs. word boundary timestamps in Wav2Vec2." + "reason": "Different domains and goals: tokenizer truncation option vs speech model word timestamp extraction." }, { "left": "issue:10519", "right": "issue:11005", "accept": false, - "reason": "One is about truncation direction, the other about learning-rate scheduling functionality; no shared underlying bug or fix." + "reason": "Unrelated functionality: text truncation behavior vs ReduceLROnPlateau-like scheduler behavior." }, { "left": "issue:11005", "right": "issue:11307", "accept": false, - "reason": "Unrelated feature requests in different subsystems, with no concrete overlap in code path or expected change." + "reason": "Different problems in different components: optimizer/scheduler feature request vs Wav2Vec2 alignment/time-offset request." } ] }, @@ -16145,12 +16316,12 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "c1b07b3e511c524eeed707235846b5c44d606a601726a6325f18536c6bc6201e", + "prepared_review_unit_hash": "0b788c1aec8199c3ca715dea69ee7f9db99d3da602a02b70782ffb712d94fe6d", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2477, + "serialized_chars": 2479, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -16158,7 +16329,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 2477, + "serialized_chars": 2479, "estimated_input_tokens": 620, "estimated_eval_tokens": 1496 }, @@ -16167,24 +16338,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues do not look like duplicates of one another. #16618 is a model-loading failure report, while #15980 is about a bad login/private-model download error message and #13244 is about Tapas tokenization differing from TensorFlow code.", - "confidence": 0.87, - "canonical_issue_reason": "#16618 is the most concrete and broadly representative of the cluster because it is the only issue directly about a failed model load, making it the best anchor for the set even though the other issues are not true duplicates.", + "summary": "These are not duplicates as a cluster: one issue is about Tapas tokenization, one about a private-model auth/error-message problem, and one about loading bert-base-uncased. Only the two model-loading issues are loosely related, but they still appear to describe different failure modes.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 16618 is the broadest and most central model-loading report, but the cluster does not contain a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the best single issue to represent the cluster because it is the most central user-facing failure case among the three; however, it should not be treated as a duplicate of the others.", + "best_issue_reason": "16618 is the best representative because it is the most general user-facing model load failure among the three; the others are clearly about different topics.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tapas tokenization mismatch and inability to load bert-base-uncased are different problems affecting different code paths; they do not describe the same underlying bug." + "reason": "Different problems: Tapas tokenization vs. model loading for bert-base-uncased. No shared code-path or concrete failure mode." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "A private-model download/authentication error message is unrelated to a generic 'can't load bert-base-uncased' failure; same subsystem perhaps, but not the same bug." + "reason": "Both mention model download/load, but one is specifically a private-model login/error-message issue and the other is a generic bert-base-uncased load failure; too different to treat as the same bug." } ] }, @@ -16214,12 +16385,12 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "740361ac90c2811f1e0640057570bf7ae02b8fdafde926bbdd0a292547853382", + "prepared_review_unit_hash": "6b5dd876227352b905a3f199171ac178a6e7ce815e620d9af6bb8162a4f0de1c", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1590, + "serialized_chars": 1589, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -16227,7 +16398,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1590, + "serialized_chars": 1589, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -16236,18 +16407,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are both community contribution feature requests for expanding model/runtime support, but they target different capabilities: Flash Attention 2 vs GGUF. They do not look like the same underlying bug or change, so they should not be deduplicated.", - "confidence": 0.98, - "canonical_issue_reason": "If a representative issue is needed, #33260 is the better anchor because it is newer and has inbound references, but it is not a duplicate of #26350.", + "summary": "These are not duplicates: one issue requests Flash Attention 2 support for more architectures, while the other requests GGUF support for more architectures. They share a broad theme but describe different features and code paths.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "#33260 is the better cluster representative only in a loose organizational sense; it is more recent and externally referenced, though it covers a different feature area than #26350.", + "best_issue_reason": "If a single representative is needed, issue 26350 is slightly better because it is older and more specific, but the two issues are heterogeneous and should remain separate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Different support requests with different concrete targets: Flash Attention 2 architecture coverage vs GGUF architecture coverage. Same broad theme, but not the same underlying change." + "reason": "Different feature requests (Flash Attention 2 vs GGUF) with different underlying changes; they are related only at a broad \"more architectures\" level." } ] }, @@ -16269,17 +16440,19 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-27088-6", + "cluster_id": "cluster-27088-7", "nodes": [ "issue:27088", "issue:28936", "issue:38435", "issue:43834", "issue:44365", - "issue:44370" + "issue:44370", + "issue:46222" ], "soft_pairs": [ "issue:27088|issue:44370", + "issue:27088|issue:46222", "issue:27088|issue:44365", "issue:27088|issue:43834", "issue:27088|issue:38435", @@ -16289,130 +16462,164 @@ "issue:28936|issue:38435", "issue:28936|issue:44370", "issue:38435|issue:44370", + "issue:38435|issue:46222", "issue:38435|issue:44365", "issue:38435|issue:43834", "issue:43834|issue:44370", + "issue:43834|issue:46222", "issue:43834|issue:44365", - "issue:44365|issue:44370" + "issue:44365|issue:44370", + "issue:44365|issue:46222", + "issue:44370|issue:46222" ], - "prepared_review_unit_hash": "988b9a1040506a9b172fc1ba513f55db238f1c38341126cdde23c3fcbb6718cd", + "prepared_review_unit_hash": "2adc2e7ff48520849d8ae6ff3881e00e09fbf3972547c4a2574e6639c43c825c", "component_budget": { - "node_count": 6, - "item_count": 6, - "soft_pair_count": 15, - "serialized_chars": 8789, - "estimated_input_tokens": 2198, - "estimated_eval_tokens": 4652 + "node_count": 7, + "item_count": 7, + "soft_pair_count": 20, + "serialized_chars": 11132, + "estimated_input_tokens": 2783, + "estimated_eval_tokens": 5822 }, "budget": { - "node_count": 6, - "item_count": 6, - "soft_pair_count": 15, - "serialized_chars": 8789, - "estimated_input_tokens": 2198, - "estimated_eval_tokens": 4652 + "node_count": 7, + "item_count": 7, + "soft_pair_count": 20, + "serialized_chars": 11132, + "estimated_input_tokens": 2783, + "estimated_eval_tokens": 5822 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are separate i18n translation-request issues, not duplicates of the same underlying bug/change. The Turkish, Spanish, and Romanian tickets are language-specific, and the generic placeholder-titled issues still read like distinct translation requests rather than one shared fix.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "This cluster mixes distinct i18n translation requests for specific languages with a handful of near-identical generic template issues. There is no single underlying bug/change shared by all items, so I rejected all soft duplicate edges.", + "confidence": 0.71, + "canonical_issue_reason": "issue:44370 is the closest central representative of the generic template-placeholder subgroup, with exact/near-exact similarity to issue:46222 and issue:44365. The Turkish, Spanish, and Romanian requests are separate translation tasks and should not be collapsed into it.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:44370 is the best global representative only for the templated placeholder issues, not for the whole mixed cluster. It is the strongest duplicate-like center, but the language-specific issues remain distinct.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Both are translation requests, but there is no evidence they target the same language or the same concrete work item." + "reason": "Turkish translation request vs generic placeholder issue; same i18n theme, but not the same concrete request." + }, + { + "left": "issue:27088", + "right": "issue:46222", + "accept": false, + "reason": "Turkish request and a generic placeholder entry; no evidence they target the same language or task." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Turkish docs translation is a distinct request from the other issue; same broad category is not enough to merge." + "reason": "Turkish request vs generic placeholder text; boilerplate similarity is not enough to merge." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "Different translation ticket; the placeholder title does not show this is the same language or task as the Turkish issue." + "reason": "Turkish request vs generic placeholder issue; different concrete translation work." }, { "left": "issue:27088", "right": "issue:38435", "accept": false, - "reason": "Turkish and Romanian docs translations are separate language-specific issues, not duplicates." + "reason": "Turkish and Romanian translation requests are different language tasks, not duplicates." }, { "left": "issue:27088", "right": "issue:28936", "accept": false, - "reason": "Turkish and Spanish docs translations are different requests for different target languages." + "reason": "Turkish and Spanish translation requests are separate language-specific issues." }, { "left": "issue:28936", "right": "issue:43834", "accept": false, - "reason": "Spanish docs translation is distinct from a generic placeholder issue; no concrete shared change is demonstrated." + "reason": "Spanish request vs generic placeholder issue; same subsystem, but not the same underlying request." }, { "left": "issue:28936", "right": "issue:44365", "accept": false, - "reason": "These are both translation-related, but the available evidence does not show the same target language or same underlying task." + "reason": "Spanish translation request vs template placeholder issue; no concrete match on language target." }, { "left": "issue:28936", "right": "issue:38435", "accept": false, - "reason": "Spanish and Romanian translation requests are separate issues." + "reason": "Spanish and Romanian translation requests are distinct tasks." }, { "left": "issue:28936", "right": "issue:44370", "accept": false, - "reason": "No evidence they are the same translation ticket; only the broad docs-i18n theme overlaps." + "reason": "Spanish request vs generic placeholder entry; insufficient evidence that they are the same issue." }, { "left": "issue:38435", "right": "issue:44370", "accept": false, - "reason": "Romanian translation is distinct from the placeholder-titled issue; not enough to treat as the same request." + "reason": "Romanian request vs generic placeholder issue; no clear shared language/task." + }, + { + "left": "issue:38435", + "right": "issue:46222", + "accept": false, + "reason": "Romanian request vs generic placeholder issue; boilerplate similarity alone is not a duplicate signal." }, { "left": "issue:38435", "right": "issue:44365", "accept": false, - "reason": "Romanian docs translation and the placeholder issue are not shown to be the same language-specific task." + "reason": "Romanian request vs generic placeholder issue; different concrete translation target." }, { "left": "issue:38435", "right": "issue:43834", "accept": false, - "reason": "Separate translation requests; shared subsystem is too broad to merge." + "reason": "Romanian request vs generic placeholder issue; not the same underlying change." }, { "left": "issue:43834", "right": "issue:44370", "accept": false, - "reason": "The two placeholder issues may be similar in wording, but there is no concrete evidence they describe the same language or work item." + "reason": "Both are generic placeholder template issues, but the available evidence does not prove they refer to the same actual language request." + }, + { + "left": "issue:43834", + "right": "issue:46222", + "accept": false, + "reason": "Near-identical template text, but no explicit language target or code to confirm a true duplicate." }, { "left": "issue:43834", "right": "issue:44365", "accept": false, - "reason": "Likely template-like translation issues, but the data does not establish the same underlying request." + "reason": "Template-placeholder similarity only; too little concrete evidence to merge." }, { "left": "issue:44365", "right": "issue:44370", "accept": false, - "reason": "Both look like generic translation tickets, but not enough detail to conclude they are the same issue." + "reason": "Very similar placeholder text, but the issues are not tied to a clearly identical concrete request." + }, + { + "left": "issue:44365", + "right": "issue:46222", + "accept": false, + "reason": "Near-match on boilerplate only; no explicit target language or change path to confirm duplication." + }, + { + "left": "issue:44370", + "right": "issue:46222", + "accept": false, + "reason": "Exact/near-exact template wording, but still only boilerplate similarity with no concrete same-language evidence." } ] }, @@ -16491,12 +16698,12 @@ "issue:43837|issue:45177", "issue:45322|issue:46133" ], - "prepared_review_unit_hash": "64555a2a4072fde57243d5f920b2bf87394e0d0f7b6008d735827e3f9900fe95", + "prepared_review_unit_hash": "050753e8f3d5656ac78f6b5448008d0d644bb685b091e70b0f0c31a7e4cc95f6", "component_budget": { "node_count": 16, "item_count": 16, "soft_pair_count": 36, - "serialized_chars": 21657, + "serialized_chars": 21658, "estimated_input_tokens": 5415, "estimated_eval_tokens": 11086 }, @@ -16504,7 +16711,7 @@ "node_count": 16, "item_count": 16, "soft_pair_count": 36, - "serialized_chars": 21657, + "serialized_chars": 21658, "estimated_input_tokens": 5415, "estimated_eval_tokens": 11086 }, @@ -16513,228 +16720,228 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly a set of distinct model-request issues that share a generic \"add model support\" pattern, not the same underlying bug/change. No PRs are present.", - "confidence": 0.74, - "canonical_issue_reason": "issue:43671 is the most central open request in this set by similarity fan-in, so it is the best single representative of the cluster's broad model-request theme.", + "summary": "These are a collection of separate model-support requests spanning different architectures and modalities (vision, OCR, ASR/TTS, audio, transformers). They are only superficially similar, so none of the soft edges look like true duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 42738 ('BERT-like models with RoPE') is the broadest, most category-level request and is the closest thing to an umbrella representative for this noisy cluster, though it is not a duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43671 is the best global issue representative: open, broadly connected to other request-like issues, and close to the center of the similarity graph, though still not a duplicate of them.", + "best_issue_reason": "42738 is the best single representative issue because it is the least model-specific and most general of the set; the others are distinct named-model requests that should stay separate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different requested models (EuroBert vs DEIMv2); only the generic \"add model\" framing overlaps." + "reason": "EuroBert config vs DEIMv2: different models and different request scopes." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert and Qwen3-TTS are unrelated model additions." + "reason": "EuroBert config vs Qwen3-TTS support: unrelated model families and modalities." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "EuroBert vs RF-DETR are different architectures and use cases." + "reason": "EuroBert vs RF-DETR: distinct models, no shared concrete change." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are separate model requests, not the same change." + "reason": "RF-DETR vs DEIMv2: different architectures and tasks." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "Object detection model request vs audio model request; unrelated." + "reason": "RF-DETR detection request vs LFM2.5 Audio request are unrelated." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "Different model families and code paths; only broad request similarity." + "reason": "RF-DETR vs sparse transformer: different model types and code paths." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR and Qwen3-ASR are unrelated model additions." + "reason": "RF-DETR detection request vs Qwen3-ASR support: different modalities." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR vs Qwen3-TTS are different model support requests." + "reason": "RF-DETR vs Qwen3-TTS support: different tasks and model families." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT and Qwen3-ASR are unrelated; same generic request theme only." + "reason": "NeoBERT vs Qwen3-ASR: unrelated model requests." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT vs weight-sparse transformer are different concrete model changes." + "reason": "NeoBERT vs weight-sparse transformer: different concrete models." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "BERT model request vs audio model request; not the same underlying change." + "reason": "NeoBERT vs LFM2.5 Audio: unrelated architectures and modalities." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are different models and code paths." + "reason": "RF-DETR detection model vs NeoBERT language model: distinct requests." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are different model requests despite similar naming." + "reason": "NeoBERT vs ModernVBERT: different model additions, not one bug/change." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture vs Qwen3-ASR are distinct model integrations." + "reason": "MiniCPM3 vs Qwen3-ASR: different model support requests." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 and the weight-sparse transformer request are unrelated." + "reason": "MiniCPM3 vs sparse transformer: unrelated concrete code changes." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 architecture and ModernVBERT are separate model additions." + "reason": "MiniCPM3 vs ModernVBERT: separate model-specific requests." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral TTS are different model families and tasks." + "reason": "MiniCPM3 vs Voxtral TTS: different modalities and model families." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 and Qwen3-TTS are unrelated model requests." + "reason": "DEIMv2 vs Qwen3-TTS: unrelated models and tasks." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT and Qwen3-ASR are different model support requests." + "reason": "ModernVBERT vs Qwen3-ASR: different support requests." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT and Qwen3-TTS are unrelated." + "reason": "ModernVBERT vs Qwen3-TTS: different models and code paths." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT and generic BERT-like RoPE support are not the same concrete change." + "reason": "ModernVBERT vs broad BERT-like RoPE request: related family, but not the same concrete change." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "Generic RoPE/BERT-variant request vs Voxtral TTS support; different targets." + "reason": "BERT-like models with RoPE vs Voxtral TTS: unrelated modalities." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Same vendor family, but TTS and ASR are distinct models/features and would not be one merged PR." + "reason": "Qwen3-TTS vs Qwen3-ASR: same vendor, different tasks and implementations." }, { "left": "issue:43671", "right": "issue:45027", "accept": false, - "reason": "Both are audio-related, but Qwen3-TTS and Voxtral TTS are separate model integrations." + "reason": "Qwen3-TTS vs Voxtral TTS: different model-specific support requests." }, { "left": "issue:43671", "right": "issue:45177", "accept": false, - "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated model requests." + "reason": "TTS support vs DeepSeek-OCR2: different modalities and code paths." }, { "left": "issue:43671", "right": "issue:44121", "accept": false, - "reason": "TTS support and a weight-sparse transformer proposal are different code-path changes." + "reason": "Qwen3-TTS vs weight-sparse transformer: unrelated model classes." }, { "left": "issue:43671", "right": "issue:43909", "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio are separate model additions." + "reason": "Qwen3-TTS vs LFM2.5 Audio: both audio-related but distinct model additions." }, { "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "ASR and LFM2.5 Audio are different concrete model support requests." + "reason": "Qwen3-ASR vs LFM2.5 Audio: different audio model support requests." }, { "left": "issue:43837", "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and EUPE are unrelated model architectures/tasks." + "reason": "Qwen3-ASR vs EUPE: ASR model request versus vision-language encoder request." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "ASR support and weight-sparse transformer support are different changes." + "reason": "Qwen3-ASR vs sparse transformer: different concrete models." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "Audio model request vs SAM3-LiteText; no shared underlying bug/change." + "reason": "LFM2.5 Audio vs SAM3-LiteText: audio model versus vision-language model." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Weight-sparse transformer and EUPE are distinct proposals." + "reason": "Sparse transformer request vs EUPE: different architectures and use cases." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are separate audio model integrations." + "reason": "Qwen3-ASR vs Voxtral TTS: different tasks, not the same support change." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated model requests." + "reason": "NeoBERT vs Voxtral TTS: unrelated model families." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "ASR support and OCR2 support are different model additions." + "reason": "ASR support vs OCR model support: different modalities." }, { "left": "issue:45322", "right": "issue:46133", "accept": false, - "reason": "Both are vision-language related, but they target different architectures and objectives, not one duplicate change." + "reason": "EUPE vs TIPSv2: both vision-language related, but they are distinct model proposals with different changes." } ] }, @@ -16764,12 +16971,12 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "21c10e9a8e8dccf2a940d514e183b60a4a95424da65636112da8158521c2e6ed", + "prepared_review_unit_hash": "34bc3063617364029e19ecad276c43ce05079dba3d4d7d3c60fb30cf00c4b6b3", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1480, + "serialized_chars": 1479, "estimated_input_tokens": 370, "estimated_eval_tokens": 996 }, @@ -16777,7 +16984,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1480, + "serialized_chars": 1479, "estimated_input_tokens": 370, "estimated_eval_tokens": 996 }, @@ -16786,18 +16993,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are not duplicates: one is a general request about block decoding, while the other asks for DeepSeek v3.2 support. They concern different features with no shared targets or code path evidence.", - "confidence": 0.96, - "canonical_issue_reason": "No canonical issue; the requests are unrelated and do not describe the same bug or feature.", + "summary": "These two issues are not duplicates: #41084 is about block decoding behavior, while #43037 is a request for DeepSeek v3.2 support. They describe different underlying work with no clear shared code path.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the titles and likely scopes are unrelated, so neither issue can stand in for the other.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43037 is the more specific, actionable request, but it is not a duplicate of 41084.", + "best_issue_reason": "No single best issue for deduplication; #43037 is more specific as a standalone feature request, but it does not overlap with #41084.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different topics: block decoding behavior vs model support request; no evidence they describe the same underlying issue." + "reason": "Different topics and likely different code paths: block decoding vs. model-specific support request." } ] }, @@ -16827,7 +17034,7 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "0703ab5d91e0f87bf6b6373538982b9e807704471d679825296fb93497b57fe2", + "prepared_review_unit_hash": "89389ba2c07ccbc79da1b3829b4407b65fdf0ab09ed3b549a96c7ca986be465e", "component_budget": { "node_count": 2, "item_count": 2, @@ -16849,18 +17056,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related only at a very high level (both concern Trainer custom behavior), but they target different code paths: one is about `remove_unused_column` and input-column handling, the other is about FLOPs estimation for custom trainers. They should not be treated as duplicates.", - "confidence": 0.92, - "canonical_issue_reason": "issue:43598 is the cleaner representative because it describes a concrete Trainer customization problem around `remove_unused_column`, with a more specific code-path focus than the FLOPs-estimation request.", + "summary": "These two issues are about different Trainer behaviors: one is about `remove_unused_column` and customizability, the other about FLOPS estimation for custom trainers. They are related to Trainer internals but do not describe the same bug or change.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:43598 is the better standalone issue to keep as the cluster representative since it is narrowly scoped and likely easier to act on; issue:43600 addresses a separate instrumentation/metrics concern.", + "best_issue_reason": "No clear canonical issue for this cluster because the reports target different code paths; if forced to pick one, `#43598` is the more focused configuration-behavior report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "Reject: the titles and implied code paths differ. `remove_unused_column` affects data-column pruning/custom trainer behavior, while FLOPs estimation is a separate accounting/metrics feature. They are not the same underlying bug." + "reason": "Different underlying problems: one concerns `remove_unused_column` customization in Trainer, the other concerns accounting for custom trainers in FLOPS estimation. Same subsystem, but not the same bug." } ] }, @@ -16890,7 +17097,7 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "cd614fae16889f9430e48c54c39c0f50440e604419ff611a08cfe166acaa4890", + "prepared_review_unit_hash": "1c6dafd3271d6c14d3ead1d5750bc33b17e7e25f763a6012ac3269595e389e34", "component_budget": { "node_count": 2, "item_count": 2, @@ -16912,18 +17119,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are both about Qwen model support, but they target different gaps: one requests registration for Qwen3-Omni in generic auto classes, while the other asks for sequence-classification support for Qwen3.5. They are related by ecosystem area, not the same underlying bug or change.", - "confidence": 0.9, - "canonical_issue_reason": "Issue #43684 is the broader and more foundational request: adding Qwen3-Omni registration to AutoModel / AutoModelForConditionalGeneration. It is a direct model-registration gap rather than a single task-specific head.", + "summary": "These are separate feature requests, not duplicates: one asks for Qwen3-Omni registration on AutoModel/AutoModelForConditionalGeneration, while the other asks for AutoModelForSequenceClassification support for Qwen3.5 (Qwen3_5Config). They target different model families and different heads/code paths.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue #43684 is the better representative of the cluster because it covers the core auto-class registration problem, whereas #44405 is a separate, narrower feature request for AutoModelForSequenceClassification on a different config.", + "best_issue_reason": "If one issue must represent the cluster, issue 43684 is the broader core-registration request, but it is still distinct from 44405 and should not be treated as a duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different targets and likely different fixes: generic Qwen3-Omni auto-model registration versus sequence-classification support for Qwen3.5. They share a model family theme, but not the same concrete change." + "reason": "Different model families and different AutoModel heads: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs Qwen3.5 sequence-classification support. Not the same underlying bug/change." } ] }, @@ -16960,12 +17167,12 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "57e3cef988e4209a66fcb9828c80beb0bf14420181f5a73922e5687d9e861440", + "prepared_review_unit_hash": "da62a0b1772c8bd2a65ee232dd22141c5491af492cfa4c133ef3af9b8bd19904", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4263, + "serialized_chars": 4264, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -16973,7 +17180,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4263, + "serialized_chars": 4264, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -16982,58 +17189,58 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "43845, 43846, and 43859 look like a tentative same-title cluster, but the packet only shows title similarity, close timestamps, and soft-similarity scores; that is not enough to confidently label them the same duplicate issue. 43835 looks unrelated. No PRs are present.", - "confidence": 0.54, - "canonical_issue_reason": "issue:43845 is the best available representative for the similar 'huggingface' issues because it is the earliest of that small title-matched set, but the duplicate relationship is only tentative from the available metadata.", + "summary": "Three issues titled \"huggingface\" look like the same duplicate report; the separate \"Fett\" issue does not. Among the duplicate-looking issues, #43859 is the best representative because it has the same title and at least some discussion activity.", + "confidence": 0.77, + "canonical_issue_reason": "Issue #43859 is the best canonical choice: it matches the repeated title and has the most activity among the duplicate-looking issues.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43845 is the best overall issue candidate because it is the earliest member of the tentatively related 'huggingface' group and there is no stronger distinguishing evidence for the others.", + "best_issue_reason": "#43859 is the strongest global issue candidate because it appears to be the same report as #43845/#43846 and has the most discussion.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles and no body/link evidence tying them to the same underlying report; the metadata does not support a duplicate match." + "reason": "Different titles and no body detail tying them to the same underlying issue." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "Different titles and no supporting evidence of a shared bug/report." + "reason": "Different titles and no evidence that \"Fett\" refers to the same problem as the \"huggingface\" reports." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "Different titles and no supporting evidence of a shared bug/report." + "reason": "No substantive overlap beyond both being short issues; titles do not match." }, { "left": "issue:43845", "right": "issue:43846", - "accept": false, - "reason": "Same short title and close timing suggest possible relation, but title similarity alone is not enough to confirm the same underlying issue." + "accept": true, + "reason": "Same title and highly similar sparse issue content, so they likely describe the same report." }, { "left": "issue:43845", "right": "issue:43859", - "accept": false, - "reason": "The packet lacks body content or explicit linkage; identical titles and timing make them plausible duplicates, but not confirmable." + "accept": true, + "reason": "Same title and same apparent topic; no evidence of a distinct issue." }, { "left": "issue:43846", "right": "issue:43859", - "accept": false, - "reason": "Only title similarity and close timestamps are available, which is insufficient to accept this as the same issue." + "accept": true, + "reason": "Same title and same apparent topic; likely duplicate reports of the same issue." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The analysis is a bit too strong for the packet. The only evidence for 43845/43846/43859 is identical titles plus close timestamps and soft-similarity scores; the packet does not provide body content or explicit linkage, and all soft pairs have deterministic_accept=false. It is reasonable to say these three are likely related or may be duplicate reports, but not to state confidently that they are the same duplicate issue. The rejection of 43835 as unrelated is fine. Please soften the cluster/canonical wording and avoid overclaiming duplicate identity from title similarity alone." + "accept": true, + "feedback": "The summary is grounded in the packet: #43845, #43846, and #43859 share the same title and strong soft-similarity signals, while #43835 has a different title and no stronger evidence tying it to the others. The representative choice of #43859 is conservative and supported by its slightly higher discussion activity. The pairwise verdicts are also suitably cautious given the sparse evidence." }, "evaluator_used": true, - "retried": true, - "accepted_nontrivial_soft_edge": false, + "retried": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -17067,12 +17274,12 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "fa76c0604c8faba6242518d32a002cc89de4080776a94ca87a75748c0a47fdfe", + "prepared_review_unit_hash": "f94db69eb35e276fff23d89b44f2f057e199a620a3aef1466def79e8f8528e37", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5788, + "serialized_chars": 5785, "estimated_input_tokens": 1447, "estimated_eval_tokens": 3150 }, @@ -17080,7 +17287,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5788, + "serialized_chars": 5785, "estimated_input_tokens": 1447, "estimated_eval_tokens": 3150 }, @@ -17089,66 +17296,66 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster looks like a mix of spam/placeholder issues rather than one real duplicated bug report. The three \"\" issues are similar in title only, while the documentation and \"Google LLC\" items are unrelated low-signal posts.", - "confidence": 0.94, - "canonical_issue_reason": "issue:44371 is the earliest of the repeated \"\" entries, so it is the least-bad anchor if a canonical node is required, but the cluster does not show a real shared issue.", + "summary": "This cluster contains only vague/spam-like issues and no concrete bug report. The titles do not indicate the same underlying problem, so none of the soft pairs should be merged as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the items are unrelated or too content-free to establish a shared bug or request.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44418 is the only item with a non-placeholder title and is the most readable representative, though it still does not look like a true duplicate target.", + "best_issue_reason": "No strong best issue exists; #44418 is only marginally more descriptive, but still too vague to represent the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are just \"\" placeholders with no evidence of the same underlying bug or request beyond identical noise." + "reason": "Both are spam-like placeholders with no concrete problem description; no evidence they describe the same issue." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Identical spam-like titles are not enough to treat them as the same issue; there is no substantive content linking them." + "reason": "Both are spam-like placeholders with no concrete problem description; no evidence they describe the same issue." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "One is a spam placeholder and the other is a generic documentation suggestion; they do not describe the same problem." + "reason": "One is spam and the other is an extremely vague documentation suggestion; not the same underlying issue." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "A spam placeholder and a \"Google LLC\" promo-style post are unrelated." + "reason": "Completely different titles and no shared technical context; not duplicates." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "Generic documentation suggestion versus spam placeholder; no shared underlying request is visible." + "reason": "A vague documentation request and a spam placeholder are not the same request." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "Generic documentation suggestion versus spam placeholder; not the same issue." + "reason": "A vague documentation request and a spam placeholder are not the same request." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Same placeholder title, but there is no concrete bug/change described to justify duplicate merging." + "reason": "Both are spam-like placeholders, but there is no content showing they refer to the same bug or change." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Two different spam-like posts with no evidence of a shared topic or fix." + "reason": "No overlapping subject matter; one is spam-like, the other references a different named topic." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "No substantive overlap beyond low-quality content; these are not the same underlying issue." + "reason": "No overlapping subject matter; one is spam-like, the other references a different named topic." } ] }, @@ -17178,12 +17385,12 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "8c3d91dbf076e1d3e4c5c576e91b3e037d1feaa724defdbdfb0f7588f2a93a97", + "prepared_review_unit_hash": "46b72ddb7de1090daa29d22822c72ee2ec0072229840af5126762d49935506cf", "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 }, @@ -17191,7 +17398,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1646, + "serialized_chars": 1645, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -17200,24 +17407,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues are likely related and may be duplicates, but the evidence is not strong enough to call them a certain duplicate. They share an identical title and moderate soft similarity, while the packet does not show near-identical bodies or stronger deterministic signals. #45145 remains the better canonical representative because it has the same topic plus the only inbound reference.", - "confidence": 0.84, - "canonical_issue_reason": "#45145 is the best canonical issue because it matches the same title/topic as #45151 and has slightly stronger linkage via one inbound reference.", + "summary": "The two closed issues have identical titles and very similar body lengths, and #45145 was created first with an inbound reference, but the available packet does not include body text or other strong proof that they are the same report. The soft link is therefore too weak to accept confidently.", + "confidence": 0.81, + "canonical_issue_reason": "#45145 is the better canonical issue because it was created earlier and has an inbound reference, while #45151 appears to be the later, likely related report. The evidence is suggestive, but not strong enough to claim near-identical content.", "canonical_pr_reason": null, - "best_issue_reason": "#45145 is a reasonable cluster representative for this issue pair because it appears to be the more referenced copy of the same topic.", + "best_issue_reason": "#45145 is the strongest issue representative for the cluster due to earlier creation and the only inbound reference. It is the safest canonical choice given the limited evidence.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", "accept": false, - "reason": "The pair has identical titles and a moderate soft-similarity score, but the packet does not provide enough evidence to conclude a clear duplicate with high confidence. The conservative read is that they are probably related, not definitively the same issue." + "reason": "Same title and close body lengths suggest similarity, but the packet lacks body text, explicit links, or other concrete evidence that these are the same underlying issue. That is not enough to accept the edge." } ] }, "evaluator_result": { "accept": false, - "feedback": "The canonical choice is reasonable, but the duplicate verdict is too strong for the evidence provided. The packet only shows identical titles and a soft_similarity signal (jaccard ~0.63) with deterministic_accept=false; it does not establish \u201cnear-identical\u201d bodies or a \u201cclear duplicate\u201d with high confidence. Please soften the wording and keep the conclusion conservative." + "feedback": "The cluster looks plausibly duplicate, but the analyst overstates the evidence. The packet supports identical titles, close body lengths, and later creation for #45151, plus a soft-similarity signal; it does not provide body text or other proof that the content is \u2018nearly identical\u2019 or that the relationship is \u2018essentially exact.\u2019 The soft-edge accept is too strong for the available evidence, so this should be rejected as insufficiently conservative." }, "evaluator_used": true, "retried": true, @@ -17298,7 +17505,7 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "384d10d13b8de50fa77712737a482ee7f4d8bb8632513a6354365435e9a45ae2", + "prepared_review_unit_hash": "e86c262675e0651be4f58517e0204b7461c73f5e6d094baa4e04c89124b1ec02", "component_budget": { "node_count": 2, "item_count": 2, @@ -17320,8 +17527,8 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate 4-bit inference bugs in the same broad area, but they do not look like duplicates: one is a Gemma4 audio-module uint8/torch.finfo TypeError, the other is a BitsAndBytesConfig skip_modules regression that drops the default lm_head exclusion and triggers an AssertionError.", - "confidence": 0.96, + "summary": "These two issues describe different 4-bit inference failures in different code paths: one is a torch.finfo() TypeError triggered by uint8 weights in Gemma4 audio modules, the other is an AssertionError caused by llm_int8_skip_modules changing the default lm_head exclusion. They should not be deduplicated.", + "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -17331,7 +17538,7 @@ "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Different failure modes and code paths: 45672 is Gemma4/audio-module dtype handling during NF4 inference, while 45674 is a config regression around llm_int8_skip_modules clearing the default lm_head exclusion. Similar 4-bit context, but not the same underlying bug." + "reason": "Different root causes and code paths: Gemma4 audio-module uint8/torch.finfo() failure vs. BitsAndBytesConfig skip-module handling that clears lm_head exclusion. Same broad 4-bit inference area, but not the same bug." } ] }, @@ -17361,40 +17568,40 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "46b0a9a374a692058f62728ea176bd577ccdf2d8af148f95419c3c6bfe27b37e", + "prepared_review_unit_hash": "e106d292ca186bdaa15a5f5c40434590b993a0fe95f331b0cfec395ec46411a6", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1476, - "estimated_input_tokens": 369, - "estimated_eval_tokens": 994 + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1476, - "estimated_input_tokens": 369, - "estimated_eval_tokens": 994 + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both issues appear to be unrelated spam/personal-name entries with no technical content; they should not be clustered as duplicates.", + "summary": "The two issues are unrelated entries with different personal names and dates, and contain no bug/report context. This is not a duplicate cluster.", "confidence": 0.98, - "canonical_issue_reason": "Issue 45762 is marginally earlier, but neither issue has substantive technical detail to serve as a meaningful canonical report.", + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "If one must be retained as a representative, 45762 is slightly better only because it was created first; otherwise neither is suitable as a canonical issue.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "The titles are different personal names with different dates and there is no shared bug, feature, or code-path context; this is not the same underlying issue." + "reason": "Different names and birthdates; no shared technical problem, code context, or explicit linkage." } ] }, @@ -17424,7 +17631,7 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "68e86a5578e7ed3f85cac345652c5d012325157b2154cb54fd8c996f86bdafc6", + "prepared_review_unit_hash": "4b7a72edc099ab82626a2b51867a843381ac540c371993ab97a6e7d052d84ff3", "component_budget": { "node_count": 2, "item_count": 2, @@ -17446,18 +17653,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both items are closed issues with only personal-name/date titles and no body or technical context; they do not appear to describe the same bug or change. This looks like unrelated spam/miscellaneous entries rather than a duplicate cluster.", + "summary": "The two issues have unrelated titles consisting of different personal names and dates, with no body content or shared problem evidence. This looks like accidental similarity rather than duplicate reports.", "confidence": 0.98, - "canonical_issue_reason": "Neither issue has enough technical content to serve as a canonical bug report; they are just name/date titles and appear unrelated.", + "canonical_issue_reason": "No clear canonical issue: neither issue describes a bug or task, and the titles reference different people/dates with no shared underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "No issue in this pair is a good canonical candidate because there is no shared underlying problem to preserve.", + "best_issue_reason": "Neither issue is a strong canonical candidate; if one must be chosen for bookkeeping, issue #45764 is marginally earlier, but there is no substantive basis to prefer it.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "The titles refer to different personal names and dates, with no description, links, or evidence of a shared bug/change; not a duplicate." + "reason": "Different names and dates, no body text, and no evidence of the same underlying issue." } ] }, @@ -17497,88 +17704,88 @@ "issue:45871|issue:45873", "issue:45872|issue:45873" ], - "prepared_review_unit_hash": "a720d5be17ae9edb80637cf8fdb696adba8ff2244c3724003a6318daa5c2971d", + "prepared_review_unit_hash": "74d8434447fc560323b09c2d48e3089d88333f33194de5e561a4128b812d2e00", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5722, - "estimated_input_tokens": 1431, - "estimated_eval_tokens": 3118 + "serialized_chars": 5728, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5722, - "estimated_input_tokens": 1431, - "estimated_eval_tokens": 3118 + "serialized_chars": 5728, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is not one single duplicate set: it contains two exact duplicate issue pairs (45870/45871 and 45872/45873) plus one separate, related-but-distinct issue (45869).", - "confidence": 0.93, - "canonical_issue_reason": "Issue 45870 is the best canonical issue for its pair: it is an exact duplicate of 45871, appears slightly earlier, and has the clearest self-contained title. Note that 45872/45873 form a separate duplicate pair, not the same underlying request.", + "summary": "This set splits into two separate exact-duplicate issue pairs: 45870/45871 and 45872/45873. Issue 45869 is a different dataset-promo item and is not a duplicate of the others.", + "confidence": 0.96, + "canonical_issue_reason": "45872 is the strongest representative of the substantive request thread: it is a concrete DataForge feature request and has an exact duplicate in 45873, while the 45870/45871 pair is a different example-oriented request and 45869 is unrelated.", "canonical_pr_reason": null, - "best_issue_reason": "45870 is the best issue representative overall because it is an exact duplicate pair leader and the earliest clear duplicate in the set, but it should not absorb the unrelated 45869 or the separate 45872/45873 request.", + "best_issue_reason": "45872 is the best single issue to anchor triage because it is the clearest, more specific request among the near-duplicates and most likely to capture the intended code-change discussion.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45869", "right": "issue:45870", "accept": false, - "reason": "Both mention financial data/time series, but 45869 is a dataset bundle offer and 45870 is an example request; different underlying issue." + "reason": "Different topics: a financial data bundle promotion vs a DataForge example request." }, { "left": "issue:45869", "right": "issue:45871", "accept": false, - "reason": "Same as 45869 vs 45870: related topic, but a dataset offer is not the same as an example request." + "reason": "Different topics: a financial data bundle promotion vs a DataForge example request." }, { "left": "issue:45870", "right": "issue:45871", "accept": true, - "reason": "Exact same title and very likely same body/content; these are clear duplicates of the same issue." + "reason": "Exact duplicate titles/body length and same underlying example request." }, { "left": "issue:45870", "right": "issue:45872", "accept": false, - "reason": "Both are DataForge financial/time-series items, but one is an example request and the other includes a scraping service; different requests." + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." }, { "left": "issue:45870", "right": "issue:45873", "accept": false, - "reason": "Same as 45870 vs 45872; similar theme, but not the same concrete issue." + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." }, { "left": "issue:45871", "right": "issue:45872", "accept": false, - "reason": "Despite shared keywords, these describe different asks: example request vs time-series+scraping service." + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." }, { "left": "issue:45871", "right": "issue:45873", "accept": false, - "reason": "Same as 45871 vs 45872; not the same underlying request." + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." }, { "left": "issue:45872", "right": "issue:45873", "accept": true, - "reason": "Exact same title and matching content pattern; clear duplicate issues." + "reason": "Exact duplicate titles/body length and same underlying scraping-service request." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: 45870/45871 and 45872/45873 are clearly supported as duplicate pairs by identical titles and matching bodies, while 45869 is only loosely related and should stay separate. The soft-edge verdicts are conservative and do not overstate evidence." + "feedback": "The summary is well grounded in the packet: 45870/45871 and 45872/45873 have identical titles and body lengths, while 45869 is clearly a different topic. The soft-edge verdicts are appropriately conservative overall, with the two accepted pairs supported by the strongest available evidence and the rejected cross-pairs remaining within distinct request themes." }, "evaluator_used": true, "retried": false, @@ -17633,12 +17840,12 @@ "pull_request:43823|pull_request:45213", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "9c82aec2a7de057e1023f03e9842db4134d385deffb6a782d7843aabf89e610c", + "prepared_review_unit_hash": "d61a2175817ffcac4cdd5d775fd623149c6f58a721426115e5135518226d9127", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 18, - "serialized_chars": 34769, + "serialized_chars": 34772, "estimated_input_tokens": 8693, "estimated_eval_tokens": 17642 }, @@ -17646,7 +17853,7 @@ "node_count": 13, "item_count": 13, "soft_pair_count": 18, - "serialized_chars": 34769, + "serialized_chars": 34772, "estimated_input_tokens": 8693, "estimated_eval_tokens": 17642 }, @@ -17655,129 +17862,129 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Only one true duplicate pair stands out: the two `fixed_cross_entropy` PRs (43251 and 43254). The rest are unrelated model additions, refactors, or tests and should stay separate.", - "confidence": 0.98, + "summary": "This cluster is mostly a mix of unrelated PRs that only share broad thematic similarity. The only clear duplicate-like pair is the two `fixed_cross_entropy` patches for issue 43240, which both adjust the same loss helper code path; the rest should stay separate.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the clearest representative of the actual fix: it directly addresses the cross-entropy kwargs bug, has an explicit issue link, and makes the narrowest self-contained change in `loss_utils.py`.", + "canonical_pr_reason": "PR 43251 is a reasonable canonical representative for the 43240 loss-helper fix: it is tightly scoped to `fixed_cross_entropy` and explicitly targets the issue. PR 43254 is a very close alternative that also links 43240 and patches the same code path, so the choice is representative rather than evidence of unique linkage.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the best overall representative because it fixes the concrete bug most explicitly and with the most direct traceability to the reported issue; PR 43254 is effectively the same change but less specific.", + "best_pr_reason": "PR 43251 is a strong overall representative for the cluster\u2019s only true near-duplicate pair, because it is a focused implementation of the 43240 `fixed_cross_entropy` change. That said, PR 43254 is similarly issue-linked and code-path-equivalent, so this is a conservative representative choice rather than a uniquely privileged one.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Unrelated features: VideoPrism model/docs vs an ExecuTorch dynamic-shape test. Same broad area of training/runtime infrastructure is not enough." + "reason": "Different work: VideoPrism model/docs addition vs an ExecuTorch dynamic-shape export test." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Mistral tokenizer methods vs ExecuTorch export test; different code paths and different problems." + "reason": "Different code paths: tokenizer API additions vs ExecuTorch export testing." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Tokenizer API cleanup vs adding a new MobileLLM model; unrelated changes." + "reason": "Unrelated: tokenizer method additions vs adding a new MobileLLM model." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor-pretrained robustness work vs new MobileLLM model implementation; not the same bug/change." + "reason": "Different scope: processor auto-loading robustness vs adding MobileLLM support." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Cross-entropy kwargs fix vs new MobileLLM model addition; no shared underlying defect." + "reason": "Loss helper kwargs fix is unrelated to a new model implementation." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Loss utility kwargs fix vs Mistral4 test/model updates; different concrete issues." + "reason": "Different bug domains: cross-entropy kwargs vs Mistral4 test/model fixes." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "ExecuTorch dynamic-shape test vs Mistral4 test fixes; both are tests but not the same underlying change." + "reason": "ExecuTorch dynamic-shape export tests are unrelated to Mistral4 test fixes." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Dynamic-shape export test vs MobileLLM model addition; unrelated." + "reason": "Different artifacts and problems: export test coverage vs new model addition." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "Model implementation work vs a core class attribute-resolution fix; different code paths and intents." + "reason": "New model addition is unrelated to `cls.config` resolution order." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "New model addition vs Falcon output-collection refactor; not the same change." + "reason": "MobileLLM model files are unrelated to Falcon output-interface refactoring." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "Unrelated: model addition vs model-creation skill/docs repo changes." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon refactor vs a model-creation skill PR; no shared bug or code path." + "reason": "Falcon refactor and model-creation skill are different changes with no shared code-path bug." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon output-interface refactor vs Mistral4 tests/model changes; unrelated." + "reason": "Falcon output-collection refactor is unrelated to Mistral4 test/model fixes." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 tests/model fixes vs `layrnorm` renaming cleanup; different concrete changes." + "reason": "Mistral4 fixes and `layrnorm` typo renaming are different concrete issues." }, { "left": "pull_request:44827", "right": "pull_request:46048", "accept": false, - "reason": "Mistral4 test fixes vs adding a TDT loss kernel; unrelated." + "reason": "Different subsystems: Mistral4 fixes vs adding a TDT loss kernel." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 test fixes vs config-resolution ordering fix; different code paths." + "reason": "Model-specific test fixes are unrelated to `cls.config` resolution behavior." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Model/test fixes vs model-creation skill content; not a duplicate change." - }, - { - "left": "pull_request:43823", - "right": "pull_request:45213", - "accept": false, - "reason": "MobileLLM model implementation vs model-creation skill/docs; unrelated." + "reason": "Model-specific fixes are unrelated to the model-creation skill PR." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs modify `src/transformers/loss/loss_utils.py` to fix the same `fixed_cross_entropy` issue by forwarding supported `nn.functional.cross_entropy` kwargs (notably `weight` and `label_smoothing`). They are mergeable into one PR." + "reason": "These are effectively the same `fixed_cross_entropy` fix for issue 43240: both add support for extra `cross_entropy` kwargs in the same code path." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The judgments stay grounded in the packet and the lone accepted duplicate pair is well supported by shared file/issue-target evidence. The other pair rejections are conservative; none look mergeable as a single PR for the same bugfix." + "accept": false, + "feedback": "The soft-edge verdicts look conservative and the cluster summary is mostly grounded, but the reasoning overstates the evidence for PR 43251. PR 43254 also has an explicit issue link to 43240 and the same `fixed_cross_entropy` code path, so 43251 is not the only PR here with clear issue linkage. The canonical/representative rationale should be phrased more conservatively." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -17801,12 +18008,12 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "926984a8d5e460a648e89ef415d1c57fed30b3445d0140979f17e0d00e71766f", + "prepared_review_unit_hash": "b51635748fb7d6b5da65cfd107ef150cf4985a888e6a03df3d6f19836819ace4", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7226, + "serialized_chars": 7225, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -17814,7 +18021,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7226, + "serialized_chars": 7225, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -17823,18 +18030,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related VibeVoice PRs, but they target different work: initial VibeVoice support vs. a later realtime/acoustic-tokenizer extension. Not duplicates.", - "confidence": 0.88, + "summary": "The cluster contains two related but distinct VibeVoice PRs: one for the base model integration and one for a later realtime extension with additional tokenizer/generation work. They overlap on shared scaffolding, but they are not the same change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 40546 is the core VibeVoice implementation (model, docs, auto-registry, processing). PR 42781 is a separate realtime follow-up with additional tokenizer/feature-extractor work.", + "canonical_pr_reason": "PR #42781 is the broader and newer VibeVoice PR, covering realtime-specific components in addition to the shared base integration, so it is the better representative of the cluster topic.", "best_issue_reason": null, - "best_pr_reason": "PR 40546 is the better cluster anchor because it represents the main VibeVoice integration; 42781 is a distinct extension rather than the same change.", + "best_pr_reason": "PR #42781 is the strongest representative because it subsumes more of the VibeVoice stack and appears to be the more complete follow-on implementation, though it is not a duplicate of #40546.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Related but not the same underlying change: 40546 adds base VibeVoice support, while 42781 adds VibeVoice Realtime and acoustic-tokenizer changes. Too distinct to merge as one PR." + "reason": "Shared VibeVoice files indicate related work, but #40546 is the base implementation while #42781 adds realtime and acoustic-tokenizer changes; they are not the same concrete PR and would not naturally merge into one PR." } ] }, @@ -17864,7 +18071,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "a9c041c2bb68f8d6a62eb7ce3c9a258214f1488d3d437c2cc1a47abef4d421b8", + "prepared_review_unit_hash": "3e0c6b1226ac35babb093253ccb1350f35ca59dc73bb1780b1257d47f2b3cef7", "component_budget": { "node_count": 2, "item_count": 2, @@ -17886,18 +18093,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two unrelated feature pull requests in different model families: TimesFM covariate forecasting vs. DINOv3 image classification support. They should not be merged or triaged as duplicates.", + "summary": "The two PRs are unrelated: one adds TimesFM covariate forecasting support, the other adds DINOv3 image classification support. They touch different models, code paths, and documentation, so this is not a duplicate pair.", "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR as a duplicate target: the PRs address different models, code paths, and user-facing capabilities. If one must be chosen as the representative, 41224 is the more narrowly scoped and self-contained change.", + "canonical_pr_reason": "No canonical PR: the PRs target different products/features and do not represent the same underlying change.", "best_issue_reason": null, - "best_pr_reason": "pull_request:41224 is the best single PR in the cluster because it is focused on one concrete capability addition with a tight implementation surface, while 40755 is a separate larger feature for a different model.", + "best_pr_reason": "41224 is the more self-contained standalone PR in the pair, but only as a local representative; it is not a duplicate of 40755.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different underlying changes: TimesFM covariate forecasting vs. DINOv3 image classification support. They do not fix the same code-path problem and could not plausibly be merged into one PR." + "reason": "Different models and change goals: TimesFM covariates vs DINOv3 image classification. They do not fix the same code-path problem and could not plausibly be merged into one PR." } ] }, @@ -17992,12 +18199,12 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "fa6d7c238f155cb13c29b120743fdb2d0a50caf556bba95fe7a5d8a365bd5947", + "prepared_review_unit_hash": "c334841605cd69d3ff1fc0a223ca1be13b6f2e94e0336be876d50125aeae30ba", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10436, + "serialized_chars": 10435, "estimated_input_tokens": 2609, "estimated_eval_tokens": 5474 }, @@ -18005,7 +18212,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10436, + "serialized_chars": 10435, "estimated_input_tokens": 2609, "estimated_eval_tokens": 5474 }, @@ -18014,24 +18221,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-integration pull requests (DeepSeek OCR, Isaac, Kimi2-6), not duplicate fixes for the same underlying bug or change. The shared files are just common Transformers boilerplate for new model additions, so the soft links should be rejected.", - "confidence": 0.97, + "summary": "All three items are separate model-addition PRs (DeepSeek OCR, Isaac, Kimi2-6). They share Transformers boilerplate and auto-registration edits, but the titles, model names, files, and code paths are different, so they are not duplicates.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical duplicate exists here because the PRs add different models and implement different code paths. If forced to pick one representative, 45630 is the strongest candidate because it has the broadest implementation surface and highest review activity.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "45630 is the most substantial and reviewed of the three new-model PRs, with extensive auto-mapping and model files plus test coverage, so it is the best representative of this cluster even though it is not semantically the same change as the others.", + "best_pr_reason": "pull_request:45630 is the strongest representative of the cluster because it has the broadest integration surface and the most review activity, but it is still a distinct model-addition PR rather than a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different model additions: DeepSeek OCR vs Isaac. Shared Transformers scaffolding files do not indicate the same bug or change, and these would not be merged as one PR." + "reason": "Different model additions for DeepSeek OCR vs Isaac. Overlap is limited to shared framework boilerplate and registry/docs updates, not the same underlying change." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different model additions: Isaac vs Kimi2-6. The overlap is generic integration plumbing, not a shared concrete code-path fix or feature." + "reason": "Different model additions for Isaac vs Kimi2-6. Similar auto-mapping and docs scaffolding do not indicate the same bug or code-path fix." } ] }, @@ -18061,12 +18268,12 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "019d8a8ef99a0fa869b71af98f60cf0bb7d5c71cae52ed2ae02edc2a4b18f90a", + "prepared_review_unit_hash": "91f5131001cebfb476cdcdc609032e29a9cfa5b232eca369421e9c7bb6d5c8fe", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, + "serialized_chars": 5933, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -18074,7 +18281,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, + "serialized_chars": 5933, "estimated_input_tokens": 1484, "estimated_eval_tokens": 3224 }, @@ -18083,18 +18290,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate GitHub Actions maintenance PRs, not the same underlying change: one is a broad Node 24 compatibility upgrade for workflow actions, while the other mainly bumps docker/build-push-action and related workflow action versions. The overlap in workflow files is incidental.", - "confidence": 0.96, + "summary": "These are both broad dependency-maintenance PRs touching overlapping GitHub Actions workflows, but they fix different upgrade sets and different underlying compatibility concerns, so they should not be merged as duplicates.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No clear canonical duplicate PR: the two PRs address different dependency upgrade goals and should remain separate.", + "canonical_pr_reason": "No canonical PR: the two PRs are related maintenance updates, but they target different action families and different upgrade goals rather than the same concrete change.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the broader, more central workflow-actions upgrade and is the better representative of the cluster theme, but it is still not a duplicate of 42976.", + "best_pr_reason": "PR 42975 is the better representative of the cluster because it is the broader workflow-actions compatibility update and covers more of the shared workflow surface.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Different concrete changes: 42975 targets Node 24 compatibility across GitHub Actions, while 42976 upgrades docker/build-push-action and a smaller set of related workflow actions. Shared workflow paths alone are not enough to treat them as the same PR." + "reason": "Both are GitHub Actions version bumps, but 42975 upgrades checkout/cache/upload-artifact and other workflow actions for Node 24 compatibility, while 42976 upgrades docker/build-push-action and a different set of workflow actions. They overlap in files, not in the same underlying fix or mergeable change." } ] }, @@ -18146,7 +18353,7 @@ "pull_request:46151|pull_request:46214", "pull_request:46162|pull_request:46214" ], - "prepared_review_unit_hash": "3a023daa2042dcf1a6d6de47911619e8766eeb251314b097fa39e41c028b1b6d", + "prepared_review_unit_hash": "6af528238739bbd9a55ebd4bd8922081006c06c4f201f1111e2a83d62a7f6e18", "component_budget": { "node_count": 10, "item_count": 10, @@ -18168,102 +18375,102 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs form two loose themes\u2014new model additions and XPU/test expectation tweaks\u2014but none of the soft edges look like true duplicates of the same concrete change. The similarities are mostly broad-file overlap (docs/auto mappings/tests) rather than shared bug fixes.", - "confidence": 0.95, + "summary": "This cluster is mostly a set of unrelated model-addition PRs plus separate XPU/distributed test expectation updates. The overlaps are driven by shared docs/auto-mapping/test infrastructure rather than the same underlying bug or change, so there is no true duplicate canonical here.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR stands out: the set mixes unrelated model additions (Molmo, Molmo2, CTSM, ViT NEPA) with unrelated test-only XPU/distributed updates, so there is no one artifact that safely represents the cluster.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "No clear global best PR for duplicate-triage purposes; the apparent overlaps are superficial and the PRs address different models or different test paths.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Both are model-addition PRs, but for different model families (ViT NEPA vs Molmo); shared docs/auto files are just repository plumbing." + "reason": "Different model additions (ViT NEPA vs Molmo). Shared docs/auto-mapping files are broad infrastructure, not the same change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different model additions (ViT NEPA vs Molmo2); not the same underlying change." + "reason": "Different model additions (ViT NEPA vs Molmo2). Similar files, but separate model implementations and docs." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "Unrelated model additions (ViT NEPA vs CTSM); overlap is only in shared registration/docs files." + "reason": "Different model additions (ViT NEPA vs CTSM). Same repo areas touched, but unrelated model families and code paths." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are distinct model additions, not one duplicate change." + "reason": "Molmo and Molmo2 are distinct model families with different configs/processors/features, so not the same PR change." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo vs CTSM are unrelated model adds; shared auto/docs edits are incidental." + "reason": "Molmo vs CTSM are unrelated model additions; overlap is only in generic model-registration/docs plumbing." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are different models with different codepaths and tests." + "reason": "Molmo2 and CTSM are separate model introductions with different implementation details and targets." }, { "left": "pull_request:45487", "right": "pull_request:46214", "accept": false, - "reason": "AltCLIP/ChineseCLIP model-parallel fix is unrelated to HRM text XPU expectation updates." + "reason": "AltCLIP/ChineseCLIP model-parallel fix is a different code-path issue from HRM text XPU expectation updates." }, { "left": "pull_request:45487", "right": "pull_request:46151", "accept": false, - "reason": "Different problems: model-parallel device handling vs pipeline token-classification test expectations." + "reason": "Model-parallel device placement fix vs token-classification test expectations are unrelated changes." }, { "left": "pull_request:45490", "right": "pull_request:46162", "accept": false, - "reason": "CTSM model implementation PR vs Florence2 XPU test adjustments; not the same bug or change." + "reason": "CTSM model addition is unrelated to Florence2/LFM2_VL XPU test expectation updates." }, { "left": "pull_request:46109", "right": "pull_request:46214", "accept": false, - "reason": "Both touch tests, but one is distributed trainer parity and the other is HRM text expectations; different concrete test paths." + "reason": "Distributed trainer test parity tweak is not the same underlying bug as HRM text XPU expectations." }, { "left": "pull_request:46109", "right": "pull_request:46151", "accept": false, - "reason": "Distributed trainer test genericization and token-classification expectations are separate changes." + "reason": "Both mention XPU-related test behavior, but they target different test suites and different assertions." }, { "left": "pull_request:46135", "right": "pull_request:46214", "accept": false, - "reason": "Kosmos2.5 XPU expectations and HRM text XPU expectations are model-specific, not a single duplicate fix." + "reason": "Kosmos2.5 integration expectations are model-specific and unrelated to HRM text expectations." }, { "left": "pull_request:46135", "right": "pull_request:46151", "accept": false, - "reason": "Different model test suites and different expectation updates; not mergeable as one PR." + "reason": "Kosmos2.5 XPU expectations and token-classification expectations are separate model/test changes." }, { "left": "pull_request:46151", "right": "pull_request:46214", "accept": false, - "reason": "Token-classification pipeline expectations vs HRM text expectations are unrelated model/test updates." + "reason": "Different test domains (pipeline token classification vs HRM text) and different expectation data; not mergeable as one duplicate fix." }, { "left": "pull_request:46162", "right": "pull_request:46214", "accept": false, - "reason": "Florence2 XPU expectations and HRM text XPU expectations are distinct model-specific test changes." + "reason": "Florence2/LFM2_VL XPU expectations are model-specific and do not fix the same code path as HRM text." } ] }, @@ -18285,71 +18492,63 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-43291-4", + "cluster_id": "cluster-43291-3", "nodes": [ "pull_request:43291", "pull_request:43665", - "pull_request:44815", - "pull_request:46102" + "pull_request:44815" ], "soft_pairs": [ "pull_request:43291|pull_request:43665", "pull_request:43291|pull_request:44815", - "pull_request:43665|pull_request:46102", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "21c978c73e3a32f2fb1de0c1ae4a2239380534c24e5e4aa1a22074200ee57a22", + "prepared_review_unit_hash": "a9fcc1982e99f3a7b2238586f6006ecf872b0164403e1ba03e65327fcaa377f5", "component_budget": { - "node_count": 4, - "item_count": 4, - "soft_pair_count": 4, - "serialized_chars": 9390, - "estimated_input_tokens": 2348, - "estimated_eval_tokens": 4952 + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 }, "budget": { - "node_count": 4, - "item_count": 4, - "soft_pair_count": 4, - "serialized_chars": 9390, - "estimated_input_tokens": 2348, - "estimated_eval_tokens": 4952 + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are not duplicates: two are test-only edits, one fixes Whisper decoding, one fixes dequant/FP8 loading, and one fixes FSDP tied-weights handling. They touch different code paths and should stay separate.", - "confidence": 0.95, + "summary": "These PRs do not look like duplicates: one fixes Whisper decoding/tests, one is an unrelated CLIP/ViT test edit, and one is a separate FP8 dequant/model-loading fix.", + "confidence": 0.82, "canonical_issue_reason": null, - "canonical_pr_reason": "If a representative PR is needed, 44815 is the strongest standalone code fix: it changes real loading/quantization logic across multiple files, while the others are either test-only or different subsystems.", + "canonical_pr_reason": "PR 44815 is the most substantive standalone fix, with a clear code-path change and supporting model/integration updates; the other PRs are unrelated to it.", "best_issue_reason": null, - "best_pr_reason": "44815 is the best representative of a substantive bug fix in this cluster; it has concrete implementation changes, unlike 43665 which is test-only and the others which address unrelated areas.", + "best_pr_reason": "PR 44815 appears to be the strongest representative of the set because it addresses a concrete runtime bug across loading/FP8 code, whereas PR 43291 is Whisper-only and PR 43665 is test-only and not clearly a real fix.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Whisper tokenizer decoding vs CLIP/ViT test edits; different subsystems and no shared bug/change." + "reason": "Different subsystems and different problems: Whisper tokenizer decoding vs CLIP/ViT test edits. No shared code path or concrete same bug." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper timestamp/batch decode fix is unrelated to FP8 dequant/loading changes." - }, - { - "left": "pull_request:43665", - "right": "pull_request:46102", - "accept": false, - "reason": "Test-only CLIP/ViT assertions are unrelated to FSDP tied-weights logic." + "reason": "Whisper decoding/test fix is unrelated to the FP8 dequant/model-loading changes in 44815." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "Both touch tests superficially, but the underlying changes are unrelated: model tests vs quantization/loading code." + "reason": "These touch unrelated areas and solve different issues; broad title similarity is not enough to treat them as one change." } ] }, @@ -18386,70 +18585,70 @@ "pull_request:45932|pull_request:46100", "pull_request:46100|pull_request:46114" ], - "prepared_review_unit_hash": "9659f88bb7446b99f073d17e482942180306a7fa696ed903be67ac33d0421692", + "prepared_review_unit_hash": "b314a8ba5a2da23a414fe8716a6cb68c505e60725a76ddf3f9d168358145d666", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 5, - "serialized_chars": 11341, - "estimated_input_tokens": 2836, - "estimated_eval_tokens": 5928 + "serialized_chars": 11340, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 5, - "serialized_chars": 11341, - "estimated_input_tokens": 2836, - "estimated_eval_tokens": 5928 + "serialized_chars": 11340, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Only 46100 and 46114 are true duplicates: they carry the same one-file ViT test migration diff. The other PRs are test/noise PRs or broader unrelated changes that merely overlap on a filename or subsystem.", + "summary": "Only PRs 46100 and 46114 are effectively the same change; the others are either unrelated test/bot scaffolding or a much broader model/config update and should not be deduped together.", "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 46100 is the clean canonical representative: it matches 46114 exactly at the diff level, and its title is the simpler of the duplicate pair.", + "canonical_pr_reason": "PR 46100 is the cleanest canonical representative of the exact duplicate pair (46100/46114): same file, same diff, same purpose, and it was opened first.", "best_issue_reason": null, - "best_pr_reason": "46100 is the best overall PR candidate because it is the clearest exact duplicate target in the cluster and represents the only truly mergeable duplicate pair.", + "best_pr_reason": "PR 46100 best represents the duplicate cluster because it is the earliest instance of the identical ViT test-migration change and has the clearest standalone identity among the duplicates.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:46114", "accept": false, - "reason": "Shared ViT test filename is incidental; 43488 changes setup/version/dependencies while 46114 only edits test assertions. Not the same underlying change." + "reason": "Same test file, but the PRs are different bot/debug scaffolds with different surrounding setup and intent; not the same underlying change." }, { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "These are different fake PRs with different code paths and files; the overlap is too broad and not a concrete duplicate." + "reason": "Both are intentional repo-bot/debug PRs, but they change different workflows and test-related plumbing, not one concrete shared fix." }, { "left": "pull_request:43532", "right": "pull_request:46114", "accept": false, - "reason": "43532 is a workflow/infra change, while 46114 is a local test-file edit. They do not fix the same bug or implement the same change." + "reason": "Overlap on the ViT test file is incidental; one is CI/workflow plumbing while the other is a forked test-migration PR with a different purpose." }, { "left": "pull_request:45932", "right": "pull_request:46100", "accept": false, - "reason": "45932 is a broad multi-file model/config/workflow change; 46100 is a narrow ViT test migration. Same broad area, but not the same underlying code change." + "reason": "These touch different code paths and scopes: 45932 is a broad model/config and CI-secrets change, while 46100 is a tiny ViT test-only migration stub." }, { "left": "pull_request:46100", "right": "pull_request:46114", "accept": true, - "reason": "Exact same diff in tests/models/vit/test_modeling_vit.py; these are the same test migration change and could plausibly be merged as one PR." + "reason": "They have the same file and identical diff hunk, and both are clearly the same ViT test-migration PR duplicated under a forked title." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet. The only accepted soft edge, 46100/46114, is supported by identical diff previews in the same file, and the rejected pairs are conservative given the broader or unrelated changes. Canonical PR 46100 is a reasonable duplicate representative." + "feedback": "The cluster summary is grounded in the packet: PRs 46100 and 46114 are an exact duplicate pair with the same file and identical diff, while the other linked pairs are broader or different-purpose changes that do not look mergeable as a single bugfix. The soft-edge false/true calls are conservative overall." }, "evaluator_used": true, "retried": false, @@ -18476,7 +18675,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "5a07b8df0a7e47e3c115639cd3ee798ee1184dd2927552ec18ce7b21f4180cc8", + "prepared_review_unit_hash": "4addd3107cd6ae18cf3a710a758408cf1b48b91ee532950020f3b77ac073e7e7", "component_budget": { "node_count": 2, "item_count": 2, @@ -18498,18 +18697,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are closely related in theme and documentation scaffolding, but they implement different pipelines for different segmentation tasks and model integrations. They should not be treated as duplicates.", + "summary": "These are two distinct open PRs adding new, related segmentation pipelines. They share documentation and pipeline scaffolding, but they target different tasks and model integrations, so they are not duplicates.", "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: 43612 adds Promptable Concept Segmentation (SAM3-focused), while 43613 adds Promptable Visual Segmentation with different model hooks and test coverage.", + "canonical_pr_reason": "No canonical duplicate PR: 43612 adds promptable concept segmentation, while 43613 adds promptable visual segmentation; they are separate features.", "best_issue_reason": null, - "best_pr_reason": "43613 is the better representative PR for the cluster because it is the broader, more fully integrated pipeline addition; 43612 is a separate narrower feature.", + "best_pr_reason": "If one PR must represent the cluster, 43613 is the broader/more integrated addition, with extra model and test coverage. It is still distinct from 43612.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Reject: they share pipeline/docs boilerplate, but the underlying changes are different features with different code paths and model/test integrations (concept segmentation vs visual segmentation)." + "reason": "Related pipeline-template changes, but different underlying tasks and code paths: concept segmentation vs visual segmentation. They are not the same change and would not be merged into one PR." } ] }, @@ -18539,40 +18738,40 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "17aca8c302f0419d5d93e8cfcb5c87d1718c26f9a34f6322cf81a2d93b29e603", + "prepared_review_unit_hash": "f51683e574004618c45b542f2311919809fd88268269b99badcb176421cb4484", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, - "estimated_input_tokens": 1073, - "estimated_eval_tokens": 2402 + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, - "estimated_input_tokens": 1073, - "estimated_eval_tokens": 2402 + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two unrelated trainer.py pull requests: one adds `_loss_is_scaled_for_ga` for gradient-accumulation loss scaling, the other extracts `_get_signature_columns` for column filtering. Same file, different code paths, not the same underlying change.", - "confidence": 0.97, + "summary": "These two PRs both touch `trainer.py` but address different trainer extension points: one changes gradient-accumulation loss scaling, the other refactors signature-column filtering for custom trainers. They do not look like the same underlying change.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the patches solve different Trainer extension-point problems and are not mergeable into one coherent fix.", + "canonical_pr_reason": "No issue is linked, and the PRs are not duplicates. If one PR must represent the cluster, `#43651` is the better anchor because it makes a concrete behavioral change in the training loss path rather than a general refactor hook.", "best_issue_reason": null, - "best_pr_reason": "Neither PR is a good global representative for the cluster because they address unrelated behaviors in `Trainer` despite touching the same file.", + "best_pr_reason": "`#43651` is the more representative standalone change: it introduces a specific fix/behavioral control for loss scaling during gradient accumulation. `#43663` is also a standalone trainer extensibility refactor, but it is a different code path and less suitable as a cluster representative.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different functionality and different code paths: one changes gradient-accumulation loss normalization, the other refactors signature-column inspection for data filtering." + "reason": "Both modify `trainer.py`, but one targets loss scaling in `training_step` while the other targets signature-column computation for column filtering. Different code paths, different behavior, and they would not naturally merge into one PR." } ] }, @@ -18602,7 +18801,7 @@ "soft_pairs": [ "pull_request:43656|pull_request:43842" ], - "prepared_review_unit_hash": "f60eca232ef0b4e630eb6a8a5365ab10bae824d47494678849c386f5b5098c28", + "prepared_review_unit_hash": "f2ebc50ebe407c1531a975bebf66b88823366ce3252f32741ad504c638e85812", "component_budget": { "node_count": 2, "item_count": 2, @@ -18624,18 +18823,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch the same file and both address annotation-related NameErrors in `src/transformers/cli/serve.py`, but they fix different runtime paths: one is a broad typing/future-annotations cleanup, the other is specifically about `TypeAdapter` when `pydantic` is absent.", - "confidence": 0.87, + "summary": "Two open PRs touch the same CLI file and both mention TypeAdapter NameError, but they appear to fix different failure modes: one modernizes annotations / runtime typing, the other makes TypeAdapter safe when pydantic is absent.", + "confidence": 0.83, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43656 is the broader representative fix for import-time typing/annotation errors in the CLI, with more review/discussion and a wider cleanup than the narrower `TypeAdapter`-specific patch.", + "canonical_pr_reason": "PR 43656 looks like the broader fix for the CLI type-annotation NameError, with a wider typing cleanup in the same code path.", "best_issue_reason": null, - "best_pr_reason": "PR #43656 most centrally captures the cluster\u2019s underlying serve.py annotation problem and is the more comprehensive change set.", + "best_pr_reason": "PR 43656 is the better canonical PR because it appears to address the underlying annotation/runtime NameError more generally, rather than only the optional-pydantic import case.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Related but not duplicates: #43656 adds `from __future__ import annotations` and broad type-hint cleanup, while #43842 specifically guards/quotes `TypeAdapter` for the no-pydantic case. They address different concrete NameError paths and could be merged separately." + "reason": "They overlap in `src/transformers/cli/serve.py` and the title mentions the same symptom, but the diffs point to different fixes: 43656 changes future-annotation/type-hint behavior, while 43842 specifically avoids importing `TypeAdapter` at runtime when pydantic is unavailable. These are related but not the same concrete bug, and both could plausibly land separately." } ] }, @@ -18775,8 +18974,8 @@ "pull_request:44018|pull_request:44116", "pull_request:44068|pull_request:44722", "pull_request:44071|pull_request:44722", - "pull_request:44018|pull_request:44086", "pull_request:44018|pull_request:44085", + "pull_request:44018|pull_request:44086", "pull_request:44068|pull_request:44086", "pull_request:44071|pull_request:44085", "pull_request:44059|pull_request:44086", @@ -18794,8 +18993,8 @@ "pull_request:44073|pull_request:44101", "pull_request:44059|pull_request:44071", "pull_request:44018|pull_request:44059", - "pull_request:44073|pull_request:44161", "pull_request:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", "pull_request:44059|pull_request:44068", "pull_request:44101|pull_request:44161", "pull_request:44017|pull_request:44018", @@ -18827,295 +19026,415 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "274d4d38f118395514d4dbd5706eeed927fc123e9abf8e28d63166c45d66481d", + "prepared_review_unit_hash": "4e6fcbcd6ec510bbef48318d616d0944da1f5e6b803792858821d30d32ccbb18", "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": 84889, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 }, "budget": { "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75096, - "estimated_input_tokens": 18774, - "estimated_eval_tokens": 37804 + "serialized_chars": 75084, + "estimated_input_tokens": 18771, + "estimated_eval_tokens": 37798 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a wave of standardized output-tracing refactors across many model backbones. Many of the relevant PRs point to #43979, but several do not, so it\u2019s better framed as a broad theme plus a GPT-style subset where same-file duplicates are plausible.", - "confidence": 0.87, - "canonical_issue_reason": "#43979 is the shared umbrella tracker for the output-tracing modernization work in the relevant PRs, though not every PR in the cluster explicitly links it.", - "canonical_pr_reason": "PR 44722 is the clearest representative because it explicitly targets #43979 and captures the core GPT-J/CodeGen output-tracing refactor in the same code path as the GPT-style duplicates.", - "best_issue_reason": "#43979 is the best cluster anchor because it ties together the main standardized output-tracing refactor wave, especially the GPT-style subset.", - "best_pr_reason": "PR 44722 is the best single representative: it is explicit about the shared tracker, spans the core GPT-J/CodeGen implementation, and best summarizes the duplicate-prone subset.", + "summary": "This cluster is mostly a broad standardized output-tracing migration across many unrelated model families. The only strong duplicate pockets are the GPT-J/CodeGen PRs and the GPT-Neo PRs; the rest are same-theme but different code paths and should not be merged together.", + "confidence": 0.89, + "canonical_issue_reason": "Issue #43979 is the umbrella tracking issue for the output-tracing/decorator migration, and many PRs in the cluster explicitly target it.", + "canonical_pr_reason": "PR #44722 is the clearest canonical PR for the true duplicate set: it directly refactors GPT-J/CodeGen output tracing, links the tracking issue, and overlaps the other GPT-J-focused PRs.", + "best_issue_reason": "#43979 best represents the shared migration theme that ties the cluster together.", + "best_pr_reason": "#44722 is the best representative PR because it covers the same concrete GPT-J/CodeGen tracing change as the closest duplicates and is the most focused consolidation point.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model families and code paths; shared output-tracing theme is not enough." + "reason": "Different model families (FNet/CVT vs GPT-J); same broad refactor theme but not the same code-path bug/change." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different backbones and refactor scopes; same tracker/theme alone does not make them duplicates." + "reason": "Different models and code paths (FNet/CVT vs DeBERTa v2); not mergeable as one concrete fix." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Same GPT-J output-tracing code path in the same file; this looks like an overlapping slice of one refactor." + "reason": "Both are GPT-J output-tracing refactors on the same underlying block/call pattern; 44066 just bundles the related CodeGen copy as well." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "ResNet/RT-DETR ResNet versus EfficientNet are different model implementations, so these are separate changes." + "reason": "Both are output-tracing migrations, but they touch different architectures and code paths (ResNet/RegNet vs EfficientNet)." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths; only the refactor pattern matches." + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths; same issue family is not enough." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen versus EfficientNet are different implementations and should not be merged as one PR." + "reason": "GPT-J/CodeGen refactor versus EfficientNet refactor; different concrete implementations." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are unrelated model-specific refactors." + "reason": "MobileNetV2 and DeBERTa v2 are separate model implementations; no shared concrete bug/change." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen and MGP-STR are different model families and code paths." + "reason": "GPT-J/CodeGen versus MGP-STR; only the tracing pattern matches, not the underlying code path." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen versus MPT are distinct implementations; the shared decorator pattern is not enough." + "reason": "GPT-J/CodeGen and MPT are distinct model code paths." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Same GPT-Neo output-tracing refactor in the same model/file; these plausibly duplicate the same change." + "reason": "Both are GPT-Neo output-tracing refactors on the same model/file and appear to address the same concrete change." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different model implementations." + "reason": "GPT-Neo versus GPT-J/CodeGen; related theme but different model code paths." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are different code paths, so these are not duplicates." + "reason": "GPT-J/CodeGen and GPT-Neo are separate model implementations, so these are not the same fix." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet and GPT-J/CodeGen are unrelated backbones despite similar refactor wording." + "reason": "ResNet-focused refactor versus GPT-J/CodeGen refactor; different concrete code paths." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are separate model-specific changes." + "reason": "MGP-STR and GPT-J/CodeGen are unrelated model paths." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPT-J are unrelated implementations; same theme is not enough." + "reason": "ResNet versus GPT-J; same migration family but different underlying changes." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are different model families and not the same concrete change." + "reason": "GPT-Neo and ResNet are unrelated implementations." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are separate model-specific refactors." + "reason": "ResNet versus MPT; not the same concrete bug/change." }, { "left": "pull_request:44068", - "right": "pull_request:44086", + "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated model implementations." + "reason": "GPT-Neo and Flaubert/XLM are different model code paths." }, { "left": "pull_request:44018", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert/XLM are different code paths; only the refactor style is shared." + "reason": "GPT-Neo and Flaubert/XLM are separate fixes." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo versus GPT-J/CodeGen are different implementations, so this is not a duplicate." + "reason": "GPT-Neo output tracing versus GPT-J/CodeGen output tracing; same theme, different code paths." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen are unrelated model families." + "reason": "MPT and GPT-J/CodeGen are unrelated implementations." }, { "left": "pull_request:44018", - "right": "pull_request:44059", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo versus GPT-J; too different to be one merged PR." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo versus MGP-STR; not the same concrete fix." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo and GPT-2 are separate model implementations and should stay separate." + "reason": "MPT and GPT-J/CodeGen touch different model internals." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 and MGP-STR are unrelated model families." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J and MGP-STR are unrelated apart from the shared output-tracing pattern." + "reason": "GPT-J/CodeGen versus MGP-STR; not the same underlying bug/change." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert/XLM are different model families with distinct code paths." + "reason": "ViLT and Flaubert/XLM are different model implementations." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 versus GPT-J/CodeGen; same refactor style, different code paths." }, { "left": "pull_request:44017", "right": "pull_request:44722", "accept": false, - "reason": "SegFormer and GPT-J/CodeGen are unrelated model implementations." + "reason": "Segformer and GPT-J/CodeGen are unrelated fixes." }, { "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "SegFormer and LongT5 are different architectures; only the refactor style matches." + "reason": "Segformer and LongT5 are different code paths." }, { "left": "pull_request:44017", "right": "pull_request:44073", "accept": false, - "reason": "SegFormer and VisualBERT are different code paths and not duplicates." + "reason": "Segformer versus VisualBERT; not the same concrete change." }, { "left": "pull_request:44068", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are different model-specific output-tracing changes." + "reason": "GPT-Neo and MPT are distinct model implementations." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBERT and Flaubert/XLM are unrelated code paths." }, { "left": "pull_request:44059", - "right": "pull_request:44086", + "right": "pull_request:44068", "accept": false, - "reason": "GPT-2 and MGP-STR are separate model implementations." + "reason": "GPT-2 versus GPT-Neo; separate model fixes." }, { - "left": "pull_request:44085", - "right": "pull_request:44722", - "accept": true, - "reason": "Same GPT-J file and same decorator-based refactor; 44722 just broadens coverage with the same underlying GPT-J change." + "left": "pull_request:44101", + "right": "pull_request:44161", + "accept": false, + "reason": "Flaubert/XLM and LongT5 are different model code paths." }, { - "left": "pull_request:44085", - "right": "pull_request:44129", + "left": "pull_request:44017", + "right": "pull_request:44018", + "accept": false, + "reason": "Segformer and GPT-Neo are unrelated implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44073", "accept": false, - "reason": "GPT-J and SpeechT5 are unrelated code paths; the shared tracker does not make them duplicates." + "reason": "RegNet and VisualBERT touch different model internals." }, { "left": "pull_request:43996", - "right": "pull_request:44007", + "right": "pull_request:44161", "accept": false, - "reason": "Different model families and different forward/output plumbing changes." + "reason": "FNet/CVT and LongT5 are different code paths." }, { "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "FNet/CVT and Segformer are separate fixes, not one concrete bug." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBERT and MPT are unrelated model code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBERT versus VisualBERT; different concrete changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet and TextNet are distinct model implementations." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44018", + "accept": false, + "reason": "SqueezeBERT and GPT-Neo are different code paths." + }, + { + "left": "pull_request:44071", "right": "pull_request:44129", "accept": false, - "reason": "CVT/FNet and SpeechT5 are unrelated implementations." + "reason": "MPT and SpeechT5 are unrelated implementations." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44074", + "accept": false, + "reason": "FNet/CVT and TextNet are different model fixes." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBERT and DeBERTa v2 are separate code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa v2 and TextNet are unrelated model implementations." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa and SpeechT5 are different model families with separate refactors." + "reason": "DeBERTa v2 and SpeechT5 are different concrete fixes." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa and VITS are unrelated model-specific output-tracing changes." + "reason": "DeBERTa v2 and Vits are unrelated code paths." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are different model implementations." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are separate fixes." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "VisualBERT and LongT5 are different code paths." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert/XLM are unrelated model fixes." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44073", + "accept": false, + "reason": "ViLT and VisualBERT are separate model implementations." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J/CodeGen output-tracing refactor in the same code path; 44722 looks like the broader overlapping iteration." + "reason": "Same GPT-J/CodeGen output-tracing refactor family; these are the closest duplicate implementations in the cluster." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J output-tracing change in the same file; 44722 incorporates that change and extends it to CodeGen." + "reason": "Both are GPT-J output-tracing refactors on the same file/code path, so they plausibly collapse into one PR." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are unrelated code paths." + "reason": "GPT-J/CodeGen and SpeechT5 are unrelated code paths." }, { "left": "pull_request:43996", "right": "pull_request:44007", "accept": false, - "reason": "Different model families and different output-handling implementations." + "reason": "FNet/CVT and ResNet are different model code paths; same migration style is not enough." }, { "left": "pull_request:43996", "right": "pull_request:44129", "accept": false, - "reason": "CVT/FNet and SpeechT5 are unrelated model implementations." + "reason": "FNet/CVT and SpeechT5 are unrelated fixes." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa and SpeechT5 are distinct model families." + "reason": "DeBERTa v2 and SpeechT5 are different concrete code-path changes." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa and VITS are different code paths; same refactor pattern only." + "reason": "DeBERTa v2 and Vits are separate implementations." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster theme is mostly grounded, but the summary overstates the evidence by saying all PRs are \"orbiting\" #43979; several items in the packet have no explicit issue link, so that should be softened to \"many/most\" or \"the relevant PRs.\" The soft-edge verdicts are generally conservative, and the same-model duplicate calls look plausible, but I would still tighten the umbrella claim before accepting." + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative about cross-model pairings. The accepted soft-edge pairs are plausibly mergeable duplicates within the same GPT-J/CodeGen or GPT-Neo code paths, and the rejections correctly avoid conflating shared migration style with the same concrete fix." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -19150,70 +19469,70 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "f38a7ba969b9d7759b3af9963b1a1d2f9ab5d677b8533c1d9bdac70f3c509405", + "prepared_review_unit_hash": "455ba10e803d6715197729142893817c6b756c274910d07036028d78e7d9663b", "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": 84889, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17124, - "estimated_input_tokens": 4281, - "estimated_eval_tokens": 8818 + "serialized_chars": 17126, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs are all related to a common standardized output-tracing refactor pattern, but they touch different model implementations and distinct code paths, so they are not duplicates of one another. I would treat them as separate PRs in the same thematic cluster.", + "summary": "These PRs are all model-specific refactors to the new standardized output-capturing mechanism, but they affect different architectures and code paths, so they are not duplicates of one another.", "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "44129 is the strongest representative because it has the clearest scoped refactor, an explicit linked issue target, and concrete output-tracing changes in one model. That said, it is still not a duplicate of the others.", + "canonical_pr_reason": "PR 44056 is the clearest representative of the shared refactor pattern: it introduces `capture_outputs` plus an explicit `_can_record_outputs` mapping, making it a strong canonical example of the standardized tracing change.", "best_issue_reason": null, - "best_pr_reason": "44129 is a good cluster representative since it is a focused model-specific implementation of the shared output-capture refactor theme and includes an explicit issue reference.", + "best_pr_reason": "PR 44056 is the best standalone representative of this cluster, but only as an example of the pattern; it is not a duplicate of the other model-specific refactors.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are standardized-output refactors, but one is for FocalNet and the other for ImageGPT; they change different model code paths and are not mergeable as one PR without becoming an unrelated multi-model sweep." + "reason": "Both are output-tracing refactors, but they touch different models (`FocalNet` vs `ImageGPT`) and different forward paths, so they are not the same concrete change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "VisualBERT and TextNet are separate implementations. The similarity is the refactor pattern, not the underlying bug/change in a single code path." + "reason": "These are separate model migrations (`VisualBert` vs `TextNet`); the shared goal is too broad to make them duplicate PRs." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "These target different models (MPNet vs VisualBERT) and different tracing hooks, so they are not the same concrete fix." + "reason": "Both adopt capture-based output tracing, but in different model implementations and call paths (`MPNet` vs `VisualBert`)." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "MPNet and TextNet are unrelated model files with separate output-tracing refactors; same theme, different changes." + "reason": "Different models and different implementation details; they are related by refactor theme only, not the same bug/change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBERT are distinct model-specific migrations to the shared output-capture pattern, not the same underlying bug or change." + "reason": "`RegNet` and `SqueezeBert` are unrelated model code paths; these are separate standardized-output migrations, not one duplicate fix." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBERT and SpeechT5 modify different model forward paths. Sharing the standardized output-capture goal is not enough to treat them as duplicates." + "reason": "`SqueezeBert` and `SpeechT5` are distinct model stacks; the overlap is only the capture-output refactor pattern, not the same PR-worthy change." } ] }, @@ -19272,7 +19591,6 @@ "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", @@ -19299,298 +19617,298 @@ "pull_request:44002|pull_request:46106", "pull_request:43998|pull_request:46106" ], - "prepared_review_unit_hash": "bfbd37308589ee199874faa3eaa56ea422b593f808c719179147d4323e46ccd4", + "prepared_review_unit_hash": "77541cba6e06cf1e038a30f48dcd2fc1acb48c5b30c2604b25b06b0d771123e6", "component_budget": { "node_count": 14, "item_count": 14, - "soft_pair_count": 45, - "serialized_chars": 43783, - "estimated_input_tokens": 10946, - "estimated_eval_tokens": 22148 + "soft_pair_count": 44, + "serialized_chars": 43401, + "estimated_input_tokens": 10851, + "estimated_eval_tokens": 21958 }, "budget": { "node_count": 14, "item_count": 14, - "soft_pair_count": 45, - "serialized_chars": 43783, - "estimated_input_tokens": 10946, - "estimated_eval_tokens": 22148 + "soft_pair_count": 44, + "serialized_chars": 43401, + "estimated_input_tokens": 10851, + "estimated_eval_tokens": 21958 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is a set of separate model-specific PRs that all follow the same output-tracing refactor pattern, but they do not fix the same concrete code path. I reject the soft duplicate edges and treat them as distinct PRs. PR 44025 is the best representative of the cluster.", + "summary": "These PRs are mostly the same high-level refactor theme (\u201coutput tracing\u201d), but they target different model families and code paths, so they are not duplicates. The only non-model change is the docs toctree fix, which is unrelated.", "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44025 is the clearest representative: it is a self-contained output-tracing refactor, spans two closely related files, and directly reflects the cluster\u2019s common migration pattern.", + "canonical_pr_reason": "PR 44025 is the best representative of the cluster because it is a clean, self-contained output-tracing refactor spanning two closely related model files and sits in the densest similarity group.", "best_issue_reason": null, - "best_pr_reason": "PR 44025 is the best single PR to anchor the cluster because it is explicit, focused, and representative without being overly specialized to one unusual code path.", + "best_pr_reason": "PR 44025 is the strongest exemplar of the shared refactor pattern: it makes the output-tracing change explicitly with the new decorator/imports and is more central than the single-file variants.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model implementations and forward paths; same refactor theme, but not the same mergeable change." + "reason": "Same refactor theme, but different model architectures (timm_backbone vs upernet) and different forward/output code paths." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different architectures (`timm_backbone` vs `vision_text_dual_encoder`); similar output-tracing cleanup only." + "reason": "Both are output-tracing refactors, but they touch unrelated models and cannot plausibly be merged as one concrete fix." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Separate model code paths; not the same underlying bug or fix." + "reason": "Different model families and implementations; only the general refactor style matches." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Both are output-tracing refactors, but they target different model families and concrete implementations." + "reason": "timm_backbone refactor is unrelated to the mamba/falcon_mamba output-tracing changes." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Different code paths and model behavior; shared wording is not enough for a duplicate." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Unrelated model-specific forward paths; too broad to be one duplicate PR." + "reason": "Different architectures and output mechanisms; not the same underlying bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:46106", + "accept": false, + "reason": "Model refactor vs docs toctree edit; clearly unrelated." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "Different model code paths (`mobilenet_v1` vs `univnet`); only the refactor style overlaps." + "reason": "Both are refactors of output handling, but for different models and forward signatures." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and outputs; not the same concrete change." + "reason": "Separate model implementations; same subsystem theme only at a very high level." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Separate models with distinct forward logic; same tracing migration, not one PR-worthy fix." + "reason": "MobileNetV1 and Depth Anything have different forward/output logic and are not the same fix." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model code paths; the similarity is only the output-tracing refactor pattern." + "reason": "Unrelated model wrappers; no shared concrete bug or code path." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "No shared underlying bug or code path beyond the general refactor theme." + "reason": "Different model families and output-tracing refactors only match superficially." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Different architectures (`vision_text_dual_encoder` vs `univnet`); not mergeable as one fix." + "reason": "Vision-text dual encoder and UnivNet are unrelated models; same refactor pattern, different implementation details." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different model implementations; only a shared migration approach." + "reason": "Different model classes and output types; not mergeable into one PR as a single fix." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Distinct model families and forward methods; not the same concrete problem." + "reason": "Different model families and code paths; shared wording is only a template-level similarity." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "CodeGen and vision-text dual encoder are unrelated concrete changes." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Both touch output handling, but on unrelated model code paths." + "reason": "Different model architectures and output-capture changes; not the same underlying bug/change." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "Separate models and outputs; same refactor pattern is not enough to duplicate them." + "reason": "UnivNet and UperNet are different models with different forward contracts." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different model stacks (`univnet` vs `falcon_mamba/mamba`); not one underlying fix." + "reason": "Different model families; no evidence they fix the same concrete problem." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Different code paths and different model families; only broadly similar tracing cleanup." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44029", - "accept": false, - "reason": "Different model implementations; not the same bug or change." + "reason": "Depth Anything and UnivNet are separate output-tracing refactors, not duplicates." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Separate model code paths; same general refactor class only." + "reason": "UperNet and mamba/falcon_mamba do not share the same code path or bug." }, { - "left": "pull_request:44003", - "right": "pull_request:44028", + "left": "pull_request:44002", + "right": "pull_request:44004", "accept": false, - "reason": "Different model families (`mamba` vs `superpoint`) and distinct output structures." + "reason": "Different model implementations; similarity is only in the refactor naming." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Codegen refactor is a different concrete change than the Mamba/Falcon-Mamba tracing work." + "reason": "These are both refactors, but for distinct model code paths and output behavior." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Different model families and forward paths; similar refactor intent only." - }, - { - "left": "pull_request:44001", - "right": "pull_request:44004", - "accept": false, - "reason": "Different code paths (`univnet` vs `codegen`); not a duplicate change." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44004", - "accept": false, - "reason": "Different model-specific output handling; no single shared bug to merge." + "reason": "timm_backbone and CodeGen are unrelated; not the same fix." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Different models (`depth_anything` vs `vision_encoder_decoder`) and different forward logic." + "reason": "Depth Anything vs VisionEncoderDecoder are different model wrappers and output contracts." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Different model wrappers and output signatures; same refactor pattern only." + "reason": "Different model families; only the output-tracing refactor motif is shared." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Unrelated model code paths; not the same underlying change." + "reason": "Depth Anything and SuperPoint are unrelated model implementations." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different architectures and output plumbing; too broad to count as one duplicate." + "reason": "Different architectures and tracing mechanisms; not the same underlying change." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Different model code paths; only the output-tracing migration overlaps." + "reason": "Depth Anything and DPR target different model code paths and output shapes." }, { "left": "pull_request:44026", - "right": "pull_request:44029", + "right": "pull_request:44027", "accept": false, - "reason": "Different model families and forward implementations; not one fix." + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are different wrappers with different modality-specific behavior." }, { "left": "pull_request:44026", - "right": "pull_request:44027", + "right": "pull_request:44028", "accept": false, - "reason": "Different encoder-decoder wrappers; same broad refactor theme, but not the same code path." + "reason": "Different model code and output handling; not mergeable as one duplicate fix." }, { "left": "pull_request:44026", - "right": "pull_request:44028", + "right": "pull_request:44029", "accept": false, - "reason": "Different model implementations and output types; not mergeable into one PR." + "reason": "Vision encoder-decoder vs RWKV are unrelated model families." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Distinct model code paths; shared tracing refactor only." + "reason": "Different subsystems and output logic; same generic refactor theme only." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech encoder-decoder and SuperPoint are unrelated concrete changes." + "reason": "Speech encoder-decoder and SuperPoint are unrelated changes." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different model families and output handling; not a duplicate." + "reason": "Different model families and code paths." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Separate model-specific forward paths; only the refactor style is similar." + "reason": "Speech encoder-decoder vs DPR are separate implementations, not the same bug." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "Different models and outputs; no shared underlying bug." + "reason": "SuperPoint and RWKV are unrelated model families." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Unrelated model code paths; same broad output-tracing refactor only." + "reason": "Different models and output mechanics; not the same underlying change." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "Different model families and internal logic; not the same concrete fix." + "reason": "RWKV and DPR are unrelated code paths and should not be merged as duplicates." }, { "left": "pull_request:44027", "right": "pull_request:46106", "accept": false, - "reason": "Documentation/toctree change is unrelated to the speech encoder-decoder tracing refactor." + "reason": "Model refactor vs docs navigation cleanup; clearly different work." }, { "left": "pull_request:44026", "right": "pull_request:46106", "accept": false, - "reason": "Docs toctree cleanup is not the same as the vision-encoder-decoder code change." + "reason": "Unrelated model code and documentation change." }, { "left": "pull_request:44001", "right": "pull_request:46106", "accept": false, - "reason": "Unrelated docs navigation edit versus a model tracing refactor." + "reason": "UnivNet output-tracing refactor is unrelated to the docs toctree fix." }, { "left": "pull_request:44002", "right": "pull_request:46106", "accept": false, - "reason": "Documentation tree update is unrelated to UperNet output tracing." + "reason": "Model refactor vs documentation tree edit; not duplicates." }, { "left": "pull_request:43998", "right": "pull_request:46106", "accept": false, - "reason": "Docs-only toctree change is unrelated to the timm_backbone refactor." + "reason": "Different artifact types and unrelated changes." } ] }, @@ -19623,52 +19941,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "97016c49c9930f8896c30fdcf6ff36a2f98b26e014812c5b3364d146e0126788", + "prepared_review_unit_hash": "9c43cb965442b5f330914c29c9995df391f45888344328b0b40a194a7170505d", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10912, - "estimated_input_tokens": 2728, - "estimated_eval_tokens": 5712 + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10912, - "estimated_input_tokens": 2728, - "estimated_eval_tokens": 5712 + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs are standalone model-addition changes for different models (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share only framework boilerplate and auto-registration patterns, not the same underlying feature or code-path fix.", + "summary": "These are three separate model-addition PRs for different models (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). The shared files are just standard Transformers boilerplate for adding a new model, not evidence of the same underlying change.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical PR: these are separate model implementation PRs for different architectures, so there is no duplicate to collapse into one.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 45075 is the strongest standalone representative: it has the broadest implementation surface (core model, processing, auto mappings, tests, docs, and conversion helpers) and a clear, self-contained scope.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different models and different functionality (PenguinVL vs Voxtral TTS). Shared files are only registration/docs boilerplate, not the same bug or feature." + "reason": "Different models and different code paths: PenguinVL vs Voxtral TTS. Shared auto-registration/docs scaffolding is generic new-model boilerplate, not a duplicate fix or one mergeable change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Both add model support, but for unrelated models with different code paths and artifacts; this is broad subsystem overlap, not a duplicate change." + "reason": "PenguinVL and DeepSeek-OCR-2 are unrelated model integrations. Similar filenames reflect template-based model addition work, but the actual implementations, configs, and tests are for distinct models." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model integrations with different processing and modeling logic; they are not plausibly mergeable into one PR as the same change." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are different models with different purposes and files. Overlap is limited to common Transformers integration points, so they are not the same underlying change." } ] }, @@ -19698,7 +20016,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "e6d9a11e0ed8bd4021ac41e680dc1615b7bf9fedf589a013bdd75ea25af1680c", + "prepared_review_unit_hash": "a37660598d7f71f82585f8190536573ef0bfd1939a1684a44dd2289461510e1b", "component_budget": { "node_count": 2, "item_count": 2, @@ -19720,18 +20038,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related in the broad area of module/kernel fusion, but they are not the same change: one adds a standalone Module Fusion API scaffold, while the other wires up n-to-1 kernel fusion through KernelConfig and integration points. I would not treat them as duplicates.", - "confidence": 0.86, + "summary": "The two PRs are related to module/fusion infrastructure, but they implement different layers and different concrete code paths: #44979 adds a generic Module Fusion API, while #45363 adds n-to-1 kernel fusion via KernelConfig and integration glue. They do not look like duplicate changes.", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45363 is the better canonical PR because it is the more complete, user-facing feature implementation with multiple integration changes, whereas #44979 is mainly the lower-level Module Fusion API foundation.", + "canonical_pr_reason": "#45363 is the more concrete user-facing feature PR: it wires fusion through KernelConfig and runtime integration points. #44979 is a lower-level enabling API that supports a broader abstraction, so it is better treated as related infrastructure rather than the same change.", "best_issue_reason": null, - "best_pr_reason": "PR #45363 is the best representative of the cluster\u2019s overall theme since it delivers the broader kernel-fusion workflow; #44979 is supporting infrastructure rather than the same concrete change.", + "best_pr_reason": "#45363 is the best representative of the cluster because it describes a specific end-to-end fusion workflow and touches the execution path, whereas #44979 is mainly the generic API foundation.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Related fusion infrastructure, but not the same concrete bug/change and not something that should be merged into a single PR." + "reason": "Related fusion work, but not the same underlying fix/change: one introduces a generic Module Fusion API, the other implements n-to-1 kernel fusion through KernelConfig and integration code. They would not plausibly be merged as one duplicate PR." } ] }, @@ -19761,7 +20079,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "724597b27a3cef28d0c2128dc1553b048b6911a327270a16447c8982e6183007", + "prepared_review_unit_hash": "f5286346b89905a03ab53d0c68570ef51b1ff6bb73bb56f2dbe6abca58b80d42", "component_budget": { "node_count": 2, "item_count": 2, @@ -19783,18 +20101,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests address the same Mistral regex patching AttributeError in the same code path and target the same issue; 45317 is the more complete variant because it adds tests.", - "confidence": 0.97, - "canonical_issue_reason": "Issue #45081 is the shared explicit target for both PRs, so it is the natural canonical issue.", - "canonical_pr_reason": "PR 45317 is the better canonical PR because it contains the same fix plus test coverage, making it the more complete and likely final form of the change.", - "best_issue_reason": "#45081 is the only explicit issue target and represents the underlying bug both PRs are trying to resolve.", - "best_pr_reason": "pull_request:45317 is the best representative PR: same fix, same file, and it adds tests to validate the AttributeError regression.", + "summary": "Both PRs implement the same fix for the Mistral regex patch AttributeError in the same function and file; 45317 is the more complete variant with tests, so the pair should be clustered together with 45317 as the representative PR.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "45317 is the fuller implementation of the same bug fix and adds test coverage, making it the best canonical PR for this cluster.", + "best_issue_reason": null, + "best_pr_reason": "45317 is the strongest representative because it targets the same issue as 45086 but includes the test update and appears more complete/stable.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying AttributeError fix in _patch_mistral_regex, same target issue #45081, and the diffs overlap on the exact code-path; 45317 is a stricter superset with tests, so these are duplicate/same-change PRs." + "reason": "Same concrete code-path bug fix in src/transformers/tokenization_utils_tokenizers.py for _patch_mistral_regex; 45317 is essentially the expanded version of 45086 with tests, so they are the same underlying change." } ] }, @@ -19824,7 +20142,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "1b71047d5bf36b9aca79b73d2fb8e0308e74f8b85cecaad6793215abd9f32f6d", + "prepared_review_unit_hash": "31d5db2e18f5d6eb4c16786e3b66e54e441176006f0ea1703d7c5739f979db75", "component_budget": { "node_count": 2, "item_count": 2, @@ -19846,18 +20164,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related to NemotronH internals, but they address different changes: one is a refactor/inheritance and checkpoint conversion mapping update, while the other introduces the dense/sparse model split with docs, auto-mapping, and tests.", + "summary": "Both PRs are about Nemotron-H support, but they tackle different slices of the work: one is a refactor/inheritance and checkpoint-conversion mapping change, while the other is a broader \u201cproper\u201d model split into nemotron_h / dense / sparse with docs and auto/model wiring. They overlap in shared files, but not the same concrete change set.", "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45569 is the better canonical representative because it is the broader, more complete feature change: it adds the new NemotronH dense/sparse model structure, updates docs and auto-mappings, and includes tests. PR 45115 is a narrower refactor focused on GraniteMoeHybrid-style inheritance and conversion renames.", + "canonical_pr_reason": "PR #45569 is the broader, more complete Nemotron-H implementation effort and better represents the cluster\u2019s main direction; PR #45115 looks like a narrower precursor/refactor.", "best_issue_reason": null, - "best_pr_reason": "PR 45569 is the strongest standalone PR in the cluster since it carries the main user-visible/model-structure work and supporting documentation/tests, whereas PR 45115 is a narrower implementation refactor.", + "best_pr_reason": "PR #45569 is the best representative PR because it covers the larger end-state work: model variants, docs, auto mappings, and tests.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Reject: despite overlapping NemotronH files, the PRs are not the same underlying change. 45115 is about refactoring NemotronH to inherit GraniteMoeHybrid and adding conversion-key renames, while 45569 is about introducing NemotronH dense/sparse variants plus docs, auto-mapping, and tests. They could coexist, but they are not one mergeable duplicate PR." + "reason": "Shared Nemotron-H files are not enough here: #45115 focuses on GraniteMoeHybrid-style inheritance and conversion mapping, while #45569 implements the fuller Nemotron-H / Dense / Sparse model split and docs. They are related, but not the same fix and would not plausibly merge into one PR." } ] }, @@ -19887,7 +20205,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "2c1454679a95544862b9541330e98e2cec70c98157195ee5865798e5ca03dcc6", + "prepared_review_unit_hash": "c95f513002cd097440b249a35c186a30531766ec16ec3a2c7e82544734f3b8d0", "component_budget": { "node_count": 2, "item_count": 2, @@ -19909,18 +20227,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related but distinct feature PRs: one adds heterogeneous config support, the other adds heterogeneous model/runtime support. They overlap in shared config helpers, but they do not look like the same mergeable change.", - "confidence": 0.79, + "summary": "These two PRs are related but not duplicates: one adds heterogeneous per-layer config support, the other adds heterogeneous modeling/runtime support. They share infrastructure files, but they target different parts of the feature and would not be the same mergeable change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the more canonical umbrella change: it implements the concrete model/runtime behavior for heterogeneous layers and includes the cache/modeling updates that depend on config support.", + "canonical_pr_reason": "PR #45332 is the broader end-to-end feature PR, covering heterogeneous modeling/runtime changes in addition to config plumbing, so it is the better canonical anchor for the cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the strongest standalone candidate because it covers the main end-user behavior change, not just the supporting config plumbing.", + "best_pr_reason": "PR #45332 is the best representative because it spans the larger underlying feature area and includes the concrete model-path changes, while #45333 is only the config-side subset.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "These are related layers of the same feature area, but one is config plumbing and the other is model/runtime support; they do not look like the same concrete code-path problem that could be merged into a single PR." + "reason": "Reject: #45332 adds heterogeneous modeling/runtime support, while #45333 adds per-layer configuration support. They are adjacent pieces of the same feature family, but not the same concrete code-path fix/change and would not be merged as one PR." } ] }, @@ -19950,7 +20268,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "88128e6ef8b67744d07c06e7f912a37f00472f2d4c421b82781fa87f5f88c598", + "prepared_review_unit_hash": "6bfc4757f11bbb38c6fcfee5a22286e81863f0dcb4e72a2f121cf73aa06bbfd7", "component_budget": { "node_count": 2, "item_count": 2, @@ -19972,18 +20290,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are typing-focused cleanups, but they are not the same concrete change: #45415 is a broad repo-wide type-checking pass with pyproject typing-ignore adjustments, while #45425 adds specific typing helper protocols/aliases and related modeling-utils annotations. They share some files, but the underlying work is different enough that they should not be merged as duplicates.", - "confidence": 0.79, + "summary": "These are related typing-related pull requests, but they are not the same underlying change. PR 45415 is a broad repository-wide type-checking sweep, while PR 45425 adds specific typing protocols and utility types for a narrower set of model/integration code paths.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "#45415 is the broader umbrella typing cleanup and best represents the cluster\u2019s overall theme; #45425 is a narrower, more specialized follow-up-style typing change.", + "canonical_pr_reason": "45415 is the broader umbrella change: it updates many `src/transformers/*.py` files plus `pyproject.toml` to make type checking work. 45425 is a narrower typing refactor focused on `_typing.py`, `modeling_utils`, and related helpers.", "best_issue_reason": null, - "best_pr_reason": "#45415 is the best representative PR because it covers the widest scope of the typing initiative and includes the typing-policy change in pyproject.toml, making it the most canonical cluster member.", + "best_pr_reason": "45415 is the best representative PR for this cluster because it covers the larger cross-cutting type-checking effort and subsumes the general theme more than the focused follow-up in 45425.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Shared typing-related files are not enough: #45415 is a large multi-file type-checking sweep, while #45425 introduces new typing protocols/aliases for specific internals. They do not fix the same concrete bug or merge cleanly into one PR." + "reason": "Both are typing-related, but they address different scopes and likely different mergeable changes: a broad typing sweep versus targeted protocol/type additions. Shared files alone are not enough to treat them as the same fix." } ] }, @@ -20015,12 +20333,12 @@ "pull_request:45513|pull_request:46084", "pull_request:46084|pull_request:46098" ], - "prepared_review_unit_hash": "ce1bf896e68f5dd02102fd168710da03ac3ce91c513e0de8852e7c74b5c8f9d1", + "prepared_review_unit_hash": "053000d38193d6343a20b199e5f1432e7fe146bd83307a9bc0dde8905ccb5578", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 7427, + "serialized_chars": 7428, "estimated_input_tokens": 1857, "estimated_eval_tokens": 3970 }, @@ -20028,7 +20346,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 7427, + "serialized_chars": 7428, "estimated_input_tokens": 1857, "estimated_eval_tokens": 3970 }, @@ -20037,30 +20355,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two Mamba2 PRs appear to address the same use_cache seq_len>1 bug; the Qwen3.5 PR is unrelated and should stay separate. The broader Mamba2 PR is the best representative of that fix.", - "confidence": 0.78, + "summary": "Two PRs (46084, 46098) appear to fix the same Mamba2 cached-forward bug for `use_cache` with `seq_len > 1`; the Qwen3.5 PR (45513) is a separate model-specific fix and should stay separate.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #46098 is the best canonical representative because it directly targets the Mamba2 use_cache seq_len>1 incorrect-results bug, covers both CPU/GPU paths, and includes tests/docs, making it the most complete version of the fix.", + "canonical_pr_reason": "PR 46098 is the most complete and explicit version of the Mamba2 fix: it names the concrete bug, targets the shared issue (#46032), and includes model, test, and docs updates.", "best_issue_reason": null, - "best_pr_reason": "PR #46098 is the strongest cluster representative: it is explicit about the underlying bug, has the same Mamba2 code path, and is broader/more complete than the narrower GPU-focused predecessor PR #46084.", + "best_pr_reason": "PR 46098 is the best representative because it clearly states the failure mode, is tied to the tracked issue, and appears broader/more finished than the narrower implementation in 46084.", "soft_edge_verdicts": [ { "left": "pull_request:45513", "right": "pull_request:46084", "accept": false, - "reason": "Different model families and different implementations; they only share a generic cached-forward symptom, not the same concrete bug or mergeable change." + "reason": "Different model families and different code paths: Qwen3.5 GDN linear attention vs Mamba2 cache handling. Similar wording about multi-token cached forward is not enough to treat them as the same change." }, { "left": "pull_request:46084", "right": "pull_request:46098", "accept": true, - "reason": "Both target the same Mamba2 use_cache seq_len>1 bug in modeling_mamba2.py; #46098 looks like a broader follow-up/superset with the same underlying fix and could plausibly be merged into one PR." + "reason": "Both target the same Mamba2 `use_cache` bug for `seq_len > 1`, share the same issue target (#46032), and touch the same model/test files; they look like overlapping fixes for the same underlying code-path problem." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: PR #45513 is a different model family and does not look mergeable with the Mamba2 fix, while PRs #46084 and #46098 share the same issue target and Mamba2 files, so treating #46098 as the broader canonical representative is conservative. No evidence is overstated." + "feedback": "The summary is grounded in the packet: 45513 is a separate Qwen3.5/OLMo-hybrid cached-forward fix, while 46084 and 46098 both target the same Mamba2 `use_cache`/`seq_len > 1` bug under issue #46032 and share the same core files. The soft-edge verdicts are conservative enough, and the two Mamba2 PRs look mergeable as one bugfix." }, "evaluator_used": true, "retried": false, @@ -20087,7 +20405,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "738cdf6fadb059a2922d512c4a817a4753d3e7ad472b9fad9596fb34b13a705e", + "prepared_review_unit_hash": "8ccc548a0a6dada48d48583649edbfba9d3d3cee4abeedc30303497a877c6cbf", "component_budget": { "node_count": 2, "item_count": 2, @@ -20109,18 +20427,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs touch expert-parallel loading, but they fix different bugs: one addresses missing distributed config/EP detection for ZeRO-3 + accelerate launch, while the other fixes experts being overwritten during FSDP2 sharding/broadcast. They are related but not duplicates.", - "confidence": 0.92, + "summary": "Related but not duplicate: both PRs touch expert-parallel loading, yet they fix different distributed bugs and different code paths. One targets EP + DeepSpeed ZeRO-3 / accelerate launch config handling; the other targets EP + FSDP2 expert parameters being overwritten during rank-0 broadcast.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45662 is the better canonical representative: it targets a concrete, specific code-path failure (expert weights being overwritten during distributed loading) and includes the broader set of loading-path changes needed for that bug.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR #45662 is the strongest standalone PR in the cluster because it fixes a clearly defined runtime bug with broader implementation coverage; #45548 is narrower and more about enabling EP metadata/detection for a different loading path.", + "best_pr_reason": "pull_request:45662 is the stronger standalone fix: it addresses a concrete silent corruption path in expert parameter loading under FSDP2, with narrowly scoped code changes tied to the failure mode.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Different underlying bugs and fix paths: #45548 is about EP + DeepSpeed ZeRO-3 loading via accelerate launch and serialization of distributed_config/has_ep, while #45662 fixes EP + FSDP2 experts being silently overwritten by rank-0 broadcast via post-shard wrapping. Shared subsystem only, not the same change." + "reason": "Same broad EP area, but different bugs: ZeRO-3/accelerate config loading vs FSDP2 rank-0 broadcast overwriting experts. Not mergeable as one fix." } ] }, @@ -20150,7 +20468,7 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "b4d3d2474892b2c331ec845fb57ffdca67449743d433224688b3ddf66e45b557", + "prepared_review_unit_hash": "3db06b4901eb7c064c7f9b10bd073cd7f6f13c21f7e75d6316ec6c36efbf110a", "component_budget": { "node_count": 2, "item_count": 2, @@ -20172,18 +20490,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs address the same xdist collision around `captured_info`/patched testing debug output, but PR 45645 is the broader superset that also updates CI log collection. PR 45639 looks like the narrower core fix; 45645 is the better canonical PR.", - "confidence": 0.92, + "summary": "Both PRs address the same xdist collision in captured_info handling, but PR #45645 is the more complete fix because it includes the worker-safe logging change plus the CI workflow update needed to read multiple captured_info files.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the most complete version of the fix: it includes the xdist-safe output handling in `testing_utils.py` plus the CI/workflow changes needed to collect multiple `captured_info*.txt` files, so it subsumes PR 45639.", + "canonical_pr_reason": "PR #45645 is the better canonical representative: it contains the core xdist-safe output change from #45639 and also updates the workflow to preserve/aggregate the resulting debug logs.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the best representative because it covers the same underlying xdist collision bug while also preserving downstream CI/debug-log behavior, making it the more comprehensive and merge-ready change.", + "best_pr_reason": "PR #45645 is the strongest overall candidate because it fully covers the underlying bug and its CI-log fallout, whereas #45639 is only the narrower helper/test change.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Accept: both PRs fix the same xdist collision around `captured_info` artifacts in `testing_utils.py`; 45645 extends the same fix with workflow/log-handling updates, so they are close enough to be merged as one change set." + "reason": "Same underlying captured_info xdist-collision fix; #45645 is a superset that extends the same code-path change with workflow support, so they could plausibly be merged into one PR." } ] }, @@ -20286,70 +20604,70 @@ "pull_request:46073|pull_request:46196", "pull_request:46154|pull_request:46196" ], - "prepared_review_unit_hash": "c4bd2cb23e1dad30f2521a0881b22dbffcb724be34b6d1680dccf93e6cd46d50", + "prepared_review_unit_hash": "7e1eb31f9e5c227b9fc93b04823ec5a2cec3b9e55f977da749a2ba0731f7f85a", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10497, - "estimated_input_tokens": 2625, - "estimated_eval_tokens": 5506 + "serialized_chars": 10495, + "estimated_input_tokens": 2624, + "estimated_eval_tokens": 5504 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10497, - "estimated_input_tokens": 2625, - "estimated_eval_tokens": 5506 + "serialized_chars": 10495, + "estimated_input_tokens": 2624, + "estimated_eval_tokens": 5504 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are all about adding SDPA / attn_implementation dispatch support, but each one targets a different model family and code path. They are similar feature PRs, not true duplicates.", - "confidence": 0.93, + "summary": "These PRs all implement SDPA/attention-dispatch support, but they do so for different model families and code paths. They are related by theme, not duplicates, so none of the soft edges should be accepted.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: each PR implements the same feature pattern in a different model-specific attention path, so they should remain separate.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 46196 is the strongest representative of the cluster because it covers two closely related model variants (SeamlessM4T and SeamlessM4T-v2) and has the broadest attention-dispatch changes.", + "best_pr_reason": "PR 46196 is the strongest representative of the theme because it spans both SeamlessM4T and SeamlessM4T-v2 and includes the broadest code/test coverage, but it is still a model-specific implementation, not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:46069", "right": "pull_request:46073", "accept": false, - "reason": "Same broad SDPA support theme, but ShieldGemma2 and CTRL are different model implementations with different attention code paths." + "reason": "Different models and code paths (ShieldGemma2 vision model vs CTRL text model); same high-level feature, but not the same concrete fix." }, { "left": "pull_request:46069", "right": "pull_request:46154", "accept": false, - "reason": "Both add attention-dispatch support, but ShieldGemma2 and T5 are unrelated architectures and the fixes are model-specific." + "reason": "Different architectures and implementations (ShieldGemma2 vs T5 seq2seq); these would not be merged into one PR." }, { "left": "pull_request:46069", "right": "pull_request:46196", "accept": false, - "reason": "Different model families and files; this is the same feature pattern, not the same concrete bug/change." + "reason": "Different model families and attention plumbing; one is ShieldGemma2, the other SeamlessM4T/v2, so not a duplicate." }, { "left": "pull_request:46073", "right": "pull_request:46154", "accept": false, - "reason": "CTRL and T5 each need separate dispatch plumbing; they are not the same underlying code-path fix." + "reason": "Both add SDPA dispatch, but for distinct model internals (CTRL vs T5) and separate test/documentation updates." }, { "left": "pull_request:46073", "right": "pull_request:46196", "accept": false, - "reason": "These are separate model-specific SDPA integrations, not a single change that could plausibly be merged into one PR." + "reason": "Same broad subsystem, but different models and code paths; not the same underlying bug/change." }, { "left": "pull_request:46154", "right": "pull_request:46196", "accept": false, - "reason": "T5 and SeamlessM4T/v2 are different implementations; similarity is limited to the shared attention-dispatch feature." + "reason": "T5 and SeamlessM4T/v2 have different attention implementations and fixes; too model-specific to treat as duplicates." } ] }, @@ -20379,7 +20697,7 @@ "soft_pairs": [ "pull_request:46152|pull_request:46207" ], - "prepared_review_unit_hash": "47ebff8889b0589ea55af2a3ba2af351eb6425439cc43afba987a7fe4e94f938", + "prepared_review_unit_hash": "869764d2688f6533e8a1a0cfb9b5f7521f06ba7cfdcc7d50e0847504fb6d40db", "component_budget": { "node_count": 2, "item_count": 2, @@ -20401,18 +20719,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs aim to remove file-open/source-reading hacks, but they fix different code paths in different modules and are not mergeable as one change.", - "confidence": 0.91, + "summary": "Two open PRs share a broad theme of removing source-file reads, but they target different code paths in different modules: `import_utils.py` vs `modeling_utils.py`. They are related refactors, not the same underlying bug/fix.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #46152 is the broader umbrella fix: it updates import-time path resolution in `import_utils.py` to avoid reading the module\u2019s own source file, which matches the cluster\u2019s shared theme most directly.", + "canonical_pr_reason": "No single PR is a clear duplicate/canonical representative; both are independent changes in separate modules with different implementation details and test impact.", "best_issue_reason": null, - "best_pr_reason": "PR #46152 is the better cluster representative because its title and diff capture the general pattern of eliminating self-source-file reads, while #46207 is a separate, narrower introspection refactor in `modeling_utils.py`.", + "best_pr_reason": "PR #46207 is slightly more representative of the cluster because it directly replaces a source-reading helper with introspection and includes an accompanying test, but it is still not a canonical duplicate of #46152.", "soft_edge_verdicts": [ { "left": "pull_request:46152", "right": "pull_request:46207", "accept": false, - "reason": "Related pattern, but not the same underlying bug/change: one rewrites resource-path resolution in `import_utils.py`, the other changes attention-implementation capability detection in `modeling_utils.py`. They touch different subsystems and would not plausibly be one PR." + "reason": "Both aim to avoid reading source files, but they fix different concrete behaviors in different subsystems (`import_utils` resource resolution vs `modeling_utils` attention-implementation detection). They are not mergeable as one PR without conflating separate problems." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index e59289e53c918ae917cc8d6272801eba56818b75..3781cd21535784d3bac4a3781c394b25c90086b3 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260526t120027z", + "analysis_id": "hybrid-model-20260526t180028z", "archived_artifacts": { - "hybrid": "snapshots/20260526T120027Z/analysis-runs/hybrid-model-20260526t120027z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260526T120027Z/analysis-runs/hybrid-model-20260526t120027z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-26T12:14:05Z", + "published_at": "2026-05-26T18:20:13Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260526T120027Z", + "snapshot_id": "20260526T180028Z", "variant": "hybrid" } diff --git a/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.json b/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..704867e84142c34cee8a60f8072f61522fc9078e --- /dev/null +++ b/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.json @@ -0,0 +1,2232 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260526T180028Z", + "generated_at": "2026-05-26T18:20:10Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-46032-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #46032.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 46032, + "canonical_pr_number": 46084, + "issue_numbers": [ + 46032 + ], + "pr_numbers": [ + 46084, + 46098 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 46084, + "right_pr_number": 46098, + "code_similarity": 0.43, + "size_similarity": 0.5, + "file_overlap": 0.667, + "area_overlap": 0.226, + "patch_similarity": 0.339, + "shared_filenames": [ + "src/transformers/models/mamba2/modeling_mamba2.py", + "tests/models/mamba2/test_modeling_mamba2.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/mamba2/modeling_mamba2.py", + "left_ranges": [ + [ + 256, + 262 + ], + [ + 303, + 353 + ], + [ + 461, + 467 + ], + [ + 471, + 491 + ], + [ + 496, + 502 + ], + [ + 599, + 609 + ] + ], + "right_ranges": [ + [ + 255, + 373 + ], + [ + 481, + 495 + ] + ] + }, + { + "filename": "tests/models/mamba2/test_modeling_mamba2.py", + "left_ranges": [ + [ + 206, + 236 + ], + [ + 285, + 322 + ] + ], + "right_ranges": [ + [ + 476, + 542 + ] + ] + } + ] + } + ] + }, + { + "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-46100-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 46100, + "issue_numbers": [], + "pr_numbers": [ + 46100, + 46114 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 46100, + "right_pr_number": 46114, + "code_similarity": 1.0, + "size_similarity": 1.0, + "file_overlap": 1.0, + "area_overlap": 1.0, + "patch_similarity": 1.0, + "shared_filenames": [ + "tests/models/vit/test_modeling_vit.py" + ], + "shared_file_areas": [ + { + "filename": "tests/models/vit/test_modeling_vit.py", + "left_ranges": [ + [ + 216, + 226 + ] + ], + "right_ranges": [ + [ + 216, + 226 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44001-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44004, + "issue_numbers": [], + "pr_numbers": [ + 44001, + 44004 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44001, + "right_pr_number": 44004, + "code_similarity": 0.087, + "size_similarity": 0.237, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.262, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "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-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-44001-2", + "canonical_pr_number": 44004, + "duplicate_pr_numbers": [ + 44001 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44001-2 are treated as duplicates because they share 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." + }, + { + "cluster_id": "cluster-46032-3", + "canonical_pr_number": 46084, + "duplicate_pr_numbers": [ + 46098 + ], + "target_issue_number": 46032, + "reason": "PRs in cluster-46032-3 are treated as duplicates because they converge on issue #46032 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-46100-2", + "canonical_pr_number": 46100, + "duplicate_pr_numbers": [ + 46114 + ], + "target_issue_number": null, + "reason": "PRs in cluster-46100-2 are treated as duplicates because they share soft_similarity 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 13 discussion comments plus 8 inbound references.", + "score": 164.0 + }, + "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/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..592f1db6f598797ef818ef42a9cb17dc116fcec3 --- /dev/null +++ b/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,20745 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260526T180028Z", + "generated_at": "2026-05-26T18:20:10Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43425", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43827", + "issue:43828", + "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", + "issue:46015", + "issue:46165" + ], + "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:45901|issue:46015", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:44918|issue:46165", + "issue:43638|issue:44805", + "issue:43638|issue:46165", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44560|issue:46165", + "issue:43596|issue:46165", + "issue:44805|issue:44918", + "issue:43572|issue:46165", + "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:34928|issue:41720", + "issue:43828|issue:45161", + "issue:44918|issue:45161", + "issue:43828|issue:44292", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:44292|issue:44918", + "issue:43716|issue:44292", + "issue:45507|issue:45685", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44918|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:45237|issue:46015", + "issue:43039|issue:44805", + "issue:41762|issue:43596", + "issue:39290|issue:41720", + "issue:45237|issue:45901", + "issue:43901|issue:44512", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43975|issue:46015", + "issue:45812|issue:45920", + "issue:44863|issue:46015", + "issue:43866|issue:44863", + "issue:44292|issue:46015" + ], + "prepared_review_unit_hash": "7fc1927efed8da07ce1eeaba26f2c3e797e909d72fec4f71c0e48257c2c83bc9", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 69, + "serialized_chars": 48404, + "estimated_input_tokens": 12101, + "estimated_eval_tokens": 24458 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issues, with two small duplicate clusters: a DeepSpeed ZeRO-3 empty-tensor/index-0 failure cluster and an AutoTokenizer wrong-token-IDs regression cluster. Most other pairs are only superficially similar and should stay separate.", + "confidence": 0.69, + "canonical_issue_reason": "issue:43596 is the clearest representative of the ZeRO-3 empty-tensor / index-0 failure cluster: it is concise, model-agnostic, and matches the near-identical follow-up issue 43638.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43596 is the best overall issue candidate because it describes the underlying failure mode most generally and cleanly, making it the strongest anchor for duplicate triage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different bugs: one is a config attribute error, the other is a streaming chat/completions failure." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Both touch GPU/MoE behavior, but the failures are different (AMD GPU support vs MPS histogram op missing)." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Both involve model/runtime compatibility, but one is image preprocessor dtype mismatch and the other is AMD GPU execution failure." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Different dtype/autocast bug versus GPU backend incompatibility; same broad area only." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different model families and different failure modes; not the same concrete bug." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Both are Qwen-3 related, but the reported runtime errors and code paths are different." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Both are model/runtime errors, but one is DeepSpeed collective mismatch and the other is ONNX export failure." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different model/export issue versus fine-grained FP8 failure; no concrete shared bug." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export and CUDA assert under auto device map are unrelated failures." + }, + { + "left": "issue:45901", + "right": "issue:46015", + "accept": false, + "reason": "Both are task/example related, but one is a task crash and the other is outdated RAG examples." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs cleanup for v5 removals, but they reference different removed content and likely different edits." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export error and GenerationMixin import error are separate regressions." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Both mention device/mask style errors, but the concrete errors and models differ." + }, + { + "left": "issue:44918", + "right": "issue:46165", + "accept": false, + "reason": "Different training failures: embedding unpacking with TRL versus resume-training with trust-remote-code." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Same general IndexError family, but 44805 is a different mask-shape mismatch and not the same bug." + }, + { + "left": "issue:43596", + "right": "issue:46165", + "accept": false, + "reason": "ZeRO-3 empty-index failure and resume-training/trust-remote-code are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different underlying errors: empty parameter/index-0 versus mask/tensor shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different bugs: mask shape mismatch versus tensor-parallel-only failure on GPT-OSS MoE." + }, + { + "left": "issue:44560", + "right": "issue:46165", + "accept": false, + "reason": "Different model/task failures with no shared code-path evidence." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Both are tensor-shape related, but the failures occur in different parts of the stack and are not clearly the same bug." + }, + { + "left": "issue:43572", + "right": "issue:46165", + "accept": false, + "reason": "Config field regression versus training resume issue; unrelated." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "Processor preset bug and ONNX export bug are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both involve DeepSpeed, but one is collective mismatch and the other is an index-0 empty-tensor failure." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 empty-parameter/index-0 failure during BertModel loading/training; only wording and model-pretraining context differ." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger Kernel cross-entropy dispatch and GPT-OSS tensor-parallel failure are different problems." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Tokenizer detokenization bug and LoRA merge/save mismatch are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Different model/runtime issues; no common underlying bug." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation checkpointing/FSDP tensor recomputation issue is not the same as the mask shape mismatch." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both are DeepSpeed training errors, but the concrete failures are different (weight rank error vs collective mismatch)." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": false, + "reason": "Same model component, but one is CPU-offload incompatibility and the other is uninitialized-memory after materialization; not clearly one bug." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "DeepSpeed ZeRO-3 index-0 failure and GPT-OSS tensor-parallel failure are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Different training-stack regressions: activation checkpointing/FSDP vs custom compute_loss signature." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different model-parallel failures with no shared concrete bug." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model-specific failures: dtype mismatch in preprocessing vs invalid method call in GraniteMoEHybrid." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Different compatibility bugs: vLLM config attribute missing vs Mistral tokenizer regex patch crash." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Both are Gemma4 issues, but one is device-map mismatch and the other is expensive reverse-embedding lookup." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version compatibility and Qwen running error are not the same bug." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "FSDP/checkpointing recompute mismatch and CUDA assert on auto device mapping are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch and tensor-parallel-only failure are different code paths." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "Different bugs: TRL SFT embedding unpacking versus GPT-OSS TP failure." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Both are Qwen-related runtime issues, but the specific failures differ and do not look like one fix." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Different MoE implementation problems on different backends; not the same underlying defect." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy call and TRL SFT embedding unpacking are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Same DeepSpeed ZeRO-3 size-0/index-0 failure pattern; only the affected model differs." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are documentation regressions, but they concern different removed APIs/commands and would need separate edits." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different model bugs: dtype mismatch in preprocessing versus StopIteration in video embedding." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Autocast dtype mismatch and MPS histogram op missing are different failures." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "TRL embedding unpacking and MPS histogram issue are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Both involve tensor computations, but one is Liger Kernel cross-entropy dispatch and the other is autocast dtype mismatch." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and custom trainer signature breakage are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Activation checkpointing/FSDP error and GenerationMixin import error are separate regressions." + }, + { + "left": "issue:45237", + "right": "issue:46015", + "accept": false, + "reason": "Model GPU compatibility bug and outdated RAG docs are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger Kernel cross-entropy issue and video StopIteration are different bugs." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": true, + "reason": "Same ZeRO-3 empty-tensor/index-0 bug; different model names only." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different issues: missing config attribute for vLLM vs CUDA assert in auto device mapping." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "Both affect Qwen-3 family areas, but the concrete crash modes are different." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs drift: TextClassificationPipeline return_all_scores versus transformers run command removal." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral and Gemma4 device mismatch are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:46015", + "accept": false, + "reason": "Tokenizer detokenization bug and outdated RAG examples are unrelated." + }, + { + "left": "issue:45812", + "right": "issue:45920", + "accept": true, + "reason": "Same AutoTokenizer wrong-token-IDs v5 regression across model families; 45920 is the broader manifestation of the same bug." + }, + { + "left": "issue:44863", + "right": "issue:46015", + "accept": false, + "reason": "NemotronH checkpoint loading failure and outdated examples are unrelated." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Corrupted checkpoint versus model-loading implementation problem are not the same bug." + }, + { + "left": "issue:44292", + "right": "issue:46015", + "accept": false, + "reason": "Qwen-3 runtime error and outdated RAG docs are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: it identifies the two supported duplicate clusters (ZeRO-3 index-0/empty-tensor and AutoTokenizer wrong-token-IDs) and treats the rest as unrelated. The soft-edge verdicts are generally conservative, and the accepted pairs are backed by nearly identical titles/error patterns." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36010", + "issue:39186", + "issue:39290", + "issue:40990", + "issue:41093", + "issue:41762", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43645", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44589", + "issue:44841", + "issue:44918", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45084", + "issue:45161", + "issue:45362", + "issue:45399", + "issue:45464", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45901", + "issue:45902" + ], + "soft_pairs": [ + "issue:39290|issue:43531", + "issue:43792|issue:45901", + "issue:43854|issue:43866", + "issue:41093|issue:43638", + "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:45464|issue:45685", + "issue:43404|issue:43866", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:44841|issue:45084", + "issue:36010|issue:39290", + "issue:45800|issue:45823", + "issue:41093|issue:41762", + "issue:43572|issue:45070", + "issue:43296|issue:43366", + "issue:43541|issue:45161", + "issue:44387|issue:45005", + "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:45759|issue:45902", + "issue:45542|issue:45800", + "issue:39186|issue:44918", + "issue:43716|issue:44918", + "issue:40990|issue:44960", + "issue:45632|issue:45698", + "issue:43645|issue:45399", + "issue:43404|issue:45005" + ], + "prepared_review_unit_hash": "c80ba2c97484a5344cd5a5f483fd828a234dd5a2d74f8b16de77c9f2a35a981c", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 39, + "serialized_chars": 39131, + "estimated_input_tokens": 9783, + "estimated_eval_tokens": 19822 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous cluster with a few real duplicate pockets. The main correction is to reject 39290 vs 43531: they both mention sliding_window, but the model families and failure contexts differ too much. A couple of tighter matches remain, especially SigLIP2 and custom-module loading.", + "confidence": 0.69, + "canonical_issue_reason": "Issue 39290 is still the strongest single anchor among the near-duplicate pockets, but only as a local representative; the cluster overall is too diverse for a strong global canonical.", + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must stand in for the cluster, 39290 is the best representative because it is the clearest specific bug report with the strongest nearby duplicate signal, though the overall set is not one bug family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Same keyword, but Gemma3TextConfig/vLLM and Qwen3-MoE point to different model-specific failures; not enough evidence for one bug." + }, + { + "left": "issue:43792", + "right": "issue:45901", + "accept": false, + "reason": "Whisper runtime failure and table QA crash are unrelated code paths and symptoms." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Model-loading test failure vs corrupted checkpoint; different underlying problems." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are index errors, but the models, shapes, and triggers differ." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch version incompatibility and PretrainedConfig/pydantic regression are separate issues." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "ZeRO-3/Bert index error is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:43975", + "right": "issue:45901", + "accept": false, + "reason": "Detokenization bug and table-question-answering crash are not the same bug." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper runtime failure is unrelated to the pydantic field regression." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Both involve Qwen3.5/chat, but the concrete failures differ too much to merge." + }, + { + "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "NVFP4 runtime failure is unrelated to the table QA crash." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Different model families and symptoms: sliding_window/vLLM versus Gemma4 device-mapping." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Streaming chat failure and MPS Int histogram error are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Untied weights in Mistral3 and a corrupted checkpoint are different causes." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Grouped_mm tracing error and MPS histogram error are distinct failure paths." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Different models and different runtime errors; not the same bug." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Processor failure and template compilation error are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "GenerationMixin import error is unrelated to the sliding_window bug." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "Torch/transformers incompatibility and Gemma4 PLE device mismatch are not the same issue." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are index errors around loading, but the model paths and exact failures differ." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "StableLm pad_token_idx regression is unrelated to the PretrainedConfig/pydantic issue." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "PaddleOCR-VL loading and GGUF gpt-oss support are different problems." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing failure and TP-not-working are not the same underlying bug." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Int4 OOM regression and tied-weights translation bug are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Autocast dtype mismatch and chat streaming failure are different code paths." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "init_empty_weights argument handling is unrelated to the pydantic field regression." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF gpt-oss support and Qwen3.5 streaming inference are unrelated." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Remote_code breakage and torch/transformers incompatibility are not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window and PretrainedConfig/pydantic breakage are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Grouped_mm tracing failure and Float8 storage lookup error are different issues." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are index errors, but the affected scenarios and tensors differ." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": true, + "reason": "Both concern SigLIP2 producing bad outputs on the same model family; this looks like the same underlying issue." + }, + { + "left": "issue:45759", + "right": "issue:45902", + "accept": false, + "reason": "Composite config unwrapping and uninitialized rotary memory are unrelated." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard-without-TF backend error is unrelated to torch/transformers incompatibility." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP weight-shape error and Qwen3.5 embedding unpacking are different bugs." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Mistral dtype mismatch and Qwen3.5 SFT unpacking are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and GLM5 are different reports with no shared failure mode." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": true, + "reason": "Both point to wrong custom-module resolution after save/load; same dynamic-module path bug." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Jupyter custom-model initialization and flash-attn fallback blocking are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Mistral3 tied-weight bug and translation-model tied-weight regressions are different model families and fixes." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster-level summary is mostly grounded, but one soft-edge acceptance is too strong: issue:39290 vs issue:43531. They share a sliding_window keyword, but the packet shows different model families and different failure contexts (Gemma3TextConfig/vLLM vs Qwen3-MoE), so calling them the same bug overstates the evidence. For a conservative review, that pair should be marked false or at most tentative. The other accepted pairs are more plausible, but this single overconfident accept is enough to reject." + }, + "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": 3, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "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: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:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:45005", + "issue:45020", + "issue:45237", + "issue:45399", + "issue:45507", + "issue:45663", + "issue:45685", + "issue:45701", + "issue:45800", + "issue:45823", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:42915|issue:45399", + "issue:44530|issue:45005", + "issue:43873|issue:45005", + "issue:44863|issue:45005", + "issue:44360|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:44492|issue:44512", + "issue:44292|issue:45507", + "issue:43950|issue:44534", + "issue:43644|issue:43950", + "issue:39692|issue:43054", + "issue:43828|issue:44928", + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:43950|issue:45902", + "issue:43872|issue:44589", + "issue:43866|issue:44403", + "issue:43054|issue:45701", + "issue:41553|issue:43883", + "issue:38175|issue:43054", + "issue:45663|issue:45902", + "issue:44910|issue:45859", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:43054|issue:43493", + "issue:44403|issue:44451", + "issue:43975|issue:45237", + "issue:44403|issue:44488", + "issue:43643|issue:45020", + "issue:42947|issue:43856", + "issue:41762|issue:42915", + "issue:43881|issue:43883", + "issue:45685|issue:45823" + ], + "prepared_review_unit_hash": "9ae4db3ea942906e931f9fda13dc770f42ce24e3cf87a12b852c7d2c71ca4b7e", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37578, + "estimated_input_tokens": 9395, + "estimated_eval_tokens": 19046 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue set, with a few small duplicate clusters around non-persistent buffer corruption, remote_code regressions, and SigLIP2 discrepancy/quality problems. No PRs are present.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43950 is the clearest broad regression report in the cluster: it describes the underlying non-persistent-buffer corruption bug directly, and it has the strongest duplicate-style overlap with issue:44534 (plus likely the related 45902 symptom).", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 is the best global anchor because it states a concrete Transformers 5.x regression with a clear code-path focus and likely absorbs the closest duplicate reports in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "Different problems: Qwen3Moe FP8 config failure vs flash-attn2 fallback being blocked by checks." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "Different code paths: Qwen3.5 PagedAttentionCache crash vs tied-weights handling on translation models." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to tied-weights regressions." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "Checkpoint-loading failure for NemotronH is not the same as tied-weights handling." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "Unrelated: DSA indexer ReLU discussion vs a docs typo about a removed command." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Different failures in different models/subsystems; no shared concrete bug." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Different symptoms: detokenization bug vs Qwen-3 NVFP4 runtime error." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo is unrelated to old docs mentioning the removed run command." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "No common underlying bug; they affect different models and failure modes." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Both describe the same Transformers 5.x non-persistent-buffer corruption regression." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": false, + "reason": "AutoConfig remote_code field loss is a different bug than buffer corruption." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Both mention SigLIP2, but one is a docs/example issue and the other is a model quality discrepancy." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Different training/runtime issues: autocast dtype mismatch vs Qwen3.5 RLHF gradient explosion." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Trainer API mismatch and ZeRO-3 load failure are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Import/export API issue is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": true, + "reason": "Same non-persistent-buffer materialization bug; 45902 is a model-specific manifestation after meta\u2192to_empty(cuda)." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Different low-level compatibility problems: bitsandbytes kwarg mismatch vs missing Float8 storage." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Corrupted checkpoint vs noisy loading behavior are not the same bug." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality and tokenization changes are different problems." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error messaging vs missing all_tied_weights_keys attribute are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both concern SigLIP2 outputs, but the observed failures are too different to treat as the same bug." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states issue is unrelated to non-persistent buffer initialization." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Flash-attn packed-sequence misinterpretation is different from CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different failure layers; no shared root cause." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing inefficiency and int4 memory blowup are different optimization issues." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": true, + "reason": "Both point to the same SigLIP2 implementation discrepancy/quality regression versus the expected/original behavior." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "General loading noise is not the same as failing to load a specific model." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Detokenization bug and AMD GPU compatibility failure are unrelated." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Noisy loading messages are unrelated to the specific model-load failure." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": true, + "reason": "Same remote_code regression family; 43643 is a concrete AutoConfig missing-fields symptom of the broader breakage." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "LoRA checkpointing behavior and Qwen3 MoE memory usage are different issues." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "ZeRO-3 load indexing error and FP8 config failure are unrelated." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "GLM-4V loading failure is not the same as the Molmo tied-weights attribute bug." + }, + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "MPS int histogram support and Gemma4 device mismatch are different runtime problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The accepted soft-edge pairs are supported by the issue titles and the provided soft-pair evidence, and the rejections do not overclaim shared root causes. No PRs are present, so the anchor choice is reasonable." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 4, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "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:43782", + "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:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45305", + "issue:45313", + "issue:45356", + "issue:45399", + "issue:45538", + "issue:45588", + "issue:45823", + "issue:45923" + ], + "soft_pairs": [ + "issue:43782|issue:44960", + "issue:44991|issue:45399", + "issue:43824|issue:43872", + "issue:42491|issue:44368", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:43828|issue:45823", + "issue:45081|issue:45399", + "issue:43742|issue:45399", + "issue:45020|issue:45356", + "issue:43404|issue:43950", + "issue:43638|issue:45823", + "issue:42915|issue:45020", + "issue:43827|issue:44509", + "issue:43872|issue:44291", + "issue:43257|issue:43866", + "issue:43792|issue:44220", + "issue:42915|issue:43872", + "issue:41553|issue:44991", + "issue:36331|issue:41093", + "issue:43257|issue:45305", + "issue:42947|issue:45923", + "issue:43940|issue:45313", + "issue:43854|issue:44863", + "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:43366|issue:43828" + ], + "prepared_review_unit_hash": "fd3079dccae342689c5c53338d250c89a63f0ea14141903d017d30e301516ec7", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 37048, + "estimated_input_tokens": 9262, + "estimated_eval_tokens": 18780 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: only a few pairs look like true duplicates, mainly doc typos/regressions and a couple of same-error code-path bugs. Most soft-similar pairs share only broad subsystem/theme overlap, not the same underlying issue.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Different models and failures: Qwen3VL from_pretrained weight_only error vs a generic GLM5 model-loading issue." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer-loading regression vs flash-attn fallback gating; unrelated code paths." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "ImportError for Qwen2.5-VL class name vs bitsandbytes Int8Params kwarg incompatibility; not the same bug." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Different LoRA/tie_word_embeddings warning issue, not the same HF4.x to HF5.x Qwen3 MoE loading failure." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Remote_code regressions broadly vs a Gemma4 device_map forward mismatch; no shared concrete bug." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Model-like addition failing in tokenizer mapping vs remote_code regressions; overlapping theme only." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch in Phi-tiny-MoE vs Gemma4 PLE device mismatch; distinct failures." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Mistral regex patch crash vs flash-attn fallback blocking; unrelated bugs." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM key error while loading vs flash-attn install/fallback checks; different code paths." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "General remote_code breakage vs Kimi-K2.5 tokenizer codec regression; not the same issue." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "lm_head tying bug vs non-persistent buffer corruption on from_pretrained; separate loading semantics." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "Deepspeed ZeRO-3 index error on non-pretrained Bert vs Gemma4 device mismatch; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "FineGrainedFP8 Qwen3 MoE failure vs remote_code regression broadly; too different." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Same doc regression: both note removed v5 pipeline tasks (summarization/translation/text2text) still referenced in docs." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same underlying `_is_hf_initialized` / `Int8Params.__new__` incompatibility when loading models with init_empty_weights or bitsandbytes." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate+deepspeed vs corrupted Ovis2 checkpoint; unrelated model issues." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": true, + "reason": "Both point to the Whisper audio feature-extraction path failing; `_torch_extract_fbank_features()` is the likely root cause of 'can't run'." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3 MoE FP8 failure vs bitsandbytes/init_empty_weights kwarg issue; different subsystems." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Bad AutoTokenizer error message for Voxtral vs tokenizer loading failure for est-roberta; not the same bug." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Trainer compute_loss signature change vs mask/tensor shape mismatch; unrelated errors." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "DeepSpeed weight-conversion failure vs gradient averaging with GAS/model_accepts_loss_kwargs; different training bugs." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "PEFT LoRA gradient checkpointing ineffective vs missing supports_gradient_checkpointing flag on a remote-code variant." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both are ZeRO-3 weight-loading failures, but on different Qwen families and with different symptoms; not clearly the same defect." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "GLM-4.7-Flash test loading failure vs NemotronH checkpoint loading failure; distinct models and failure modes." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "Qwen3.5 RLHF NaN/SDPA fallback issue vs flash_attention.py s_aux=None crash; unrelated." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes kwarg incompatibility vs CLIPTokenizer max_length sentinel value; no shared root cause." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same mask/index shape mismatch error pattern; the later report is the same underlying IndexError with different tensor sizes." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer-loading failures on different models; one is an error-message issue, the other a load failure." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": true, + "reason": "Both describe the same Qwen video-input regression in v5.3.0, with StopIteration being a concrete symptom of the broader video pipeline breakage." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash vs NemotronH checkpoint loading failure; separate bugs." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "DeepSpeed training weight dimension error vs void segmentation map processing failure; unrelated." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss support request vs Phi-tiny-MoE autocast dtype mismatch; no common code-path bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: it describes the cluster as mostly heterogeneous while calling out only a few plausible duplicate pairs. The accepted soft-edge verdicts are defensible from the issue titles/body context, and the rejected ones avoid overclaiming shared root causes." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "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:43720", + "issue:43824", + "issue:43950", + "issue:43957", + "issue:43994", + "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:45325", + "issue:45357", + "issue:45584", + "issue:45663", + "issue:45685", + "issue:45823", + "issue:45834", + "issue:45902" + ], + "soft_pairs": [ + "issue:45325|issue:45902", + "issue:45663|issue:45823", + "issue:43366|issue:43531", + "issue:44155|issue:45584", + "issue:43950|issue:45834", + "issue:44560|issue:45685", + "issue:43824|issue:43957", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:42915|issue:43957", + "issue:43366|issue:44589", + "issue:44560|issue:44918", + "issue:42617|issue:43366", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:44560|issue:44805", + "issue:43632|issue:45834", + "issue:38175|issue:43994", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:44877|issue:45030", + "issue:43317|issue:44756", + "issue:43644|issue:44534", + "issue:38175|issue:39692", + "issue:42491|issue:43720", + "issue:41720|issue:42915", + "issue:44960|issue:44977", + "issue:44451|issue:44488", + "issue:42915|issue:44756", + "issue:45313|issue:45357", + "issue:42491|issue:45276" + ], + "prepared_review_unit_hash": "521c103eb31bd9fa102759c9a3b13f0ce9636d713aa69ed23056a619f3a99db6", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36684, + "estimated_input_tokens": 9171, + "estimated_eval_tokens": 18598 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated model-specific regressions; only a few soft pairs look like true duplicates. The clearest duplicate groups are the non-persistent-buffer regression, the custom-model init regression, and the SigLIP2 wrong-output reports.", + "confidence": 0.74, + "canonical_issue_reason": "issue:43644 is the best anchor for the non-persistent-buffer regression: it is the earlier, more fully specified report, and issue:44534 is essentially the same bug phrased later.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the strongest single issue to keep as canonical because it is concrete, well-scoped, and has a clear near-duplicate; it is easier to triage than the more model-specific or ambiguous reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "Different models and different failure modes: rope scaling bug vs uninitialized-memory rotary embedding issue." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Same model family, but distinct code paths: FSDP2 shared_kv_states KeyError vs device_map auto device mismatch." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Unrelated topics: GGUF architecture support vs Qwen3-MoE sliding_window behavior." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "Different inference bugs in different pipelines; no shared concrete code path." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Non-persistent buffer corruption vs OCR long-input index error are not the same bug." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Video StopIteration issue and MPS histogram Int limitation are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Import error for a missing class vs meta-device loading regression; not the same issue." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different concrete failures: torch.compile with SDPA vs flash-attention crash on Qwen3.5 position_ids." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These are the same custom-model initialization regression; one is just a notebook-specific phrasing of the other." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Qwen3MoE FineGrainedFP8Config failure is unrelated to meta-device loading bugs." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF support request and Float8 storage TypeError are different problems." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Video StopIteration vs unpacking embeddings in TRL SFT trainer are different code paths." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "A script runtime failure and GGUF model support are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "GenerationMixin import error is unrelated to Qwen3MoE FP8 loading." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer-mapping/model-like failure and Gemma4 device mismatch are different bugs." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Different symptoms and likely different tensor-shape issues; not enough to treat as duplicates." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "_is_hf_initialized flag regression is unrelated to the long OCR index error." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": true, + "reason": "Both report incorrect SigLIP2 outputs for the same model family; the later one is essentially the same underlying inference bug." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "Deepspeed ZeRO-3 Bert initialization failure is unrelated to add-new-model-like tokenizer mapping behavior." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Zero3 Bert index error is a different bug from the tokenizer-mapping/model-like issue." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both involve config loading, but the model-specific failures are not the same concrete bug." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "device_map dequantized-model offload failure and mmap OOM on Strix Halo are different issues." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Exact duplicate regression: both say transformers v5 fills non-persistent buffers with junk." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "SigLIP2 wrong outputs and docs-example mismatches/quantization failures are related only by model family, not the same bug." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Qwen3_moe LoRA hf4.x/hf5.x compatibility and BitNet packed-weight loading are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Auto device mapping CUDA assert and FineGrainedFP8Config failure are different Qwen issues." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "GLM5 issue and Qwen3.5 flash-attention generation bug are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are BERT loading failures, but the titles do not establish the same concrete underlying bug." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "ZeRO-3 weight loading and incorrect save_pretrained visual encoder keys are different Qwen3.5 regressions." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Qwen3_moe LoRA compatibility on hf5.x and Gemma4 resize_token_embeddings behavior are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and the duplicate judgments stay conservative overall. The canonical non-persistent-buffer pair is well supported by the titles, and the accepted soft pairs are plausibly same-bug matches without overclaiming beyond the available evidence. No pair is forced together on weak evidence, and the rejected pairs are explained in a cautious way." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43381", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43708", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44488", + "issue:44756", + "issue:44910", + "issue:44912", + "issue:44960", + "issue:44991", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45859", + "issue:46050" + ], + "soft_pairs": [ + "issue:43708|issue:44075", + "issue:43644|issue:43645", + "issue:44488|issue:44991", + "issue:43854|issue:43931", + "issue:45488|issue:45812", + "issue:39692|issue:43994", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42491|issue:43931", + "issue:43856|issue:44387", + "issue:45362|issue:45406", + "issue:44960|issue:46050", + "issue:42491|issue:45292", + "issue:44164|issue:44291", + "issue:44910|issue:45588", + "issue:45276|issue:45335", + "issue:36010|issue:39404", + "issue:43404|issue:43454", + "issue:43425|issue:43957", + "issue:41720|issue:44155", + "issue:39692|issue:44960", + "issue:44402|issue:44488", + "issue:42947|issue:45704", + "issue:45663|issue:45759", + "issue:43873|issue:44387", + "issue:44291|issue:44756", + "issue:45663|issue:45859", + "issue:44155|issue:45823", + "issue:43335|issue:45663", + "issue:44292|issue:44912", + "issue:44387|issue:44756", + "issue:43957|issue:44756", + "issue:42947|issue:43381", + "issue:45276|issue:45292", + "issue:44164|issue:44756" + ], + "prepared_review_unit_hash": "c7771e78b7b4192731d92935b995cd8b50f4c107943c00197fa0c5edc3527706", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38299, + "estimated_input_tokens": 9575, + "estimated_eval_tokens": 19406 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated issue reports. The only soft edge that looks like the same underlying bug is the resize_token_embeddings/output_embeddings pair; all other candidates are too model-/path-specific to merge confidently.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 45292 is the cleanest canonical for the shared resize_token_embeddings bug: it states the core generic symptom on output_embeddings, while 45276 is a broader Gemma4-specific manifestation of the same failure.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45292 is the best representative because it describes the common root symptom without extra model-specific detail, making it the most reusable target for deduplication.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Different training/runtime bugs: checkpoint resume/max_steps accounting vs optimizer arguments being ignored." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both mention Transformers 5.0.0, but one is about non-persistent buffers and the other about custom model initialization in Jupyter; different problems." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading failures, but for different models and likely different root causes; not the same bug." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Different model-loading failures for different architectures; no clear shared code-path bug." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer regressions in v5, but one is LlamaTokenizer pre-tokenizer handling and the other is AutoTokenizer token IDs for Granite; not the same change." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but one is a documentation/example issue plus quantization failure; the other is a runtime nonsensical-results report. Too different to merge confidently." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3 MoE weight conversion/offload behavior vs GLM-4.7-Flash loading in tests; unrelated." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Different resource problems: Qwen3 MoE training memory usage vs quantized offloading behavior." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "A LoRA compatibility regression across branches is unrelated to a Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both involve memory, but one is MoE training memory usage and the other is int4 quantization reserved-memory/OOM; different issues." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different models and failures: Qwen3.5 chat crash vs Gemma4Processor missing _tokenizer in serve." + }, + { + "left": "issue:44960", + "right": "issue:46050", + "accept": false, + "reason": "GLM5 loading and sinq save/load corruption are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "LoRA hf4.x/hf5.x compatibility has no overlap with resize_token_embeddings behavior." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Both are loading/saving related, but extra_state handling and init_empty_weights _is_hf_initialized are distinct bugs." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both hit flash_attention paths, but one is a packed-sequence/position_ids crash and the other is an s_aux=None AttributeError; different code paths." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "Similar symptom, but model-specific implementations differ (Gemma4 vs T5Gemma) and the reports do not establish a single shared root cause." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to Whisper pipeline return_language behavior." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both mention untied lm_head weights, but they are different model families and the evidence is not enough to treat them as the same bug." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch 2.10 compatibility and meta-device model loading are different incompatibility reports." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert is unrelated to AudioFlamingo3 track-to-track leakage." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Different models and failures; no shared underlying bug." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer vocab-size mismatch is unrelated to failing to load a specific model." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing/PEFT and apex RMSNorm memory leak are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma4 FSDP2 attention state rebuilding and Qwen multimodal text_config unwrapping are different model-architecture bugs." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Quantization offloading vs int4 reserved-memory growth are related broadly to memory, but not the same concrete bug." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "init_empty_weights argument handling is unrelated to mmap/OOM on Strix Halo." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Different Gemma4 vs Qwen3.5 MoE offload issues; not mergeable as one fix." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "Different models and failures: embedding/token leakage vs PLE device mismatch." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and Gemma4 FSDP2 attention state are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Different quantized-model loading problems for different models/quantization formats." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Different memory/OOM reports with no shared code-path evidence." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading failures and disabling mmap for Strix Halo are different issues." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to PEFT LoRA checkpointing effectiveness." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Both describe the same resize_token_embeddings failure to update output_embeddings; 45276 is the broader model-specific instance, while 45292 is the generic core report." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "save/from_pretrained extra_state handling is unrelated to mmap/OOM on Strix Halo." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft edge, issue:45276 \u2194 issue:45292, is well supported by the titles and the shared resize_token_embeddings/output_embeddings symptom. The rejected pairs are phrased cautiously and do not overstate evidence. 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": 7, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36032", + "issue:39404", + "issue:43257", + "issue:43299", + "issue:43381", + "issue:43425", + "issue:43452", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43716", + "issue:43828", + "issue:43854", + "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:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44928", + "issue:45084", + "issue:45216", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43854|issue:45216", + "issue:43381|issue:44928", + "issue:44479|issue:44877", + "issue:45684|issue:45698", + "issue:45588|issue:45663", + "issue:43646|issue:43708", + "issue:43645|issue:44164", + "issue:43828|issue:43957", + "issue:45292|issue:45335", + "issue:43425|issue:43828", + "issue:44402|issue:44451", + "issue:43257|issue:44863", + "issue:44589|issue:44756", + "issue:39404|issue:45701", + "issue:44683|issue:45823", + "issue:43425|issue:45823", + "issue:43611|issue:43645", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:39404|issue:44912", + "issue:43906|issue:44530", + "issue:44265|issue:44898", + "issue:44479|issue:44805", + "issue:43994|issue:44079", + "issue:43425|issue:44918", + "issue:43901|issue:44509", + "issue:44589|issue:45084", + "issue:43299|issue:43931", + "issue:44164|issue:45759", + "issue:36032|issue:43452" + ], + "prepared_review_unit_hash": "e44fba1572dce3fbf5b76a47c515c65fcaf1232fff60a035d44c2b67aa14e082", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36815, + "estimated_input_tokens": 9204, + "estimated_eval_tokens": 18664 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous Transformers bug reports. Only one soft edge looks like a true duplicate pair: the `resize_token_embeddings` regression in 45292/45335, where the general bug and the T5Gemma-specific symptom match the same underlying API issue.", + "confidence": 0.86, + "canonical_issue_reason": "Issue 45292 is the broader, model-agnostic report: `resize_token_embeddings` does not update the affected embeddings. Issue 45335 appears to be the T5Gemma-specific manifestation of the same bug, so 45292 is the better canonical anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "45292 is the best representative issue because it describes the root regression in general terms, while 45335 is a narrower model-specific reproduction.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Different bugs: one is a model load/save corruption case, the other is a Qwen3.5 checkpoint save_pretrained regression." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Different failure modes: gradient checkpointing in eval mode vs RLHF NaNs from Qwen3.5 position_ids/SDPA behavior." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Both are loading regressions, but on different model/config paths (video-input Qwen VL vs granite_speech strict config)." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Distinct issues: read-only permission propagation during save_pretrained vs loading the wrong custom module after save_pretrained." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Different code paths: flash_attention crash on sink-less models vs Gemma4 FSDP2 shared_kv_states rebuild KeyError." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization vs Trainer resume_from_checkpoint max_steps calculation are unrelated regressions." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook custom-model init failure is not the same bug as extra_state not being handled by save/from_pretrained." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Different root causes: autocast dtype mismatch in Phi-tiny-MoE vs meta-device loading breakage in some models." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same underlying API regression: `resize_token_embeddings` does not propagate to the relevant output/decoder embeddings; 45335 is the T5Gemma-specific reproduction." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version compatibility is a different problem from the Phi-tiny-MoE autocast dtype mismatch." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Both involve tokenizer/model loading, but the specific failures differ (vocab-size mismatch vs inability to load a particular model)." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Separate model-loading bugs affecting different architectures and mechanisms." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Unrelated issues: missing Float8 storage object vs mmap-induced OOM on Strix Halo." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline return_language regression is unrelated to a broad tokenization-change report." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device_map mismatches are different failures." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch 2.10 incompatibility is not the same bug as Gemma4 PLE device placement mismatch." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Loading models with base_model_prefix is a different regression from Jupyter notebook custom-model initialization." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Torch compatibility problems are unrelated to the Mistral-3 image preprocessor dtype mismatch." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "Different failures: PagedAttentionCache linear_attention crash vs a template-node compilation TypeError." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline behavior and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "No clear evidence they are the same underlying bug; the titles point to different reproduction contexts and failure modes." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export/torch_compilable_check and Perceiver interpolation are different code paths." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression in Qwen VL models is unrelated to the mask-shape IndexError." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP2 inference quality issue is not the same as ModelOutput key assignment behavior." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch compatibility is unrelated to the Qwen3.5 embedding unpacking issue in TRL SFTTrainer." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but they cover different removed/changed pipeline behaviors and are not the same issue." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Missing Float8 storage object and non-template-node compilation are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both mention Qwen3-VL loading, but the concrete failures differ too much to merge confidently." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "extra_state save/load handling is unrelated to unwrapping text_config for composite Qwen multimodal configs." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict is unrelated to gguf_file breaking from_pretrained for tokenizer/model loading." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The only accepted duplicate pair, 45292/45335, is a reasonable merge candidate from the titles alone: both report `resize_token_embeddings` failing to update downstream embeddings, with 45335 being the T5Gemma-specific manifestation. The remaining pairwise rejections do not overclaim sameness and are phrased cautiously enough for the available 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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42175", + "issue:42915", + "issue:43317", + "issue:43421", + "issue:43452", + "issue:43482", + "issue:43541", + "issue:43582", + "issue:43596", + "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:44479", + "issue:44488", + "issue:44530", + "issue:44661", + "issue:44671", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45584", + "issue:45859", + "issue:45987", + "issue:46178" + ], + "soft_pairs": [ + "issue:43596|issue:44683", + "issue:44671|issue:44991", + "issue:39404|issue:44671", + "issue:44991|issue:45081", + "issue:43856|issue:44756", + "issue:44164|issue:44479", + "issue:44737|issue:45859", + "issue:32090|issue:39404", + "issue:43582|issue:43632", + "issue:44661|issue:44683", + "issue:44488|issue:45081", + "issue:44488|issue:44987", + "issue:43611|issue:43644", + "issue:40990|issue:43421", + "issue:43716|issue:45084", + "issue:44206|issue:44220", + "issue:36032|issue:42915", + "issue:43883|issue:44488", + "issue:43643|issue:44530", + "issue:34567|issue:40444", + "issue:42175|issue:46178", + "issue:44811|issue:45584", + "issue:43541|issue:45084", + "issue:44451|issue:44987", + "issue:42915|issue:44530", + "issue:43644|issue:43646", + "issue:44464|issue:45987", + "issue:43452|issue:43482", + "issue:36032|issue:43645", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:44987|issue:44991" + ], + "prepared_review_unit_hash": "eb9d4803d52350f448dd896917dd93483ffc3f05dca020db179711655aea898c", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37231, + "estimated_input_tokens": 9308, + "estimated_eval_tokens": 18872 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous; the soft matches are high-similarity false positives across different models, tokenizers, and regression types. I did not find any pair that looks like the same concrete bug/change.", + "confidence": 0.81, + "canonical_issue_reason": "Issue 43646 is the broadest v5 regression among the set and best represents the cluster\u2019s general model-initialization breakage theme, though it is not a true duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43646 is the most general and central issue, with the widest scope among the candidates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Different failures in different subsystems: deepspeed/BertModel broadcast vs compiled flex_attention on newer torch." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "Both are v5-era loading regressions, but one is CamemBERT masked-LM output quality and the other is tokenizer loading for a different model." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline language return bug is unrelated to CamemBERT masked-LM prediction regression." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizer loading, but they hit different models and distinct code paths (_patch_mistral_regex vs generic tokenizer load failure)." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory/OOM, but one is Qwen3 MoE training memory usage and the other is mmap behavior on Strix Halo." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Save/from_pretrained extra_state handling and Qwen VL video-input regression are separate bugs." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both are device-placement issues, but they affect different models and code paths (XLNet relative positions vs Qwen3.5 MoE rotary embedding)." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer gpu_broadcast NoneType crash is unrelated to Whisper return_language behavior." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "AppleSilicon allocator TypeError and _is_hf_initialized regression are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Tokenizer mapping lookup failure and torch >=2.9 flex_attention compilation failure are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-loading reports, but they concern different models and different breakages." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are loading regressions, but one is a specific model load failure and the other is a different model's tokenizer load failure." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but base_model_prefix loading and non-persistent buffer junk are distinct initialization bugs." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "High perplexity on gpt-oss and runtime special-token post-processor updates are unrelated." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Image preprocessor dtype mismatch and template-node compilation error are unrelated." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Both touch audio features, but the reported crashes and APIs differ; not the same concrete bug." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Molmo tied-weights metadata error is unrelated to loading cjvt/sleng-bert." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "AutoConfig trust_remote_code field loss is unrelated to Qwen3.5 PagedAttentionCache group-type crash." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token-count tracking and Qwen2.5-VL multi-image IterableDataset failure are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:46178", + "accept": false, + "reason": "Both involve backend handling, but one is install extras coverage and the other is a missing BACKENDS_MAPPING entry for tensorflow_text." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper-related, but batch_decode skip_special_tokens handling and empty-transcription generation after align_special_tokens are different bugs." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Mixtral grouped_mm tracing failure and template-node compilation failure are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different model-loading failures for different artifacts; not the same underlying bug." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Qwen3.5 linear_attention group-type crash are distinct model/runtime issues." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 initialization regressions, but one is non-persistent buffers and the other is custom model initialization; separate concrete bugs." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Chunked generation with compiled forward and StaticCache sequence-length return type are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "gguf_file path breakage and Qwen2.5-GGUF loading failure are related to GGUF loading broadly, but not the same concrete failure." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer method-name conflict and Jupyter custom-model initialization regression are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "Dequantized-model device_map offload failure and Qwen2.5-GGUF loading failure are different loading paths." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen model families and different bugs: hidden-states output vs rope index scaling." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are transformers>=5 loading regressions, but they affect different models and failure modes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 9, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36032", + "issue:40444", + "issue:41553", + "issue:41720", + "issue:42915", + "issue:43089", + "issue:43262", + "issue:43296", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43540", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43819", + "issue:43883", + "issue:43994", + "issue:44062", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45507", + "issue:45987" + ], + "soft_pairs": [ + "issue:45084|issue:45507", + "issue:43883|issue:44991", + "issue:43262|issue:43377", + "issue:43645|issue:44534", + "issue:43089|issue:45987", + "issue:43646|issue:44534", + "issue:43404|issue:44466", + "issue:43322|issue:43540", + "issue:44403|issue:45081", + "issue:43994|issue:44610", + "issue:42915|issue:45084", + "issue:43377|issue:43819", + "issue:44265|issue:44610", + "issue:44451|issue:45081", + "issue:44987|issue:45081", + "issue:44220|issue:44683", + "issue:42915|issue:44291", + "issue:43632|issue:44756", + "issue:45216|issue:45357", + "issue:36032|issue:43742", + "issue:44062|issue:44987", + "issue:42915|issue:44589", + "issue:44479|issue:45325", + "issue:43296|issue:43531", + "issue:43404|issue:45127", + "issue:43531|issue:44877", + "issue:36032|issue:41720", + "issue:40444|issue:45325", + "issue:43611|issue:44534", + "issue:43425|issue:44403", + "issue:43632|issue:44534", + "issue:41553|issue:43582" + ], + "prepared_review_unit_hash": "19c3dc1c7459266af054a56bea1389f7f7e801d8f86169a4d197eeefd109a3b9", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "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": "The cluster is a loose collection of mostly unrelated Transformers bug reports, with a strong but not exact concentration around v5 model-loading/serialization regressions. None of the soft pairs look like the same concrete bug, so I rejected all of them.", + "confidence": 0.57, + "canonical_issue_reason": "Issue 43611 is the broadest, most central representative of the repeated v5 loading/initialization regressions in this set, even though the cluster overall is heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43611 is the best issue anchor because it describes a general v5 compatibility break rather than a single model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Different failures: a template compilation error versus an invalid method call in GraniteMoEHybrid. Same framework area, not the same bug." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Both are model-loading issues, but one is a missing attribute on Molmo and the other is a tokenizer loading failure for a specific model. No concrete shared code path." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio chat-template sampling-rate default and MIMI batched-vs-single output mismatch are unrelated defects." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook custom model initialization breakage and non-persistent buffer corruption are different v5 regressions." + }, + { + "left": "issue:43089", + "right": "issue:45987", + "accept": false, + "reason": "Generation performance overhead and a cache API type-contract bug are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization failure versus non-persistent buffer junk values; not the same underlying bug." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both involve tied weights/serialization, but one is a missing tie in Mistral3 conditional generation and the other is inconsistent lm_head serialization by device. Similar theme, different defect." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Segfault on Llava Next loading and a Qwen3OmniMoe video-processing ValueError are distinct multimodal issues." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Noise while loading transformers and a Mistral regex patch crash are not the same failure mode." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different model families and different symptoms: bad AutoModel/pipeline outputs for SigLIP2 versus incorrect processor image size for OmDet-Turbo." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "FP8 config failure for Qwen3Moe and template-node compilation error are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI padding-mask batching mismatch and DAC STE mismatch are different audio-model bugs." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export with torch_compilable_check and OmDet-Turbo image-size mismatch are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "ScandiBERT loading failure and Mistral regex patch crash are different tokenizer/model-loading issues." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Physical-Intelligence/fast loading regression and Mistral regex patch crash are not the same code-path problem." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "_torch_extract_fbank_features() and compiled flex_attention on torch>=2.9 concern different subsystems." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3Moe FP8 failure and init_empty_weights/_is_hf_initialized argument mismatch are different initialization bugs." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized breakage and mmap OOM avoidance on Strix Halo are unrelated." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen3.5 save_pretrained regressions, but one is generic checkpoint correctness and the other is specifically incorrect visual encoder keys. Similar area, not clearly one bug." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "Tokenizer method-name conflict and MobileLLM key error are different loading failures." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken special-flag duplication and physical-intelligence/fast loading failure are unrelated tokenizer/model issues." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "FP8 config failure and missing Float8 storage type are different Torch/version compatibility problems." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Video-input regression across several Qwen models and still-image rope-index scaling in Qwen2.5-VL are different multimodal bugs." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL loading failure in vLLM and Qwen3-MoE sliding_window behavior are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both touch tied embeddings, but one is missing lm_head tying and the other is LoRA merge collapse with extended vocabulary. Not the same concrete bug." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window and granite_speech strict-config loading are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "T5 tokenizer add_special_tokens conflict and Qwen3 auto device mapping cuda assert are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Multiple-images IterableDataset failure and Qwen2.5-VL temporal position scaling are different multimodal training/inference bugs." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 regressions, but one is a base_model_prefix loading break and the other is junk-filled non-persistent buffers. Same release, different defect." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch 2.10 incompatibility and noisy loading logs are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "_is_hf_initialized flag handling and non-persistent buffer corruption are different v5 breakages." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error for Voxtral and AppleSilicon caching_allocator_warmup TypeError 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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:33666", + "issue:35707", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43381", + "issue:43421", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43749", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:43957", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44811", + "issue:44829", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45542", + "issue:45663", + "issue:45812", + "issue:45923" + ], + "soft_pairs": [ + "issue:40990|issue:44811", + "issue:43792|issue:44589", + "issue:44079|issue:45663", + "issue:44683|issue:45020", + "issue:33666|issue:40444", + "issue:44403|issue:44991", + "issue:43421|issue:44568", + "issue:43381|issue:45923", + "issue:35707|issue:40444", + "issue:44462|issue:45812", + "issue:44291|issue:44589", + "issue:43482|issue:45538", + "issue:42175|issue:45542", + "issue:44829|issue:45479", + "issue:43317|issue:43856", + "issue:43482|issue:43525", + "issue:44079|issue:44534", + "issue:43818|issue:45357", + "issue:43531|issue:44291", + "issue:41720|issue:45081", + "issue:43377|issue:45491", + "issue:44265|issue:45072", + "issue:40444|issue:45381", + "issue:43644|issue:44079", + "issue:43749|issue:44079", + "issue:42175|issue:43296", + "issue:43632|issue:45072", + "issue:45325|issue:45381", + "issue:43611|issue:43646", + "issue:43792|issue:43957" + ], + "prepared_review_unit_hash": "da05d36dd29e3de7b5e8e2e0561e8b33d3961116e68242e06bbbeffeefdbe930", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36899, + "estimated_input_tokens": 9225, + "estimated_eval_tokens": 18706 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of distinct Transformers/v5 regressions and model-specific loading/training bugs, not a tight duplicate set. Only one soft pair looks like the same underlying Qwen2.5-VL position-id bug.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45020 is the broadest umbrella in the set ('Recent transformers versions break models using `remote_code`') and best represents the overall v5 regression theme across multiple model-loading failures.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most suitable cluster representative because it is the broadest, most reusable description of the loading/regression class, even though many other items are more specific manifestations.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Different models and failures: perplexity on GPT-OSS vs Whisper batch_decode special-token handling." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Unrelated symptoms: Whisper runtime failure vs missing Float8 storage type." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "Different code paths: ModelOutput key assignment vs Gemma4 attention shared_kv_states rebuild." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Different layers: torch>=2.9 flex_attention compilation vs remote_code model loading regressions." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both are Qwen2-VL/Qwen2.5-VL related, but one is multi-GPU training and the other is iterable dataset handling with multiple images per prompt." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "One is generic loading noise, the other is a specific tokenizer loading regression for EMBEDDIA/est-roberta." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both involve tokenizers, but one is runtime post-processor updates and the other is add_special_tokens/BOS-EOS behavior for a specific tokenizer." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "Eval-mode gradient checkpointing error is not the same as a missing supports_gradient_checkpointing flag on a remote-code model." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen2.5-VL iterable-dataset multi-image finetuning." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both are AutoTokenizer regressions, but one is ignoring tokenizer.json while the other is wrong token IDs for Granite models; too different to merge confidently." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized argument breakage is separate from the Float8 storage lookup failure." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading in Transformers v5 is unrelated to CLIPTokenizer max_length semantics." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both mention TF/backend packaging, but one is missing TensorFlow in a torch extra and the other is a tensorboard-only undefined backend error." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "FlashAttention-3 training degeneration is not the same bug as single-label classification with num_labels=1 yielding zero loss." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Device-map/offload loading failure is distinct from Qwen3 MoE memory inefficiency during training." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Different model-loading regressions: GGUF/Transformers v5 vs Llama4Config missing pad_token_id." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key bookkeeping is unrelated to non-persistent buffer initialization." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA architecture/weights issue is separate from Qwen3.5 save_pretrained visual-encoder key regression." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to init_empty_weights argument handling." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 auto device-map CUDA assert is unrelated to Mistral tokenizer regex patch crashing." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "MIMI padding-mask mismatch and Gemma3 mixed-length NaNs are both batching issues but appear to be different mechanisms and models." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export/compilable_check failure is not the same as bfloat16 dtype mismatches in inference." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal Qwen2.5-VL issues, but one is dataset finetuning with multiple images and the other is video position-id calculation." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk and ModelOutput key assignment are different object-state bugs." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM efficient loading regression is unrelated to ModelOutput field handling." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Packaging/backend omission in a torch install extra is not the same as PaddleOCR-VL loading failure in vLLM." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized regression and bfloat16 dtype mismatch are different Transformers v5 issues." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": true, + "reason": "Same Qwen2.5-VL position-id/rope-index code path; one reports still-image temporal scaling, the other video input vision_position_ids being wrong." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are Transformers v5 init/load regressions, but one is base_model_prefix loading and the other is custom model initialization; not clearly the same bug." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper model runtime failure is not the same as meta-device loading breakage affecting other models." + }, + { + "left": "issue:45020", + "right": "issue:45381", + "accept": false, + "reason": "Remote-code loading regressions and Qwen2.5-VL video position IDs are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The cluster is indeed heterogeneous, and the lone accepted Qwen2.5-VL position-id pair is the only clearly mergeable one. The choice of issue:45020 as a broad umbrella is defensible given the repeated v5/remote-code loading regressions in the set." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 11, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "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:43322", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43701", + "issue:43746", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43994", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44568", + "issue:44610", + "issue:44877", + "issue:44898", + "issue:45072", + "issue:45325", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45834", + "issue:45920", + "issue:45923", + "issue:46050" + ], + "soft_pairs": [ + "issue:45325|issue:45834", + "issue:43994|issue:44898", + "issue:43454|issue:44466", + "issue:42915|issue:43482", + "issue:43296|issue:45800", + "issue:44479|issue:45823", + "issue:43701|issue:45325", + "issue:44291|issue:44877", + "issue:43881|issue:44488", + "issue:43606|issue:44265", + "issue:43873|issue:45701", + "issue:43262|issue:43746", + "issue:40990|issue:45584", + "issue:34634|issue:35707", + "issue:44568|issue:45920", + "issue:35707|issue:41720", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:41720|issue:45823", + "issue:43454|issue:43550", + "issue:39692|issue:40444", + "issue:43377|issue:44610", + "issue:43454|issue:45072", + "issue:43572|issue:45759", + "issue:43257|issue:45923", + "issue:43377|issue:44898", + "issue:43317|issue:43873", + "issue:40990|issue:42947", + "issue:43526|issue:43883", + "issue:43322|issue:46050" + ], + "prepared_review_unit_hash": "ad4a78dd2a4e8475ab64e94a47d8bd6eec8dace9b4f2f9a3a8c5551a308b5e99", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36827, + "estimated_input_tokens": 9207, + "estimated_eval_tokens": 18670 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of semantically similar but non-duplicate bug reports spanning different models and code paths. The soft pairs share broad themes like loading, offloading, quantization, or tied weights, but they are not the same underlying bug/change, so none should be merged.", + "confidence": 0.95, + "canonical_issue_reason": "issue:43873 is the broadest umbrella candidate (offloading + quantization) among the items, but the cluster is too heterogeneous for a true canonical duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best cluster representative because it is the most general and central of the few offloading/quantization reports, though it still does not subsume the rest.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Different models and different failures: Qwen2.5-VL rope-index scaling vs Kosmos2.5 OCR length/index error." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Both are vision-related, but they describe different models and bugs: SigLIP2 inference mismatch vs Perceiver resolution/interpolation failure." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied weights/lm_head, but one is an AyaVision model bug and the other is a v5 serialization inconsistency; not the same code-path problem." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Different quantization/loading issues on different model families (Qwen3Moe FP8 vs Qwen2.5-GGUF v5 load failure)." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "Unrelated compatibility reports: PaddleOCR-VL loading in vLLM vs a torch/transformers version incompatibility." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Both involve multimodal/device behavior, but one is a video-input regression and the other is a Gemma4 PLE device mismatch." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to Qwen2.5-VL rope-index scaling." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Both are loading/config issues, but one is an init_empty_weights API break and the other is strict config validation for granite_speech." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different models and symptoms: glm-4v-9b load failure vs cjvt/sleng-bert load failure." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch in Bark is unrelated to torch.export failures in torch_compilable_check models." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Offloading/quantization behavior is unrelated to a tokenizer-version regression." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting is unrelated to GraniteSpeech PEFT checkpoint loading." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "Different tasks and bugs: perplexity on gpt-oss-20b vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "Bark voice_preset and progressive generation with inputs_embeds/past_key_values are different code paths." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "A specific BOS/EOS tokenizer bug is not the same as the broader AutoTokenizer wrong-IDs regression." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation failure is unrelated to Qwen3 auto device mapping cudaErrorAssert." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer crashes on NER/padding are unrelated to torch.export failures with torch_compilable_check." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Both are model-specific runtime bugs, but Bark CPU offload mismatch and DAC.from_latents STE mismatch are different problems." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Both involve device_map auto, but the model families and failure modes differ (cudaErrorAssert vs forward device mismatch)." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "AyaVision tied-weights issue is unrelated to Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Documentation/example errors for SigLIP2 are unrelated to Qwen2.5-VL multi-image finetuning failure." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "MIMI padding-mask batch mismatch is unrelated to OmDet-Turbo image-size mismatch." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Different subsystems: tied lm_head weights vs dtype mismatch in bfloat16 inference." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to composite Qwen config unwrapping." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate/deepspeed is unrelated to a missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "MIMI encoder padding-mask issue is unrelated to Perceiver non-default-resolution interpolation behavior." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both mention offload/quantization, but one is dequantized-model loading on gpu+cpu offload and the other is a broader offloading regression." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity on a benchmark is unrelated to gradient checkpointing not taking effect with PEFT LoRA." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction is unrelated to Molmo missing all_tied_weights_keys." + }, + { + "left": "issue:43322", + "right": "issue:46050", + "accept": false, + "reason": "Llava Next loading segfault and sinq save/load quantization breakage are distinct failure modes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 12, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36010", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43296", + "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: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:43881|issue:44991", + "issue:43454|issue:43720", + "issue:41720|issue:43322", + "issue:43296|issue:44877", + "issue:43749|issue:44534", + "issue:44466|issue:45357", + "issue:41720|issue:44977", + "issue:42617|issue:42915", + "issue:40990|issue:45701", + "issue:44387|issue:45704", + "issue:44008|issue:45823", + "issue:36331|issue:42617", + "issue:44186|issue:45072", + "issue:43577|issue:43708", + "issue:44877|issue:44991", + "issue:36331|issue:42915", + "issue:43404|issue:45357", + "issue:43450|issue:45701", + "issue:43550|issue:43720", + "issue:43873|issue:44756", + "issue:44423|issue:45406", + "issue:41720|issue:42617", + "issue:45632|issue:45684", + "issue:44479|issue:44918", + "issue:43550|issue:43606", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:42915|issue:43317", + "issue:43295|issue:45701", + "issue:43526|issue:43881", + "issue:41720|issue:45161", + "issue:36010|issue:42617", + "issue:44671|issue:44743" + ], + "prepared_review_unit_hash": "d6844e82e0aa3a14bfac0af6512ac07876fde015f299440df4e1d88bb226d1ac", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37121, + "estimated_input_tokens": 9281, + "estimated_eval_tokens": 18818 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of unrelated Transformers issues with only superficial overlap around loading, offloading, and model-specific regressions. I did not find any soft pair that looks like the same underlying bug or change, so all soft edges are rejected.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43873 is the best cluster anchor: it is a broad, currently open infrastructure bug about offloading/quantization with strong discussion and inbound-reference signals, while most other items are narrower model-specific regressions or API breakages.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the most representative and actionable issue in this set because it captures a broad class of loading/offloading failures and has the strongest evidence of ongoing impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Both are loading failures, but one is a GLM model load problem and the other is a tokenizer loading regression for a specific repo; no sign of the same bug." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different code paths: tied lm_head weights in a multimodal model vs packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Both crash during model use/loading, but they involve different models and different failure modes (cuda assert vs segfault)." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "One is a vLLM/PaddleOCR-VL loading failure, the other is strict config validation blocking granite_speech; these are unrelated." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "Both touch loading/serialization, but one is FSDP CPU RAM-efficient loading and the other is non-persistent buffer initialization; not the same bug." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both are save_pretrained regressions, but one is tied lm_head serialization varying by device and the other is incorrect visual encoder keys for Qwen3.5." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Auto device-map CUDA failure and flash-attention generation issues are different bugs in different execution paths." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "One is a script/runtime failure for 3d_parallel.py; the other is a model/config-specific FineGrainedFP8 failure." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Tokenizer/version-related reasoning is too broad here; one reports high perplexity on a model/dataset, the other a general tokenization change across versions." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Both mention memory, but one is CUDA reserved-memory growth under int4 quantization and the other is an apex FusedRMSNorm leak in T5." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Different Gemma model families and different symptoms: variable name collision vs device-mapping mismatch." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Trainer compute_loss signature breakage is unrelated to the 3d_parallel.py execution problem." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crash on NER/batched padding is unrelated to bfloat16 dtype mismatches in inference." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "Blip2 dtype loading bug and Trainer max_steps resume calculation are separate concerns." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config validation for granite_speech is not the same as tokenizer loading for EMBEDDIA/est-roberta." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Trainer API incompatibility and FineGrainedFP8 model failure do not share the same underlying bug." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Weight-tying bug in Mistral3 and incorrect visual encoder keys in Qwen3.5 are different save/serialization defects." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video processor shape handling and tokenization-version changes are unrelated issues." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile with SDPA on Bamba-9B-v2 is a different code path from packed-weight loading in BitNet." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both involve memory/offload concerns, but one is quantization/offloading correctness and the other is a Strix Halo mmap OOM workaround." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both crash in serve/multimodal scenarios, but they fail in different processor paths with different missing attributes." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collisions for local trust_remote_code models and read-only permission propagation during save_pretrained are unrelated filesystem issues." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "A video-input regression across Qwen VL models is not the same as TRL SFT embedding unpacking failure." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Different model families and distinct causes: compile/SDPA failure versus CPU-offload device mismatch." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both are image preprocessing/resolution bugs, but the affected models and mechanism differ enough that they do not look like one bug." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer crash on NER inputs and processor output-size mismatch are separate issues." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "FineGrainedFP8 model failure and dequantized model loading with cpu offload are not the same underlying defect." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Processor/tokenizer regression in v4.57.5 is not the same as a broad tokenization-change report." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "Label-reduction logic in BeitImageProcessorFast is unrelated to a GLM model loading failure." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Auto device-map CUDA assert and GPT-OSS MoE tensor-parallel failure are different distributed/inference problems." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to the 3d_parallel.py runtime failure." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM prediction regression and Qwen3.5 recurrent-state reset with cache are different model-specific 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": 13, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:29159", + "issue:30064", + "issue:33357", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36032", + "issue:36331", + "issue:41720", + "issue:42490", + "issue:42915", + "issue:43316", + "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:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44625", + "issue:44898", + "issue:44913", + "issue:44991", + "issue:45059", + "issue:45072", + "issue:45081", + "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:43316|issue:44913", + "issue:43540|issue:43782", + "issue:42915|issue:43322", + "issue:44186|issue:44361", + "issue:43421|issue:45812", + "issue:36331|issue:41720", + "issue:29159|issue:36032", + "issue:43388|issue:45059", + "issue:45406|issue:45464", + "issue:30064|issue:34634", + "issue:33357|issue:35707", + "issue:43606|issue:43720", + "issue:43550|issue:43653", + "issue:41720|issue:43746", + "issue:43873|issue:45704", + "issue:43421|issue:45701", + "issue:43606|issue:43653", + "issue:43531|issue:45759", + "issue:34634|issue:41720", + "issue:42490|issue:43329", + "issue:44492|issue:44509", + "issue:34567|issue:35707", + "issue:44514|issue:44545", + "issue:44625|issue:45479", + "issue:43421|issue:43927", + "issue:44898|issue:45072", + "issue:44451|issue:44991" + ], + "prepared_review_unit_hash": "08eb5397ce4e9e7ffffae1b8ca8d68e1c74cb9d05ec3221f4611af875c1c0bd2", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36630, + "estimated_input_tokens": 9158, + "estimated_eval_tokens": 18572 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Only one soft pair is a true duplicate: the two Qwen2_5_VLProcessor.apply_chat_template crashes are the same bug. All other pairs are related at a broad subsystem level but describe different failures, models, or code paths, so they should stay separate.", + "confidence": 0.97, + "canonical_issue_reason": "issue:44514 is the best canonical issue: it is the earlier, more complete report for the exact same batched-input/padding=False crash, while issue:44545 is a near-verbatim duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44514 is the strongest representative overall because it has the same concrete failure mode as issue:44545 and appears to be the primary report that the later issue duplicates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenizer regressions, but they are different bugs: Mistral regex patching vs Granite token ID corruption." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different models and different config issues; one is sliding_window handling, the other is missing pad_token_idx after v5." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Both are config-serialization discrepancies, but they affect different fields and model families." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Different Qwen multimodal failures with different inputs and error modes; not the same underlying bug." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Different loading/runtime failures in different architectures; one is FP8 config, the other is Llava Next segfault." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Tokenizer crashes on different models and tasks; not one shared defect." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Both concern tokenizer behavior after special-token changes, but one is runtime post-processor refresh and the other is a Granite token-ID regression." + }, + { + "left": "issue:36331", + "right": "issue:41720", + "accept": false, + "reason": "Unrelated failures: Trainer custom loss signature vs Qwen3 device-mapping cuda assert." + }, + { + "left": "issue:29159", + "right": "issue:36032", + "accept": false, + "reason": "Different tokenizer problems: slow/fast inconsistency versus T5 tokenizer load-time method conflict." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Different subsystems and symptoms; metric-gathering label trimming is not related to SAM3 PCS text/bbox behavior." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Different runtime paths and models: Gemma4Processor missing _tokenizer vs Qwen3.5 streaming chat/completions failure." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Different processor bugs affecting different modalities; segmentation-map handling is unrelated to Bark voice_preset." + }, + { + "left": "issue:33357", + "right": "issue:35707", + "accept": false, + "reason": "Completely different issues: MacOS bus error on CLIP vs generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both are CI/offload-related, but one is a CPU-offload device mismatch and the other is packed-weight unpacking in accelerate loading." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Different bugs in different areas: torch.compile/SDPA vs tokenizer special-token registration." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Different loading problems: auto device mapping crash vs PEFT adapter local-checkpoint loading." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Different features and failure modes: quantization offloading vs T5/apex RMSNorm memory leak." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "One is a specific TokenizersBackend post-processor update bug; the other is a broader tokenization-version-change report." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Different bug classes: offload device mismatch vs tokenizer special-token decode behavior." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Different model/config issues; sliding_window in Qwen3-MoE is unrelated to AutoModelForCausalLM unwrapping text_config in Qwen 3.5/3.6." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "Different symptom and subsystem: BarkProcessor voice_preset vs Qwen3 auto device mapping crash." + }, + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "Both involve loading-related behavior, but one is path parsing/import warning and the other is a multimodal token-counting bug." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "Unrelated docs/typo issues: cache strategy typo vs pipeline docs mentioning removed tasks." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token-count tracking is unrelated to progressive generation with inputs_embeds and past_key_values." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same exact crash report: Qwen2_5_VLProcessor.apply_chat_template fails on batched input when padding=False; 44545 is a duplicate of 44514." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Different classification bugs: config propagation in Qwen3.5 vs degenerate zero loss across sequence-classification models." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Both are tokenizer/config state issues, but one is post-processor refresh and the other is DiaConfig persistence of custom token IDs." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Different model/runtime failures: Perceiver non-default resolution vs dtype mismatch in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer load failures for different models; no evidence of the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative on the soft-edge pairs. The accepted duplicate pair, issue:44514/issue:44545, is strongly supported by matching titles and closely aligned failure descriptions, with 44514 appearing to be the earlier and fuller report. I don\u2019t see any overstatement in the other pair judgments based on the provided 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": 14, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:39692", + "issue:40444", + "issue:41720", + "issue:42886", + "issue:43381", + "issue:43421", + "issue:43531", + "issue:43596", + "issue:43645", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43819", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44368", + "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:45356", + "issue:45357", + "issue:45381", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45859", + "issue:45907", + "issue:45923", + "issue:46050" + ], + "soft_pairs": [ + "issue:45759|issue:45859", + "issue:44077|issue:44625", + "issue:43531|issue:44589", + "issue:43782|issue:45381", + "issue:44987|issue:45042", + "issue:45588|issue:45759", + "issue:44062|issue:44451", + "issue:44368|issue:45357", + "issue:39692|issue:44610", + "issue:43746|issue:46050", + "issue:44918|issue:44936", + "issue:45704|issue:45923", + "issue:43421|issue:43653", + "issue:45663|issue:45923", + "issue:43381|issue:43844", + "issue:42886|issue:44843", + "issue:45704|issue:45859", + "issue:43531|issue:43645", + "issue:41720|issue:45704", + "issue:43421|issue:44186", + "issue:43994|issue:44671", + "issue:43746|issue:43873", + "issue:39692|issue:43873", + "issue:45081|issue:45356", + "issue:43596|issue:44220", + "issue:40444|issue:43746", + "issue:45356|issue:45907", + "issue:30064|issue:36010", + "issue:43720|issue:43819", + "issue:44220|issue:44661", + "issue:43653|issue:43720" + ], + "prepared_review_unit_hash": "0067a6f5ed62946114e3b99c12f3a10c08c63da3b58aa98e5b2e2adaba0ef8f0", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36772, + "estimated_input_tokens": 9193, + "estimated_eval_tokens": 18642 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No duplicates or mergeable equivalents stand out here. The soft pairs mostly share broad areas like tokenizers, multimodal models, offloading, or training, but each describes a different concrete failure mode or root cause, so all edges should be rejected.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Different bugs: one is config unwrapping for composite Qwen multimodal models, the other is CPU offload incompatibility in rotary embedding forward." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Unrelated failures: optional post_init policy in patchtsmixer vs num_labels propagation in Qwen3.5 config." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Different subsystems and symptoms: Qwen3-MoE sliding window handling vs missing Float8 storage type on load." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen/VL-related, but one is a weight_only loading error and the other is a video vision_position_ids bug; not the same defect." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Separate problems: loading a specific model fails vs PIL image processors incorrectly requiring torchvision." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Different code paths: flash_attention sink-less s_aux handling vs from_config not unwrapping text_config." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "No shared bug: AddedToken keyword duplication error vs a model loading failure for ScandiBERT." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "Distinct Qwen issues: warning about tie_word_embeddings vs incorrect visual encoder keys during save_pretrained." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Different model/docs problems: SigLIP2 example errors vs OmDet-Turbo processor/model input-size mismatch." + }, + { + "left": "issue:43746", + "right": "issue:46050", + "accept": false, + "reason": "Not the same issue: local PEFT checkpoint loading for GraniteSpeech vs quantized sinq save/load corruption." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different failures: SFT trainer input embedding unpacking vs trainer.evaluate() breaking after train()." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "Unrelated: apex FusedRMSNorm memory leak in T5 vs missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Different tokenizer bugs: runtime special-token post-processor refresh vs BigBird mask token registration/decode output." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Distinct issues: FSDP2 shared_kv_states rebuilding per layer vs trust_remote_code gradient-checkpointing flag missing." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Both involve training behavior, but one is eval-mode gradient checkpointing support and the other is gradient explosion under ZeRO-3." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Related to offline tokenizer loading, but not the same bug: one is generic cache/offline failure, the other is a specific _patch_mistral_regex model_info call." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "Different models and symptoms: memory leak from fused norm use vs CPU offload incompatibility in Qwen rotary embedding." + }, + { + "left": "issue:43531", + "right": "issue:43645", + "accept": false, + "reason": "Distinct regressions: sliding_window handling in Qwen3-MoE vs Jupyter custom model definition/initialization in Transformers 5." + }, + { + "left": "issue:41720", + "right": "issue:45704", + "accept": false, + "reason": "No overlap beyond being model-runtime bugs: cudaErrorAssert on Qwen3 auto device mapping vs T5 fused RMSNorm memory leak." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Different tokenizer paths: special-token post-processor update issue vs LayoutLMv2Tokenizer crashes on NER/padding." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Separate model correctness bugs: SigLIP2 AutoModel/pipeline output regression vs CamemBERT masked LM predictions in v5." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "Different areas: PEFT local checkpoint loading vs quantization/offloading behavior." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "One is a documentation/example mismatch, the other is a quantization offloading issue; not the same bug." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both touch mistral regex logic, but one is a crash on fix_mistral_regex and the other is a Kimi tokenizer regression with codec handling/warning." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Different runtime errors in different components: ZeRO-3/BertModel indexing vs audio fbank feature extraction." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "Unrelated multimodal training failure vs local checkpoint loading with PEFT adapters." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Completely different: tokenizer regression vs hub API list_repo_files not forwarding revision." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Different domains entirely: image processor segmentation-map handling vs GenerationMixin import error." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Separate bugs: packed BitNet weights not unpacked on accelerate load vs DAC.from_latents not matching forward pass without STE." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Different code paths: torch fbank feature extraction vs add-new-model-like failing inside TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "No shared underlying defect: BigBird special-token decode bug vs BitNet packed-weight loading." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 15, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:30064", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43950", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44442", + "issue:44448", + "issue:44488", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45183", + "issue:45381", + "issue:45479", + "issue:45584", + "issue:45685", + "issue:45834", + "issue:45987", + "issue:46032" + ], + "soft_pairs": [ + "issue:43540|issue:44008", + "issue:43618|issue:43697", + "issue:43550|issue:45072", + "issue:45183|issue:45479", + "issue:43295|issue:45834", + "issue:43550|issue:43819", + "issue:43388|issue:46032", + "issue:44062|issue:44488", + "issue:43716|issue:44008", + "issue:43335|issue:43756", + "issue:43322|issue:45685", + "issue:44186|issue:44898", + "issue:43653|issue:43819", + "issue:43531|issue:43643", + "issue:43950|issue:45987", + "issue:43643|issue:44877", + "issue:44843|issue:45081", + "issue:30064|issue:36331", + "issue:43540|issue:45381", + "issue:44448|issue:44671", + "issue:43421|issue:44811", + "issue:41720|issue:44991", + "issue:39692|issue:45834", + "issue:43577|issue:43818", + "issue:43782|issue:44977", + "issue:44821|issue:45084", + "issue:45584|issue:45834", + "issue:44186|issue:44442" + ], + "prepared_review_unit_hash": "17ca86f12c6443af6d5748b803825e884b962b795653e5cfb7be2b99641f824e", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36510, + "estimated_input_tokens": 9128, + "estimated_eval_tokens": 18512 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose grab-bag of unrelated Transformers issues across tokenizers, multimodal models, generation, and cache logic. None of the soft pairs looks like the same concrete bug; the closest is the two Mistral regex issues, but they describe different failure modes.", + "confidence": 0.93, + "canonical_issue_reason": "No strong canonical issue: the items are heterogeneous and do not form a single duplicate set. If one must be chosen as an anchor, issue 44843 is the closest because it is the most specific and directly tied to the Mistral tokenizer patch path.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44843 is the best representative only in a weak sense: it is specific, reproducible, and the only item in a near-related soft pair, but it still does not unify the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Different models and failure modes: Qwen3OmniMoe video input validation vs Gemma 3n attribute collision in forward()." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Both are regressions, but on different models/code paths: CLIP attentions assignment vs RTDetrV2 output drift." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Unrelated bugs: torch.compile+SDPA on Bamba vs dtype mismatch in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Different core problems: input validation XOR logic vs degenerate single-label classification loss." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "One is a processor/tokenizer regression; the other is a long-ocr index error in Kosmos2.5." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Different models and bugs: SDPA/compile failure vs DAC forward/from_latents mismatch." + }, + { + "left": "issue:43388", + "right": "issue:46032", + "accept": false, + "reason": "Different training/runtime paths: gather_for_metrics batching vs Mamba2 cache correctness." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "Both involve tokenizer loading, but one is an AddedToken keyword conflict and the other is a model-specific load failure." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different subsystems: dtype mismatch in image preprocessing vs Gemma 3n audio mask name collision." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Distinct model/config bugs: sparse-layer construction vs RoPE layer dropping." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "No shared code path: Llava Next loading segfault vs MPS histogram not implemented for Int." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "Different model families and symptoms: LayoutLMv2 tokenizer crashes vs Perceiver interpolation failure." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Tokenizer special-token registration bug vs DAC STE mismatch; unrelated." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Different areas: Qwen3-MoE sliding window vs AutoConfig trust_remote_code field loss." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Both are cache/state-related regressions, but one corrupts non-persistent buffers and the other violates get_seq_length return type." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both are config-loading issues, but they concern different mechanisms and model families." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both mention _patch_mistral_regex, but the failures differ: offline model_info access vs missing backend_tokenizer attribute." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Completely unrelated: image segmentation-map processing vs CustomTrainer loss signature mismatch." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen variants, but the bugs are different: video input handling vs flash-attention generation behavior." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Separate model regressions with different outputs and different tasks: summarization vs masked LM." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Related to tokenization/special tokens in a broad sense, but the concrete bugs are different: runtime post-processor refresh vs Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Unrelated failures: Qwen3 device-mapping cuda assert vs tokenizer load failure for est-roberta." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "Different multimodal/documentation issues: SigLIP2 example problems vs Kosmos2.5 OCR index error." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Different model loading bugs: BLIP2 dtype propagation vs Video-LLaVA video_tower/temporal-attention issue." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Different Qwen model families and failures: weight_only load error vs flash-attention generation problem." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "No shared underlying bug: AutoImageProcessor-from-URL loading vs template-node compilation error." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Different input domains and failure modes: Whisper empty transcription after token alignment vs Kosmos2.5 long OCR index error." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer bugs affecting different models and APIs; not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 16, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:28218", + "issue:29159", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:42175", + "issue:43262", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43644", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:43994", + "issue:44060", + "issue:44291", + "issue:44368", + "issue:44479", + "issue:44485", + "issue:44509", + "issue:44554", + "issue:44561", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45406", + "issue:45701", + "issue:45834", + "issue:45987", + "issue:46192", + "issue:46209" + ], + "soft_pairs": [ + "issue:43644|issue:43749", + "issue:43606|issue:45072", + "issue:44479|issue:45834", + "issue:44561|issue:45020", + "issue:34634|issue:36010", + "issue:43577|issue:43582", + "issue:43825|issue:43994", + "issue:44805|issue:44936", + "issue:45987|issue:46192", + "issue:44671|issue:45701", + "issue:44485|issue:44509", + "issue:44610|issue:45072", + "issue:28218|issue:29159", + "issue:43720|issue:45072", + "issue:43825|issue:43827", + "issue:43782|issue:45325", + "issue:43906|issue:46209", + "issue:42175|issue:45081", + "issue:43749|issue:44291", + "issue:43582|issue:44857", + "issue:45081|issue:45406", + "issue:43262|issue:43819", + "issue:34634|issue:36331", + "issue:43526|issue:43697", + "issue:43650|issue:43906", + "issue:44060|issue:44368", + "issue:43653|issue:44912", + "issue:43742|issue:45020", + "issue:43526|issue:44554" + ], + "prepared_review_unit_hash": "15a17dbba50b445dff34ac4f6c746368c730b9a88e82671d3935e780e1100d6a", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36600, + "estimated_input_tokens": 9150, + "estimated_eval_tokens": 18556 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue mix; only the tokenizer added-token spacing reports look like the same underlying bug. The rest are similar at a subsystem level but not concrete duplicates.", + "confidence": 0.78, + "canonical_issue_reason": "issue:28218 is the clearest concrete report of the tokenizer added-token spacing bug, and it best matches the one plausible duplicate in the set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:28218 is the strongest representative issue: specific, self-contained, and directly tied to the duplicate tokenizer behavior.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both concern model/loading behavior, but one is about non-persistent buffer initialization and the other about FSDP CPU RAM efficient loading; not the same bug." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Different models and failures: CPU offload device mismatch vs bfloat16 dtype mismatch. Same broad inference area, not the same issue." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Both are multimodal input bugs, but they affect different models and different failure modes." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "issue:44561 is a specific trust_remote_code regression from a removed helper; issue:45020 is a broad umbrella report. Related, but not the same concrete bug." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "One is a BarkProcessor preset bug, the other an import error for GenerationMixin; no duplicate evidence." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Different domains: BLIP2 dtype loading vs Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "One is a v5 pipeline error-message mismatch; the other is a bad AutoModel/pipeline result for a specific model. Not the same bug." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Generic index-shape error vs trainer evaluate-after-train failure; too little concrete overlap to treat as duplicate." + }, + { + "left": "issue:45987", + "right": "issue:46192", + "accept": false, + "reason": "One is a StaticCache return-type contract bug, the other silently ignores return_tensors when text_kwargs is passed." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT masked-LM regression and a general tokenization-version complaint are not the same code-path problem." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "One discusses GLM-5 RoPE implementation, the other stale docs about removed pipeline tasks." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Different processors/models and different defects: input-size mismatch vs dtype mismatch." + }, + { + "left": "issue:28218", + "right": "issue:29159", + "accept": true, + "reason": "Both describe the same tokenizer added-token spacing inconsistency, with slow/fast tokenizer behavior and an extra space after added tokens." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "BitNet packed-weight loading failure is unrelated to dtype mismatch issues in other models." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Both mention v5 pipeline removals, but one is an error-message issue and the other is stale docs; different artifacts and fixes." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen-VL bugs: weight_only loading error vs still-image temporal position scaling." + }, + { + "left": "issue:43906", + "right": "issue:46209", + "accept": false, + "reason": "A reproduction of an older issue is not the same bug as an FP8/B200 inference failure." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Packaging/backend selection issue vs tokenizer regex patch crash; unrelated." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both are loading-related, but one is FSDP CPU RAM efficient loading and the other is init_empty_weights argument handling; distinct failures." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon warmup TypeError and CUDA AMP float16 crash are different platform-specific bugs." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Tokenizer regex patch crash and Gemma4Processor missing _tokenizer are separate component bugs." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and DAC latent reconstruction mismatch are unrelated." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "Processor voice_preset failure and CustomTrainer compute_loss signature mismatch do not describe the same defect." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Different vision bugs: label reduction returning one label vs RTDetrV2 output drift in v5." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "No meaningful overlap; one is an empty placeholder title, the other a reproduction issue." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both involve Qwen tie-word-embedding warnings, but one is a wrong tied-weights mapping bug and the other is a user-facing warning during LoRA fine-tuning." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer special-token registration and MXFP4 quantization loading are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "A specific MobileLLM load key error is not the same underlying problem as a broad remote_code regression." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and MPS attention correctness are different issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded and appropriately conservative. The summary stays within the packet evidence, and the only accepted soft-edge pair is plausibly the same tokenizer spacing bug based on the issue titles. The other pairings are correctly rejected as subsystem-level similarities rather than clear duplicates." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "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:43696", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:44387", + "issue:44479", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44617", + "issue:44756", + "issue:44811", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45042", + "issue:45084", + "issue:45356", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45759", + "issue:45803", + "issue:45859" + ], + "soft_pairs": [ + "issue:45084|issue:45538", + "issue:43329|issue:45600", + "issue:44589|issue:45042", + "issue:43638|issue:44936", + "issue:43746|issue:44811", + "issue:43452|issue:44991", + "issue:44387|issue:44617", + "issue:43550|issue:44912", + "issue:36010|issue:43645", + "issue:43819|issue:43927", + "issue:43257|issue:43329", + "issue:43854|issue:44977", + "issue:39692|issue:44912", + "issue:38175|issue:44610", + "issue:43720|issue:44610", + "issue:45459|issue:45803", + "issue:36010|issue:36331", + "issue:43454|issue:43577", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43329|issue:44479", + "issue:43257|issue:43696", + "issue:42490|issue:43257", + "issue:43643|issue:45759", + "issue:43606|issue:45859", + "issue:43329|issue:43450", + "issue:43749|issue:44756", + "issue:34567|issue:40990", + "issue:44568|issue:45356" + ], + "prepared_review_unit_hash": "fb0fadd3e3b2d7fa119080baef4663f42585049a6f58372a1750cae28223fc3a", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36622, + "estimated_input_tokens": 9156, + "estimated_eval_tokens": 18568 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated Transformer issue reports with a few thematically similar pairs. Only the Qwen video-input regression pair looks like the same underlying bug; no PRs are present.", + "confidence": 0.61, + "canonical_issue_reason": "issue:43329 is the clearest root-cause report in the set: it names the broken video branch in `_get_num_multimodal_tokens` and affects multiple VLM processors.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43329 is the best representative because it describes a concrete, centralized multimodal-video code-path bug with broad downstream impact.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Different problems: compilation/template-node errors vs tokenizer max-length behavior." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Unrelated subsystems: multimodal video token counting vs stale auto_mappings references." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Different failure modes: missing Float8 storage vs image processor torchvision dependency." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Training/DeepSpeed index error is not the same as evaluate-after-train state failure." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Different APIs and bugs: PEFT local checkpoint loading vs Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both concern loading, but different entrypoints and concrete regressions; not the same bug." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both mention OOM, but one is quantization-memory regression and the other is a model-specific memory limit issue." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "Different model/code-path failures: torch.compile+SDPA vs MXFP4 load fallback." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to Jupyter custom-model initialization breakage." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "Unrelated bugs: DAC forward/from_latents mismatch vs config fields lost after save/load." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Different loading/dispatch paths: Qwen3-MoE weight conversion vs multimodal token counting." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Different models and symptoms; both are generation-related but not the same concrete bug." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "SigLIP2 doc-example failures are unrelated to gpt-oss MXFP4 loading." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Different vision-model issues: zero probabilities vs processor output shape/input-size mismatch." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Accelerate packed-weight unpacking bug is unrelated to OmDet processor size mismatch." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both hide errors with exceptions, but they are different functions and different root causes." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Import-time GenerationMixin failure is unrelated to custom compute_loss keyword regression." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "Different multimodal model bugs: lm_head tying vs dtype propagation for BLIP2." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to PIL backend torchvision requirements." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Different audio processor methods and symptoms; not the same bug." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": true, + "reason": "Both point to the same broken video-input path in Qwen multimodal processors; 44479 reads like the broader v5.3.0 manifestation of the helper bug in 43329." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Qwen3-MoE loading/conversion is unrelated to GPT-oss OOM." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Local-path import warning with trailing slash is unrelated to Qwen3-MoE accelerate/deepspeed weight conversion." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config handling, but different methods and failure modes; not the same underlying bug." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Both mention CPU offload/device handling, but they are model-specific issues in different code paths." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Video token counting bug is unrelated to batched video processor output shape." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Different memory-loading contexts: FSDP CPU RAM efficient loading vs mmap on Strix Halo." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer token counter bug is unrelated to GPT-oss perplexity." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and different tokenizer code paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft edge (43329/44479) is reasonably supported by the overlapping Qwen video-input regression context, and the other pair rejections do not overclaim sameness. No PRs are present, so there is no mergeability issue." + }, + "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": 18, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:29159", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:38175", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43452", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43697", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43782", + "issue:43824", + "issue:43927", + "issue:43931", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44568", + "issue:44821", + "issue:44849", + "issue:44898", + "issue:44912", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45137", + "issue:45357", + "issue:45381", + "issue:45405", + "issue:45488", + "issue:45538", + "issue:45701", + "issue:45907" + ], + "soft_pairs": [ + "issue:43257|issue:43931", + "issue:29159|issue:34567", + "issue:42915|issue:43742", + "issue:44291|issue:45042", + "issue:42915|issue:44821", + "issue:44849|issue:45701", + "issue:44568|issue:45488", + "issue:44987|issue:45538", + "issue:43452|issue:43582", + "issue:41720|issue:43540", + "issue:43697|issue:45357", + "issue:43927|issue:44912", + "issue:42915|issue:45538", + "issue:44479|issue:45381", + "issue:33357|issue:34567", + "issue:43540|issue:44479", + "issue:42175|issue:43824", + "issue:43540|issue:44560", + "issue:43317|issue:45538", + "issue:44062|issue:44991", + "issue:24643|issue:29159", + "issue:45137|issue:45405", + "issue:44987|issue:45907", + "issue:28282|issue:34689", + "issue:43577|issue:45072", + "issue:43742|issue:44291", + "issue:43257|issue:43756", + "issue:28282|issue:29127", + "issue:42175|issue:44488", + "issue:42915|issue:43749", + "issue:43582|issue:43782", + "issue:38175|issue:44898" + ], + "prepared_review_unit_hash": "427ab9fafce1a8b60dfd7648f4ae88d095bf249cdc3943a96d8a607f260c7cf7", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36692, + "estimated_input_tokens": 9173, + "estimated_eval_tokens": 18602 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues mostly share model-loading/tokenization language but describe different concrete failures. I did not find any soft pair that looks like the same underlying bug or change; they span distinct code paths such as DeepSpeed/FSDP loading, video preprocessing, tokenizer behavior, quantization, and model-specific config regressions.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45701 is the best umbrella-style issue in this set: it is broad, open, and explicitly about version-dependent tokenization changes, which makes it the closest thing to a cluster representative.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45701 is the strongest global representative because it is broad enough to subsume related tokenizer regressions, has active inbound references, and is phrased as a general behavioral regression rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Both are Qwen3/VL-related loading bugs, but one is about MoE weight conversion under accelerate+deepspeed and the other is a weight-shape mismatch for Qwen3-VL-30B-A3B-Instruct. Different failure modes and code paths." + }, + { + "left": "issue:29159", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer inconsistency vs TrainerState token-count tracking. Same broad area only at a high level, but unrelated bugs." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe fine-grained FP8 failure vs MobileLLM key error during model loading. Different models and different loading/quantization failures." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Init-empty-weights argument handling vs PIL backend requiring torchvision. Completely different subsystems." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "FP8 config failure vs AutoImageProcessor URL loading. Different functionality and error classes." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 output_hidden_states bug is a model-specific forward-pass regression, while 45701 is a broad tokenization/version-change complaint." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "mdeberta tokenizer add_special_tokens regression vs LlamaTokenizer overriding ByteLevel with Metaspace. Both tokenizer-related, but distinct tokenizer implementations and behaviors." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Loading a specific model fails vs CLIPTokenizer max length bug. Not the same issue." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "gguf_file breaks pretrained loading APIs vs Apple Silicon TypeError in caching_allocator_warmup. Unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Qwen3 auto device map cuda assert vs Qwen3OmniMoe video-input ValueError. Same family name, different concrete failure." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output mismatch in v5 vs Qwen3.5 save_pretrained saving wrong visual encoder keys. Different model behavior and different lifecycle stage." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig token IDs lost on save/load vs MXFP4 quantization fallback. Different models and unrelated bugs." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Qwen3Moe FP8 loading failure vs CLIPTokenizer model_max_length bug. No substantive overlap." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": false, + "reason": "Qwen2.5/Qwen3.5 video-input regression vs qwen2.5-vl vision_position_ids wrong. Related family, but one is a broad multi-model regression and the other is a specific positional-ID bug." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "MacOS bus error with community CLIP model vs TrainerState token counter bug. Different components and symptoms." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Qwen3OmniMoe video processing ValueError vs broader v5.3 video-input regression across several model families. Overlapping theme, but not the same concrete bug." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "TensorFlow missing from torch install vs import error for Qwen2_5_VLForConditionalGeneration. Dependency packaging vs symbol export/import issue." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Qwen3OmniMoe video ValueError vs Qwen3-vl-embedding StopIteration in 5.3.0. Different model and different exception path." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "device_map=auto dequantized model offload failure vs CLIPTokenizer max length bug. Different code paths." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "AddedToken special-argument collision vs tokenizer loading failure for est-roberta. Same area, but not the same bug." + }, + { + "left": "issue:24643", + "right": "issue:29159", + "accept": false, + "reason": "DeepSpeed training runtime error about weight dimensionality vs tokenizer slow/fast inconsistency. Unrelated." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error vs PEFT minimum version bump. Completely unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Model loading failure for physical-intelligence/fast vs list_repo_files not forwarding revision. Different APIs and failures." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Missing PyTorch ImportError for AutoModel vs Llama 3.2 90B Vision model loading regression. Both are load-time errors, but the causes are different." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Blip2 dtype staying float32 vs SwitchTransformers/TimmWrapperModel dtype mismatches in bf16 inference. Both dtype-related, but different models and symptoms." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "MobileLLM key error while loading a model vs init_empty_weights TypeError from unexpected internal argument. Not the same bug." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Qwen3 MoE weight conversion/loading issue vs Smollm3 RoPE layer count mismatch. Different model families and different bug types." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "PyTorch missing ImportError vs LayoutLMv3 box-information error message clarity. No duplicate signal." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Packaging dependency omission vs failure to load cjvt/sleng-bert. Different issues." + }, + { + "left": "issue:42915", + "right": "issue:43749", + "accept": false, + "reason": "Qwen3Moe FP8 failure vs FSDP_CPU_RAM_EFFICIENT_LOADING broken. Both involve advanced loading, but distinct mechanisms and models." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Apple Silicon warmup TypeError vs Qwen3VL weight_only=True error. Different backend and failure mode." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Unexpected zero probabilities in a specific model vs Perceiver non-default resolution failure. Separate model behaviors, 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": 19, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:24643", + "issue:29127", + "issue:34567", + "issue:36331", + "issue:41762", + "issue:43404", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43643", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43906", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44488", + "issue:44514", + "issue:44589", + "issue:44625", + "issue:44737", + "issue:44792", + "issue:44821", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44936", + "issue:44964", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45588", + "issue:45600", + "issue:45823", + "issue:45920", + "issue:45987", + "issue:46121", + "issue:46202" + ], + "soft_pairs": [ + "issue:44737|issue:45588", + "issue:43540|issue:45823", + "issue:43404|issue:45987", + "issue:43526|issue:45479", + "issue:43906|issue:45381", + "issue:43493|issue:43994", + "issue:34567|issue:36331", + "issue:44291|issue:44821", + "issue:43756|issue:45325", + "issue:44913|issue:46121", + "issue:44062|issue:45081", + "issue:44792|issue:44964", + "issue:45042|issue:45081", + "issue:45357|issue:45920", + "issue:43742|issue:44589", + "issue:43452|issue:44488", + "issue:43531|issue:44821", + "issue:43643|issue:45375", + "issue:45405|issue:45600", + "issue:44625|issue:44877", + "issue:24643|issue:29127", + "issue:43720|issue:44898", + "issue:43697|issue:45216", + "issue:43906|issue:46202", + "issue:41762|issue:44936", + "issue:44514|issue:45381" + ], + "prepared_review_unit_hash": "667db3c19375eec2524434462e643aecf3f81564776b50f3075753054ac4bd45", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 26, + "serialized_chars": 35941, + "estimated_input_tokens": 8986, + "estimated_eval_tokens": 18228 + }, + "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 different models/components. The only plausible duplicate pair is the SigLIP2 implementation mismatch vs. user-visible nonsensical outputs; everything else looks distinct and should stay separate.", + "confidence": 0.78, + "canonical_issue_reason": "No single canonical issue fits the whole cluster; if we need one anchor, issue 43493 is the best root-cause-style report for the only likely duplicate pair (SigLIP2).", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43493 is the clearest technical statement of the underlying bug, while 43994 reads more like a downstream symptom/reproduction on the same SigLIP2 path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "Unrelated problems: XLNet CPU rope indexing vs flash-attention aux-state crash." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Different models and failure modes: Qwen3OmniMoe video processing vs Gemma4 device-mapping mismatch." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "Different subsystems: Mistral3 weight tying vs StaticCache seq-length return type." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Unrelated image-label reduction bug vs sequence-classification loss degeneracy." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen/VL themes, but one is a reproduction of another issue and the other is a specific video position-id bug; not enough evidence of the same concrete defect." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Both point to the same SigLIP2 model correctness problem: HF/JAX discrepancy and broken/nonsensical outputs on the same model family." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Trainer state token counting and custom loss signature incompatibility are different bugs." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "Different areas: init_empty_weights/_is_hf_initialized loading path vs AutoImageProcessor URL loading." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Different models and different RoPE-related bugs." + }, + { + "left": "issue:44913", + "right": "issue:46121", + "accept": false, + "reason": "Config reload defaulting and rope-validation list handling are separate issues." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer AddedToken argument collision is unrelated to Mistral regex patching." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Both are multimodal-related, but one is a failing test and the other is a model-loading regression for a different model." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "Image processor torchvision dependency issue is unrelated to tokenizer regex crash." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Different regression classes: save_pretrained key serialization vs incorrect token IDs from AutoTokenizer." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "Different load failures: MobileLLM key error vs missing Float8 storage type." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading issues, but for different models and likely different code paths." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding window behavior and AutoImageProcessor URL loading are unrelated." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both mention missing config fields, but the former is a generic trust_remote_code AutoConfig issue and the latter is a model-specific @strict field drop; not clearly the same bug." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "Version-pin/release issue is unrelated to stale auto_mappings references." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "num_labels propagation and strict config loading are different configuration bugs." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed training RuntimeError and LayoutLMv3 error-message clarity are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight loading and Perceiver interpolation failure are different model-specific bugs." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "RTDetrV2 output drift and Qwen3.5 save_pretrained checkpoint corruption are unrelated regressions." + }, + { + "left": "issue:43906", + "right": "issue:46202", + "accept": false, + "reason": "No clear shared underlying defect; one is a reproduction of an older issue, the other is a Gemma pipeline roundtrip bug." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Gemma3 ZeRO-3 load failure and trainer.evaluate-after-train are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Same model family, but batched chat-template padding crash is a different code path from wrong video vision_position_ids." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall: the packet is heterogeneous, and the soft-edge rejections are mostly conservative given the available titles. The only accepted pair, issue:43493 / issue:43994, is a reasonable likely duplicate on the same SigLIP2 path based on the titles alone. Minor caveat: the cluster summary says \"closed issues\" even though a few items are open, but that does not materially affect the verdict." + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:28282", + "issue:29159", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:35141", + "issue:38175", + "issue:41720", + "issue:43295", + "issue:43452", + "issue:43531", + "issue:43577", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43742", + "issue:43749", + "issue:43819", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44484", + "issue:44493", + "issue:44514", + "issue:44568", + "issue:44704", + "issue:44743", + "issue:44811", + "issue:44843", + "issue:44936", + "issue:44991", + "issue:45005", + "issue:45290", + "issue:45356", + "issue:45372", + "issue:45440", + "issue:45542", + "issue:45701", + "issue:45704", + "issue:45823", + "issue:46050", + "issue:46170", + "issue:46178" + ], + "soft_pairs": [ + "issue:43688|issue:43749", + "issue:45372|issue:46170", + "issue:43452|issue:43577", + "issue:44466|issue:45005", + "issue:44493|issue:46050", + "issue:43819|issue:44811", + "issue:30064|issue:33666", + "issue:43452|issue:44843", + "issue:44936|issue:45823", + "issue:45542|issue:46178", + "issue:44484|issue:44704", + "issue:43295|issue:45356", + "issue:28282|issue:32090", + "issue:43653|issue:44361", + "issue:44361|issue:44442", + "issue:28282|issue:33357", + "issue:44514|issue:45290", + "issue:44464|issue:44743", + "issue:38175|issue:43295", + "issue:28282|issue:35141", + "issue:41720|issue:43906", + "issue:43653|issue:44568", + "issue:43577|issue:43697", + "issue:43688|issue:45704", + "issue:44843|issue:44991", + "issue:43646|issue:43749", + "issue:43531|issue:43742", + "issue:29159|issue:33357", + "issue:43688|issue:45440", + "issue:43688|issue:45701", + "issue:43653|issue:43927" + ], + "prepared_review_unit_hash": "413774f79871653359b4834ac934b7e853611d94b3f9b3e1aadc669efa9c5f7e", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37143, + "estimated_input_tokens": 9286, + "estimated_eval_tokens": 18828 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are distinct bugs across tokenization, loading, training, serialization, and backend detection. I would not merge any of the proposed soft edges as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 45701 is the broadest umbrella in the set, but the cluster is still too mixed to make it a safe duplicate canonical.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45701 is the best available anchor because it is broad, open, and about tokenizer/version regressions, but it still does not represent the unrelated training/loading/model-init failures in the rest of the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Auxiliary-loss normalization and FSDP CPU RAM loading are different bugs in different code paths." + }, + { + "left": "issue:45372", + "right": "issue:46170", + "accept": false, + "reason": "Both are import/dependency failures, but they involve different packages, platforms, and root causes." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "gguf_file loading and Blip2 dtype propagation are unrelated failures." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but one is device-dependent serialization and the other is a broader translation-model behavior report; not the same concrete bug." + }, + { + "left": "issue:44493", + "right": "issue:46050", + "accept": false, + "reason": "Unexpected position-id keys and sinq quantization save/load breakage are different issues." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC latent mismatch and Whisper batch_decode skip_special_tokens are unrelated code paths." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Void segmentation map processing and Qwen2-VL multi-GPU training are different problems." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file loading and offline mistral-regex patch behavior are separate tokenizer/model-loading bugs." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "trainer.evaluate() after train and Gemma4 device-map mismatch are unrelated training/runtime issues." + }, + { + "left": "issue:45542", + "right": "issue:46178", + "accept": false, + "reason": "These are different backend-detection/import problems involving different dependencies." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "max_shard_size documentation/behavior and cached_file kwargs forwarding are not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Processor/tokenizer regression and Kimi-K2.5 codec handling are distinct tokenizer issues." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "Missing PyTorch import and NoneType broadcast errors are unrelated failures." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "BigBird special-token registration and MLukeTokenizer AttributeError are different tokenizer bugs." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "These are different tokenizer-loading failures for different models." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "PyTorch import error and Mac bus error on CLIP are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both are chat-template crashes, but they hit different inputs and failure modes, so they are not clearly the same bug." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Compiled chunked generation inconsistency and Qwen3 modular recurrent-state reset are different generation bugs." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Siglip2 zero probabilities and processor.tokenizer regression are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "Missing PyTorch import and output-embedding reinitialization after resize are different issues." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "A device-map cudaErrorAssert and a reproduction issue are not the same concrete bug." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both involve special tokens, but they affect different tokenizers and different mechanics." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Blip2 dtype propagation and RTDetrV2 output divergence are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Auxiliary-loss normalization and T5 apex RMSNorm memory leak are unrelated." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Offline model_info call in the mistral regex patch and tokenizer load failure for est-roberta have different root causes." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Custom model initialization breakage and FSDP CPU RAM loading are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and MobileLLM-125M key errors are different model-specific bugs." + }, + { + "left": "issue:29159", + "right": "issue:33357", + "accept": false, + "reason": "Slow/fast tokenizer inconsistency and MacOS bus error are not the same failure." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Auxiliary-loss normalization and DeepSeekV3 MoE divergence are unrelated model bugs." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "A specific auxiliary-loss bug and a broad tokenization-regression report do not match the same underlying issue." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "BigBird special-token registration and DiaConfig save/load token-ID loss are different persistence/tokenizer 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": 21, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:28218", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43643", + "issue:43688", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43825", + "issue:43927", + "issue:43994", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44479", + "issue:44554", + "issue:44561", + "issue:44610", + "issue:44625", + "issue:44821", + "issue:44849", + "issue:44913", + "issue:44977", + "issue:45491", + "issue:45588", + "issue:45823", + "issue:46002", + "issue:46050", + "issue:46192", + "issue:46209" + ], + "soft_pairs": [ + "issue:45491|issue:46002", + "issue:43550|issue:43927", + "issue:44464|issue:44977", + "issue:43643|issue:44561", + "issue:43550|issue:44361", + "issue:44479|issue:44625", + "issue:41720|issue:44464", + "issue:44977|issue:46209", + "issue:43577|issue:45588", + "issue:32090|issue:34567", + "issue:43577|issue:44554", + "issue:43504|issue:43550", + "issue:43504|issue:43720", + "issue:43504|issue:44610", + "issue:32090|issue:33666", + "issue:44466|issue:46050", + "issue:33666|issue:36010", + "issue:43742|issue:44821", + "issue:43720|issue:43927", + "issue:45823|issue:46050", + "issue:43606|issue:43927", + "issue:43452|issue:44451", + "issue:43262|issue:43295", + "issue:44849|issue:46209", + "issue:43278|issue:43688", + "issue:43994|issue:46192", + "issue:43525|issue:43572", + "issue:33666|issue:36331", + "issue:43720|issue:44361", + "issue:43756|issue:44913", + "issue:44625|issue:46002", + "issue:43493|issue:43825", + "issue:28218|issue:33357" + ], + "prepared_review_unit_hash": "d9f3e1583510069040ed682b12a2b78559e6b25b19b19eb45e423a4ec2ebc44a", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37046, + "estimated_input_tokens": 9262, + "estimated_eval_tokens": 18780 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is not a cohesive duplicate cluster: the issues span unrelated bugs across training, loading, config serialization, multimodal processors, attention kernels, and model-specific regressions. The soft-similarity pairs mostly share only broad keywords, not the same concrete code path.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43550 is the strongest standalone report here: it names a specific model, a concrete failure mode (torch.compile with SDPA), and a plausible single code path to fix.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45491", + "right": "issue:46002", + "accept": false, + "reason": "Both mention NaNs, but one is Gemma3 sliding-window attention on GPU and the other is classification-head NaNs after checkout/init; different symptoms and likely different causes." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "One is a Bamba torch.compile/SDPA failure; the other is a DiaConfig save/load field-loss bug. No shared code path." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both affect generation, but one is chunked generation with compiled forward and the other is Qwen3.5 flash-attention inference. Too broad to merge." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both involve trust_remote_code-adjacent behavior, but one is missing fields in AutoConfig output and the other is a v5 API removal breaking remote-code models. Different fixes." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Completely different models and failures: SDPA/compile versus tokenizer AttributeError on tasks." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is a video-input regression and the other is num_labels propagation into text config." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "A CUDA assert in Qwen3 auto device mapping is unrelated to chunked generation output inconsistency under compiled forward." + }, + { + "left": "issue:44977", + "right": "issue:46209", + "accept": false, + "reason": "Both are inference bugs, but one is flash-attention behavior in Qwen3.5 and the other is FP8 inference on B200; different paths." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "One is dtype drift in BLIP2 loading, the other is a flash_attention integration crash on s_aux=None; unrelated." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast TypeError and TrainerState token-count tracking are separate training bugs." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype mismatch and an MPS attention correctness issue are different subsystems and failure modes." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Beit legacy-field loading and Bamba compile/SDPA are unrelated model-specific bugs." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Legacy config-field loading for Beit is not the same as BitNet packed-weight handling during accelerate loading." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Beit pretrained-load failure and OmDet processor/model size mismatch are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Both mention training/multi-GPU, but one is a broadcast TypeError and the other is a Qwen2-VL multi-GPU training setup issue." + }, + { + "left": "issue:44466", + "right": "issue:46050", + "accept": false, + "reason": "Serialization of tied lm_head weights and sinq quantization save/load breakage are both persistence bugs, but not the same concrete bug." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and a GenerationMixin import error are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "MobileLLM loading key error and AutoImageProcessor-from-URL failure are different loading paths." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "BitNet packed-weight unpacking and DiaConfig custom-token-ID loss are unrelated save/load bugs." + }, + { + "left": "issue:45823", + "right": "issue:46050", + "accept": false, + "reason": "Gemma4 device-map mismatch during forward and sinq quantized model persistence are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU-offload device mismatch in bark-small and DiaConfig field loss after save/load are not the same bug." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "GGUF loading failures for AutoTokenizer/AutoModel and a specific model load failure are too different to merge." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting and a processor.tokenizer/image-input regression are both processor issues but different code paths." + }, + { + "left": "issue:44849", + "right": "issue:46209", + "accept": false, + "reason": "Qwen3.5 hidden-states bug and FP8 inference failure on B200 are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Embedding dtype drift during evaluate and incorrect auxiliary-loss normalization are unrelated model-train bugs." + }, + { + "left": "issue:43994", + "right": "issue:46192", + "accept": false, + "reason": "SigLIP2 bad outputs and return_tensors being ignored when text_kwargs is passed are unrelated." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both are config padding-token attribute issues, but for different model configs and different missing-field names; not a single concrete bug." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and CustomTrainer.compute_loss signature breakage are different training issues." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet loading/unpacking and MLukeTokenizer task AttributeError are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch and GPTNeoXConfig rotary_pct reload regression are both config-related, but not the same underlying bug." + }, + { + "left": "issue:44625", + "right": "issue:46002", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and classification-head NaNs are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and a pipeline translation error-message issue are not the same bug." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer added-space behavior and a MacOS bus error in CLIP loading are completely unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 22, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:33357", + "issue:33666", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43927", + "issue:43994", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44464", + "issue:44466", + "issue:44488", + "issue:44493", + "issue:44568", + "issue:44589", + "issue:44734", + "issue:44792", + "issue:44843", + "issue:44849", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45357", + "issue:45405", + "issue:45520", + "issue:45584", + "issue:45759", + "issue:45812", + "issue:45823" + ], + "soft_pairs": [ + "issue:44964|issue:45405", + "issue:44849|issue:45357", + "issue:39692|issue:43493", + "issue:44568|issue:45812", + "issue:43540|issue:44977", + "issue:43334|issue:43572", + "issue:44488|issue:44843", + "issue:45200|issue:45229", + "issue:43493|issue:43844", + "issue:43278|issue:43844", + "issue:43334|issue:45759", + "issue:39692|issue:43295", + "issue:43756|issue:45083", + "issue:43257|issue:43299", + "issue:43646|issue:44466", + "issue:43824|issue:44589", + "issue:33357|issue:33666", + "issue:43504|issue:43606", + "issue:45229|issue:45823", + "issue:43927|issue:44361", + "issue:44589|issue:45520", + "issue:43572|issue:44291", + "issue:44464|issue:45584", + "issue:43278|issue:43701", + "issue:43606|issue:44112", + "issue:43504|issue:43653", + "issue:43575|issue:45405", + "issue:44792|issue:45405", + "issue:43994|issue:44493", + "issue:44423|issue:44734" + ], + "prepared_review_unit_hash": "1a7faf2eb776ce19006563196a7bcfb8e73f4f804bf6c9603a4d8eeb6b27e605", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36912, + "estimated_input_tokens": 9228, + "estimated_eval_tokens": 18712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a loose, heterogeneous cluster of mostly Transformers v5 regression reports across unrelated model families (Qwen, Gemma, SigLIP, tokenizer/config loading, serving, and CI). Based on the titles alone, none of the soft-edge pairs look like the same concrete bug or change.", + "confidence": 0.69, + "canonical_issue_reason": "Issue 43646 is the broadest representative of the recurring \"v5 breaks model initialization/loading\" theme, but the cluster is too mixed to treat any single issue as a true canonical duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43646 is the best global representative because it most directly captures the common regression pattern seen across several nearby reports, even though the cluster is not a single bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Different problems: one is a model-load failure for Phi-4 multimodal, the other is a dependency/version bump issue for PEFT." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Both involve Qwen3.5, but one is about output_hidden_states behavior and the other about save_pretrained writing wrong visual encoder keys; not the same bug path." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "SigLIP2 docs/example errors are not the same as a model-vs-JAX implementation discrepancy." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both concern tokenizer special-token behavior, but one is about mdeberta add_special_tokens and the other is a Granite token-ID regression; too different to merge." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Both are Qwen3.5-family issues, but one is a video-input ValueError in Qwen3OmniMoe and the other is flash-attention generation quality; different concrete failures." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both are config attribute-missing regressions, but they affect different configs and fields (pad_token_id vs pad_token_idx) with no evidence of one underlying bug." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "sleng-bert load failure and HF_HUB_OFFLINE/Mistral regex patch are unrelated code paths." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "One is a missing default for mm_token_type_ids, the other is a multi-GPU CUDA OOM; not the same bug." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch and a ZeRO-3 gradient increase issue are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift and gradient explosion under DeepSpeed are different training bugs." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3-VL pad_token_id missing and AutoModelForCausalLM not unwrapping text_config are distinct model-loading issues." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "SigLIP2 example/documentation errors do not match the processor.tokenizer regression in custom model code." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "RoPE-layer count mismatch and a helper-function length calculation issue in qwen3_omni_moe are not the same defect." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both mention Qwen3 MoE loading, but one is about accelerate/deepspeed weight conversion and the other is a broader Qwen3VL MoE load failure; insufficient evidence of one code-path bug." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Both are v5-related, but one is custom model initialization and the other is lm_head.weight serialization depending on device; not the same change." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Qwen2.5-VL import error and Float8 storage lookup failure are unrelated." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS bus error in CLIP and Qwen2-VL multi-GPU training are completely different issues." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "BEiT legacy-field loading and bark-small CPU offload device mismatch are unrelated." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4 issues, but one is CUDA OOM during inference and the other is a PLE device mismatch during forward; different bugs." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig losing token IDs after save/load and MLukeTokenizer task AttributeError are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage-object lookup and flash_attn import KeyError are different failure modes." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "StableLmConfig missing pad_token_idx and init_empty_weights receiving an unexpected argument are separate compatibility regressions." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Chunked generation with compiled forward and Whisper empty-transcription generation after align_special_tokens are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "Embedding dtype drift in eval and resume_from_checkpoint key mismatch are different problems." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "CPU offload device mismatch and a stale GraniteSpeech CI test are not the same underlying bug." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "BEiT legacy-field loading and BigBirdTokenizer special-token registration are unrelated." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "Qwen2 large-model TP OOM and a PEFT version bump issue do not share the same code path." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A janus test failure and a dependency version bump are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 wrong outputs with AutoModel/pipeline and unexpected position-id keys are different serialization/loading issues." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Serve crashes with multimodal models and KV-cache continuation tensor indexing are both serving bugs, but the concrete failure modes are distinct." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29159", + "issue:29942", + "issue:30333", + "issue:32090", + "issue:34567", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:42490", + "issue:43232", + "issue:43295", + "issue:43450", + "issue:43493", + "issue:43540", + "issue:43572", + "issue:43582", + "issue:43696", + "issue:43701", + "issue:43824", + "issue:43844", + "issue:43873", + "issue:43957", + "issue:44186", + "issue:44521", + "issue:44554", + "issue:44610", + "issue:44849", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45084", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45356", + "issue:45381", + "issue:45406", + "issue:45446", + "issue:45520", + "issue:45588", + "issue:45823", + "issue:46050", + "issue:46121", + "issue:46192", + "issue:46209" + ], + "soft_pairs": [ + "issue:43873|issue:46050", + "issue:29942|issue:30333", + "issue:45406|issue:46121", + "issue:45588|issue:46050", + "issue:42490|issue:43696", + "issue:43844|issue:44964", + "issue:28218|issue:34567", + "issue:29159|issue:32090", + "issue:44521|issue:45290", + "issue:43582|issue:44977", + "issue:44554|issue:45446", + "issue:45084|issue:45520", + "issue:15354|issue:38175", + "issue:43540|issue:45200", + "issue:45200|issue:45823", + "issue:45072|issue:45198", + "issue:37428|issue:43957", + "issue:43232|issue:44849", + "issue:44186|issue:46192", + "issue:43493|issue:43701", + "issue:45381|issue:46209", + "issue:45823|issue:46192", + "issue:43295|issue:43450", + "issue:43295|issue:44610", + "issue:43572|issue:44987", + "issue:44554|issue:45356", + "issue:43572|issue:43957", + "issue:37428|issue:43824", + "issue:39692|issue:46192" + ], + "prepared_review_unit_hash": "fb0168e1e8442db267d917e8de506a97b472f4317f0247e63831a13615ff8eb9", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36426, + "estimated_input_tokens": 9107, + "estimated_eval_tokens": 18470 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is noisy and mostly spans separate transformers bugs around tokenization/processor APIs, multimodal chat templating, generation, quantization, and model loading. None of the soft pairs look like true duplicates; the closest subtheme is apply_chat_template / multimodal tokenization.", + "confidence": 0.34, + "canonical_issue_reason": "issue:44521 is the best cluster anchor because it is a clearly reproduced, user-facing multimodal chat-template/tokenization bug and is the closest semantic match to another soft candidate (45290), while the other items are more peripheral or unrelated.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the strongest standalone representative of the cluster\u2019s recurring tokenizer/processor surface area, with direct impact, active discussion, and the broadest overlap to the nearby chat-template regression reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43873", + "right": "issue:46050", + "accept": false, + "reason": "Both involve quantization, but one is about offloading behavior and the other about save/load corruption; not the same bug." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Unrelated failures: Flash Attention 2 tests vs MLFlow reporting after a failed training job." + }, + { + "left": "issue:45406", + "right": "issue:46121", + "accept": false, + "reason": "Different code paths: Gemma4Processor/_tokenizer regression vs rope-validation TypeError." + }, + { + "left": "issue:45588", + "right": "issue:46050", + "accept": false, + "reason": "AttributeError in flash_attention sinkless models is unrelated to quantized model save/load breakage." + }, + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Local-path import warning and CUDA OOM are unrelated." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "Different problems: ZeRO-3 gradient growth vs a model loading failure for Phi-4-multimodal-instruct." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing bug and TrainerState token count tracking are different features." + }, + { + "left": "issue:29159", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer consistency issue vs trainer broadcast NoneType error are unrelated." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Same general apply_chat_template area, but different failure modes: assistant masks vs crash on tool-call messages with no content." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator TypeError and Qwen3.5 flash-attention generation bug are not the same bug." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness vs PyTorch version gating for AuxRequest import are different issues." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Template compilation TypeError and flash_attn import KeyError are unrelated." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "JIT scripting/export limitation and zero-probabilities on SigLIP2 are different bugs." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing error in Qwen3OmniMoe vs Gemma4 mm_token_type_ids defaulting issue." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4-related, but one is missing token-type defaults and the other is a device mismatch in forward." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "Different subsystems and symptoms: dtype mismatch in inference vs save_pretrained/tokenization failure." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Flash-attention import error and meta-device loading breakage are separate runtime issues." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to the Qwen3.5 output_hidden_states bug." + }, + { + "left": "issue:44186", + "right": "issue:46192", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash on NER/padding is not the same as return_tensors being ignored when text_kwargs is passed." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and resume_from_checkpoint key mismatch do not share the same code path." + }, + { + "left": "issue:45381", + "right": "issue:46209", + "accept": false, + "reason": "Wrong video vision_position_ids in Qwen2.5-VL is unrelated to FP8 inference failure on B200." + }, + { + "left": "issue:45823", + "right": "issue:46192", + "accept": false, + "reason": "Gemma4 device placement mismatch and return_tensors precedence bug are different issues." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor.tokenizer regression/passing images to tokenizer and batched video shape errors are distinct multimodal bugs." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "These are both processor/model mismatches, but they affect different models and different failure modes." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Missing pad_token_idx in config and a model-loading regression for physical-intelligence/fast are unrelated." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness issue and Kimi-K2.5 tokenizer regression are not the same bug." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Config default regression and meta-device loading failures are different problems." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "flash_attention_utils import error and Qwen2_5_VL import error are separate import regressions." + }, + { + "left": "issue:39692", + "right": "issue:46192", + "accept": false, + "reason": "SigLIP2 docs/example errors and a generic return_tensors precedence 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": 24, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:28218", + "issue:35141", + "issue:38175", + "issue:41720", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43388", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43653", + "issue:43819", + "issue:43824", + "issue:43827", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43901", + "issue:43975", + "issue:44112", + "issue:44206", + "issue:44442", + "issue:44466", + "issue:44514", + "issue:44521", + "issue:44610", + "issue:44792", + "issue:44857", + "issue:44898", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45325", + "issue:45412", + "issue:45520", + "issue:45563", + "issue:45584", + "issue:46170", + "issue:46178", + "issue:46192", + "issue:46209" + ], + "soft_pairs": [ + "issue:45200|issue:45325", + "issue:45520|issue:46178", + "issue:43295|issue:43873", + "issue:43550|issue:43844", + "issue:44898|issue:45412", + "issue:44466|issue:45127", + "issue:43334|issue:43525", + "issue:43450|issue:43575", + "issue:44792|issue:45563", + "issue:43824|issue:43975", + "issue:41720|issue:46209", + "issue:42915|issue:43824", + "issue:43388|issue:43526", + "issue:42490|issue:43493", + "issue:43278|issue:43856", + "issue:28218|issue:35141", + "issue:43653|issue:44112", + "issue:38175|issue:43493", + "issue:43526|issue:46192", + "issue:43975|issue:45520", + "issue:44442|issue:45198", + "issue:38175|issue:45412", + "issue:44514|issue:44521", + "issue:45520|issue:46170", + "issue:43262|issue:43450", + "issue:44206|issue:45584", + "issue:43819|issue:44112", + "issue:43827|issue:43901", + "issue:44610|issue:44857" + ], + "prepared_review_unit_hash": "3df6e8d5b52176db8fbe94b0e645a12a82145efa868c4954d5a7cf2a6e1fc256", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36620, + "estimated_input_tokens": 9155, + "estimated_eval_tokens": 18566 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous single-issue reports rather than a true duplicate set. None of the soft pairs look like the same concrete bug/change, so I would not merge any of them.", + "confidence": 0.69, + "canonical_issue_reason": "Issue 44521 is the most representative issue here: it has the strongest activity/attention and is the closest to the only nearby Qwen2.5-VL processor/chat-template candidate.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44521 is the best overall representative of the cluster because it is active, user-facing, and sits in the clearest adjacent area to one other item in the set (`apply_chat_template`/multimodal processor behavior).", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Different bugs: Gemma 4 multimodal token-type IDs vs Qwen2.5-VL still-image rope/position scaling." + }, + { + "left": "issue:45520", + "right": "issue:46178", + "accept": false, + "reason": "Unrelated import/backend failures in different code paths: `flash_attn` on Python 3.13 vs `tensorflow_text` backend mapping." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor regression around `processor.tokenizer`/image passing is unrelated to quantization offloading behavior." + }, + { + "left": "issue:43550", + "right": "issue:43844", + "accept": false, + "reason": "Different failure modes: `torch.compile` + SDPA on Bamba vs DeepSpeed ZeRO-3 gradient growth." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "One is a Perceiver resolution/interpolation bug; the other is a memory release/GC issue for RT-DETR." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both involve tied weights, but one is device-dependent serialization of `lm_head.weight`; the other is LoRA merge collapse with extended vocab." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Same symptom class (`pad_token_id` missing) but different models/config paths; not the same concrete bug." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batched video processor shape bug is unrelated to Qwen2-57B tensor-parallel OOM." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Different subsystems: Janus image-generation test failure vs stale paged-generate warning." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "ImportError for Qwen2.5-VL class is unrelated to DeepSeek detokenization regression." + }, + { + "left": "issue:41720", + "right": "issue:46209", + "accept": false, + "reason": "Both are hardware-related inference failures, but they affect different models and different failure mechanisms." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3Moe FP8 failure is unrelated to the missing Qwen2.5-VL import." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both are label-processing issues, but one is `gather_for_metrics` dropping tuple labels and the other is `reduce_labels` returning only one label." + }, + { + "left": "issue:42490", + "right": "issue:43493", + "accept": false, + "reason": "Trailing-slash import warning and SigLIP2 implementation discrepancy are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype regression in evaluation is not the same as MoE training memory inefficiency." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing after added token and embedding reinitialization after resize are different bugs." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug is unrelated to a GraniteSpeech CI device-override test failure." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Both mention SigLIP2, but one reports zero probabilities and the other a broader HF-vs-JAX discrepancy; not enough to treat as the same bug." + }, + { + "left": "issue:43526", + "right": "issue:46192", + "accept": false, + "reason": "Different API bugs: `reduce_labels` truncation vs `return_tensors` being ignored when `text_kwargs` is passed." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization regression and `flash_attn` import error are unrelated." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different speech-model failures: tokenizer loading vs save_pretrained/tokenization failure." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both are Qwen2.5-VL `apply_chat_template` issues, but one is a batching/padding crash and the other is incorrect all-zero assistant masks; not the same concrete bug." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sample-rate default bug is unrelated to video processor batched-shape output." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC latent/forward mismatch is unrelated to the GraniteSpeech CI test flake." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs-related, but one is about removed `pipeline()` references and the other about `return_all_scores`; different content." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor output resolution mismatch and AMP/CUDA loss crash are different bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 25, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:39692", + "issue:42490", + "issue:43278", + "issue:43335", + "issue:43425", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43825", + "issue:43854", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44351", + "issue:44360", + "issue:44448", + "issue:44493", + "issue:44561", + "issue:44743", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:45072", + "issue:45083", + "issue:45127", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859", + "issue:45920", + "issue:46192" + ], + "soft_pairs": [ + "issue:43819|issue:45083", + "issue:37428|issue:43425", + "issue:43335|issue:43550", + "issue:43606|issue:45083", + "issue:44857|issue:45593", + "issue:29942|issue:32090", + "issue:44448|issue:44743", + "issue:45127|issue:45245", + "issue:37428|issue:44351", + "issue:45290|issue:45381", + "issue:45200|issue:45588", + "issue:43335|issue:43653", + "issue:43611|issue:43931", + "issue:44206|issue:45823", + "issue:43550|issue:44112", + "issue:43819|issue:44493", + "issue:43278|issue:43825", + "issue:44855|issue:45083", + "issue:43335|issue:43504", + "issue:45588|issue:45859", + "issue:29127|issue:32090", + "issue:43335|issue:45083", + "issue:39692|issue:43526", + "issue:39692|issue:44493", + "issue:45310|issue:45478", + "issue:43720|issue:44112", + "issue:43335|issue:44112", + "issue:43335|issue:45072", + "issue:44448|issue:44779", + "issue:44360|issue:44561", + "issue:42490|issue:43854", + "issue:45920|issue:46192", + "issue:43606|issue:44857", + "issue:34689|issue:35141" + ], + "prepared_review_unit_hash": "48cf2da9cc5e96143b088fcb8becdaee0e06116e9e243412dd54a9c3cd249034", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 38091, + "estimated_input_tokens": 9523, + "estimated_eval_tokens": 19302 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated issues; the only clear duplicate pair is the Qwen3.5 MoE from_pretrained regression. I would keep the earlier report as canonical.", + "confidence": 0.95, + "canonical_issue_reason": "Issue 45310 is the earlier report of the same Qwen3.5 MoE from_pretrained failure as 45478, with identical title and the same concrete regression.", + "canonical_pr_reason": null, + "best_issue_reason": "45310 is the best issue to keep as the canonical representative because it is the first report of the duplicated Qwen3.5 MoE loading bug and already captures the core failure mode.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "Different models and failures: DAC latent decoding/STE mismatch vs a Qwen3-Omni helper length computation issue." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "One is an import error for a flash-attention helper; the other is a broad Torch 2.10 compatibility issue." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and Bamba torch.compile/SDPA failure are unrelated code paths." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch in Bark-small is unrelated to the Qwen3-Omni output-length helper bug." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "Float16 AMP crash in LwDetrImageLoss is not the same bug as D-FINE skipping auxiliary losses." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and a Trainer NoneType broadcast error are different failures." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output differences and Qwen3 recurrent-state reset are separate model-specific regressions." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA/vocab merge collapse and category-count overflow are unrelated problems." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import-related, but they concern different missing symbols and different breakages." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Chat-template tool-call crash and Qwen2.5-VL vision position-id bug are unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 text-only mm_token_type_ids handling and flash_attention sink-less s_aux handling are different code paths." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config and BigBirdTokenizer special-token registration are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "base_model_prefix loading breakage and Qwen3-VL weight-shape mismatch are different model-loading issues." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Unsupported center arg in an audio feature extractor is unrelated to Gemma4 PLE device mismatch." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure and GraniteSpeech stale device-override test are not the same bug." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC STE mismatch and unexpected position-id keys are different symptoms and code paths." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift in evaluate and a pipeline translation-task warning are unrelated regressions." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "DebertaV2 Python 3.13 import parsing error and Qwen3-Omni helper behavior are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation bug and BEiT legacy-field loading bug are not the same issue." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both touch offload/attention-adjacent logic, but they fail in different modules with different root causes." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and Trainer broadcast TypeError are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers sparse-layer config and Qwen3-Omni feature-length helper are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 doc/example problems and BeitImageProcessorFast label reduction are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "Documentation/model-processor mismatch and unexpected position-id keys are different issues." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same title, same model family, same from_pretrained regression, and both describe the same loading failure." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight loading and GraniteSpeech CI device-override failures are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "SwitchTransformers config bug and GraniteSpeech CI failure do not share a concrete root cause." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and bfloat16 dtype mismatch in inference are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output change and DeepSeek tokenizer regression are different model-specific v5 regressions." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer activation discussion and removal of is_torch_fx_available breakage are not the same bug." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Local-path trailing-slash import warning and GLM-4.7-Flash unit-test loading failure are unrelated." + }, + { + "left": "issue:45920", + "right": "issue:46192", + "accept": false, + "reason": "Tokenizer ID regressions across many models and return_tensors being ignored with explicit text_kwargs are different issues." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch and float16 AMP loss crash are different failure modes." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Llama 3.2 Vision model-loading breakage and post_init reinitializing tied embeddings are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the only clearly supported duplicate pair is issue:45310 and issue:45478, which share the same title and the same Qwen3.5 MoE from_pretrained regression. The soft-edge verdicts are conservative and stay within the evidence provided, mostly rejecting pairs as unrelated without overclaiming. 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": 26, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:10000", + "issue:15354", + "issue:28218", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:40444", + "issue:41720", + "issue:42490", + "issue:43278", + "issue:43329", + "issue:43381", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43701", + "issue:43723", + "issue:43746", + "issue:43873", + "issue:43927", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44554", + "issue:44561", + "issue:44568", + "issue:44779", + "issue:44857", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45372", + "issue:45406", + "issue:45491", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45803", + "issue:45823", + "issue:46209" + ], + "soft_pairs": [ + "issue:38175|issue:44493", + "issue:44977|issue:45229", + "issue:44857|issue:45072", + "issue:43746|issue:46209", + "issue:44448|issue:44977", + "issue:40444|issue:43526", + "issue:28218|issue:32090", + "issue:43701|issue:45083", + "issue:32090|issue:33357", + "issue:29942|issue:35141", + "issue:43550|issue:45083", + "issue:43723|issue:44554", + "issue:37428|issue:44987", + "issue:44561|issue:44779", + "issue:43873|issue:45229", + "issue:43927|issue:45698", + "issue:44462|issue:44561", + "issue:43278|issue:43329", + "issue:42490|issue:43575", + "issue:10000|issue:15354", + "issue:41720|issue:45229", + "issue:44977|issue:45563", + "issue:45372|issue:45588", + "issue:44568|issue:45491", + "issue:44857|issue:45588", + "issue:43412|issue:45588", + "issue:45198|issue:45803", + "issue:45372|issue:45406", + "issue:43278|issue:43381", + "issue:45588|issue:45823" + ], + "prepared_review_unit_hash": "3501a7cbe037eb3adae7942ff13c9ceddf5677c85bb5ba052415ef00b46ff028", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36251, + "estimated_input_tokens": 9063, + "estimated_eval_tokens": 18382 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are mostly broad semantic matches rather than true duplicate bugs; I would reject all of them. The strongest standalone issue in the set looks like 43873 because it is open and has the most inbound discussion, while 45698 is the clearest self-contained bug report.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43873 is the best canonical anchor here: it is open, has the highest discussion/inbound-reference signal in the set, and describes a broadly relevant user-facing bug that can absorb related reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 is the most clearly written standalone bug report with a concrete failure mode in from_pretrained/save_pretrained, so it is the best single issue for a reader to understand and act on quickly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Both mention incorrect model outputs, but one is siglip2 zero probabilities and the other is a position-id key warning; different symptoms and likely different code paths." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Flash-attention generation failure for Qwen3.5 and multi-GPU CUDA OOM for Gemma4 are unrelated bugs." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "AMP/CUDA crash in a loss module and bfloat16 dtype mismatches in inference are distinct issues." + }, + { + "left": "issue:43746", + "right": "issue:46209", + "accept": false, + "reason": "PEFT/local checkpoint loading for GraniteSpeech and FP8 inference failure on B200 are different problems." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Version-to-version output drift for Pegasus and a flash-attention generation failure for Qwen3.5 are not the same underlying bug." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "IterableDataset multi-image finetuning failure and BeitImageProcessorFast label reduction are unrelated data-processing bugs." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer spacing after added tokens has no overlap with Trainer broadcast TypeError." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint resume key mismatch and an omni-moe feature-length helper bug are different code paths." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer NoneType broadcast error and MacOS bus error with a CLIP model do not describe the same failure." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization after resizing token embeddings." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and a helper-function logic bug in qwen3_omni_moe are different." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "AutoTokenizer v5 loading issue and MPS attention correctness on value/query head mismatch are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "Missing flash-attention utility import and a model load failure for physical-intelligence/fast are both import-related at a high level, but not the same concrete bug." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Removal of is_torch_fx_available breaking trust_remote_code models and Deepseek tokenizer regression in v5 are distinct issues." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization offloading behavior and multi-GPU CUDA OOM are different root causes and would not be merged into one fix." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load flows, but one is custom token IDs being lost and the other is the wrong custom module being loaded; separate bugs." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer.json being ignored and trust_remote_code breaking after a removed helper are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "BF16-to-FP32 dtype drift in evaluate is unrelated to undefined variables in the video token-count helper." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "Trailing-slash local path import warning and tensor-parallel OOM loading Qwen2-57B are unrelated." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBertModel issue and torch.jit.script generator-expression export failure are different historical bugs." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "cudaErrorAssert with auto device mapping and multi-GPU OOM are separate inference failures." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation correctness and a stale warning for num_return_sequences are different problems." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma 4 processor loading import failure and flash_attention crash on s_aux=None are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token insertion regression and Gemma3 NaN embeddings are different failure modes." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "AMP/CUDA loss crash and flash_attention s_aux=None AttributeError are not the same code-path issue." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export issues in Gemma3n and flash_attention sink-less-model crash are unrelated." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure and a bare-except bug in Fuyu tensor conversion are different bugs." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "ReasoningEffort import failure for Gemma 4 processors and missing _tokenizer in Gemma4Processor are distinct load-time issues." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype changes and gradient checkpointing in eval mode are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "flash_attention.py crashing on s_aux=None and Gemma4 PLE device mismatch under device_map=auto are different bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 27, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:25251", + "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:43278", + "issue:43381", + "issue:43421", + "issue:43575", + "issue:43611", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43873", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44442", + "issue:44448", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45563", + "issue:45712", + "issue:46121" + ], + "soft_pairs": [ + "issue:43976|issue:45440", + "issue:44448|issue:44466", + "issue:45459|issue:45712", + "issue:43653|issue:44743", + "issue:25251|issue:32090", + "issue:45245|issue:45563", + "issue:44206|issue:44479", + "issue:43065|issue:43994", + "issue:45372|issue:45459", + "issue:44186|issue:45198", + "issue:43065|issue:45412", + "issue:43611|issue:46121", + "issue:44871|issue:44977", + "issue:44361|issue:45198", + "issue:32090|issue:33290", + "issue:42490|issue:43873", + "issue:33357|issue:39692", + "issue:29942|issue:30064", + "issue:29127|issue:34567", + "issue:42915|issue:42994", + "issue:43994|issue:45412", + "issue:44265|issue:45198", + "issue:43066|issue:44462", + "issue:43278|issue:43575", + "issue:43756|issue:45440", + "issue:43421|issue:45491", + "issue:43381|issue:43701", + "issue:43653|issue:44442", + "issue:44610|issue:45412" + ], + "prepared_review_unit_hash": "220f151e3a5ead8f5c97ba880bb847846d0202f4cfbe3ff74eab79b21290783c", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36409, + "estimated_input_tokens": 9103, + "estimated_eval_tokens": 18462 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is not a true duplicate cluster: the issues span unrelated areas (tokenizers, training, quantization, vision processors, model loading, and CI). No single canonical issue or PR stands out, and all soft edges should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Different failures: Python version incompatibility vs DeepseekV3MoE implementation divergence." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Different bugs: generation output drift vs inconsistent lm_head.weight serialization." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Unrelated tokenizer error masking vs leftover dummy class cleanup." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token registration is unrelated to Qwen3.5 recurrent-state reset behavior." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Nested pipeline output shape change is unrelated to Trainer _gpu_broadcast_one NoneType crash." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category cardinality/runtime error is unrelated to stale generate() warning behavior." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported center argument in LasrFeatureExtractor is unrelated to video-input regression in Qwen models." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Sam3PixelDecoder dummy Conv2d is unrelated to SigLIP2 AutoModel/pipeline nonsense outputs." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor import failure from mistral_common is unrelated to protobuf error masking in tokenizers." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes on NER/padding are unrelated to Wav2Vec2 save_pretrained/tokenization failures." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to RT-DETR memory release problems." + }, + { + "left": "issue:43611", + "right": "issue:46121", + "accept": false, + "reason": "base_model_prefix loading breakage is unrelated to rope-parameter JSON list handling." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma-3 eos_token_id mismatch is unrelated to Qwen3.5 flash-attention generation issues." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer AttributeError is unrelated to Wav2Vec2 save/tokenization failure." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer NoneType broadcast crash is unrelated to Adafactor/DeepSpeed OOM." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Trailing-slash import warning is unrelated to offloading-with-quantization behavior." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error with CLIP is unrelated to SigLIP2 doc example mistakes." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to void segmentation map processing." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity is unrelated to TrainerState token counter not updating." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "FineGrainedFP8Config failure for Qwen3Moe is unrelated to quantized model saving." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 inference mismatch is unrelated to RT-DETR memory leaks." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export/torch_compilable_check failure is unrelated to Wav2Vec2 save/tokenization issues." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Wrong tokenizer decoder type in v5 is unrelated to AutoTokenizer ignoring tokenizer.json." + }, + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "Embedding dtype drift during eval is unrelated to tp loading OOM for Qwen2-57B-A14B-Instruct." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch is unrelated to DeepseekV3MoE implementation divergence." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime special-token post-processor updates are unrelated to Gemma3 NaN embeddings with mixed-length batching." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer mask-token registration is unrelated to AutoTokenizer failing to load FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR memory reclamation." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:33290", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43334", + "issue:43381", + "issue:43452", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43646", + "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:44898", + "issue:44977", + "issue:45072", + "issue:45103", + "issue:45245", + "issue:45372", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:43824|issue:44279", + "issue:29127|issue:33357", + "issue:29942|issue:36010", + "issue:45440|issue:45593", + "issue:43761|issue:45859", + "issue:43526|issue:45834", + "issue:43526|issue:44186", + "issue:45103|issue:45372", + "issue:29127|issue:35141", + "issue:44625|issue:45584", + "issue:43334|issue:43531", + "issue:44442|issue:45072", + "issue:43575|issue:43701", + "issue:42915|issue:43931", + "issue:43526|issue:44857", + "issue:42490|issue:43381", + "issue:44977|issue:45245", + "issue:43575|issue:44387", + "issue:44464|issue:45491", + "issue:43262|issue:44206", + "issue:43646|issue:44077", + "issue:44743|issue:44811", + "issue:43452|issue:45588", + "issue:44062|issue:45907", + "issue:43761|issue:44079", + "issue:33290|issue:34689", + "issue:44442|issue:44898" + ], + "prepared_review_unit_hash": "49e63cdcda54e50d7465058e56f34643575ab7606f127b38863fd9c07b392e7f", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35765, + "estimated_input_tokens": 8942, + "estimated_eval_tokens": 18140 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items do not form a true duplicate cluster; they span many unrelated Transformers bugs across different models, loaders, processors, and runtime paths. All proposed soft edges are reject-worthy on the available evidence.", + "confidence": 0.77, + "canonical_issue_reason": "If a representative must be chosen, issue 44279 is the broadest/most umbrella-like title, but it is still too generic to be a strong canonical for this set.", + "canonical_pr_reason": null, + "best_issue_reason": "44279 is the least specific issue here, but the collection is too heterogeneous for any issue to be a reliable duplicate anchor.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Specific Qwen2.5-VL import failure vs generic dependency issue; not the same bug." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error-message clarity vs CLIP MacOS bus error; unrelated symptoms and code paths." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures vs GenerationMixin import regression; different failures." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepSeekV3MoE implementation divergence vs D-FINE auxiliary-loss omission; unrelated model bugs." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression vs Qwen3.5Moe CPU-offload incompatibility; different components." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs Kosmos2.5 long-OCR index error; not the same issue." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Image processor label handling vs LayoutLMv2Tokenizer NER/padding crash; unrelated." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotations crash vs mistral_common import error in Gemma processor loading; different root causes." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "Error-message clarity issue vs post_init reinitialization bug; not the same code path." + }, + { + "left": "issue:44625", + "right": "issue:45584", + "accept": false, + "reason": "Config propagation bug vs Whisper empty-transcription generation failure; unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id for Qwen3-VL text config vs sliding_window issue in Qwen3-MoE; different model families." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure vs bfloat16 dtype mismatch during inference; different concrete problems." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Tensor-parallel OOM on model load vs checkpoint key mismatch; unrelated failures." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FineGrainedFP8Config failure vs Qwen3-VL weight-shape mismatch; different issues." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs LwDetrImageLoss AMP/CUDA crash; unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Path import warning vs gradient-checkpointing-in-eval restriction; not the same bug." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug vs category-count limit error; unrelated." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both are OOM-related, but one is TP load OOM and the other is int4 memory growth; not the same concrete problem." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency vs Gemma3 NaN embeddings from sliding-window padding; different bugs." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Chat-template sample-rate default vs feature-extractor center-arg crash; unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Generic custom-init regression vs patchtsmixer post_init policy issue; not a shared concrete fix." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Recurrent-state reset bug vs Whisper batch_decode skip_special_tokens behavior; unrelated." + }, + { + "left": "issue:43452", + "right": "issue:45588", + "accept": false, + "reason": "gguf_file loading regression vs flash_attention.py s_aux=None crash; different subsystems and failures." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken keyword collision vs list_repo_files revision forwarding; unrelated API bugs." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "CLIP hidden_states regression vs ModelOutput key assignment bug; different code paths." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Adafactor+DeepSpeed OOM vs Llama 3.2 vision model loading breakage; unrelated." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer load failure vs Perceiver non-default resolution failure; not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 29, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:33290", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:42490", + "issue:42907", + "issue:43232", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43493", + "issue:43525", + "issue:43611", + "issue:43643", + "issue:43650", + "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:44743", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:44987", + "issue:45003", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45440", + "issue:45479", + "issue:45698", + "issue:45759", + "issue:45803", + "issue:46178", + "issue:46202", + "issue:46209" + ], + "soft_pairs": [ + "issue:33290|issue:34567", + "issue:33290|issue:35141", + "issue:45003|issue:45440", + "issue:43723|issue:45479", + "issue:43381|issue:43873", + "issue:43232|issue:43388", + "issue:43316|issue:43525", + "issue:42490|issue:44743", + "issue:43761|issue:44188", + "issue:34689|issue:43611", + "issue:44479|issue:45290", + "issue:43720|issue:44442", + "issue:44987|issue:46178", + "issue:44442|issue:45803", + "issue:44077|issue:44479", + "issue:43931|issue:45216", + "issue:43493|issue:43827", + "issue:34689|issue:36010", + "issue:33290|issue:36331", + "issue:43316|issue:45759", + "issue:42907|issue:45698", + "issue:45290|issue:46209", + "issue:43873|issue:44871", + "issue:43749|issue:43931", + "issue:43643|issue:44913", + "issue:43650|issue:46202", + "issue:44190|issue:44496", + "issue:44855|issue:45137" + ], + "prepared_review_unit_hash": "a38092142cb8957161dfccba6207c799108865976f3a1ec35a6c8f85cab5209a", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35710, + "estimated_input_tokens": 8928, + "estimated_eval_tokens": 18112 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft pair appears to describe the same underlying bug or change. The set is a grab bag of unrelated issues spanning loading, generation, training, quantization, and docs regressions, so there is no canonical duplicate to select.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "OOM with Adafactor/DeepSpeed is unrelated to TrainerState.num_input_tokens_seen not updating." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "Different failure modes: optimizer memory blowup vs embedding reinitialization after resize." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "sys.modules access bug is unrelated to DeepSeekV3MoE implementation divergence." + }, + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer loading regression and zero-loss sequence-classification bug are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and offloading/quantization are different issues." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs after sync_gpus does not match metric gathering dropping tuple labels." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Different config API problems: Gemma3TextConfig discrepancy vs missing pad_token_id on Llama4Config." + }, + { + "left": "issue:42490", + "right": "issue:44743", + "accept": false, + "reason": "Trailing-slash path import warning is unrelated to Qwen recurrent-state reset with cache." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIP hidden_states regression is unrelated to attention-kernel divergence under torch.compile." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Llama 3.2 model loading break and base_model_prefix loading regression are distinct." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression in Qwen VL models is unrelated to chat-template tool-call crashes." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading bug is unrelated to AutoTokenizer failing on FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:44987", + "right": "issue:46178", + "accept": false, + "reason": "Physical-intelligence/fast load failure is unrelated to missing tensorflow_text backend mapping." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer loading failure and FuyuBatchFeature exception handling are different code paths." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "patchtsmixer post_init policy issue is unrelated to Qwen video-input regression." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Weight-shape mismatch on load is unrelated to a bad save_pretrained checkpoint for Qwen3.5." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation mismatch is unrelated to docs still mentioning pipeline()." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Model-loading failure and GenerationMixin import error are separate regressions." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed Adafactor OOM is unrelated to CustomTrainer.compute_loss receiving a new kwarg." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy is unrelated to composite Qwen multimodal from_config unwrapping." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals is unrelated to loading the wrong custom module after save_pretrained." + }, + { + "left": "issue:45290", + "right": "issue:46209", + "accept": false, + "reason": "Chat-template tool-call crash is unrelated to FP8 inference failure on B200." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior does not match Gemma eos_token_id configuration mismatch." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and Qwen3-VL shape mismatch are different loading bugs." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code returning missing fields is unrelated to GPTNeoX rotary_pct resetting on reload." + }, + { + "left": "issue:43650", + "right": "issue:46202", + "accept": false, + "reason": "The vague 'ADD THE DATA' issue is not the same as Gemma pipeline roundtrip failure." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading script issue is unrelated to unrecognized model config loading." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "PyTorch 3.13 decorator parsing/import error is unrelated to DeepSpeed ZeRO3 deque underflow." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:25251", + "issue:28282", + "issue:32090", + "issue:35141", + "issue:41950", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43316", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43452", + "issue:43475", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43688", + "issue:43701", + "issue:43716", + "issue:43742", + "issue:43761", + "issue:43825", + "issue:44077", + "issue:44162", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44534", + "issue:44617", + "issue:44743", + "issue:44792", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45200", + "issue:45584", + "issue:45803", + "issue:46050", + "issue:46170", + "issue:46178" + ], + "soft_pairs": [ + "issue:25251|issue:28282", + "issue:43065|issue:44617", + "issue:43295|issue:43825", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43316|issue:44877", + "issue:43316|issue:43716", + "issue:42617|issue:43575", + "issue:43540|issue:44514", + "issue:44077|issue:44534", + "issue:44162|issue:44792", + "issue:16998|issue:22355", + "issue:44871|issue:45584", + "issue:43575|issue:43742", + "issue:43404|issue:43441", + "issue:45803|issue:46170", + "issue:43295|issue:44871", + "issue:43673|issue:44743", + "issue:43761|issue:44479", + "issue:41950|issue:43475", + "issue:43388|issue:43688", + "issue:43452|issue:44496", + "issue:43646|issue:44913", + "issue:44871|issue:46050", + "issue:45127|issue:45200", + "issue:43572|issue:46178", + "issue:32090|issue:35141" + ], + "prepared_review_unit_hash": "865123dcf87d23c2abc168a7458f99fbbec2be29425cfc2de3e5a58e0caf8204", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35721, + "estimated_input_tokens": 8931, + "estimated_eval_tokens": 18118 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated transformer issues that only share broad subsystem or release-regression language; none look like true duplicates, so there is no strong canonical item.", + "confidence": 0.18, + "canonical_issue_reason": "No clear canonical duplicate exists; the set spans many different bug classes (pipelines, configs, model loading, training, multimodal/video, distributed, and checkpoints).", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the broadest umbrella-style regression report in the set, but it still does not subsume the others and should not be treated as a duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline output nesting bug vs missing PyTorch import are unrelated failure modes." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video OOM are different SAM3 problems." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor/tokenizer regression is unrelated to a pipeline error message about translation tasks." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile/SDPA failure is unrelated to a checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch and resume_from_checkpoint key mismatch are different bugs." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy is not the same as strict config loading failure for granite_speech." + }, + { + "left": "issue:43316", + "right": "issue:43716", + "accept": false, + "reason": "Config API discrepancy and image preprocessor dtype mismatch are separate issues." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py startup failure and tp-related OOM are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Both are multimodal/video-related, but one is a Qwen3OmniMoe video input validation error and the other is a Qwen2_5_VL batching crash." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Optional post_init policy for patchtsmixer is unrelated to non-persistent buffer junk initialization." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 training breakage and janus image-generation test failure do not share the same bug." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "model_max_length question for DeBERTa-V3 is unrelated to missing transformers.onnx module import." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Gemma eos_token_id config inconsistency is not the same as Whisper empty transcription failure." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "OOM on large Qwen2 model loading is unrelated to a KeyError while loading MobileLLM-125M." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Mistral3 lm_head tying bug is different from a FlashAttention failure in Ministral-3." + }, + { + "left": "issue:45803", + "right": "issue:46170", + "accept": false, + "reason": "Bare except swallowing errors in tensor conversion is unrelated to Windows/ROCm torch.distributed import issues." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Processor regression and Gemma eos_token_id config mismatch are different code paths." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Missing GenerationMixin cache during chunked_prefill is not the same as recurrent state reset in modular_qwen3_5.py." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and Qwen video input regression are unrelated." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification pipeline selecting image processors is different from a missing fpn_position_embeddings attribute in Sam3 video." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "gather_for_metrics label truncation is unrelated to auxiliary loss normalization in OLMoE/GPT OSS." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "gguf loading breaks for tokenizer/model APIs, while the other is an unrecognized model config error." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Generic custom-model initialization breakage is not the same as GPTNeoX rotary_pct reload persistence." + }, + { + "left": "issue:44871", + "right": "issue:46050", + "accept": false, + "reason": "Gemma eos_token_id mismatch is unrelated to sinq quantization save/load breakage." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge collapse with tied embeddings is a different bug from missing mm_token_type_ids defaults." + }, + { + "left": "issue:43572", + "right": "issue:46178", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is unrelated to tensorflow_text backend mapping errors." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "NoneType GPU broadcast failure and embedding reinitialization after resize are different training/model-init bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 31, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:35141", + "issue:41720", + "issue:42490", + "issue:43065", + "issue:43335", + "issue:43504", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43644", + "issue:43761", + "issue:43827", + "issue:43931", + "issue:43976", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44737", + "issue:44792", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44933", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45357", + "issue:45362", + "issue:45381", + "issue:45406", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45698", + "issue:45803", + "issue:45987" + ], + "soft_pairs": [ + "issue:43504|issue:45698", + "issue:44617|issue:45584", + "issue:44734|issue:45406", + "issue:45563|issue:45584", + "issue:43525|issue:43531", + "issue:43761|issue:44242", + "issue:44792|issue:44977", + "issue:43931|issue:44060", + "issue:44479|issue:44734", + "issue:44534|issue:44913", + "issue:44190|issue:44964", + "issue:44792|issue:45600", + "issue:44464|issue:45563", + "issue:43827|issue:43994", + "issue:44855|issue:45588", + "issue:44521|issue:45381", + "issue:35141|issue:42490", + "issue:41720|issue:45245", + "issue:45803|issue:45987", + "issue:43065|issue:44610", + "issue:44933|issue:45362", + "issue:43335|issue:44855", + "issue:43644|issue:44913", + "issue:44077|issue:44877", + "issue:43976|issue:44855", + "issue:43550|issue:44190", + "issue:43540|issue:44734", + "issue:45127|issue:45357", + "issue:44737|issue:45803" + ], + "prepared_review_unit_hash": "bf7d97444aec167c24983f713d74e949ec1daa3b58a0249f09638cb4cd3f7706", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36387, + "estimated_input_tokens": 9097, + "estimated_eval_tokens": 18450 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are largely heterogeneous and do not describe the same underlying bug or change. They span unrelated model-loading, multimodal preprocessing, generation, config, and docs/runtime regression issues, so none of the proposed duplicate links should be accepted.", + "confidence": 0.93, + "canonical_issue_reason": "issue:44521 is the most active/open issue in the set and has the strongest cross-referencing signal, so it is the best representative if one must be chosen; however, the overall set is not a true duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the strongest global issue candidate by discussion and inbound references, but it should be treated as representative only, not as a merge target for the other unrelated issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "BEiT legacy-field preset loading vs custom-module resolution after save/load; different subsystems and failure modes." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Sam3Video CUDA OOM vs Whisper empty-transcription failure; unrelated code paths and symptoms." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation tensor indexing in serve vs Gemma4Processor missing _tokenizer; distinct serve bugs." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Paged-generate warning regression vs empty transcription after align_special_tokens; not the same bug." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config vs sliding_window handling in Qwen3-MoE; unrelated config issues." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "CLIP hidden_states regression vs MoE load-balancing loss gating; separate model behaviors." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "janus image-generation test failure vs Qwen3.5 flash-attention generation bug; different failure surfaces." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Qwen3-VL weight-shape load mismatch vs incorrect tied-weights warning; not the same underlying defect." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression in Qwen VL models vs serve KV-cache indexing crash; unrelated paths." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer junk regression vs GPTNeoX rotary_pct reload defaulting; different config/runtime problems." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Example script dataset loading failure vs Phi-4 multimodal model loading error; not duplicates." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus test failure vs removed Sam3LiteText config references in auto_mappings; unrelated CI/test issues." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward vs stale num_return_sequences warning; different generation bugs." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() vs SigLIP2 nonsensical runtime results; documentation and model behavior are separate." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 import parsing error vs flash_attention s_aux=None crash; unrelated breakages." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal-preprocessing bugs, but assistant_masks being zero and vision_position_ids being wrong are different code paths and fixes." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "Embedding resize reinitialization bug vs trailing-slash local-path warning; no shared underlying issue." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3 auto device mapping cuda assert vs category-count limit error; distinct runtime failures." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except swallowing errors vs StaticCache length contract mismatch; unrelated utilities." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs OmDet-Turbo processor/model size mismatch; different model-specific problems." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing import from image_utils vs Qwen3.5 chat crash; unrelated defects." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation bug vs Python 3.13 import parsing error; different areas." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Both involve config/regression symptoms, but non-persistent buffer junk and rotary_pct reload behavior are not the same bug." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Optional post_init allowance vs strict config blocking granite_speech; related theme, but different concrete change and failure." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python-version compatibility issues, but one is version support failure and the other is a parser/indentation import error; not a duplicate." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "Bamba torch.compile/SDPA bug vs local dataset loading in a training script; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError vs serve KV-cache indexing crash; different subsystems." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge with extended vocab collapsing model vs incorrect visual encoder keys saved in Qwen3.5; separate save/merge issues." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "XLNet CPU arange bug vs bare except swallowing errors; not the same code path or symptom." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:42907", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43335", + "issue:43404", + "issue:43441", + "issue:43479", + "issue:43531", + "issue:43643", + "issue:43650", + "issue:43854", + "issue:43976", + "issue:44016", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44462", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44938", + "issue:44964", + "issue:44987", + "issue:45003", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45335", + "issue:45375", + "issue:45446", + "issue:45542", + "issue:45584", + "issue:45600", + "issue:45632", + "issue:45907", + "issue:46082", + "issue:46121" + ], + "soft_pairs": [ + "issue:44112|issue:45600", + "issue:44462|issue:45907", + "issue:43335|issue:44190", + "issue:46082|issue:46121", + "issue:43116|issue:44190", + "issue:44938|issue:45542", + "issue:45276|issue:45584", + "issue:43295|issue:45276", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:45245|issue:45584", + "issue:43650|issue:44220", + "issue:36246|issue:38617", + "issue:42175|issue:44279", + "issue:44186|issue:44734", + "issue:41950|issue:44016", + "issue:44246|issue:45003", + "issue:44683|issue:45446", + "issue:43404|issue:45216", + "issue:38175|issue:43065", + "issue:44016|issue:44220", + "issue:43643|issue:44496", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:43854|issue:44964", + "issue:44734|issue:45632", + "issue:44561|issue:45632", + "issue:43976|issue:44987", + "issue:43531|issue:45600", + "issue:42907|issue:43441", + "issue:43295|issue:45335" + ], + "prepared_review_unit_hash": "20689046d7b1c35d566095ae2528820d5218de2f717cc8a13794be4c26d4ecf5", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36948, + "estimated_input_tokens": 9237, + "estimated_eval_tokens": 18730 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is very heterogeneous: it mixes import/export regressions, model-specific configuration bugs, backend/dependency problems, and notebook/script failures. None of the soft edges look like true duplicates of the same underlying bug or change.", + "confidence": 0.91, + "canonical_issue_reason": "issue:41628 is the broadest, clearest representative of the small import-regression subset in this set, but the overall cluster is too diverse to have a strong true canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41628 is the best global anchor by title clarity and breadth of symptom, though it still only represents one slice of the cluster rather than the whole.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "Both are CI-related, but they involve different models, different files, and different failure modes." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "One is AutoTokenizer ignoring tokenizer.json; the other is list_repo_files not forwarding revision. Related area, different bug." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers config initialization is unrelated to a local-dataset loading failure in an example script." + }, + { + "left": "issue:46082", + "right": "issue:46121", + "accept": false, + "reason": "LlamaConfig head_dim validation and rope-param JSON list handling are separate config-validation bugs." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Multi-label classification output logic is unrelated to dataset loading in a different example script." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 import/load failure and missing TensorFlow backend wiring are different root causes." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 embedding-resize behavior is unrelated to Whisper empty-transcription generation." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Processor.tokenizer regression is a different code path from Gemma4 token-embedding resizing." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Phi4Multimodal default sub-config initialization and missing deepstack_visual_indexes are different config bugs." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but one is a model-module symbol and the other is a top-level AutoImageProcessor export." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category cardinality limits and Whisper special-token alignment are unrelated." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Generic content and fbank feature extraction are not the same bug." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Different missing symbols from different modules; same symptom class, not the same defect." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Pip extra/backend dependency packaging and a vague dependency issue are not concrete duplicates." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer padding/truncation crash is unrelated to serve-time KV-cache continuation indexing." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Pipeline processor lookup and a notebook syntax error are completely different issues." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowness and unsafe sys.modules access may be adjacent, but the reports describe different failures." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Compiled flex_attention failure on new torch and a version-check bug for AuxRequest import are not the same concrete problem." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Mistral3 lm_head tying and Qwen3.5 save_pretrained regression affect different model behaviors." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Zero probabilities in SigLIP2 is unrelated to a dummy Conv2d in Sam3PixelDecoder." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and audio feature extraction are unrelated." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading and unrecognized-model config.json validation are different config-loader failures." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Phi-4 multimodal load failure and stale auto_mappings references to removed configs are different issues." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "GraniteSpeech CI device override and Phi-4 multimodal model loading are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Both involve model loading, but they are different models with different failure contexts." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve KV-cache indexing and trust_remote_code cache-path collisions are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Removal of is_torch_fx_available breaks remote-code models; cache-path collisions are a different trust_remote_code bug." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python version support and loading a specific model with transformers>=5.1.0 are different problems." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior has nothing to do with stale auto_mappings references." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Saving dequantized models and FlashAttention failure in Ministral-3 are distinct code paths." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor.tokenizer regression and t5gemma embed_tokens resizing are separate model/API 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": 33, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42490", + "issue:43295", + "issue:43299", + "issue:43335", + "issue:43381", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43577", + "issue:43650", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44242", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44496", + "issue:44521", + "issue:44617", + "issue:44779", + "issue:44933", + "issue:45020", + "issue:45042", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45325", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45632", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:46209" + ], + "soft_pairs": [ + "issue:42490|issue:45632", + "issue:43526|issue:43901", + "issue:43441|issue:45588", + "issue:44496|issue:45042", + "issue:43673|issue:44336", + "issue:43335|issue:45593", + "issue:44016|issue:44062", + "issue:43824|issue:44933", + "issue:44075|issue:44368", + "issue:43299|issue:45216", + "issue:43381|issue:45593", + "issue:43901|issue:44496", + "issue:43976|issue:44279", + "issue:43650|issue:46209", + "issue:44496|issue:45759", + "issue:45335|issue:45584", + "issue:43479|issue:43525", + "issue:44242|issue:45200", + "issue:44521|issue:45325", + "issue:43299|issue:45357", + "issue:38175|issue:44617", + "issue:43577|issue:45216", + "issue:44351|issue:45278", + "issue:41950|issue:45020", + "issue:44279|issue:45405", + "issue:44779|issue:45812", + "issue:41950|issue:45823", + "issue:39692|issue:43901", + "issue:43295|issue:44779" + ], + "prepared_review_unit_hash": "8e4efc9ba432e1338c1b9d1d3f64a23f07997d88b2b6cf470c37fdd10bda8290", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36383, + "estimated_input_tokens": 9096, + "estimated_eval_tokens": 18448 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated single-issue reports spanning different model families, pipelines, and regressions; I found no strong duplicate/merge candidates among the soft pairs.", + "confidence": 0.93, + "canonical_issue_reason": "issue:45278 is the broadest representative regression report in the set, covering multiple import failures after an upgrade and plausibly subsuming narrower import-surface breakages.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best global representative because it has the clearest high-impact upgrade-regression framing and broad user reach.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42490", + "right": "issue:45632", + "accept": false, + "reason": "Trailing-slash local-path import warning and trust_remote_code cache-path collision are different path-handling bugs." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "A processor output bug and a documentation mismatch about return_all_scores are not the same issue." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Both mention flash attention, but one is model-specific Ministral-3 loading and the other is a generic sink-less s_aux=None crash." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model config loading and PIL image processor torchvision dependency are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache lookup during chunked_prefill and ANSI color output in loading_report are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "Sparse-layer construction with num_sparse_encoder_layers=0 is different from D-FINE auxiliary-loss handling." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "A notebook syntax error and an AddedToken keyword conflict are separate bugs." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "These are different import failures in different modules/symbols, not the same concrete bug." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Unused SGD args and a tie_word_embeddings warning in ms-swift are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "One is a Qwen3VL model loading failure; the other is an incorrect save_pretrained checkpoint regression." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient-checkpointing eval-mode behavior and D-FINE auxiliary-loss omission are different code paths." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "A pipeline docs mismatch and a model-import/config error are not the same issue." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python-version compatibility breakage and a vague dependency issue do not point to one concrete bug." + }, + { + "left": "issue:43650", + "right": "issue:46209", + "accept": false, + "reason": "Placeholder/non-technical issue text and an FP8 B200 inference failure are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "These are different Qwen-related loading problems with different failure modes and code paths." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Embedding-resize propagation and Whisper empty-transcription failure after align_special_tokens are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Both are config issues, but they affect different model classes and different defaults/attributes." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Missing load-balancing loss and mm_token_type_ids defaulting are separate training semantics bugs." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "All-zero assistant masks and rope-index temporal scaling are different multimodal preprocessing bugs." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "These are distinct save/load regressions for Qwen3.5 rather than one shared bug." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint saving are unrelated issues." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "HybridCache import failure may be a symptom in the broader import-regression report, but it is not clearly the same concrete bug." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup and remote_code breakage are different failures." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A generic dependency issue and an unreleased MIN_PEFT_VERSION bump are not the same bug." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Deepseek tokenizer regression and Granite tokenizer regression affect different model families and behaviors." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video-classification processor lookup and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "These are both docs-related, but one is a SigLIP2 example error report and the other is a pipeline docs mismatch." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Custom processor.tokenizer/images regression and Deepseek tokenizer incorrect results are different issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 34, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:33290", + "issue:42175", + "issue:42994", + "issue:43065", + "issue:43262", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44361", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:45081", + "issue:45276", + "issue:45397", + "issue:45405", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45656", + "issue:45712", + "issue:45823", + "issue:45834", + "issue:45907", + "issue:46132" + ], + "soft_pairs": [ + "issue:44683|issue:45542", + "issue:43299|issue:43854", + "issue:43976|issue:45405", + "issue:43650|issue:46132", + "issue:44462|issue:45081", + "issue:43450|issue:44279", + "issue:44297|issue:44462", + "issue:44016|issue:44291", + "issue:45081|issue:45907", + "issue:44466|issue:45276", + "issue:43441|issue:45834", + "issue:45600|issue:45712", + "issue:42994|issue:43317", + "issue:43653|issue:45593", + "issue:33290|issue:45656", + "issue:44623|issue:45397", + "issue:44623|issue:44749", + "issue:43065|issue:44898", + "issue:44261|issue:44263", + "issue:44361|issue:45593", + "issue:43441|issue:44683", + "issue:44016|issue:45823", + "issue:44671|issue:44779", + "issue:43723|issue:44162", + "issue:42175|issue:43976", + "issue:43262|issue:44521", + "issue:43901|issue:43994", + "issue:43673|issue:43761" + ], + "prepared_review_unit_hash": "50718ffb6bae847f8c2d1a390a43c4feae0a17f69f3c3d106cf9d0c606192ef1", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36010, + "estimated_input_tokens": 9003, + "estimated_eval_tokens": 18262 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set looks heterogeneous rather than one true duplicate cluster; most soft pairs are only broad topical matches (often v5/tokenizer/load/save regressions) and should be rejected. If a single issue must anchor the cluster, the tokenizer-loading regression around AutoTokenizer is the closest fit.", + "confidence": 0.43, + "canonical_issue_reason": "issue:44462 is the best provisional anchor because it is a concrete v5 tokenizer-loading regression and is the closest match to the other tokenizer-related near-duplicates in the set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the most representative of the cluster\u2019s strongest theme (tokenizer loading/serialization regressions in v5), even though the overall cluster is not truly cohesive.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Compiled flex_attention failure and TensorFlow backend installation are unrelated bugs." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Both involve model loading, but they are different model-specific failures with different underlying code paths." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python version compatibility and an unreleased PEFT minimum version are separate release/dependency issues." + }, + { + "left": "issue:43650", + "right": "issue:46132", + "accept": false, + "reason": "A placeholder issue and an AttentionInterface behavior change do not describe the same change or bug." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but one ignores tokenizer.json while the other crashes in Mistral regex patching." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor shape handling and a generic dependency issue are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer class serialization mismatch is different from AutoTokenizer ignoring tokenizer.json on load." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated failure modes." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer regex patch crash and list_repo_files revision forwarding are different code paths." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "lm_head serialization inconsistency and Gemma4 embedding resize behavior are distinct model bugs." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "FlashAttention failure on Ministral and OCR index error in Kosmos2.5 are unrelated model issues." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Removed auto-mappings entries and leftover dummy classes are separate cleanup/CI problems." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model saving and dequantized model loading with offload are different quantization workflows." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss handling are unrelated." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "OOM from Adafactor in DeepSpeed and optimizer.step being called twice are different DeepSpeed bugs." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing processor save files and Gemma-4 ZeRO3 from_pretrained are separate save/load issues." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Processor saving missing files and a data-filtering slowdown are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "A dummy Conv2d in Sam3PixelDecoder and Perceiver non-default-resolution failure are different model bugs." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "Missing rms_norm_eps precision issue and torch.split return semantics are unrelated." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer AttributeError and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "FlashAttention breakage for a specific model and compiled flex_attention failure are different attention-stack issues." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "CamemBERT masked-LM regression and Deepseek tokenizer regression are different model/tokenizer bugs." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer loading regression and ESM2 model breakage are not the same underlying defect." + }, + { + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "Missing TensorFlow backend after pip install and Python 3.9/3.10 compatibility are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Default audio sampling rate and multimodal assistant mask generation are different apply_chat_template bugs." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Documentation mismatch for return_all_scores and incorrect SigLIP2 model outputs are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache missing and CLIPVision hidden_states regression are different v5 regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 35, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:42886", + "issue:43299", + "issue:43352", + "issue:43450", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43596", + "issue:43643", + "issue:43673", + "issue:43784", + "issue:43824", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44297", + "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:45003", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45397", + "issue:45542", + "issue:45561", + "issue:45563", + "issue:45593", + "issue:46132" + ], + "soft_pairs": [ + "issue:43784|issue:45542", + "issue:43824|issue:43976", + "issue:43450|issue:44617", + "issue:44297|issue:45397", + "issue:43525|issue:43881", + "issue:43901|issue:44246", + "issue:43525|issue:43643", + "issue:44188|issue:44336", + "issue:41628|issue:43976", + "issue:44589|issue:45362", + "issue:44336|issue:44373", + "issue:42491|issue:43299", + "issue:45561|issue:45563", + "issue:44295|issue:45397", + "issue:44246|issue:44496", + "issue:44242|issue:45593", + "issue:43531|issue:45362", + "issue:41950|issue:44220", + "issue:43526|issue:45003", + "issue:42886|issue:46132", + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:44246|issue:44871", + "issue:44336|issue:44485", + "issue:45003|issue:45561", + "issue:43673|issue:44561", + "issue:44779|issue:45292", + "issue:36246|issue:43596", + "issue:44295|issue:44749", + "issue:44242|issue:44857", + "issue:43352|issue:45250" + ], + "prepared_review_unit_hash": "185909242fa3092bcb1c4c9bf9da7f58c7b714394f2e28c277657cee525d59f3", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36685, + "estimated_input_tokens": 9172, + "estimated_eval_tokens": 18600 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of distinct Transformers regressions (import/export failures, model-loading issues, pipeline/config bugs). The only pair that looks like the same underlying bug is the Qwen2.5-VL import/export failure family.", + "confidence": 0.78, + "canonical_issue_reason": "issue:43824 is the clearest and most central representative of the Qwen2.5-VL import/export regression, with higher discussion and inbound references than the older sibling report.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43824 is the best standalone issue to anchor this cluster because it is specific, well-scoped, and most clearly describes a real duplicate-prone import failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Both are import-time failures, but they involve different missing backends/variables and different packages; not the same bug." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Qwen2.5-VL import failure vs Python version compatibility; unrelated problems." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Video shape bug vs CUDA OOM; different failure modes and code paths." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch vs ZeRO3 from_pretrained loading failure; not the same issue." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id on one model config vs a different model loading failure; too model-specific to be duplicates." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs mismatch for return_all_scores vs import slowdown; unrelated." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both involve config fields, but one is a specific missing attribute and the other is a trust_remote_code config hydration problem; not clearly the same bug." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Attention-kernel divergence vs ANSI codes in a loading report; unrelated subsystems." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "AutoImageProcessor import error vs Python 3.9/3.10 compatibility; different root causes." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Storage-object lookup failure vs chat-model crash; no concrete shared code path." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "Terminal formatting bug vs docstring issue; not duplicates." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both mention Qwen3 MoE, but one is LoRA compatibility on hf4.x/hf5.x and the other is Qwen3VL MoE loading; too different to merge as one PR." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "pytest-xdist file race vs a stale generate warning; unrelated." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "position_ids buffer access bug vs ZeRO3 from_pretrained failure; different issue." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import slowdown vs unrecognized model/config error; not the same bug." + }, + { + "left": "issue:44242", + "right": "issue:44871", + "accept": false, + "reason": "Router-logits load-balancing loss bug vs Gemma eos_token_id config inconsistency; different model behaviors." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Sliding-window bug in Qwen3-MoE vs chat crash in Qwen3.5-35B; too broad and not the same concrete failure." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification image-processor lookup vs fbank feature extraction; different pipelines." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BeitImageProcessorFast reduce_labels bug vs unsafe sys.modules access in modeling_utils; unrelated." + }, + { + "left": "issue:42886", + "right": "issue:46132", + "accept": false, + "reason": "Offline cache loading bug vs AttentionInterface.register behavior change; unrelated." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Qwen2.5-VL import error vs huggingface_hub offline-mode import error; both are imports, but different modules and failures." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing symbols from different namespaces; not the same regression." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import performance issue vs eos_token_id inconsistency; unrelated." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI terminal formatting bug vs GLM-5 RoPE discussion; not the same underlying problem." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "sys.modules access bug vs xdist file race; different subsystems." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "chunked_prefill cache issue vs trust_remote_code breakage after utility removal; different concrete failures." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "DeepSeek tokenizer regression vs embedding resize mismatch; unrelated." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Qwen2.5-VL import failure vs DeepSpeed/BertModel index error; unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "position_ids buffer issue vs performance regression after version upgrade; different symptoms and likely code paths." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Missing auxiliary loss vs AMP/CUDA crash; unrelated." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Specific model not supporting Flash Attention 2 vs a general Flash Attention 2 topic; not the same concrete bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 36, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:42886", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43540", + "issue:43653", + "issue:43901", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44188", + "issue:44246", + "issue:44336", + "issue:44368", + "issue:44466", + "issue:44479", + "issue:44483", + "issue:44496", + "issue:44877", + "issue:44977", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45292", + "issue:45335", + "issue:45375", + "issue:45397", + "issue:45412", + "issue:45459", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45656", + "issue:45701", + "issue:45759", + "issue:45987", + "issue:46082", + "issue:46123", + "issue:46170", + "issue:46202" + ], + "soft_pairs": [ + "issue:44162|issue:45200", + "issue:43901|issue:45003", + "issue:44496|issue:45003", + "issue:45412|issue:46123", + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:43262|issue:44246", + "issue:45292|issue:45701", + "issue:43257|issue:45137", + "issue:45375|issue:45759", + "issue:45987|issue:46082", + "issue:43232|issue:44336", + "issue:44987|issue:45459", + "issue:44479|issue:46170", + "issue:44995|issue:45200", + "issue:43065|issue:43408", + "issue:43475|issue:43540", + "issue:44466|issue:45335", + "issue:45397|issue:45656", + "issue:42886|issue:45229", + "issue:44483|issue:46202", + "issue:44060|issue:44077", + "issue:44188|issue:46202", + "issue:44995|issue:45588", + "issue:45137|issue:45600", + "issue:43653|issue:44162", + "issue:44368|issue:44977", + "issue:44877|issue:46170", + "issue:44368|issue:45563", + "issue:43931|issue:44368" + ], + "prepared_review_unit_hash": "bcb8fc576507416b12cfe43829c63919cdc67ef9f0a374fe762f3b0e9032e7b0", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36742, + "estimated_input_tokens": 9186, + "estimated_eval_tokens": 18628 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a grab-bag of unrelated issues across tokenizers, multimodal configs, generation, logging, and CI; there is no single underlying bug/change tying them together.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the items cover many distinct subsystems and failure modes (tokenizer caching, model config loading, generation internals, multimodal/video handling, memory leaks, docs/CI), so they are not duplicates of one another.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good cluster representative because the cluster is heterogeneous rather than a duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 model breakage vs Gemma 4 mm_token_type_ids defaulting; different models and failure mechanisms." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mismatch for TextClassificationPipeline vs unsafe sys.modules access in modeling_utils; unrelated subsystems." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model/config loading error vs sys.modules access bug; different code paths and symptoms." + }, + { + "left": "issue:45412", + "right": "issue:46123", + "accept": false, + "reason": "RT-DETR memory not released vs MaskGenerationPipeline dropping final partial batch; unrelated behavior." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Strict config loading for granite_speech vs missing deepstack_visual_indexes in Qwen config; different model families/config fields." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "resize_token_embeddings output embedding sync issue vs Whisper empty transcription after align_special_tokens; not the same bug." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio processor chat-template sampling-rate default vs slow import of transformers; unrelated." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Embedding resize propagation vs tokenization differing by transformers version; distinct problems." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate+deepspeed vs ZeRO3 deque pop error; different failure points." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Missing config field in Qwen3_5MoeVisionConfig vs AutoModelForCausalLM.from_config unwrapping composite multimodal configs; related area but not same concrete bug." + }, + { + "left": "issue:45987", + "right": "issue:46082", + "accept": false, + "reason": "StaticCache seq length contract issue vs LlamaConfig head_dim validation; unrelated APIs." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs after sync_gpus vs ANSI codes in loading_report; no overlap in bug or fix." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure on a specific repo/version vs tokenizer errors hidden by protobuf exception handling; different root causes." + }, + { + "left": "issue:44479", + "right": "issue:46170", + "accept": false, + "reason": "Video input regression in Qwen variants vs Windows/ROCm torch.distributed import issue; different environments and code paths." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "Stale indexer cache on second forward pass vs Gemma 4 token type ids default; unrelated model internals." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs model type mismatch warning for sam3_video/sam3_tracker; not the same defect." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Missing fpn_position_embeddings on Sam3VisionEncoderOutput vs Qwen3OmniMoe video ValueError; separate model families and failures." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "v5 tied-weight serialization inconsistency vs t5gemma resize_token_embeddings not affecting decoder.embed_tokens; different layers and symptoms." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 zero3 from_pretrained bug vs optimizer step called twice with deepspeed; unrelated training/loading issues." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "HF_HUB_OFFLINE tokenizer cache load issue vs Gemma4 multi-GPU CUDA OOM; completely different problems." + }, + { + "left": "issue:44483", + "right": "issue:46202", + "accept": false, + "reason": "Chat completions request rejection vs Gemma pipeline roundtrip failure on special character; not the same underlying bug." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Wrong tied-weights warning in Qwen3-Next vs patchtsmixer post_init allowance; unrelated model/config issues." + }, + { + "left": "issue:44188", + "right": "issue:46202", + "accept": false, + "reason": "torch.compile attention-kernel divergence vs Gemma pipeline token roundtrip failure; no common code path." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale cache on second forward pass vs flash_attention crash on s_aux=None; different bug surfaces." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error vs stale Sam3LiteText references in auto_mappings; one is runtime, the other CI/import metadata." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug vs ESM2 breakage; different tokenizer/model areas." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Tie_word_embeddings warning in Qwen3.5 LoRA fine-tuning vs flash-attention generation failure; not the same issue." + }, + { + "left": "issue:44877", + "right": "issue:46170", + "accept": false, + "reason": "granite_speech config strictness vs Windows ROCm torch.distributed import/type error; unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Tie-word-embeddings warning vs stale num_return_sequences warning in paged generate; different warnings and code paths." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch vs Qwen3.5 tie_word_embeddings warning; distinct loading vs config warning problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 37, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:41628", + "issue:42371", + "issue:42994", + "issue:43065", + "issue:43232", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43827", + "issue:43873", + "issue:44038", + "issue:44162", + "issue:44297", + "issue:44351", + "issue:44361", + "issue:44530", + "issue:44623", + "issue:44661", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44871", + "issue:44933", + "issue:44945", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45230", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45406", + "issue:45459", + "issue:45478", + "issue:45656", + "issue:46077", + "issue:46123", + "issue:46132", + "issue:46170", + "issue:46202" + ], + "soft_pairs": [ + "issue:43673|issue:44734", + "issue:44530|issue:46170", + "issue:43065|issue:46123", + "issue:44933|issue:45459", + "issue:44297|issue:44623", + "issue:44361|issue:44749", + "issue:44869|issue:45356", + "issue:43646|issue:44162", + "issue:43232|issue:43673", + "issue:44623|issue:45656", + "issue:44749|issue:45656", + "issue:43701|issue:44749", + "issue:43673|issue:43827", + "issue:44871|issue:46132", + "issue:45230|issue:45397", + "issue:42994|issue:43482", + "issue:43475|issue:45381", + "issue:43475|issue:43643", + "issue:28282|issue:30990", + "issue:44038|issue:44623", + "issue:46077|issue:46123", + "issue:45406|issue:46202", + "issue:42371|issue:45092", + "issue:41628|issue:44933", + "issue:43475|issue:44661", + "issue:42994|issue:43525", + "issue:45375|issue:45478", + "issue:45081|issue:45103", + "issue:45310|issue:45375", + "issue:43873|issue:44945", + "issue:41628|issue:44351" + ], + "prepared_review_unit_hash": "d080db09b54f121d0600490426d03eb76ac6a0a720da37f8ea7a1d28551094fb", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36838, + "estimated_input_tokens": 9210, + "estimated_eval_tokens": 18676 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous issue reports. A few are loosely related Transformers v5 loading/custom-model regressions, but none of the soft pairs are close enough to be treated as the same underlying bug or change, so I reject all soft edges. No pull requests are present. The broadest issue is the generic v5 custom-model initialization regression report.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43646 is the best umbrella candidate because it describes a broad Transformers 5.0 custom-model initialization regression that can plausibly encompass several narrower loading/meta-init failures in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the most generally applicable user-facing regression report among the issues here; the others are mostly model-specific or unrelated subsystems.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation/cache behavior, but they describe different concrete failures and code paths." + }, + { + "left": "issue:44530", + "right": "issue:46170", + "accept": false, + "reason": "PagedAttention/Qwen3.5 cache failure is unrelated to a Windows ROCm import/dependency problem." + }, + { + "left": "issue:43065", + "right": "issue:46123", + "accept": false, + "reason": "SAM3 pixel decoder dummy layer and mask pipeline batch handling are unrelated bugs." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "One is a missing import/export, the other is tokenizer error handling when protobuf is absent; not the same bug." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Both are save_pretrained regressions, but one concerns tokenizer config content while the other concerns processor file output." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and a post-upgrade performance slowdown are different issues." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Both mention tokenizer/codec problems, but they affect different models and failure modes." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "General custom-model init regression and ESM2 breakage are too different to merge as one bug." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both touch generation internals, but one is sync_gpus kwargs handling and the other is chunked_prefill cache state." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Processor save output files and optimizer stepping under deepspeed are unrelated." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Training slowdown after upgrade and duplicate optimizer stepping are unrelated." + }, + { + "left": "issue:43701", + "right": "issue:44749", + "accept": false, + "reason": "Checkpoint key mismatch and data filtering slowdown are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Generation cache regression and docs still referencing pipeline() are not the same underlying change." + }, + { + "left": "issue:44871", + "right": "issue:46132", + "accept": false, + "reason": "Gemma eos_token_id inconsistency and AttentionInterface.register behavior change are unrelated." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "The generic bug report has no evidence tying it to gemma-4 zero3 from_pretrained." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving and GGUF loading are different code paths." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Sam3 vision encoder output missing field and Qwen2.5-VL video position ids are different model bugs." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "A missing attribute on Sam3 output and missing fields from trust_remote_code config are not the same defect." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch missing import error and sentence-transformers loading hang are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe v5 bug and processor save_pretrained file omission are different issues." + }, + { + "left": "issue:46077", + "right": "issue:46123", + "accept": false, + "reason": "Gemma4 attention-mask construction and MaskGenerationPipeline final-batch handling are unrelated." + }, + { + "left": "issue:45406", + "right": "issue:46202", + "accept": false, + "reason": "Gemma4 processor missing _tokenizer and Gemma pipeline roundtrip on \u2581 are different bugs." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 settings guidance and InternVL2 meta-init incompatibility are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import errors, but they concern different symbols/modules and different failure mechanisms." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Sam3VisionEncoderOutput and add-new-model-like TOKENIZER_MAPPING_NAMES are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving and Llama4Config missing pad_token_id are different bugs." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5 MoE, but one is a missing strict field and the other is a from_pretrained regression; not enough to treat as the same bug." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Mistral regex patch tokenizer crash and auto_docstring future-annotations crash are unrelated." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen3.5 MoE regressions, but one is a generic loading error and the other is a specific vision-config field drop." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization offloading and pipeline-parallelism output correctness are different problems." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Different missing-import issues affecting different symbols; not the same underlying fix." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43479", + "issue:43504", + "issue:43526", + "issue:43673", + "issue:43704", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43976", + "issue:44038", + "issue:44079", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44792", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:45103", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45356", + "issue:45561", + "issue:45712", + "issue:45753", + "issue:45812" + ], + "soft_pairs": [ + "issue:43232|issue:44188", + "issue:42673|issue:43704", + "issue:44964|issue:45137", + "issue:44945|issue:45753", + "issue:36010|issue:41628", + "issue:42994|issue:43824", + "issue:42831|issue:44222", + "issue:44222|issue:45310", + "issue:43232|issue:44792", + "issue:43673|issue:44188", + "issue:44038|issue:45310", + "issue:42175|issue:45712", + "issue:43526|issue:45561", + "issue:44496|issue:45561", + "issue:43504|issue:45561", + "issue:42175|issue:44933", + "issue:43377|issue:44242", + "issue:42898|issue:44568", + "issue:42222|issue:45200", + "issue:43976|issue:44933", + "issue:30990|issue:35141", + "issue:43278|issue:45137", + "issue:43479|issue:44869", + "issue:43479|issue:44079", + "issue:44623|issue:45310", + "issue:30333|issue:33290", + "issue:42898|issue:45812", + "issue:43784|issue:43824", + "issue:44734|issue:45103", + "issue:43723|issue:44568", + "issue:42898|issue:44779", + "issue:42898|issue:45356" + ], + "prepared_review_unit_hash": "1099455bee87f0e63b283dca567f174fa7ffd646704ba91baa63ff9370639d9f", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "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 grab-bag of unrelated Transformers regressions (tokenizers, imports, model loading, FP8, generation, multimodal, etc.). Only the Qwen3ForCausalLM VRAM-leak reports look like a true duplicate pair; the rest are too different in code path or symptom to merge.", + "confidence": 0.87, + "canonical_issue_reason": "issue:42673 is the earlier, fuller report of the same Qwen3ForCausalLM multi-dataloader VRAM leak; issue:43704 is a duplicate with the same title/symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42673 is the strongest canonical issue candidate in this set because it has the clearest one-to-one duplicate match and the richer original bug report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Both are generation/runtime bugs, but they hit different mechanisms: sync_gpus kwargs update vs torch.compile attention-kernel branching." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same title, same Qwen3ForCausalLM VRAM leak symptom, and the later report is clearly the same bug." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "One is a Phi-4 multimodal load failure; the other is a DeepSpeed ZeRO3 deque IndexError. Different bugs." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline-parallelism output corruption and Qwen3_5 image infinite loop are different model/workflow failures." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different fixes; not the same underlying bug." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Quantized save failure and missing Qwen2.5-VL class import are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "FP8 accuracy drift and FP8 save_pretrained/moe serialization are different concrete issues." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "MoE save_pretrained failure vs Qwen3.5-MoE from_pretrained load error are not the same code path." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs/cache update bug and a janus test failure do not describe the same defect." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Chunked-prefill GenerationMixin cache issue and torch.compile attention divergence are separate generation bugs." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3-MoE, but one is a broader v5.0 compatibility issue and the other is a specific v5.4.0 from_pretrained regression." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "TensorFlow backend packaging and leftover dummy classes in dir(transformers) are unrelated maintenance issues." + }, + { + "left": "issue:43526", + "right": "issue:45561", + "accept": false, + "reason": "Beit label reduction bug and pytest-xdist file-race are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized model/config loading and captured_info.txt race are different problems." + }, + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "Legacy-field pretrained loading failure and xdist file race are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Packaging dependency mismatch and a missing image_utils import are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Padding-mask mismatch in MIMI encoder vs missing load-balancing loss when router logits are off are distinct bugs." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer cleanup-space behavior change and missing BOS/EOS insertion are different tokenizer regressions." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Broken vitpose model loading and Gemma 4 mm_token_type_ids defaulting are unrelated model/config issues." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version compatibility and nonexistent import from image_utils are unrelated." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence-transformers loading hang and embedding reinitialization on resize are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Dtype drift between train/eval and a ZeRO3 deque IndexError are different failures." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Default multimodal config initialization and Whisper word-timestamp decode crash are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Default config construction and ModelOutput key assignment are different bugs." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Missing processor save files and Qwen3.5-MoE from_pretrained loading error are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on training failure and Adafactor OOM in DeepSpeed are unrelated." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one is cleanup-space behavior and the other is wrong token IDs for Granite; different underlying issues." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Sentence-transformers import NameError and missing Qwen2.5-VL class import are unrelated import failures." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "KV-cache continuation crash in serve and auto_docstring AttributeError under future annotations are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "AutoTokenizer loading regression and add_special_tokens BOS/EOS regression are different tokenizer bugs." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Different tokenizer regressions affecting different models/symptoms; not the same bug." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Clean-up-space change and Kimi-K2.5 codec/regex regression are unrelated tokenizer issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft pair, issue:42673 vs issue:43704, is strongly supported by identical titles and matching symptom. The remaining verdicts are appropriately cautious and do not overstate 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": 39, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30333", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43122", + "issue:43232", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43761", + "issue:43874", + "issue:44060", + "issue:44190", + "issue:44206", + "issue:44222", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44448", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44933", + "issue:44977", + "issue:45071", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45245", + "issue:45310", + "issue:45405", + "issue:45406", + "issue:45656", + "issue:45712", + "issue:45834", + "issue:46082", + "issue:46132", + "issue:46209" + ], + "soft_pairs": [ + "issue:43874|issue:45092", + "issue:44060|issue:45125", + "issue:45405|issue:45712", + "issue:42898|issue:44448", + "issue:44295|issue:45656", + "issue:44448|issue:46132", + "issue:44933|issue:45712", + "issue:44222|issue:44297", + "issue:44297|issue:45656", + "issue:43479|issue:43644", + "issue:44190|issue:46082", + "issue:44222|issue:44623", + "issue:30333|issue:34689", + "issue:42831|issue:44623", + "issue:43122|issue:46209", + "issue:30333|issue:36331", + "issue:22355|issue:28282", + "issue:28282|issue:30333", + "issue:45245|issue:46132", + "issue:30333|issue:35141", + "issue:45071|issue:46082", + "issue:41628|issue:42757", + "issue:44206|issue:45103", + "issue:44297|issue:45310", + "issue:43723|issue:44977", + "issue:43232|issue:45834", + "issue:44263|issue:45092", + "issue:43761|issue:46082", + "issue:44222|issue:44484", + "issue:44295|issue:44623", + "issue:44373|issue:44485", + "issue:44483|issue:45406", + "issue:44514|issue:45103", + "issue:44263|issue:44360" + ], + "prepared_review_unit_hash": "c01abc47d7ff4f427c61f70e9fcbcee59cf06a36e584dd8e4deaa521d56bfefd", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37624, + "estimated_input_tokens": 9406, + "estimated_eval_tokens": 19068 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated issue reports that only share superficial keyword overlap (imports, v5 regressions, save/load, multimodal, FP8, trainers). None of the soft pairs looks like the same underlying bug or change, so all soft edges should be rejected.", + "confidence": 0.95, + "canonical_issue_reason": "No single canonical issue is safe here: the items span many distinct bugs and regressions rather than one duplicate thread.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a strong global representative; the set is heterogeneous and the apparent matches are only lexical, not the same code-path failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Different failures: missing image patch method in GLM46V vs meta-init incompatibility in old InternVL2 checkpoints." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Both mention Qwen MoE, but one is a tied-weights warning bug and the other is a missing tensor-parallel plan." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "PEFT version bump mismatch and leftover dummy classes are unrelated packaging/check-repo issues." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Tokenization-space cleanup behavior and Pegasus output differences are separate tokenizer/model-output regressions." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Position_ids buffer reading error is unrelated to the deepspeed optimizer-step duplication bug." + }, + { + "left": "issue:44448", + "right": "issue:46132", + "accept": false, + "reason": "Pegasus v4/v5 output differences do not match an AttentionInterface registration behavior change." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "An image_utils import problem is not the same as stale dummy classes leaking into dir(transformers)." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "FP8 save_pretrained behavior for MoE models is unrelated to tokenizer_class mismatch on save_pretrained." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save metadata corruption and duplicated optimizer steps are unrelated bugs." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Phi4Multimodal config defaults and non-persistent buffer junk initialization are different initialization paths." + }, + { + "left": "issue:44190", + "right": "issue:46082", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to LlamaConfig head_dim validation." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "MoE FP8 save_pretrained and processor.save_pretrained missing files are different save-path issues." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "MLFlow reporting on failed training jobs is unrelated to a Llama 3.2 Vision model-loading regression." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FineGrainedFP8 accuracy and processor save_pretrained missing files are not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:46209", + "accept": false, + "reason": "Tokenization differences across versions and FP8 inference failure on B200 are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLFlow job-state reporting and CustomTrainer compute_loss signature mismatch are separate trainer issues." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Missing transformers.onnx module and missing PyTorch dependency are distinct import errors." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "PyTorch import requirement failure is unrelated to MLFlow reporting behavior." + }, + { + "left": "issue:45245", + "right": "issue:46132", + "accept": false, + "reason": "Category-count runtime error and AttentionInterface registration behavior are unrelated APIs." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Failed training job reporting and embedding resize reinitialization are unrelated trainer/model-init bugs." + }, + { + "left": "issue:45071", + "right": "issue:46082", + "accept": false, + "reason": "PretrainedConfig type checking regression is unrelated to LlamaConfig head_dim validation." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "AutoImageProcessor import failure and is_offline_mode import failure are different missing-symbol issues." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Unsupported center argument in a feature extractor is unrelated to the auto-docstring AttributeError with future annotations." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer save metadata mismatch and Qwen3.5 MoE from_pretrained error are different failure modes." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading in v5 and Qwen3.5 flash-attention generation problems are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is not the same as Kosmos2.5 OCR long-input index error." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "torch.split return values in a GLM MoE indexer are unrelated to old InternVL2 meta-init incompatibility." + }, + { + "left": "issue:43761", + "right": "issue:46082", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression is unrelated to LlamaConfig head_dim rejection." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE save_pretrained bug and max_shard_size default question are not the same issue." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Position_ids buffer access error does not match missing processor save_pretrained files." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "A wrong docstring and a GLM-5 RoPE implementation discussion are not duplicate bugs." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat completions endpoint acceptance failure is unrelated to Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched apply_chat_template crash is unrelated to the auto-docstring future-annotations AttributeError." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA/GLM, but one is a torch.split return-value bug and the other is a discussion about a missing ReLU; not the same underlying 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": 40, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:30990", + "issue:33357", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43122", + "issue:43232", + "issue:43479", + "issue:43576", + "issue:43646", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44373", + "issue:44442", + "issue:44521", + "issue:44568", + "issue:44671", + "issue:44704", + "issue:44829", + "issue:44871", + "issue:44913", + "issue:44991", + "issue:45092", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45593", + "issue:45753", + "issue:46002", + "issue:46050", + "issue:46132" + ], + "soft_pairs": [ + "issue:45092|issue:45357", + "issue:43723|issue:44871", + "issue:30990|issue:38175", + "issue:42907|issue:46050", + "issue:44261|issue:45092", + "issue:43723|issue:44991", + "issue:44829|issue:46002", + "issue:43723|issue:44442", + "issue:43479|issue:44913", + "issue:41628|issue:43824", + "issue:42831|issue:45310", + "issue:44263|issue:44373", + "issue:42831|issue:44038", + "issue:39401|issue:44568", + "issue:42757|issue:45278", + "issue:43232|issue:45593", + "issue:42886|issue:42994", + "issue:42886|issue:43066", + "issue:22355|issue:28218", + "issue:42831|issue:45753", + "issue:43756|issue:44060", + "issue:44117|issue:44704", + "issue:44671|issue:46132", + "issue:43576|issue:43784", + "issue:43646|issue:46002", + "issue:43122|issue:44521", + "issue:42371|issue:44263", + "issue:30990|issue:33357" + ], + "prepared_review_unit_hash": "4aaa9316b424e5e6c526ff7f468f1361eac9a8a9d301fc14f6e54af5bf933265", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35096, + "estimated_input_tokens": 8774, + "estimated_eval_tokens": 17804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The candidate edges are mostly broad topical similarities rather than true duplicates. They span unrelated tokenizer, import, quantization, configuration, and model-specific regressions, so I would reject all soft pairs as the same underlying bug/change.", + "confidence": 0.87, + "canonical_issue_reason": "issue:43723 is the broadest representative of the cluster\u2019s recurring v5 tokenizer-loading regressions; several other items are narrower or model-specific variants, but none are clear duplicates of it.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43723 is the best overall issue representative because it captures the central failure mode repeated across multiple nearby reports: tokenizer loading breakage in Transformers v5.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Both are multimodal save/load regressions, but they affect different model families and different failure modes; not the same concrete bug." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Both involve tokenizer/model loading in v5, but one is a generic AutoTokenizer loading failure and the other is an eos_token_id configuration inconsistency." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Completely different symptoms and model areas: sentence-transformers loading hang vs zero probabilities in a SigLIP model." + }, + { + "left": "issue:42907", + "right": "issue:46050", + "accept": false, + "reason": "Both concern quantized model persistence, but they target different quantization flows and different save/load failure paths." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "Unrelated bugs: MLA layernorm precision/config issue vs remote-code meta-initialization incompatibility." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer loading reports, but they concern different models and likely different tokenizer registration/mapping causes." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "Different problems: flash_attention_3 training degeneration vs NaNs during classification-head init/checkout." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Both are AutoTokenizer loading failures, but for different tokenizers and likely different missing-registration issues." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Different config serialization bugs in different model families; not the same code path." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different missing exports and different classes; too broad to merge." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "Different issues: FineGrainedFP8 accuracy regression vs Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "A torch.split behavior report and a docstring issue are not the same underlying bug." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Different model/regression reports with no shared concrete failure mode." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer behavior bugs, but one is offset_mapping and the other is add_special_tokens/BOS-EOS handling; different code paths." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "The second is a broad collection of import errors, not the same single bug as the specific is_offline_mode import failure." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Unrelated generation-state bug vs D-FINE auxiliary-loss behavior." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Different persistence/loading failures: offline tokenizer cache loading vs quantized model save failure." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Tokenizer cache offline loading and wrong tokenizer decoder type are distinct failures." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "No shared concrete bug: missing module import vs tokenizer adding an extra space." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "Accuracy regression in FP8 training is unrelated to an infinite-loop multimodal inference bug." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Different model-specific implementation bugs: RoPE-layer dropping vs incorrect tied-weights warning behavior." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Both are loading-path issues, but one is tokenizer mapping fallback and the other is AutoProcessor kwargs forwarding." + }, + { + "left": "issue:44671", + "right": "issue:46132", + "accept": false, + "reason": "Masked LM prediction regression and AttentionInterface.register behavior change are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "A CLI/env command breakage and an import NameError in sentence-transformers are different issues." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Different initialization regressions; no evidence they stem from the same underlying change." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Different areas: tokenization drift across versions vs multimodal assistant_mask computation." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings guidance and a torch.split return-value report are unrelated." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Different symptoms and systems: loading hang vs macOS bus error on a CLIP model." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29159", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42907", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43278", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43784", + "issue:43824", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44188", + "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:45446", + "issue:45478", + "issue:45600" + ], + "soft_pairs": [ + "issue:44295|issue:44297", + "issue:44704|issue:45290", + "issue:44188|issue:44373", + "issue:42907|issue:44945", + "issue:41628|issue:45278", + "issue:43232|issue:44743", + "issue:43784|issue:45600", + "issue:44261|issue:44373", + "issue:39401|issue:44488", + "issue:43976|issue:44945", + "issue:43122|issue:44514", + "issue:43408|issue:43475", + "issue:42907|issue:43937", + "issue:39401|issue:44521", + "issue:44625|issue:44829", + "issue:43116|issue:45200", + "issue:44360|issue:44485", + "issue:42907|issue:44964", + "issue:44038|issue:44297", + "issue:44038|issue:44295", + "issue:28218|issue:30990", + "issue:43122|issue:44779", + "issue:42907|issue:43452", + "issue:36296|issue:43116", + "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:43122|issue:43906", + "issue:45216|issue:45478", + "issue:43784|issue:45446", + "issue:42757|issue:44351", + "issue:22355|issue:29159", + "issue:43278|issue:44945" + ], + "prepared_review_unit_hash": "4041b766c39146bfa13c1ed876411b810ce551139676803211307530ec2d3514", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36912, + "estimated_input_tokens": 9228, + "estimated_eval_tokens": 18712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated transformer issues with only superficial lexical similarity. I found no soft pair that clearly refers to the same underlying bug or change, so all candidate links are rejected.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "One is about reading a registered buffer; the other is about tokenizer_class metadata on save. Different failure modes and code paths." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor kwargs plumbing to cached_file is unrelated to apply_chat_template crashing on tool-call messages." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "torch.compile attention divergence and a wrong docstring for position_ids are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals and wrong pipeline-parallel outputs are different bugs." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Both mention import errors, but they concern different symbols and likely different regressions." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both are generation-related, but one is sync_gpus kwargs handling and the other is cache-state reset logic." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Sentence-transformers import NameError and auto_mappings references to removed configs are not the same issue." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A precision bug in MLA layernorm config is unrelated to a docstring issue for position_ids." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Wrong offset_mapping for Qwen3 tokenizer and failure to load cjvt/sleng-bert are separate tokenizer problems." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version compatibility and pipeline parallel output correctness are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "General tokenizer regression across versions and a batched apply_chat_template crash are different code paths." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Wrong model-class warning and a missing attribute on the SAM3 vision encoder output are not the same bug." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Dequantized save_pretrained failure and invalid GenerationConfig for GLM-5 are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Offset mapping errors and zero assistant masks in multimodal apply_chat_template are distinct tokenizer/template issues." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation in Qwen3.5 and flash_attention_3 training degeneration are unrelated." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Empty multi-label example output and mm_token_type_ids defaults in Gemma 4 affect different features." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "A missing ReLU in DSA indexer is unrelated to GLM-5 RoPE implementation details." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe loading and tokenizer_class mismatch on save are different problems." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Model loading for Qwen3-VL-Moe does not match a position_ids buffer access error." + }, + { + "left": "issue:28218", + "right": "issue:30990", + "accept": false, + "reason": "Tokenizer spacing after added token and Sentence Transformers hanging on load are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and behaviors." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models and gguf_file breakage in from_pretrained are different loading/saving paths." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor parallel training bugs and empty multi-label example outputs are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Missing Qwen2_5_VLForConditionalGeneration and missing HybridCache are different missing-export/import errors." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe loading and FP8 save_pretrained for MoE are not the same concrete bug." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "A version-to-version tokenization regression is not the same as an isolated reproduction of another issue." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 and save/load regressions, but one is about save_pretrained checkpoints and the other about from_pretrained loading; too different to merge." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "A missing nn import in sentence-transformers is unrelated to a PyTorch version check in flex_attention." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Missing is_offline_mode from huggingface_hub and missing HybridCache from transformers are separate import regressions." + }, + { + "left": "issue:22355", + "right": "issue:29159", + "accept": false, + "reason": "An absent transformers.onnx module and slow/fast tokenizer inconsistency are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Embedding dtype drift in evaluate is unrelated to incorrect outputs under pipeline parallelism." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:43064", + "issue:43066", + "issue:43116", + "issue:43441", + "issue:43450", + "issue:43493", + "issue:43611", + "issue:43673", + "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:44380", + "issue:44485", + "issue:44704", + "issue:44779", + "issue:44936", + "issue:44938", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45083", + "issue:45278", + "issue:45357", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753", + "issue:46002", + "issue:46077" + ], + "soft_pairs": [ + "issue:42175|issue:44938", + "issue:42673|issue:45072", + "issue:43493|issue:45753", + "issue:43066|issue:44779", + "issue:43992|issue:44704", + "issue:38617|issue:45278", + "issue:22355|issue:29127", + "issue:43611|issue:46002", + "issue:43937|issue:44485", + "issue:42222|issue:43441", + "issue:43976|issue:45446", + "issue:43116|issue:43493", + "issue:42371|issue:43874", + "issue:44075|issue:44936", + "issue:45357|issue:45478", + "issue:44038|issue:45478", + "issue:43064|issue:43673", + "issue:43116|issue:43825", + "issue:45083|issue:45446", + "issue:44380|issue:46077", + "issue:43937|issue:45563", + "issue:44117|issue:45588", + "issue:33453|issue:39401", + "issue:39401|issue:44779", + "issue:43827|issue:45446", + "issue:42673|issue:43906", + "issue:44291|issue:45071", + "issue:43450|issue:43986", + "issue:43937|issue:44977" + ], + "prepared_review_unit_hash": "8344b9a73ae8b746df9dc4f88fed3006f03efd0956eb2f8f13237cc0fa8a8e99", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36033, + "estimated_input_tokens": 9009, + "estimated_eval_tokens": 18274 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated Transformers issues that only share broad themes like v5 regressions, tokenizers, or multimodal models. The soft-edge candidates are superficially similar but do not describe the same concrete bug/change, so none should be merged. No PRs are present.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the broadest user-facing regression report in the set (many import errors after upgrading from 4.57.0 to 5.5.0), so it's the most representative issue if one must be chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Packaging/backend dependency mismatch vs a Python 3.14 import/load failure; different failure modes and code paths." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM threading vs dtype mismatches in inference; unrelated models and bugs." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 implementation discrepancy vs Qwen3.5 image-triggered infinite loop; both multimodal, but not the same defect." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer decoder type regression vs Deepseek tokenizer output regression; same broad area, but distinct underlying problems." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing encoder weights during load vs AutoProcessor kwargs forwarding; different components and symptoms." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Single missing import symbol vs broad upgrade-caused import failures; the latter is an umbrella report, not the same concrete bug." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "ONNX import failure vs a LayoutLMv3 error-message clarity issue; not the same bug." + }, + { + "left": "issue:43611", + "right": "issue:46002", + "accept": false, + "reason": "base_model_prefix loading regression vs NaNs in classification heads; different code paths and outcomes." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GenerationConfig validation failure vs GLM-5 RoPE implementation discussion; related model family, but not the same change or bug." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "VitPose breakage vs Ministral-3 FlashAttention failure; separate models and distinct failure mechanisms." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility break vs PyTorch version check in flex_attention; both version-related, but not the same issue." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example-script multi-label behavior vs SigLIP2 implementation discrepancy; unrelated functionality." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API messaging vs missing image-patch helper in GLM46V; completely different subsystems." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Optimizer arguments ignored vs train/evaluate interaction failure; different training bugs." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "save_pretrained saves wrong visual encoder keys vs from_pretrained error for Qwen3.5 Moe; same family, but different concrete paths." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL-Moe breakage vs Qwen3.5 Moe load error; too different in model/version and symptom." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption vs missing GenerationMixin cache during chunked prefill; unrelated training vs generation bugs." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Classification example output bug vs pipeline() translation-support messaging; different user flows and defects." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Qwen3 Omni-MoE feature-length helper behavior vs flex_attention version gating; unrelated code paths." + }, + { + "left": "issue:44380", + "right": "issue:46077", + "accept": false, + "reason": "GPT2 attention scaling ignored in SDPA/FlashAttention vs Gemma4 bidirectional mask construction; both attention-related but not the same bug." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "Invalid GenerationConfig vs stale warning for num_return_sequences; different generation-layer issues." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer mapping fallback bug vs flash_attention AttributeError on s_aux=None; unrelated components." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Generic tokenizer loading regression vs Qwen3 offset_mapping bug; the latter is much more specific." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Qwen3 offset mapping bug vs Deepseek tokenizer regression; same broad area, different model-specific issues." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing pipeline() vs PyTorch version check in flex_attention; docs cleanup is not the same as a runtime version bug." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "VRAM leak report vs isolated reproduction of another issue; not enough evidence they are the same underlying bug." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights TypeError vs PretrainedConfig type-checking regression; both v5 load-time issues, but different failure points and causes." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video processor shape bug vs missing-torchvision crash when loading video model; distinct defects." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig invalid vs Qwen3.5 flash-attention generation failure; not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 43, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "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:43097", + "issue:43122", + "issue:43408", + "issue:43421", + "issue:43577", + "issue:43582", + "issue:43673", + "issue:43742", + "issue:43937", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44410", + "issue:44466", + "issue:44483", + "issue:44484", + "issue:44493", + "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", + "issue:46002", + "issue:46178" + ], + "soft_pairs": [ + "issue:44466|issue:46002", + "issue:45405|issue:45446", + "issue:44117|issue:45081", + "issue:45341|issue:45561", + "issue:42222|issue:46178", + "issue:38617|issue:41628", + "issue:44410|issue:45310", + "issue:42617|issue:45341", + "issue:44829|issue:45216", + "issue:42673|issue:43582", + "issue:39401|issue:43421", + "issue:42490|issue:42673", + "issue:43408|issue:43742", + "issue:42371|issue:44261", + "issue:44933|issue:45278", + "issue:38617|issue:44220", + "issue:44484|issue:45310", + "issue:43937|issue:44496", + "issue:43066|issue:43122", + "issue:42222|issue:45542", + "issue:44483|issue:45464", + "issue:42371|issue:42831", + "issue:42175|issue:42222", + "issue:44075|issue:45656", + "issue:44410|issue:45478", + "issue:43012|issue:43577", + "issue:43673|issue:45341", + "issue:43097|issue:44493", + "issue:41628|issue:45071" + ], + "prepared_review_unit_hash": "19149ae030576a3d84ed43d3e25e9c918c46fa463e232a17140962f27e8c9433", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36142, + "estimated_input_tokens": 9036, + "estimated_eval_tokens": 18328 + }, + "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 (imports, tokenizers, model loading, optimizer behavior, backend/version checks). Only one soft edge looks like a plausible duplicate: a specific import failure fitting under a broader post-upgrade import-regression report.", + "confidence": 0.39, + "canonical_issue_reason": "issue:45278 is the best umbrella representative because it explicitly describes the broader import-regression pattern after upgrading from 4.57.0 to 5.5.0.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most central and reusable summary of the cluster\u2019s closest shared theme: broad import errors after a version upgrade.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "Different bugs: tied-weight serialization vs NaNs in classification heads." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Separate dependency/version issues with different affected code paths." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizers, but one is mapping-name handling and the other is a Mistral regex/backend attribute crash." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "The second is a specific xdist race in testing_utils; the first is too vague to treat as the same bug." + }, + { + "left": "issue:42222", + "right": "issue:46178", + "accept": false, + "reason": "VitPose model breakage and a tensorflow_text backend-mapping error are unrelated." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but for different symbols and different breakages." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Different Qwen model families and different failures." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated issues: a script runtime failure vs a testing_utils bug." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Training degeneration with flash_attention_3 is not the same as a save_pretrained regression." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "Both mention memory-ish symptoms, but one is a VRAM leak and the other is an Apple Silicon TypeError." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Offset-mapping bug and runtime special-token post-processor update are different tokenizer issues." + }, + { + "left": "issue:42490", + "right": "issue:42673", + "accept": false, + "reason": "Local-path import warning is unrelated to a Qwen3 VRAM leak." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Model-type warning and MobileLLM key error are different loading problems." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API warning and missing rms_norm_eps are unrelated." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": true, + "reason": "45278 is a broad umbrella for post-upgrade import errors, and 44933 reads like one specific missing import under that same regression." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "Different import/path vs feature-function failure; not the same underlying bug." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "Different API/model-loading failures." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "GenerationConfig validation and unrecognized-model config errors are distinct." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both are v5 tokenizer regressions, but they describe different concrete symptoms and code paths." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "VitPose model breakage is unrelated to missing TensorFlow in a backend install." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both mention chat/completions, but one is a general request rejection and the other is a Qwen3.5 streaming failure." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 behavior control and FineGrainedFP8 accuracy issues are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Backend-install packaging issue and VitPose model breakage are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "Different optimizer bugs: SGD args ignored vs double optimizer step under deepspeed." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen model variants and different failure modes." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Compile-time warning about bfloat16 precision is not the same as Blip2 dtype fields remaining float32 on load." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "Generation cache/chunked_prefill bug is unrelated to a testing_utils issue." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Removal of a config field and unexpected position-id keys are different issues." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Importing AutoImageProcessor and PreTrainedConfig type-checking are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The cluster does look heterogeneous, and the one accepted soft edge (44933 \u2194 45278) is a plausible umbrella-duplicate relationship based on the issue titles. The other pair verdicts are cautious and supported by the visible symptoms in 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": 44, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:38617", + "issue:42757", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43502", + "issue:43531", + "issue:43673", + "issue:43824", + "issue:43873", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44704", + "issue:44829", + "issue:44987", + "issue:45003", + "issue:45071", + "issue:45103", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45440", + "issue:45478", + "issue:45542", + "issue:45588", + "issue:46050", + "issue:46123", + "issue:46172" + ], + "soft_pairs": [ + "issue:43874|issue:44261", + "issue:44263|issue:44485", + "issue:45071|issue:45542", + "issue:44263|issue:46172", + "issue:44360|issue:46172", + "issue:43012|issue:43408", + "issue:43441|issue:44829", + "issue:44484|issue:45478", + "issue:43931|issue:44410", + "issue:43335|issue:45071", + "issue:43931|issue:44038", + "issue:43673|issue:46123", + "issue:43097|issue:43452", + "issue:45003|issue:45341", + "issue:43986|issue:45341", + "issue:44117|issue:44987", + "issue:43874|issue:44263", + "issue:43408|issue:44368", + "issue:43986|issue:44484", + "issue:43531|issue:45341", + "issue:43986|issue:45372", + "issue:45440|issue:46172", + "issue:44261|issue:44485", + "issue:38617|issue:42757", + "issue:43097|issue:46050", + "issue:43097|issue:45588", + "issue:43064|issue:44315", + "issue:44062|issue:44117", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:44038|issue:44410", + "issue:43502|issue:43992", + "issue:43097|issue:43873", + "issue:44704|issue:45103", + "issue:43986|issue:44117", + "issue:43824|issue:43986", + "issue:43066|issue:43906" + ], + "prepared_review_unit_hash": "c848b961e48e457497a59c0eddde0976c45db59e8c078cec8e0c03ac6cab2cda", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38785, + "estimated_input_tokens": 9697, + "estimated_eval_tokens": 19650 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is not a true duplicate cluster; it mixes unrelated Transformers regressions, import/export breakages, model-family-specific bugs, and warning/typing issues. I would not merge any of the soft edges.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43986 is the most self-contained, user-facing regression in the set and the clearest anchor for a loading-path bug, but the surrounding items are too heterogeneous to treat this as a real duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "43986 is the best representative only in the sense that it is concrete and actionable; it is still not a good umbrella for the rest of the set because most neighbors are unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Different failures in different GLM-related paths: image-patch counting vs RMS norm precision config." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "Same broad GLM area, but distinct bugs: DSA indexer split behavior vs RoPE implementation." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Unrelated regressions: PretrainedConfig type-checking vs TensorFlow backend detection when only tensorboard is installed." + }, + { + "left": "issue:44263", + "right": "issue:46172", + "accept": false, + "reason": "Different model families and code paths; DSA indexer split handling is unrelated to DeepSeek transpose logic." + }, + { + "left": "issue:44360", + "right": "issue:46172", + "accept": false, + "reason": "Distinct model/code-path bugs: missing ReLU in DSA indexer vs DeepSeek tensor conversion/transpose." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Both are warnings, but they come from different models and different mechanisms." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Both mention FlashAttention, but one is a loading failure and the other is degenerate training; not the same bug." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "A save_pretrained shard-size question is unrelated to Qwen3.5 MoE from_pretrained errors." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Different Qwen model problems with different symptoms and affected layers; not one concrete bug." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "Sparse-layer creation in SwitchTransformers is unrelated to a v5 PretrainedConfig type-checking regression." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Both are Qwen-related loading issues, but they affect different models and failure modes." + }, + { + "left": "issue:43673", + "right": "issue:46123", + "accept": false, + "reason": "Generation cache handling during chunked prefill is unrelated to MaskGenerationPipeline batch-finalization behavior." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Configuration removal warning vs gguf_file/from_pretrained loading breakage; different code paths." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "sys.modules access bug is unrelated to a testing_utils bug." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "AutoProcessor crashing without torchvision is not the same issue as the testing_utils bug." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None handling is a different loading bug than the physical-intelligence/fast regression." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Different GLM subcomponents and different failure signatures." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Model-type warning for sam3 is unrelated to a tie_word_embeddings warning in a Qwen fine-tuning setup." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "Optional-dependency crash in AutoProcessor is unrelated to a save_pretrained shard-size question." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to the testing_utils bug." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Missing torchvision crash is unrelated to the mistral_common ReasoningEffort import failure." + }, + { + "left": "issue:45440", + "right": "issue:46172", + "accept": false, + "reason": "DeepSeek implementation divergence is a different problem from the comb.to(dtype).transpose(-1, -2) bug." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Missing rms_norm_eps precision issue is unrelated to the GLM-5 RoPE implementation bug." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols in different modules and are not the same bug." + }, + { + "left": "issue:43097", + "right": "issue:46050", + "accept": false, + "reason": "Tie-embeddings removal and quantized save/load corruption are unrelated regressions." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Removed config flag warning and flash_attention s_aux=None crash are different code-path issues." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Distributed optimizer-state corruption is unrelated to Liger Kernel not being applied with model_init." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken constructor argument collision is unrelated to tokenizer mapping returning None." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Missing attention projections in qwen3next is unrelated to a missing deepstack_visual_indexes config field." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Different import failures: layer_type_validation vs HybridCache, with no shared code path." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Both are Qwen-family regressions, but they affect different models and different architectural components." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Ignoring local_files_only is unrelated to a missing embed_tokens.weight during UMT5Encoder loading." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Config/removal behavior is unrelated to quantization offloading not working as expected." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "kwargs propagation to cached_file is unrelated to the docstring annotation crash." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "AutoProcessor without torchvision and TOKENIZER_MAPPING_NAMES returning None are separate loading problems." + }, + { + "left": "issue:43824", + "right": "issue:43986", + "accept": false, + "reason": "Missing Qwen2_5_VLForConditionalGeneration export and missing torchvision in AutoProcessor are different failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 45, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42907", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43550", + "issue:43582", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43792", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44162", + "issue:44222", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:44938", + "issue:45290", + "issue:45478", + "issue:45479", + "issue:45698", + "issue:45753", + "issue:46123", + "issue:46132", + "issue:46172", + "issue:46178", + "issue:46209" + ], + "soft_pairs": [ + "issue:44938|issue:46178", + "issue:43208|issue:43550", + "issue:43992|issue:44484", + "issue:43825|issue:44655", + "issue:43012|issue:43550", + "issue:43012|issue:44368", + "issue:42907|issue:44655", + "issue:42907|issue:45753", + "issue:43352|issue:44380", + "issue:44162|issue:46172", + "issue:43352|issue:43976", + "issue:44380|issue:46132", + "issue:43792|issue:46123", + "issue:44380|issue:45479", + "issue:43064|issue:44380", + "issue:44483|issue:44514", + "issue:43208|issue:43526", + "issue:36683|issue:43582", + "issue:44222|issue:45478", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:43618|issue:43761", + "issue:42490|issue:43012", + "issue:45698|issue:46172", + "issue:43618|issue:44380", + "issue:38617|issue:43502", + "issue:44038|issue:44230", + "issue:44483|issue:45290", + "issue:43756|issue:44485", + "issue:43066|issue:46209", + "issue:43299|issue:43867", + "issue:36683|issue:43475" + ], + "prepared_review_unit_hash": "058e0df70daac2a2ba0e06e81280cf75cb8f49d484fbcd355ede9089ebf02348", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36948, + "estimated_input_tokens": 9237, + "estimated_eval_tokens": 18730 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is largely heterogeneous: the paired items share broad Transformers themes (loading, attention, FP8, chat templates, etc.) but not the same concrete defect. I would not merge any of the soft pairs as duplicates.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44938", + "right": "issue:46178", + "accept": false, + "reason": "Different failures: Python 3.14 import/load issue vs invalid backend mapping for tensorflow_text." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training bugs and Bamba SDPA/torch.compile failure are unrelated code paths." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing embed token weight on load is not the same as save_pretrained shard-size behavior." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline task warning text and saving Pipeline objects are distinct bugs." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "BF16 compile warning is unrelated to Bamba SDPA compile failure." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "PyTorch precision warning and Qwen3.5 LoRA warning come from different mechanisms." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Dequantized model save failure is not the same as generic Pipeline save_pretrained support." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Save/dequantization bug is unrelated to Qwen3.5 image-specific infinite loop." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "FlashAttention support error for Nemotron is different from GPT2 attention scaling being ignored." + }, + { + "left": "issue:44162", + "right": "issue:46172", + "accept": false, + "reason": "ESM2 breakage and deepseek-v4 tensor transpose issue are unrelated models and bugs." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "FlashAttention support error is unrelated to Python version compatibility." + }, + { + "left": "issue:44380", + "right": "issue:46132", + "accept": false, + "reason": "Attention scaling regression and AttentionInterface.register behavior change are separate issues." + }, + { + "left": "issue:43792", + "right": "issue:46123", + "accept": false, + "reason": "Whisper runtime failure and MaskGenerationPipeline partial-batch dropping are different pipelines and symptoms." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention backend scaling bug is unrelated to zero-loss classification behavior." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP/PEFT optimizer-state corruption is not the same as attention scaling being ignored." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Chat-completions API acceptance and Qwen2.5-VL chat-template crash are separate request-handling bugs." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs do not match BeitImageProcessorFast label reduction behavior." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Gemma3Config missing vocab_size and Apple Silicon caching_allocator_warmup TypeError are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Both involve MoE/FP8, but one is save_pretrained and the other from_pretrained loading; not the same concrete bug." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "BF16 warning is unrelated to compiled flex_attention failure on torch>=2.9." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Missing is_offline_mode import and missing Qwen2.5-VL symbol are different import regressions." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "CLIPOutput attentions assignment and CLIPVisionModel hidden_states regression are different CLIP bugs." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Trailing-slash local model warning and bf16 compile warning are unrelated." + }, + { + "left": "issue:45698", + "right": "issue:46172", + "accept": false, + "reason": "Wrong custom module after save/load and deepseek-v4 tensor transpose are different serialization vs model-shape issues." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP attentions regression and GPT2 attention scaling regression affect different models and code paths." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Missing configuration_utils import and local_files_only network requests are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Qwen3-VL-Moe loading bug and fp8 inference support issue are different failures." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Generic /v1/chat/completions compatibility issue and assistant tool-call templating crash are not the same bug." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Smollm3 RoPE layer mismatch and GLM-5 RoPE implementation discussion are related only by topic, not by defect." + }, + { + "left": "issue:43066", + "right": "issue:46209", + "accept": false, + "reason": "Tokenizer decoder type bug in v5 and FP8 inference failure on B200 are different subsystems." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL MoE loading regression and sorted-state_dict load error are different load-path failures." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config vocab_size AttributeError and SAM3 vision encoder missing fpn_position_embeddings are unrelated model classes." + } + ] + }, + "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": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:36010", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42490", + "issue:42757", + "issue:42890", + "issue:42994", + "issue:43010", + "issue:43064", + "issue:43299", + "issue:43352", + "issue:43525", + "issue:43575", + "issue:43611", + "issue:43618", + "issue:43867", + "issue:43901", + "issue:43931", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44075", + "issue:44077", + "issue:44242", + "issue:44246", + "issue:44355", + "issue:44380", + "issue:44492", + "issue:44625", + "issue:44655", + "issue:44855", + "issue:44938", + "issue:45071", + "issue:45216", + "issue:45276", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45478", + "issue:45561", + "issue:45593", + "issue:45753", + "issue:45850", + "issue:46077", + "issue:46082", + "issue:46202" + ], + "soft_pairs": [ + "issue:45276|issue:46077", + "issue:42994|issue:44655", + "issue:43901|issue:44655", + "issue:36010|issue:42757", + "issue:43299|issue:45753", + "issue:44077|issue:44380", + "issue:36683|issue:44077", + "issue:44625|issue:46077", + "issue:43611|issue:44655", + "issue:43352|issue:43937", + "issue:43867|issue:45216", + "issue:46077|issue:46082", + "issue:43976|issue:44938", + "issue:43352|issue:45593", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:36683|issue:44242", + "issue:43352|issue:43931", + "issue:43064|issue:44492", + "issue:43010|issue:45278", + "issue:43992|issue:45310", + "issue:43867|issue:46202", + "issue:44355|issue:44855", + "issue:43867|issue:45375", + "issue:41669|issue:44246", + "issue:36683|issue:43064", + "issue:44938|issue:45071", + "issue:42890|issue:45561", + "issue:43010|issue:45850", + "issue:43867|issue:45357", + "issue:42490|issue:44075", + "issue:43992|issue:45478", + "issue:43618|issue:44077", + "issue:43010|issue:43976", + "issue:36296|issue:43575" + ], + "prepared_review_unit_hash": "c1f1c46e5772532056efcccff6ee6e44ddd86d2edb6e1408b3277bb24c490b33", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37688, + "estimated_input_tokens": 9422, + "estimated_eval_tokens": 19100 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly heterogeneous, with only a few clear duplicate/near-duplicate issue pairs. The strongest matches are the Qwen3.5 Moe from_pretrained reports, the import-time slowdown reports, and the Qwen3.5 visual-config/save_pretrained serialization reports.", + "confidence": 0.71, + "canonical_issue_reason": "No single cluster-wide canonical issue fits this mixed set; the best umbrella issue is 44246 for the import-time slowdown subcluster, while 45310/45478 is the clearest exact-duplicate subcluster.", + "canonical_pr_reason": null, + "best_issue_reason": "44246 is the best global issue anchor because it is a broad, user-visible regression with a plausible duplicate in 41669 and reads like the top-level symptom for that subcluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45276", + "right": "issue:46077", + "accept": false, + "reason": "Different Gemma4 bugs: token embedding resize propagation vs bidirectional attention mask construction." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Both are save-related, but one is quantized model saving and the other is pipeline save_pretrained behavior/docs; not the same bug." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mismatch for TextClassificationPipeline is unrelated to pipeline object serialization failure." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols and different upstream modules." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Qwen3VL model loading failure and Qwen3_5 infinite loop are different code-path problems." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "Unrelated subsystems: patchtsmixer post_init validation vs GPT2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Missing config attribute in Gemma3 is unrelated to patchtsmixer post_init constraints." + }, + { + "left": "issue:44625", + "right": "issue:46077", + "accept": false, + "reason": "num_labels propagation bug is unrelated to Gemma4 bidirectional attention masks." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "Base_model_prefix loading regression is not the same as pipeline save_pretrained failure." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "FlashAttention-2 support error and invalid GenerationConfig are unrelated failures." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Both involve model persistence/loading, but one is generic state_dict ordering and the other is a Qwen3.5 save_pretrained regression." + }, + { + "left": "issue:46077", + "right": "issue:46082", + "accept": false, + "reason": "Different Gemma4 issues: attention mask mode vs LlamaConfig head_dim validation." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both are Python-version compatibility issues, but they target different Python releases and different failures." + }, + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "FlashAttention support and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Different missing config attributes in different model families; not the same bug." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to Qwen3.5 checkpoint saving." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3 vocab_size attr error and load-balancing-loss gating are different model bugs." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Unsupported FlashAttention and Qwen3-VL weight-shape mismatch are unrelated." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "FSDP/optimizer state corruption and a cache strategy typo do not share the same underlying bug." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "no_grad decoration for cache update is unrelated to broad import errors after upgrading to 5.5.0." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different models and failure modes: UMT5 missing weight vs Qwen3.5 Moe from_pretrained regression." + }, + { + "left": "issue:43867", + "right": "issue:46202", + "accept": false, + "reason": "Generic state_dict load error and Gemma pipeline roundtrip failure on a specific token are not the same bug." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Compiled-file import errors and a Python 3.13 torch.jit parsing problem are different root causes." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Generic load failure via state_dict ordering is not the same as Qwen3_5 vision config field loss." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "These look like the same import-time slowdown regression: one is the concrete diagnosis, the other is the user-facing symptom." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Missing Gemma3 config attribute is unrelated to the FSDP+PEFT optimizer-state bug." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Different breakages: Python 3.14 load failure vs PretrainedConfig type-checking regression." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Test flakiness from missing set_seed and pytest-xdist file races are not the same issue." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "Cache update no_grad bug is much more specific than the broad 'too many models' complaint." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Generic load/state_dict issues are not the same as Qwen3.5 visual-encoder key serialization." + }, + { + "left": "issue:42490", + "right": "issue:44075", + "accept": false, + "reason": "Local-path import warning and SGD arguments being ignored are unrelated." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Both are from_pretrained/load errors, but for different model families and different failure modes." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to patchtsmixer post_init gating." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache no_grad behavior and Python version compatibility are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Tensor-parallel training bug and Qwen2-57B-A14B tp OOM are different issues despite both touching TP." + }, + { + "left": "issue:45357", + "right": "issue:45375", + "accept": true, + "reason": "Both point to the same Qwen3.5 vision/save_pretrained serialization problem: missing vision config fields causing incorrect saved keys." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Near-identical titles, same model family, same from_pretrained failure, and same version window; these are clearly the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays within the packet evidence and the soft-edge calls are conservative. The accepted duplicate pairs are well grounded by the titles/body themes, and the rejected pairs avoid overclaiming similarity across different model families or failure modes. The umbrella/canonical language is cautious enough for this mixed cluster." + }, + "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": 47, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:41628", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43065", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43576", + "issue:43618", + "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:44556", + "issue:44655", + "issue:44749", + "issue:44857", + "issue:44961", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45125", + "issue:45341", + "issue:45375", + "issue:45440", + "issue:45478", + "issue:45600", + "issue:46132" + ], + "soft_pairs": [ + "issue:28282|issue:33453", + "issue:43618|issue:44857", + "issue:44360|issue:45440", + "issue:43618|issue:44977", + "issue:42890|issue:44964", + "issue:43502|issue:44062", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43723|issue:44556", + "issue:43576|issue:46132", + "issue:44387|issue:44556", + "issue:42548|issue:44351", + "issue:44222|issue:45125", + "issue:42890|issue:45341", + "issue:43010|issue:43065", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:30333|issue:33453", + "issue:43010|issue:43232", + "issue:45125|issue:45375", + "issue:30990|issue:31795", + "issue:43502|issue:44222", + "issue:43299|issue:44556", + "issue:42831|issue:43874", + "issue:43827|issue:44961", + "issue:43502|issue:44961", + "issue:44355|issue:45071", + "issue:30333|issue:36296", + "issue:44315|issue:44360", + "issue:44355|issue:44655", + "issue:33453|issue:34689", + "issue:42757|issue:43576", + "issue:43576|issue:45071", + "issue:33453|issue:36296", + "issue:44222|issue:44230", + "issue:43576|issue:43824", + "issue:41628|issue:42548" + ], + "prepared_review_unit_hash": "16a64a91c5aeefca2e53ee5ca5c5ad719362c1a3fac671b323e6b585bad220dd", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38482, + "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 a loose collection of mostly unrelated Transformers issues, many of them broad v5 regressions or loading/import problems. The soft pairs share superficial wording or subsystem overlap, but not the same concrete bug, so none should be merged as duplicates.", + "confidence": 0.88, + "canonical_issue_reason": "issue:33453 is the most representative standalone bug report in the set: it is a broad tokenizer-loading regression with high discussion activity and overlaps most with other loading-related reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:33453 is the best single issue candidate to anchor the cluster because it is broad, concrete, and central to the loading-regression theme seen here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "Both mention import/loading failures, but one is a missing PyTorch dependency error and the other is a tokenizer regression; different underlying bugs." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Different failures in different model paths; one is CLIP attentions handling, the other is an AMP/CUDA crash in LwDetrImageLoss." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "Unrelated topics: a discussion about a DSA indexer ReLU vs a DeepSeekV3MoE implementation divergence." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Only broad generation/runtime context overlaps; CLIP attentions assignment and Qwen flash-attention generation are separate bugs." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "One is a flaky test due to missing set_seed, the other is a Phi-4 multimodal model-loading regression." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "Both involve loading-related code paths, but local_files_only network leakage and AddedToken argument duplication are different defects." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Both are test failures, but they concern different tests and causes: missing set_seed vs a stale device override assertion." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "A flaky SamHQ test and a CI break from removed auto_mappings entries are not the same bug." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Both are version-related loading complaints, but one is tokenizer loading and the other is checkpoint reload compatibility after upgrading to v5." + }, + { + "left": "issue:43576", + "right": "issue:46132", + "accept": false, + "reason": "Both touch Transformers internals, but one is an env command regression and the other is changed behavior in AttentionInterface.register." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "One is an int4 quantization memory regression; the other is a model reload compatibility issue." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they refer to different symbols and likely different API breakages." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "Both mention FP8/MoE, but one is save_pretrained behavior and the other is missing tensor-parallel metadata." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "A flaky integration test and a small testing_utils bug are not the same underlying issue." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Different code paths: cache/layer update decoration vs a dummy Conv2d in Sam3PixelDecoder." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "local_files_only network behavior is unrelated to the GLM-5 RoPE implementation discussion." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "One concerns compiled Python file errors, the other is a data-filtering slowdown after upgrading Transformers." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen3.5/MoE-related, but one is tensor-parallel support metadata and the other is a from_pretrained loading error." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "Training-job MLflow reporting and tokenizer loading regression are unrelated bugs." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Both mention generation/cache internals, but they are distinct generation-state bugs." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Different model metadata issues: tensor parallel plan vs missing vision config field silently dropped by strict validation." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Sentence-transformers loading hang and documentation confusion around forward inputs are not the same issue." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Both are regressions, but one is unwanted API calls and the other is FP8 save_pretrained behavior." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "A Qwen3VL MoE loading break and a generic v4-to-v5 checkpoint reload problem are different failures." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "One reports an FP8 accuracy issue; the other is a missing image-patch helper causing an AttributeError." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Documentation referencing removed pipelines is unrelated to the 'racoon' issue." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "No real overlap beyond being bug reports; local_files_only network leakage and 'racoon' are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file errors and PretrainedConfig type-checking breakage are different regressions." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLflow reporting on failed jobs and tensor-parallel training bugs are separate subsystems and failures." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel application with model_init has nothing to do with a DSA indexer lacking ReLU." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled Python file errors and inability to save Pipeline objects are distinct issues." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Both concern loading regressions, but one is tokenizer loading and the other is Llama 3.2 vision model loading under a specific version." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Both are v5-related API complaints, but one is a missing huggingface_hub import and the other is a broken env command." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Unrelated: broken env command vs PretrainedConfig type-checking regression." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are not the same bug." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both mention FP8/MoE, but one is a save_pretrained bug and the other is inference support." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Different import/loading failures: env command breakage versus missing Qwen2_5_VLForConditionalGeneration export." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import-name errors, but for different symbols and likely different package export regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 48, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:31795", + "issue:36296", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44230", + "issue:44246", + "issue:44273", + "issue:44297", + "issue:44315", + "issue:44355", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44704", + "issue:44908", + "issue:44938", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45362", + "issue:45468", + "issue:45542", + "issue:45753", + "issue:45850", + "issue:46095", + "issue:46143", + "issue:46144", + "issue:46178", + "issue:46209", + "issue:46218" + ], + "soft_pairs": [ + "issue:44961|issue:45468", + "issue:31795|issue:38617", + "issue:44355|issue:46178", + "issue:43576|issue:44938", + "issue:44315|issue:46209", + "issue:46143|issue:46144", + "issue:44908|issue:44961", + "issue:44485|issue:44961", + "issue:36296|issue:43901", + "issue:43673|issue:44492", + "issue:36296|issue:43526", + "issue:45362|issue:45850", + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:44038|issue:45125", + "issue:44273|issue:45003", + "issue:44230|issue:46095", + "issue:44393|issue:45071", + "issue:43576|issue:44556", + "issue:43525|issue:45850", + "issue:44393|issue:45753", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:43572|issue:45850", + "issue:42371|issue:44492", + "issue:44492|issue:45850", + "issue:45278|issue:45850", + "issue:41669|issue:46218", + "issue:44246|issue:44273", + "issue:42890|issue:44908", + "issue:43408|issue:44315", + "issue:44704|issue:44908", + "issue:43976|issue:44393", + "issue:44297|issue:45230", + "issue:43352|issue:44393" + ], + "prepared_review_unit_hash": "43dcc699751e024f009f28c0361e36564297c1c5e3bdb6b2353acdd88fe2caa1", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37491, + "estimated_input_tokens": 9373, + "estimated_eval_tokens": 19002 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is not a single duplicate cluster; it contains many unrelated issue reports with only loose similarity around v5 regressions, import/performance, and a few model-specific bugs. No soft edge looks like the same underlying bug/change with enough confidence to merge.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45850 is the broadest umbrella-style regression report in the set (\u201cSince 5.0 version it breaks too many models\u201d), so it is the most central issue node for loose grouping, though it is too vague to be a precise duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the best global issue representative only because it is the closest catch-all v5 breakage report; it still lacks the specificity needed for strict duplicate consolidation.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "Unrelated: a nonsense title versus a Gemma-4 audio positional-encoding bug; no shared concrete failure path." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion about forward args vs an import error for a missing symbol; different problem classes." + }, + { + "left": "issue:44355", + "right": "issue:46178", + "accept": false, + "reason": "Compiled Python file errors are not the same as a backend-mapping ValueError for tensorflow_text." + }, + { + "left": "issue:43576", + "right": "issue:44938", + "accept": false, + "reason": "Both are version-related breakages, but one is the transformers env CLI and the other is Python 3.14 import/loading; too broad to be the same bug." + }, + { + "left": "issue:44315", + "right": "issue:46209", + "accept": false, + "reason": "Liger Kernel not applied with model_init is unrelated to an FP8 inference failure on B200." + }, + { + "left": "issue:46143", + "right": "issue:46144", + "accept": false, + "reason": "Both mention RoFormer, but one is kwargs propagation and the other is attention-interface usage; not the same concrete defect." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling is unrelated to the placeholder racoon report." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to the racoon issue." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor parallel training bug and TextClassificationPipeline docs mismatch are different areas and symptoms." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Missing GenerationMixin cache during chunked prefill is unrelated to a cache-strategy typo." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor parallel training bug is unrelated to BeitImageProcessorFast label reduction behavior." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "A specific Qwen3.5-35B chat crash is not the same concrete issue as a generic 'many models break' regression report." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing processor.save_pretrained files is a concrete serialization bug, while the other report is too generic to match." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading problems are unrelated to a backend error caused by tensorboard without TensorFlow." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "General Qwen3-VL-Moe bugs and missing _tp_plan for tensor parallelism are related only at a model-family level, not the same bug." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading failure and unsafe sys.modules access may be adjacent, but they are not clearly the same underlying defect." + }, + { + "left": "issue:44230", + "right": "issue:46095", + "accept": false, + "reason": "FP8 inference support and a weight-conversion-script question are different requests/issues." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Qwen3-VL 2D box output problems are unrelated to PretrainedConfig type-checking regressions." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Both involve v5 regressions, but one is the env command and the other is checkpoint reload compatibility; not the same bug." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Llama4Config missing pad_token_id is a specific config bug, not the same as a broad v5 breakage umbrella." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "2D bounding-box output errors are not the same as an infinite-loop generation bug for a specific image." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-time slowdowns and missing GenerationMixin cache are both v5-related, but the concrete code paths differ." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both concern old checkpoints under v5, but one is general reload failure and the other is remote-code/meta-init incompatibility." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is a specific config migration bug, not the same as a generic v5 breakage report." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API migration guidance is unrelated to a cache-strategy typo." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "A typo in cache-strategy docs/code is not the same as a broad statement that v5 breaks many models." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "General import errors after upgrading to 5.5.0 are related in theme, but not the same concrete failure as the broad v5 breakage claim." + }, + { + "left": "issue:41669", + "right": "issue:46218", + "accept": false, + "reason": "Import-* performance work and an import failure for Qwen3_5ForCausalLM are different issues." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Slow import is not the same as lazy loading not working properly; the overlap is too broad." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Missing set_seed in tests is unrelated to scheduler kwargs handling." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Model-type mismatch warning for sam3_video/tracker is unrelated to Liger Kernel application in model_init." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor cached_file kwargs propagation is unrelated to inverse_sqrt scheduler kwargs handling." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python-version compatibility failure is unrelated to Qwen3-VL bounding-box output bugs." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch is a specific serialization bug, not a generic bug report." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support for NemotronH is unrelated to Qwen3-VL bounding-box hallucination/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": 49, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43352", + "issue:43502", + "issue:43519", + "issue:43576", + "issue:43606", + "issue:43618", + "issue:43704", + "issue:43827", + "issue:43976", + "issue:44077", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44295", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44945", + "issue:44998", + "issue:45071", + "issue:45230", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478", + "issue:45850", + "issue:46018", + "issue:46095", + "issue:46172", + "issue:46218" + ], + "soft_pairs": [ + "issue:44295|issue:45230", + "issue:43576|issue:44908", + "issue:41669|issue:44351", + "issue:44908|issue:45071", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:43976|issue:45850", + "issue:43976|issue:46218", + "issue:44077|issue:44861", + "issue:44393|issue:45478", + "issue:43827|issue:44908", + "issue:31795|issue:33453", + "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:46018|issue:46172", + "issue:43576|issue:46218", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:41669|issue:43704", + "issue:31795|issue:34689", + "issue:31515|issue:31795", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:43298|issue:46095", + "issue:45850|issue:46218", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:43606|issue:45468", + "issue:44263|issue:45468", + "issue:44261|issue:45468", + "issue:44351|issue:46218", + "issue:42913|issue:43066", + "issue:43352|issue:46218", + "issue:44908|issue:44998", + "issue:44492|issue:44998", + "issue:43618|issue:44998", + "issue:44861|issue:45290", + "issue:44998|issue:45850" + ], + "prepared_review_unit_hash": "8e067e079f4dd9507bfb02698cbb00a2d75b8d63e3325d87932e5eff9ce5768b", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 44, + "serialized_chars": 40004, + "estimated_input_tokens": 10001, + "estimated_eval_tokens": 20258 + }, + "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 and docs issues, with some broad overlap around v5 breakages and tokenizer/model-loading problems. None of the soft pairs look like true duplicates under a strict same-bug standard.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45850 is the broadest umbrella in the set (\u201cSince 5.0 version it breaks too many models\u201d) and best matches the cluster\u2019s loose v5-regression theme, even though it is too generic to subsume the specific bugs cleanly.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the most representative cluster anchor because it describes the widest user-visible regression pattern; the other issues are narrower, model-specific, or unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Generic bug report versus a buffer/position_ids reading problem; no clear shared code path or concrete duplicate symptom." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken env CLI and inverse_sqrt scheduler kwargs are unrelated subsystems." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-* cleanup/perf issue is unrelated to a HybridCache import failure." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are different bugs." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Model import cleanup is unrelated to a testing_utils bug." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache-strategy typo and pipeline-parallelism output corruption are not the same bug." + }, + { + "left": "issue:43976", + "right": "issue:45850", + "accept": false, + "reason": "Python-version compatibility failure is not the same concrete problem as the broad \u201cmany models break\u201d report." + }, + { + "left": "issue:43976", + "right": "issue:46218", + "accept": false, + "reason": "Python support regression and Qwen3_5 import failure are different failure modes." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "Optional post_init policy and tied-weight-key AttributeError are unrelated." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different models and different symptoms; not the same underlying bug." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() is unrelated to scheduler kwargs being ignored." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Documentation confusion in model.forward and tokenizer-loading regression are not the same issue." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel not applied via model_init and flash_attention_3 training degeneration are distinct code paths." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "CLI env command breakage and lazy-loading failure are not the same bug." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving Pipeline objects and tied-weight-key crash are unrelated." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer ReLU discussion and Gemma-4 audio positional encoding bug do not match." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report and Qwen3.5 MoE from_pretrained error are not sufficiently specific to be duplicates." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading malfunction and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:46018", + "right": "issue:46172", + "accept": false, + "reason": "DeepSeek-V4 shared expert gating and a comb transpose issue are different model bugs." + }, + { + "left": "issue:43576", + "right": "issue:46218", + "accept": false, + "reason": "Broken env CLI is unrelated to Qwen3_5 import failure." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Timestamp calculation in Qwen3VL and GLM-5 RoPE implementation are different model-specific defects." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Processor timestamp math and scheduler kwargs are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-* cleanup/perf issue is unrelated to VRAM leakage in dataloader threads." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Model.forward docs confusion and Llama 3.2 model-loading regression are not the same underlying bug." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Slow from_pretrained checkpoint loading and forward-API documentation confusion are unrelated." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Different architectures and different implementation bugs; no shared concrete fix." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in threaded dataloading and GLM-5 RoPE implementation are not duplicates." + }, + { + "left": "issue:43298", + "right": "issue:46095", + "accept": false, + "reason": "Continuous batching support for audio models and DeepSeek-V4 weight conversion are separate feature/question areas." + }, + { + "left": "issue:45850", + "right": "issue:46218", + "accept": false, + "reason": "Broad v5 breakage report and a specific Qwen3_5 import error are too different to merge." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 settings migration and dataloader-thread VRAM leak are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only network requests and Qwen3VL timestamp calculation are unrelated bugs." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Processor timestamp math and missing save_pretrained files are different issues." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Timestamp calculation and VRAM leak are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch and Gemma-4 audio positional encoding bug are different problems." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return handling in GLM-MoE and Gemma-4 audio positional encoding do not match." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Layernorm eps precision discussion and Gemma-4 audio positional encoding are unrelated." + }, + { + "left": "issue:44351", + "right": "issue:46218", + "accept": false, + "reason": "Both are import failures, but for different symbols and likely different export paths; not the same concrete bug." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both concern tokenizer v5 behavior, but one is a generic v4\u2192v5 behavior change and the other is a specific decoder-type bug." + }, + { + "left": "issue:43352", + "right": "issue:46218", + "accept": false, + "reason": "Unsupported Flash Attention 2.0 for NemotronH and Qwen3_5 import failure are unrelated." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs and an unrelated off-topic issue are not duplicates." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "Cache-strategy typo and an off-topic issue are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIPOutput attentions regression and an off-topic issue are unrelated." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight-key list handling and chat template tool-call crash are different code paths." + }, + { + "left": "issue:44998", + "right": "issue:45850", + "accept": false, + "reason": "Off-topic issue and broad v5 regression report are not the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 50, + "review_unit_count": 50, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-431", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:33453", + "issue:36296", + "issue:37934", + "issue:38617", + "issue:42936", + "issue:43240", + "issue:43298", + "issue:43525", + "issue:43572", + "issue:43668", + "issue:43717", + "issue:43813", + "issue:44031", + "issue:44230", + "issue:44556", + "issue:44623", + "issue:44861", + "issue:44998", + "issue:45310", + "issue:46018", + "issue:46144" + ], + "soft_pairs": [ + "issue:44556|issue:44998", + "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:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230", + "issue:43717|issue:46144", + "issue:42936|issue:46018", + "issue:43668|issue:44031", + "issue:42936|issue:43240", + "issue:43240|issue:46144", + "issue:42936|issue:44031", + "issue:42936|issue:46144", + "issue:42936|issue:43813", + "issue:43240|issue:43668", + "issue:43668|issue:43813", + "issue:37934|issue:43668", + "issue:42936|issue:43668" + ], + "prepared_review_unit_hash": "0de79b46faa0c6f478fa9b0f53f9de609b7d016dbf7bce54291899ccd34eb6e6", + "component_budget": { + "node_count": 431, + "item_count": 431, + "soft_pair_count": 1595, + "serialized_chars": 825263, + "estimated_input_tokens": 206316, + "estimated_eval_tokens": 412888 + }, + "budget": { + "node_count": 23, + "item_count": 23, + "soft_pair_count": 22, + "serialized_chars": 19401, + "estimated_input_tokens": 4851, + "estimated_eval_tokens": 9958 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is not a single duplicate cluster: the items span many unrelated bugs/features across loading, config, tokenizer, training, and model-specific behavior. All soft pairs look like loose topical similarity rather than the same underlying bug or change, so they should be rejected.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44556 is the most concrete, actionable issue in the set: it describes a specific regression boundary (v4.57 to v5.x) and a clear failure mode (checkpoint reload breaks after upgrade).", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44556 is the best single issue to anchor triage because it is specific, reproducible, and framed as a versioned regression rather than a broad or ambiguous request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44556", + "right": "issue:44998", + "accept": false, + "reason": "Completely unrelated: checkpoint reload regression vs an unrelated low-signal title ('Unemployment')." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Different bugs: missing pad_token_id on Llama4Config vs AttributeError in _get_tied_weight_keys for list handling." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "Different config regression (pad_token_idx missing) vs tied-weight key crash; no shared code path." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "One is slow from_pretrained checkpoint loading; the other is an ImportError for a missing symbol. Different failure modes." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "Different areas: fp8 Qwen3-VL/Qwen3.5 inference support vs processor.save_pretrained missing files." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow reporting after failed training job vs slow checkpoint loading; unrelated subsystems and symptoms." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint load performance issue vs tensor parallel training bug; not the same underlying defect." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5, but one is fp8 inference support and the other is a from_pretrained regression after version upgrade; too different to merge as one fix." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow from_pretrained checkpoint load vs tokenizer loading regression; similar theme only at a very broad level." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching audio-model support vs fp8 inference support; different model classes and problem types." + }, + { + "left": "issue:43717", + "right": "issue:46144", + "accept": false, + "reason": "Mamba init_weights behavior vs RoFormer attention interface usage; unrelated model-specific implementation issues." + }, + { + "left": "issue:42936", + "right": "issue:46018", + "accept": false, + "reason": "Mask2Former ignore_value handling vs DeepSeek-V4 shared expert gating; different models and different logic." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "Incorrect type hint in ModernBERTConfig vs tokenizer regex warning regression; unrelated." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Ignore_value not used in Mask2Former vs kwargs not forwarded to loss calculation; related only in the broadest sense of loss code." + }, + { + "left": "issue:43240", + "right": "issue:46144", + "accept": false, + "reason": "Loss kwargs propagation vs attention interface implementation; no shared concrete bug." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Mask2Former ignore_value bug vs tokenizer regex warning after 4.57.3; different components and root causes." + }, + { + "left": "issue:42936", + "right": "issue:46144", + "accept": false, + "reason": "Mask2Former ignore_value handling vs RoFormer attention interface issue; not the same code path." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Ignore_value usage bug vs a typo in quantization_operation text; unrelated." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Missing kwargs in loss calculation vs incorrect type hint; different severity and implementation areas." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "Type hint error vs typo in an attribute name; only superficial similarity." + }, + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Question about whether Llama4TextL2Norm is really RMSNorm vs a type-hint correction; unrelated." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Mask2Former ignore_value bug vs ModernBERTConfig type hint issue; different models and bug classes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10519-3", + "nodes": [ + "issue:10519", + "issue:11005", + "issue:11307" + ], + "soft_pairs": [ + "issue:10519|issue:11307", + "issue:10519|issue:11005", + "issue:11005|issue:11307" + ], + "prepared_review_unit_hash": "20c772d1f593ae0dd0f578ec9c37a2b967b86c8a0dda7ae658e3fa98f4fac2cb", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2878, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2878, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three issues are about unrelated feature requests: tokenizer truncation behavior, learning-rate scheduling functionality, and Wav2Vec2 word time offsets. They do not appear to be duplicates or the same underlying bug/change.", + "confidence": 0.97, + "canonical_issue_reason": "No true canonical issue for this cluster; the items cover different subsystems and different requested capabilities.", + "canonical_pr_reason": "No pull requests are present in this cluster.", + "best_issue_reason": "If one issue must serve as a representative, #10519 is the most concrete and narrowly scoped request, but it is not representative of the others as a duplicate target.", + "best_pr_reason": "No pull requests are present in this cluster.", + "soft_edge_verdicts": [ + { + "left": "issue:10519", + "right": "issue:11307", + "accept": false, + "reason": "Different domains and goals: tokenizer truncation option vs speech model word timestamp extraction." + }, + { + "left": "issue:10519", + "right": "issue:11005", + "accept": false, + "reason": "Unrelated functionality: text truncation behavior vs ReduceLROnPlateau-like scheduler behavior." + }, + { + "left": "issue:11005", + "right": "issue:11307", + "accept": false, + "reason": "Different problems in different components: optimizer/scheduler feature request vs Wav2Vec2 alignment/time-offset request." + } + ] + }, + "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-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "0b788c1aec8199c3ca715dea69ee7f9db99d3da602a02b70782ffb712d94fe6d", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2479, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2479, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates as a cluster: one issue is about Tapas tokenization, one about a private-model auth/error-message problem, and one about loading bert-base-uncased. Only the two model-loading issues are loosely related, but they still appear to describe different failure modes.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 16618 is the broadest and most central model-loading report, but the cluster does not contain a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "16618 is the best representative because it is the most general user-facing model load failure among the three; the others are clearly about different topics.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Different problems: Tapas tokenization vs. model loading for bert-base-uncased. No shared code-path or concrete failure mode." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Both mention model download/load, but one is specifically a private-model login/error-message issue and the other is a generic bert-base-uncased load failure; too different 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": 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-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "6b5dd876227352b905a3f199171ac178a6e7ce815e620d9af6bb8162a4f0de1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: one issue requests Flash Attention 2 support for more architectures, while the other requests GGUF support for more architectures. They share a broad theme but describe different features and code paths.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "If a single representative is needed, issue 26350 is slightly better because it is older and more specific, but the two issues are heterogeneous and should remain separate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different feature requests (Flash Attention 2 vs GGUF) with different underlying changes; they are related only at a broad \"more architectures\" level." + } + ] + }, + "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-27088-7", + "nodes": [ + "issue:27088", + "issue:28936", + "issue:38435", + "issue:43834", + "issue:44365", + "issue:44370", + "issue:46222" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:46222", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:27088|issue:38435", + "issue:27088|issue:28936", + "issue:28936|issue:43834", + "issue:28936|issue:44365", + "issue:28936|issue:38435", + "issue:28936|issue:44370", + "issue:38435|issue:44370", + "issue:38435|issue:46222", + "issue:38435|issue:44365", + "issue:38435|issue:43834", + "issue:43834|issue:44370", + "issue:43834|issue:46222", + "issue:43834|issue:44365", + "issue:44365|issue:44370", + "issue:44365|issue:46222", + "issue:44370|issue:46222" + ], + "prepared_review_unit_hash": "2adc2e7ff48520849d8ae6ff3881e00e09fbf3972547c4a2574e6639c43c825c", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 20, + "serialized_chars": 11132, + "estimated_input_tokens": 2783, + "estimated_eval_tokens": 5822 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 20, + "serialized_chars": 11132, + "estimated_input_tokens": 2783, + "estimated_eval_tokens": 5822 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster mixes distinct i18n translation requests for specific languages with a handful of near-identical generic template issues. There is no single underlying bug/change shared by all items, so I rejected all soft duplicate edges.", + "confidence": 0.71, + "canonical_issue_reason": "issue:44370 is the closest central representative of the generic template-placeholder subgroup, with exact/near-exact similarity to issue:46222 and issue:44365. The Turkish, Spanish, and Romanian requests are separate translation tasks and should not be collapsed into it.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44370 is the best global representative only for the templated placeholder issues, not for the whole mixed cluster. It is the strongest duplicate-like center, but the language-specific issues remain distinct.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Turkish translation request vs generic placeholder issue; same i18n theme, but not the same concrete request." + }, + { + "left": "issue:27088", + "right": "issue:46222", + "accept": false, + "reason": "Turkish request and a generic placeholder entry; no evidence they target the same language or task." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Turkish request vs generic placeholder text; boilerplate similarity is not enough to merge." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Turkish request vs generic placeholder issue; different concrete translation work." + }, + { + "left": "issue:27088", + "right": "issue:38435", + "accept": false, + "reason": "Turkish and Romanian translation requests are different language tasks, not duplicates." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Turkish and Spanish translation requests are separate language-specific issues." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Spanish request vs generic placeholder issue; same subsystem, but not the same underlying request." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Spanish translation request vs template placeholder issue; no concrete match on language target." + }, + { + "left": "issue:28936", + "right": "issue:38435", + "accept": false, + "reason": "Spanish and Romanian translation requests are distinct tasks." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Spanish request vs generic placeholder entry; insufficient evidence that they are the same issue." + }, + { + "left": "issue:38435", + "right": "issue:44370", + "accept": false, + "reason": "Romanian request vs generic placeholder issue; no clear shared language/task." + }, + { + "left": "issue:38435", + "right": "issue:46222", + "accept": false, + "reason": "Romanian request vs generic placeholder issue; boilerplate similarity alone is not a duplicate signal." + }, + { + "left": "issue:38435", + "right": "issue:44365", + "accept": false, + "reason": "Romanian request vs generic placeholder issue; different concrete translation target." + }, + { + "left": "issue:38435", + "right": "issue:43834", + "accept": false, + "reason": "Romanian request vs generic placeholder issue; not the same underlying change." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "Both are generic placeholder template issues, but the available evidence does not prove they refer to the same actual language request." + }, + { + "left": "issue:43834", + "right": "issue:46222", + "accept": false, + "reason": "Near-identical template text, but no explicit language target or code to confirm a true duplicate." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Template-placeholder similarity only; too little concrete evidence to merge." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Very similar placeholder text, but the issues are not tied to a clearly identical concrete request." + }, + { + "left": "issue:44365", + "right": "issue:46222", + "accept": false, + "reason": "Near-match on boilerplate only; no explicit target language or change path to confirm duplication." + }, + { + "left": "issue:44370", + "right": "issue:46222", + "accept": false, + "reason": "Exact/near-exact template wording, but still only boilerplate similarity with no concrete same-language evidence." + } + ] + }, + "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-36817-16", + "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", + "issue:46133" + ], + "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", + "issue:45322|issue:46133" + ], + "prepared_review_unit_hash": "050753e8f3d5656ac78f6b5448008d0d644bb685b091e70b0f0c31a7e4cc95f6", + "component_budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21658, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21658, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are a collection of separate model-support requests spanning different architectures and modalities (vision, OCR, ASR/TTS, audio, transformers). They are only superficially similar, so none of the soft edges look like true duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 42738 ('BERT-like models with RoPE') is the broadest, most category-level request and is the closest thing to an umbrella representative for this noisy cluster, though it is not a duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "42738 is the best single representative issue because it is the least model-specific and most general of the set; the others are distinct named-model requests that should stay separate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "EuroBert config vs DEIMv2: different models and different request scopes." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config vs Qwen3-TTS support: unrelated model families and modalities." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert vs RF-DETR: distinct models, no shared concrete change." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR vs DEIMv2: different architectures and tasks." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR detection request vs LFM2.5 Audio request are unrelated." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR vs sparse transformer: different model types and code paths." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR detection request vs Qwen3-ASR support: different modalities." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR vs Qwen3-TTS support: different tasks and model families." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT vs Qwen3-ASR: unrelated model requests." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT vs weight-sparse transformer: different concrete models." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT vs LFM2.5 Audio: unrelated architectures and modalities." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR detection model vs NeoBERT language model: distinct requests." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT vs ModernVBERT: different model additions, not one bug/change." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 vs Qwen3-ASR: different model support requests." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 vs sparse transformer: unrelated concrete code changes." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 vs ModernVBERT: separate model-specific requests." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 vs Voxtral TTS: different modalities and model families." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 vs Qwen3-TTS: unrelated models and tasks." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT vs Qwen3-ASR: different support requests." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT vs Qwen3-TTS: different models and code paths." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT vs broad BERT-like RoPE request: related family, but not the same concrete change." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like models with RoPE vs Voxtral TTS: unrelated modalities." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS vs Qwen3-ASR: same vendor, different tasks and implementations." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS vs Voxtral TTS: different model-specific support requests." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "TTS support vs DeepSeek-OCR2: different modalities and code paths." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS vs weight-sparse transformer: unrelated model classes." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS vs LFM2.5 Audio: both audio-related but distinct model additions." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR vs LFM2.5 Audio: different audio model support requests." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR vs EUPE: ASR model request versus vision-language encoder request." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR vs sparse transformer: different concrete models." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio vs SAM3-LiteText: audio model versus vision-language model." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Sparse transformer request vs EUPE: different architectures and use cases." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR vs Voxtral TTS: different tasks, not the same support change." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT vs Voxtral TTS: unrelated model families." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "ASR support vs OCR model support: different modalities." + }, + { + "left": "issue:45322", + "right": "issue:46133", + "accept": false, + "reason": "EUPE vs TIPSv2: both vision-language related, but they are distinct model proposals with different changes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "34bc3063617364029e19ecad276c43ce05079dba3d4d7d3c60fb30cf00c4b6b3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are not duplicates: #41084 is about block decoding behavior, while #43037 is a request for DeepSeek v3.2 support. They describe different underlying work with no clear shared code path.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the titles and likely scopes are unrelated, so neither issue can stand in for the other.", + "canonical_pr_reason": null, + "best_issue_reason": "No single best issue for deduplication; #43037 is more specific as a standalone feature request, but it does not overlap with #41084.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different topics and likely different code paths: block decoding vs. model-specific support request." + } + ] + }, + "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": "89389ba2c07ccbc79da1b3829b4407b65fdf0ab09ed3b549a96c7ca986be465e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1584, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are about different Trainer behaviors: one is about `remove_unused_column` and customizability, the other about FLOPS estimation for custom trainers. They are related to Trainer internals but do not describe the same bug or change.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No clear canonical issue for this cluster because the reports target different code paths; if forced to pick one, `#43598` is the more focused configuration-behavior report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Different underlying problems: one concerns `remove_unused_column` customization in Trainer, the other concerns accounting for custom trainers in FLOPS estimation. Same subsystem, but not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "1c6dafd3271d6c14d3ead1d5750bc33b17e7e25f763a6012ac3269595e389e34", + "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 separate feature requests, not duplicates: one asks for Qwen3-Omni registration on AutoModel/AutoModelForConditionalGeneration, while the other asks for AutoModelForSequenceClassification support for Qwen3.5 (Qwen3_5Config). They target different model families and different heads/code paths.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must represent the cluster, issue 43684 is the broader core-registration request, but it is still distinct from 44405 and should not be treated as a duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model families and different AutoModel heads: Qwen3-Omni registration for AutoModel/AutoModelForConditionalGeneration vs Qwen3.5 sequence-classification support. 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": "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": "da62a0b1772c8bd2a65ee232dd22141c5491af492cfa4c133ef3af9b8bd19904", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three issues titled \"huggingface\" look like the same duplicate report; the separate \"Fett\" issue does not. Among the duplicate-looking issues, #43859 is the best representative because it has the same title and at least some discussion activity.", + "confidence": 0.77, + "canonical_issue_reason": "Issue #43859 is the best canonical choice: it matches the repeated title and has the most activity among the duplicate-looking issues.", + "canonical_pr_reason": null, + "best_issue_reason": "#43859 is the strongest global issue candidate because it appears to be the same report as #43845/#43846 and has the most discussion.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no body detail tying them to the same underlying issue." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no evidence that \"Fett\" refers to the same problem as the \"huggingface\" reports." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "No substantive overlap beyond both being short issues; titles do not match." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same title and highly similar sparse issue content, so they likely describe the same report." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same title and same apparent topic; no evidence of a distinct issue." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same title and same apparent topic; likely duplicate reports of the same issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: #43845, #43846, and #43859 share the same title and strong soft-similarity signals, while #43835 has a different title and no stronger evidence tying it to the others. The representative choice of #43859 is conservative and supported by its slightly higher discussion activity. The pairwise verdicts are also suitably cautious given the sparse evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "f94db69eb35e276fff23d89b44f2f057e199a620a3aef1466def79e8f8528e37", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster contains only vague/spam-like issues and no concrete bug report. The titles do not indicate the same underlying problem, so none of the soft pairs should be merged as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the items are unrelated or too content-free to establish a shared bug or request.", + "canonical_pr_reason": null, + "best_issue_reason": "No strong best issue exists; #44418 is only marginally more descriptive, but still too vague to represent the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are spam-like placeholders with no concrete problem description; no evidence they describe the same issue." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam-like placeholders with no concrete problem description; no evidence they describe the same issue." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam and the other is an extremely vague documentation suggestion; not the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Completely different titles and no shared technical context; not duplicates." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A vague documentation request and a spam placeholder are not the same request." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "A vague documentation request and a spam placeholder are not the same request." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam-like placeholders, but there is no content showing they refer to the same bug or change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "No overlapping subject matter; one is spam-like, the other references a different named topic." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "No overlapping subject matter; one is spam-like, the other references a different named topic." + } + ] + }, + "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": "46b72ddb7de1090daa29d22822c72ee2ec0072229840af5126762d49935506cf", + "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 very similar body lengths, and #45145 was created first with an inbound reference, but the available packet does not include body text or other strong proof that they are the same report. The soft link is therefore too weak to accept confidently.", + "confidence": 0.81, + "canonical_issue_reason": "#45145 is the better canonical issue because it was created earlier and has an inbound reference, while #45151 appears to be the later, likely related report. The evidence is suggestive, but not strong enough to claim near-identical content.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the strongest issue representative for the cluster due to earlier creation and the only inbound reference. It is the safest canonical choice given the limited evidence.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "Same title and close body lengths suggest similarity, but the packet lacks body text, explicit links, or other concrete evidence that these are the same underlying issue. That is not enough to accept the edge." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster looks plausibly duplicate, but the analyst overstates the evidence. The packet supports identical titles, close body lengths, and later creation for #45151, plus a soft-similarity signal; it does not provide body text or other proof that the content is \u2018nearly identical\u2019 or that the relationship is \u2018essentially exact.\u2019 The soft-edge accept is too strong for the available evidence, so this should be rejected as insufficiently conservative." + }, + "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": "e86c262675e0651be4f58517e0204b7461c73f5e6d094baa4e04c89124b1ec02", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe different 4-bit inference failures in different code paths: one is a torch.finfo() TypeError triggered by uint8 weights in Gemma4 audio modules, the other is an AssertionError caused by llm_int8_skip_modules changing the default lm_head exclusion. They should not be deduplicated.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different root causes and code paths: Gemma4 audio-module uint8/torch.finfo() failure vs. BitsAndBytesConfig skip-module handling that clears lm_head exclusion. Same broad 4-bit inference area, but not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "e106d292ca186bdaa15a5f5c40434590b993a0fe95f331b0cfec395ec46411a6", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated entries with different personal names and dates, and contain no bug/report context. This is not a duplicate cluster.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Different names and birthdates; no shared technical problem, code context, or explicit linkage." + } + ] + }, + "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": "4b7a72edc099ab82626a2b51867a843381ac540c371993ab97a6e7d052d84ff3", + "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 issues have unrelated titles consisting of different personal names and dates, with no body content or shared problem evidence. This looks like accidental similarity rather than duplicate reports.", + "confidence": 0.98, + "canonical_issue_reason": "No clear canonical issue: neither issue describes a bug or task, and the titles reference different people/dates with no shared underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a strong canonical candidate; if one must be chosen for bookkeeping, issue #45764 is marginally earlier, but there is no substantive basis to prefer it.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "Different names and dates, no body text, and no evidence of 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": "74d8434447fc560323b09c2d48e3089d88333f33194de5e561a4128b812d2e00", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5728, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5728, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This set splits into two separate exact-duplicate issue pairs: 45870/45871 and 45872/45873. Issue 45869 is a different dataset-promo item and is not a duplicate of the others.", + "confidence": 0.96, + "canonical_issue_reason": "45872 is the strongest representative of the substantive request thread: it is a concrete DataForge feature request and has an exact duplicate in 45873, while the 45870/45871 pair is a different example-oriented request and 45869 is unrelated.", + "canonical_pr_reason": null, + "best_issue_reason": "45872 is the best single issue to anchor triage because it is the clearest, more specific request among the near-duplicates and most likely to capture the intended code-change discussion.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Different topics: a financial data bundle promotion vs a DataForge example request." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Different topics: a financial data bundle promotion vs a DataForge example request." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Exact duplicate titles/body length and same underlying example request." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Related domain, but different underlying request: example prediction flow vs scraping-service feature." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Exact duplicate titles/body length and same underlying scraping-service request." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: 45870/45871 and 45872/45873 have identical titles and body lengths, while 45869 is clearly a different topic. The soft-edge verdicts are appropriately conservative overall, with the two accepted pairs supported by the strongest available evidence and the rejected cross-pairs remaining within distinct request themes." + }, + "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:46048" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43424", + "pull_request:41855|pull_request:43823", + "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:45213", + "pull_request:43995|pull_request:44827", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:46048", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "d61a2175817ffcac4cdd5d775fd623149c6f58a721426115e5135518226d9127", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 18, + "serialized_chars": 34772, + "estimated_input_tokens": 8693, + "estimated_eval_tokens": 17642 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 18, + "serialized_chars": 34772, + "estimated_input_tokens": 8693, + "estimated_eval_tokens": 17642 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly a mix of unrelated PRs that only share broad thematic similarity. The only clear duplicate-like pair is the two `fixed_cross_entropy` patches for issue 43240, which both adjust the same loss helper code path; the rest should stay separate.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43251 is a reasonable canonical representative for the 43240 loss-helper fix: it is tightly scoped to `fixed_cross_entropy` and explicitly targets the issue. PR 43254 is a very close alternative that also links 43240 and patches the same code path, so the choice is representative rather than evidence of unique linkage.", + "best_issue_reason": null, + "best_pr_reason": "PR 43251 is a strong overall representative for the cluster\u2019s only true near-duplicate pair, because it is a focused implementation of the 43240 `fixed_cross_entropy` change. That said, PR 43254 is similarly issue-linked and code-path-equivalent, so this is a conservative representative choice rather than a uniquely privileged one.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Different work: VideoPrism model/docs addition vs an ExecuTorch dynamic-shape export test." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Different code paths: tokenizer API additions vs ExecuTorch export testing." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Unrelated: tokenizer method additions vs adding a new MobileLLM model." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Different scope: processor auto-loading robustness vs adding MobileLLM support." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Loss helper kwargs fix is unrelated to a new model implementation." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Different bug domains: cross-entropy kwargs vs Mistral4 test/model fixes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch dynamic-shape export tests are unrelated to Mistral4 test fixes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Different artifacts and problems: export test coverage vs new model addition." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "New model addition is unrelated to `cls.config` resolution order." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "MobileLLM model files are unrelated to Falcon output-interface refactoring." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "Unrelated: model addition vs model-creation skill/docs repo changes." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon refactor and model-creation skill are different changes with no shared code-path bug." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output-collection refactor is unrelated to Mistral4 test/model fixes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 fixes and `layrnorm` typo renaming are different concrete issues." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46048", + "accept": false, + "reason": "Different subsystems: Mistral4 fixes vs adding a TDT loss kernel." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Model-specific test fixes are unrelated to `cls.config` resolution behavior." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Model-specific fixes are unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "These are effectively the same `fixed_cross_entropy` fix for issue 43240: both add support for extra `cross_entropy` kwargs in the same code path." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The soft-edge verdicts look conservative and the cluster summary is mostly grounded, but the reasoning overstates the evidence for PR 43251. PR 43254 also has an explicit issue link to 43240 and the same `fixed_cross_entropy` code path, so 43251 is not the only PR here with clear issue linkage. The canonical/representative rationale should be phrased more conservatively." + }, + "evaluator_used": true, + "retried": true, + "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": "b51635748fb7d6b5da65cfd107ef150cf4985a888e6a03df3d6f19836819ace4", + "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": "The cluster contains two related but distinct VibeVoice PRs: one for the base model integration and one for a later realtime extension with additional tokenizer/generation work. They overlap on shared scaffolding, but they are not the same change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #42781 is the broader and newer VibeVoice PR, covering realtime-specific components in addition to the shared base integration, so it is the better representative of the cluster topic.", + "best_issue_reason": null, + "best_pr_reason": "PR #42781 is the strongest representative because it subsumes more of the VibeVoice stack and appears to be the more complete follow-on implementation, though it is not a duplicate of #40546.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Shared VibeVoice files indicate related work, but #40546 is the base implementation while #42781 adds realtime and acoustic-tokenizer changes; they are not the same concrete PR 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": 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": "3e0c6b1226ac35babb093253ccb1350f35ca59dc73bb1780b1257d47f2b3cef7", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are unrelated: one adds TimesFM covariate forecasting support, the other adds DINOv3 image classification support. They touch different models, code paths, and documentation, so this is not a duplicate pair.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the PRs target different products/features and do not represent the same underlying change.", + "best_issue_reason": null, + "best_pr_reason": "41224 is the more self-contained standalone PR in the pair, but only as a local representative; it is not a duplicate of 40755.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models and change goals: TimesFM covariates vs DINOv3 image classification. They do not fix the same code-path problem and could not plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "c334841605cd69d3ff1fc0a223ca1be13b6f2e94e0336be876d50125aeae30ba", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10435, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10435, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three items are separate model-addition PRs (DeepSeek OCR, Isaac, Kimi2-6). They share Transformers boilerplate and auto-registration edits, but the titles, model names, files, and code paths are different, so they are not duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "pull_request:45630 is the strongest representative of the cluster because it has the broadest integration surface and the most review activity, but it is still a distinct model-addition PR rather than a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different model additions for DeepSeek OCR vs Isaac. Overlap is limited to shared framework boilerplate and registry/docs updates, not the same underlying change." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different model additions for Isaac vs Kimi2-6. Similar auto-mapping and docs scaffolding do not indicate the same bug or code-path fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "91f5131001cebfb476cdcdc609032e29a9cfa5b232eca369421e9c7bb6d5c8fe", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5933, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5933, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are both broad dependency-maintenance PRs touching overlapping GitHub Actions workflows, but they fix different upgrade sets and different underlying compatibility concerns, so they should not be merged as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the two PRs are related maintenance updates, but they target different action families and different upgrade goals rather than the same concrete change.", + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the better representative of the cluster because it is the broader workflow-actions compatibility update and covers more of the shared workflow surface.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Both are GitHub Actions version bumps, but 42975 upgrades checkout/cache/upload-artifact and other workflow actions for Node 24 compatibility, while 42976 upgrades docker/build-push-action and a different set of workflow actions. They overlap in files, not in the same underlying fix or mergeable change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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-42978-10", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:45487", + "pull_request:45490", + "pull_request:46109", + "pull_request:46135", + "pull_request:46151", + "pull_request:46162", + "pull_request:46214" + ], + "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:45487|pull_request:46214", + "pull_request:45487|pull_request:46151", + "pull_request:45490|pull_request:46162", + "pull_request:46109|pull_request:46214", + "pull_request:46109|pull_request:46151", + "pull_request:46135|pull_request:46214", + "pull_request:46135|pull_request:46151", + "pull_request:46151|pull_request:46214", + "pull_request:46162|pull_request:46214" + ], + "prepared_review_unit_hash": "6af528238739bbd9a55ebd4bd8922081006c06c4f201f1111e2a83d62a7f6e18", + "component_budget": { + "node_count": 10, + "item_count": 10, + "soft_pair_count": 15, + "serialized_chars": 29975, + "estimated_input_tokens": 7494, + "estimated_eval_tokens": 15244 + }, + "budget": { + "node_count": 10, + "item_count": 10, + "soft_pair_count": 15, + "serialized_chars": 29975, + "estimated_input_tokens": 7494, + "estimated_eval_tokens": 15244 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated model-addition PRs plus separate XPU/distributed test expectation updates. The overlaps are driven by shared docs/auto-mapping/test infrastructure rather than the same underlying bug or change, so there is no true duplicate canonical here.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different model additions (ViT NEPA vs Molmo). Shared docs/auto-mapping files are broad infrastructure, not the same change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different model additions (ViT NEPA vs Molmo2). Similar files, but separate model implementations and docs." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "Different model additions (ViT NEPA vs CTSM). Same repo areas touched, but unrelated model families and code paths." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are distinct model families with different configs/processors/features, so not the same PR change." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo vs CTSM are unrelated model additions; overlap is only in generic model-registration/docs plumbing." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are separate model introductions with different implementation details and targets." + }, + { + "left": "pull_request:45487", + "right": "pull_request:46214", + "accept": false, + "reason": "AltCLIP/ChineseCLIP model-parallel fix is a different code-path issue from HRM text XPU expectation updates." + }, + { + "left": "pull_request:45487", + "right": "pull_request:46151", + "accept": false, + "reason": "Model-parallel device placement fix vs token-classification test expectations are unrelated changes." + }, + { + "left": "pull_request:45490", + "right": "pull_request:46162", + "accept": false, + "reason": "CTSM model addition is unrelated to Florence2/LFM2_VL XPU test expectation updates." + }, + { + "left": "pull_request:46109", + "right": "pull_request:46214", + "accept": false, + "reason": "Distributed trainer test parity tweak is not the same underlying bug as HRM text XPU expectations." + }, + { + "left": "pull_request:46109", + "right": "pull_request:46151", + "accept": false, + "reason": "Both mention XPU-related test behavior, but they target different test suites and different assertions." + }, + { + "left": "pull_request:46135", + "right": "pull_request:46214", + "accept": false, + "reason": "Kosmos2.5 integration expectations are model-specific and unrelated to HRM text expectations." + }, + { + "left": "pull_request:46135", + "right": "pull_request:46151", + "accept": false, + "reason": "Kosmos2.5 XPU expectations and token-classification expectations are separate model/test changes." + }, + { + "left": "pull_request:46151", + "right": "pull_request:46214", + "accept": false, + "reason": "Different test domains (pipeline token classification vs HRM text) and different expectation data; not mergeable as one duplicate fix." + }, + { + "left": "pull_request:46162", + "right": "pull_request:46214", + "accept": false, + "reason": "Florence2/LFM2_VL XPU expectations are model-specific and do not fix the same code path as HRM text." + } + ] + }, + "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": "a9fcc1982e99f3a7b2238586f6006ecf872b0164403e1ba03e65327fcaa377f5", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs do not look like duplicates: one fixes Whisper decoding/tests, one is an unrelated CLIP/ViT test edit, and one is a separate FP8 dequant/model-loading fix.", + "confidence": 0.82, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44815 is the most substantive standalone fix, with a clear code-path change and supporting model/integration updates; the other PRs are unrelated to it.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 appears to be the strongest representative of the set because it addresses a concrete runtime bug across loading/FP8 code, whereas PR 43291 is Whisper-only and PR 43665 is test-only and not clearly a real fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Different subsystems and different problems: Whisper tokenizer decoding vs CLIP/ViT test edits. No shared code path or concrete same bug." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper decoding/test fix is unrelated to the FP8 dequant/model-loading changes in 44815." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "These touch unrelated areas and solve different issues; broad title similarity is not enough to treat them as one 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": 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-43488-5", + "nodes": [ + "pull_request:43488", + "pull_request:43532", + "pull_request:45932", + "pull_request:46100", + "pull_request:46114" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:46114", + "pull_request:43488|pull_request:43532", + "pull_request:43532|pull_request:46114", + "pull_request:45932|pull_request:46100", + "pull_request:46100|pull_request:46114" + ], + "prepared_review_unit_hash": "b314a8ba5a2da23a414fe8716a6cb68c505e60725a76ddf3f9d168358145d666", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 11340, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 11340, + "estimated_input_tokens": 2835, + "estimated_eval_tokens": 5926 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Only PRs 46100 and 46114 are effectively the same change; the others are either unrelated test/bot scaffolding or a much broader model/config update and should not be deduped together.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46100 is the cleanest canonical representative of the exact duplicate pair (46100/46114): same file, same diff, same purpose, and it was opened first.", + "best_issue_reason": null, + "best_pr_reason": "PR 46100 best represents the duplicate cluster because it is the earliest instance of the identical ViT test-migration change and has the clearest standalone identity among the duplicates.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:46114", + "accept": false, + "reason": "Same test file, but the PRs are different bot/debug scaffolds with different surrounding setup and intent; not the same underlying change." + }, + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Both are intentional repo-bot/debug PRs, but they change different workflows and test-related plumbing, not one concrete shared fix." + }, + { + "left": "pull_request:43532", + "right": "pull_request:46114", + "accept": false, + "reason": "Overlap on the ViT test file is incidental; one is CI/workflow plumbing while the other is a forked test-migration PR with a different purpose." + }, + { + "left": "pull_request:45932", + "right": "pull_request:46100", + "accept": false, + "reason": "These touch different code paths and scopes: 45932 is a broad model/config and CI-secrets change, while 46100 is a tiny ViT test-only migration stub." + }, + { + "left": "pull_request:46100", + "right": "pull_request:46114", + "accept": true, + "reason": "They have the same file and identical diff hunk, and both are clearly the same ViT test-migration PR duplicated under a forked title." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet: PRs 46100 and 46114 are an exact duplicate pair with the same file and identical diff, while the other linked pairs are broader or different-purpose changes that do not look mergeable as a single bugfix. The soft-edge false/true calls are conservative overall." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "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": "4addd3107cd6ae18cf3a710a758408cf1b48b91ee532950020f3b77ac073e7e7", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two distinct open PRs adding new, related segmentation pipelines. They share documentation and pipeline scaffolding, but they target different tasks and model integrations, so they are not duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical duplicate PR: 43612 adds promptable concept segmentation, while 43613 adds promptable visual segmentation; they are separate features.", + "best_issue_reason": null, + "best_pr_reason": "If one PR must represent the cluster, 43613 is the broader/more integrated addition, with extra model and test coverage. It is still distinct from 43612.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Related pipeline-template changes, but different underlying tasks and code paths: concept segmentation vs visual segmentation. They are not the same change and would not be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "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": "f51683e574004618c45b542f2311919809fd88268269b99badcb176421cb4484", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs both touch `trainer.py` but address different trainer extension points: one changes gradient-accumulation loss scaling, the other refactors signature-column filtering for custom trainers. They do not look like the same underlying change.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No issue is linked, and the PRs are not duplicates. If one PR must represent the cluster, `#43651` is the better anchor because it makes a concrete behavioral change in the training loss path rather than a general refactor hook.", + "best_issue_reason": null, + "best_pr_reason": "`#43651` is the more representative standalone change: it introduces a specific fix/behavioral control for loss scaling during gradient accumulation. `#43663` is also a standalone trainer extensibility refactor, but it is a different code path and less suitable as a cluster representative.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Both modify `trainer.py`, but one targets loss scaling in `training_step` while the other targets signature-column computation for column filtering. Different code paths, different behavior, and they 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": 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-43656-2", + "nodes": [ + "pull_request:43656", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842" + ], + "prepared_review_unit_hash": "f2ebc50ebe407c1531a975bebf66b88823366ce3252f32741ad504c638e85812", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3664, + "estimated_input_tokens": 916, + "estimated_eval_tokens": 2088 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3664, + "estimated_input_tokens": 916, + "estimated_eval_tokens": 2088 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs touch the same CLI file and both mention TypeAdapter NameError, but they appear to fix different failure modes: one modernizes annotations / runtime typing, the other makes TypeAdapter safe when pydantic is absent.", + "confidence": 0.83, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43656 looks like the broader fix for the CLI type-annotation NameError, with a wider typing cleanup in the same code path.", + "best_issue_reason": null, + "best_pr_reason": "PR 43656 is the better canonical PR because it appears to address the underlying annotation/runtime NameError more generally, rather than only the optional-pydantic import case.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "They overlap in `src/transformers/cli/serve.py` and the title mentions the same symptom, but the diffs point to different fixes: 43656 changes future-annotation/type-hint behavior, while 43842 specifically avoids importing `TypeAdapter` at runtime when pydantic is unavailable. These are related but not the same concrete bug, and both could plausibly land separately." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 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:44018|pull_request:44066", + "pull_request:44066|pull_request:44068", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44116", + "pull_request:44018|pull_request:44116", + "pull_request:44068|pull_request:44722", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44085", + "pull_request:44018|pull_request:44086", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request: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:44018|pull_request:44059", + "pull_request:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", + "pull_request:44059|pull_request:44068", + "pull_request:44101|pull_request:44161", + "pull_request:44017|pull_request:44018", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:43997|pull_request:44018", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request: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:44010|pull_request:44018", + "pull_request:44071|pull_request:44129", + "pull_request:43997|pull_request:44129", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "4e6fcbcd6ec510bbef48318d616d0944da1f5e6b803792858821d30d32ccbb18", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84889, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75084, + "estimated_input_tokens": 18771, + "estimated_eval_tokens": 37798 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a broad standardized output-tracing migration across many unrelated model families. The only strong duplicate pockets are the GPT-J/CodeGen PRs and the GPT-Neo PRs; the rest are same-theme but different code paths and should not be merged together.", + "confidence": 0.89, + "canonical_issue_reason": "Issue #43979 is the umbrella tracking issue for the output-tracing/decorator migration, and many PRs in the cluster explicitly target it.", + "canonical_pr_reason": "PR #44722 is the clearest canonical PR for the true duplicate set: it directly refactors GPT-J/CodeGen output tracing, links the tracking issue, and overlaps the other GPT-J-focused PRs.", + "best_issue_reason": "#43979 best represents the shared migration theme that ties the cluster together.", + "best_pr_reason": "#44722 is the best representative PR because it covers the same concrete GPT-J/CodeGen tracing change as the closest duplicates and is the most focused consolidation point.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families (FNet/CVT vs GPT-J); same broad refactor theme but not the same code-path bug/change." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different models and code paths (FNet/CVT vs DeBERTa v2); not mergeable as one concrete fix." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors on the same underlying block/call pattern; 44066 just bundles the related CodeGen copy as well." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "Both are output-tracing migrations, but they touch different architectures and code paths (ResNet/RegNet vs EfficientNet)." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths; same issue family is not enough." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen refactor versus EfficientNet refactor; different concrete implementations." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa v2 are separate model implementations; no shared concrete bug/change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen versus MGP-STR; only the tracing pattern matches, not the underlying code path." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are distinct model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both are GPT-Neo output-tracing refactors on the same model/file and appear to address the same concrete change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo versus GPT-J/CodeGen; related theme but different model code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are separate model implementations, so these are not the same fix." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet-focused refactor versus GPT-J/CodeGen refactor; different concrete code paths." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen are unrelated model paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet versus GPT-J; same migration family but different underlying changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are unrelated implementations." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet versus MPT; not the same concrete bug/change." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert/XLM are different model code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert/XLM are separate fixes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo output tracing versus GPT-J/CodeGen output tracing; same theme, different code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are unrelated implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo versus GPT-J; too different to be one merged PR." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo versus MGP-STR; not the same concrete fix." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44085", + "accept": false, + "reason": "MPT and GPT-J/CodeGen touch different model internals." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 and MGP-STR are unrelated model families." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen versus MGP-STR; not the same underlying bug/change." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are different model implementations." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 versus GPT-J/CodeGen; same refactor style, different code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "Segformer and GPT-J/CodeGen are unrelated fixes." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are different code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "Segformer versus VisualBERT; not the same concrete change." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are distinct model implementations." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBERT and Flaubert/XLM are unrelated code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-2 versus GPT-Neo; separate model fixes." + }, + { + "left": "pull_request:44101", + "right": "pull_request:44161", + "accept": false, + "reason": "Flaubert/XLM and LongT5 are different model code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44018", + "accept": false, + "reason": "Segformer and GPT-Neo are unrelated implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44073", + "accept": false, + "reason": "RegNet and VisualBERT touch different model internals." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "FNet/CVT and LongT5 are different code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "FNet/CVT and Segformer are separate fixes, not one concrete bug." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBERT and MPT are unrelated model code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBERT versus VisualBERT; different concrete changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet and TextNet are distinct model implementations." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44018", + "accept": false, + "reason": "SqueezeBERT and GPT-Neo are different code paths." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are unrelated implementations." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44074", + "accept": false, + "reason": "FNet/CVT and TextNet are different model fixes." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBERT and DeBERTa v2 are separate code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa v2 and TextNet are unrelated model implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa v2 and SpeechT5 are different concrete fixes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa v2 and Vits are unrelated code paths." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are different model implementations." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are separate fixes." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "VisualBERT and LongT5 are different code paths." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert/XLM are unrelated model fixes." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44073", + "accept": false, + "reason": "ViLT and VisualBERT are separate model implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J/CodeGen output-tracing refactor family; these are the closest duplicate implementations in the cluster." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors on the same file/code path, so they plausibly collapse into one PR." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J/CodeGen and SpeechT5 are unrelated code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "FNet/CVT and ResNet are different model code paths; same migration style is not enough." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "FNet/CVT and SpeechT5 are unrelated fixes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa v2 and SpeechT5 are different concrete code-path changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa v2 and Vits are separate implementations." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative about cross-model pairings. The accepted soft-edge pairs are plausibly mergeable duplicates within the same GPT-J/CodeGen or GPT-Neo code paths, and the rejections correctly avoid conflating shared migration style with the same concrete fix." + }, + "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": "455ba10e803d6715197729142893817c6b756c274910d07036028d78e7d9663b", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84889, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17126, + "estimated_input_tokens": 4282, + "estimated_eval_tokens": 8820 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These PRs are all model-specific refactors to the new standardized output-capturing mechanism, but they affect different architectures and code paths, so they are not duplicates of one another.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44056 is the clearest representative of the shared refactor pattern: it introduces `capture_outputs` plus an explicit `_can_record_outputs` mapping, making it a strong canonical example of the standardized tracing change.", + "best_issue_reason": null, + "best_pr_reason": "PR 44056 is the best standalone representative of this cluster, but only as an example of the pattern; it is not a duplicate of the other model-specific refactors.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Both are output-tracing refactors, but they touch different models (`FocalNet` vs `ImageGPT`) and different forward paths, so they are not the same concrete change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "These are separate model migrations (`VisualBert` vs `TextNet`); the shared goal is too broad to make them duplicate PRs." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "Both adopt capture-based output tracing, but in different model implementations and call paths (`MPNet` vs `VisualBert`)." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "Different models and different implementation details; they are related by refactor theme only, not the same bug/change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "`RegNet` and `SqueezeBert` are unrelated model code paths; these are separate standardized-output migrations, not one duplicate fix." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "`SqueezeBert` and `SpeechT5` are distinct model stacks; the overlap is only the capture-output refactor pattern, not the same PR-worthy 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-43998-14", + "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", + "pull_request:46106" + ], + "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: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", + "pull_request:44027|pull_request:46106", + "pull_request:44026|pull_request:46106", + "pull_request:44001|pull_request:46106", + "pull_request:44002|pull_request:46106", + "pull_request:43998|pull_request:46106" + ], + "prepared_review_unit_hash": "77541cba6e06cf1e038a30f48dcd2fc1acb48c5b30c2604b25b06b0d771123e6", + "component_budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 44, + "serialized_chars": 43401, + "estimated_input_tokens": 10851, + "estimated_eval_tokens": 21958 + }, + "budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 44, + "serialized_chars": 43401, + "estimated_input_tokens": 10851, + "estimated_eval_tokens": 21958 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are mostly the same high-level refactor theme (\u201coutput tracing\u201d), but they target different model families and code paths, so they are not duplicates. The only non-model change is the docs toctree fix, which is unrelated.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44025 is the best representative of the cluster because it is a clean, self-contained output-tracing refactor spanning two closely related model files and sits in the densest similarity group.", + "best_issue_reason": null, + "best_pr_reason": "PR 44025 is the strongest exemplar of the shared refactor pattern: it makes the output-tracing change explicitly with the new decorator/imports and is more central than the single-file variants.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Same refactor theme, but different model architectures (timm_backbone vs upernet) and different forward/output code paths." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Both are output-tracing refactors, but they touch unrelated models and cannot plausibly be merged as one concrete fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model families and implementations; only the general refactor style matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "timm_backbone refactor is unrelated to the mamba/falcon_mamba output-tracing changes." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Different code paths and model behavior; shared wording is not enough for a duplicate." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Different architectures and output mechanisms; not the same underlying bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:46106", + "accept": false, + "reason": "Model refactor vs docs toctree edit; clearly unrelated." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "Both are refactors of output handling, but for different models and forward signatures." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Separate model implementations; same subsystem theme only at a very high level." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "MobileNetV1 and Depth Anything have different forward/output logic and are not the same fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Unrelated model wrappers; no shared concrete bug or code path." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different model families and output-tracing refactors only match superficially." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Vision-text dual encoder and UnivNet are unrelated models; same refactor pattern, different implementation details." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model classes and output types; not mergeable into one PR as a single fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families and code paths; shared wording is only a template-level similarity." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "CodeGen and vision-text dual encoder are unrelated concrete changes." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model architectures and output-capture changes; not the same underlying bug/change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "UnivNet and UperNet are different models with different forward contracts." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families; no evidence they fix the same concrete problem." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "Depth Anything and UnivNet are separate output-tracing refactors, not duplicates." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "UperNet and mamba/falcon_mamba do not share the same code path or bug." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model implementations; similarity is only in the refactor naming." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "These are both refactors, but for distinct model code paths and output behavior." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "timm_backbone and CodeGen are unrelated; not the same fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Depth Anything vs VisionEncoderDecoder are different model wrappers and output contracts." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Different model families; only the output-tracing refactor motif is shared." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Depth Anything and SuperPoint are unrelated model implementations." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Different architectures and tracing mechanisms; not the same underlying change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Depth Anything and DPR target different model code paths and output shapes." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are different wrappers with different modality-specific behavior." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Different model code and output handling; not mergeable as one duplicate fix." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "Vision encoder-decoder vs RWKV are unrelated model families." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Different subsystems and output logic; same generic refactor theme only." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "Speech encoder-decoder and SuperPoint are unrelated changes." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model families and code paths." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "Speech encoder-decoder vs DPR are separate implementations, not the same bug." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are unrelated model families." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Different models and output mechanics; not the same underlying change." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are unrelated code paths and should not be merged as duplicates." + }, + { + "left": "pull_request:44027", + "right": "pull_request:46106", + "accept": false, + "reason": "Model refactor vs docs navigation cleanup; clearly different work." + }, + { + "left": "pull_request:44026", + "right": "pull_request:46106", + "accept": false, + "reason": "Unrelated model code and documentation change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:46106", + "accept": false, + "reason": "UnivNet output-tracing refactor is unrelated to the docs toctree fix." + }, + { + "left": "pull_request:44002", + "right": "pull_request:46106", + "accept": false, + "reason": "Model refactor vs documentation tree edit; not duplicates." + }, + { + "left": "pull_request:43998", + "right": "pull_request:46106", + "accept": false, + "reason": "Different artifact types and unrelated changes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "9c43cb965442b5f330914c29c9995df391f45888344328b0b40a194a7170505d", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10913, + "estimated_input_tokens": 2729, + "estimated_eval_tokens": 5714 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition PRs for different models (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). The shared files are just standard Transformers boilerplate for adding a new model, not evidence of the same underlying change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different models and different code paths: PenguinVL vs Voxtral TTS. Shared auto-registration/docs scaffolding is generic new-model boilerplate, not a duplicate fix or one mergeable change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 are unrelated model integrations. Similar filenames reflect template-based model addition work, but the actual implementations, configs, and tests are for distinct models." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are different models with different purposes and files. Overlap is limited to common Transformers integration points, so they are not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "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": "a37660598d7f71f82585f8190536573ef0bfd1939a1684a44dd2289461510e1b", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4408, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are related to module/fusion infrastructure, but they implement different layers and different concrete code paths: #44979 adds a generic Module Fusion API, while #45363 adds n-to-1 kernel fusion via KernelConfig and integration glue. They do not look like duplicate changes.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45363 is the more concrete user-facing feature PR: it wires fusion through KernelConfig and runtime integration points. #44979 is a lower-level enabling API that supports a broader abstraction, so it is better treated as related infrastructure rather than the same change.", + "best_issue_reason": null, + "best_pr_reason": "#45363 is the best representative of the cluster because it describes a specific end-to-end fusion workflow and touches the execution path, whereas #44979 is mainly the generic API foundation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Related fusion work, but not the same underlying fix/change: one introduces a generic Module Fusion API, the other implements n-to-1 kernel fusion through KernelConfig and integration code. They would not plausibly be merged as one duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "f5286346b89905a03ab53d0c68570ef51b1ff6bb73bb56f2dbe6abca58b80d42", + "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 implement the same fix for the Mistral regex patch AttributeError in the same function and file; 45317 is the more complete variant with tests, so the pair should be clustered together with 45317 as the representative PR.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "45317 is the fuller implementation of the same bug fix and adds test coverage, making it the best canonical PR for this cluster.", + "best_issue_reason": null, + "best_pr_reason": "45317 is the strongest representative because it targets the same issue as 45086 but includes the test update and appears more complete/stable.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same concrete code-path bug fix in src/transformers/tokenization_utils_tokenizers.py for _patch_mistral_regex; 45317 is essentially the expanded version of 45086 with tests, so they are 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": 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": "31d5db2e18f5d6eb4c16786e3b66e54e441176006f0ea1703d7c5739f979db75", + "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": "Both PRs are about Nemotron-H support, but they tackle different slices of the work: one is a refactor/inheritance and checkpoint-conversion mapping change, while the other is a broader \u201cproper\u201d model split into nemotron_h / dense / sparse with docs and auto/model wiring. They overlap in shared files, but not the same concrete change set.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the broader, more complete Nemotron-H implementation effort and better represents the cluster\u2019s main direction; PR #45115 looks like a narrower precursor/refactor.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 is the best representative PR because it covers the larger end-state work: model variants, docs, auto mappings, and tests.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Shared Nemotron-H files are not enough here: #45115 focuses on GraniteMoeHybrid-style inheritance and conversion mapping, while #45569 implements the fuller Nemotron-H / Dense / Sparse model split and docs. They are related, but not the same fix and would not plausibly merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "c95f513002cd097440b249a35c186a30531766ec16ec3a2c7e82544734f3b8d0", + "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 two PRs are related but not duplicates: one adds heterogeneous per-layer config support, the other adds heterogeneous modeling/runtime support. They share infrastructure files, but they target different parts of the feature and would not be the same mergeable change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader end-to-end feature PR, covering heterogeneous modeling/runtime changes in addition to config plumbing, so it is the better canonical anchor for the cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the best representative because it spans the larger underlying feature area and includes the concrete model-path changes, while #45333 is only the config-side subset.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Reject: #45332 adds heterogeneous modeling/runtime support, while #45333 adds per-layer configuration support. They are adjacent pieces of the same feature family, but not the same concrete code-path fix/change and would not be merged as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "6bfc4757f11bbb38c6fcfee5a22286e81863f0dcb4e72a2f121cf73aa06bbfd7", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related typing-related pull requests, but they are not the same underlying change. PR 45415 is a broad repository-wide type-checking sweep, while PR 45425 adds specific typing protocols and utility types for a narrower set of model/integration code paths.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "45415 is the broader umbrella change: it updates many `src/transformers/*.py` files plus `pyproject.toml` to make type checking work. 45425 is a narrower typing refactor focused on `_typing.py`, `modeling_utils`, and related helpers.", + "best_issue_reason": null, + "best_pr_reason": "45415 is the best representative PR for this cluster because it covers the larger cross-cutting type-checking effort and subsumes the general theme more than the focused follow-up in 45425.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Both are typing-related, but they address different scopes and likely different mergeable changes: a broad typing sweep versus targeted protocol/type additions. Shared files alone are not enough to treat them as the same fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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-45513-3", + "nodes": [ + "pull_request:45513", + "pull_request:46084", + "pull_request:46098" + ], + "soft_pairs": [ + "pull_request:45513|pull_request:46084", + "pull_request:46084|pull_request:46098" + ], + "prepared_review_unit_hash": "053000d38193d6343a20b199e5f1432e7fe146bd83307a9bc0dde8905ccb5578", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 7428, + "estimated_input_tokens": 1857, + "estimated_eval_tokens": 3970 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 7428, + "estimated_input_tokens": 1857, + "estimated_eval_tokens": 3970 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two PRs (46084, 46098) appear to fix the same Mamba2 cached-forward bug for `use_cache` with `seq_len > 1`; the Qwen3.5 PR (45513) is a separate model-specific fix and should stay separate.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46098 is the most complete and explicit version of the Mamba2 fix: it names the concrete bug, targets the shared issue (#46032), and includes model, test, and docs updates.", + "best_issue_reason": null, + "best_pr_reason": "PR 46098 is the best representative because it clearly states the failure mode, is tied to the tracked issue, and appears broader/more finished than the narrower implementation in 46084.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45513", + "right": "pull_request:46084", + "accept": false, + "reason": "Different model families and different code paths: Qwen3.5 GDN linear attention vs Mamba2 cache handling. Similar wording about multi-token cached forward is not enough to treat them as the same change." + }, + { + "left": "pull_request:46084", + "right": "pull_request:46098", + "accept": true, + "reason": "Both target the same Mamba2 `use_cache` bug for `seq_len > 1`, share the same issue target (#46032), and touch the same model/test files; they look like overlapping fixes for the same underlying code-path problem." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: 45513 is a separate Qwen3.5/OLMo-hybrid cached-forward fix, while 46084 and 46098 both target the same Mamba2 `use_cache`/`seq_len > 1` bug under issue #46032 and share the same core files. The soft-edge verdicts are conservative enough, and the two Mamba2 PRs look mergeable as one bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "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": "8ccc548a0a6dada48d48583649edbfba9d3d3cee4abeedc30303497a877c6cbf", + "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": "Related but not duplicate: both PRs touch expert-parallel loading, yet they fix different distributed bugs and different code paths. One targets EP + DeepSpeed ZeRO-3 / accelerate launch config handling; the other targets EP + FSDP2 expert parameters being overwritten during rank-0 broadcast.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "pull_request:45662 is the stronger standalone fix: it addresses a concrete silent corruption path in expert parameter loading under FSDP2, with narrowly scoped code changes tied to the failure mode.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Same broad EP area, but different bugs: ZeRO-3/accelerate config loading vs FSDP2 rank-0 broadcast overwriting experts. Not mergeable as one fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 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": "3db06b4901eb7c064c7f9b10bd073cd7f6f13c21f7e75d6316ec6c36efbf110a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same xdist collision in captured_info handling, but PR #45645 is the more complete fix because it includes the worker-safe logging change plus the CI workflow update needed to read multiple captured_info files.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45645 is the better canonical representative: it contains the core xdist-safe output change from #45639 and also updates the workflow to preserve/aggregate the resulting debug logs.", + "best_issue_reason": null, + "best_pr_reason": "PR #45645 is the strongest overall candidate because it fully covers the underlying bug and its CI-log fallout, whereas #45639 is only the narrower helper/test change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Same underlying captured_info xdist-collision fix; #45645 is a superset that extends the same code-path change with workflow support, so they could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 25, + "component_count": 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": 26, + "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-46069-4", + "nodes": [ + "pull_request:46069", + "pull_request:46073", + "pull_request:46154", + "pull_request:46196" + ], + "soft_pairs": [ + "pull_request:46069|pull_request:46073", + "pull_request:46069|pull_request:46154", + "pull_request:46069|pull_request:46196", + "pull_request:46073|pull_request:46154", + "pull_request:46073|pull_request:46196", + "pull_request:46154|pull_request:46196" + ], + "prepared_review_unit_hash": "7e1eb31f9e5c227b9fc93b04823ec5a2cec3b9e55f977da749a2ba0731f7f85a", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10495, + "estimated_input_tokens": 2624, + "estimated_eval_tokens": 5504 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10495, + "estimated_input_tokens": 2624, + "estimated_eval_tokens": 5504 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs all implement SDPA/attention-dispatch support, but they do so for different model families and code paths. They are related by theme, not duplicates, so none of the soft edges should be accepted.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR 46196 is the strongest representative of the theme because it spans both SeamlessM4T and SeamlessM4T-v2 and includes the broadest code/test coverage, but it is still a model-specific implementation, not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46069", + "right": "pull_request:46073", + "accept": false, + "reason": "Different models and code paths (ShieldGemma2 vision model vs CTRL text model); same high-level feature, but not the same concrete fix." + }, + { + "left": "pull_request:46069", + "right": "pull_request:46154", + "accept": false, + "reason": "Different architectures and implementations (ShieldGemma2 vs T5 seq2seq); these would not be merged into one PR." + }, + { + "left": "pull_request:46069", + "right": "pull_request:46196", + "accept": false, + "reason": "Different model families and attention plumbing; one is ShieldGemma2, the other SeamlessM4T/v2, so not a duplicate." + }, + { + "left": "pull_request:46073", + "right": "pull_request:46154", + "accept": false, + "reason": "Both add SDPA dispatch, but for distinct model internals (CTRL vs T5) and separate test/documentation updates." + }, + { + "left": "pull_request:46073", + "right": "pull_request:46196", + "accept": false, + "reason": "Same broad subsystem, but different models and code paths; not the same underlying bug/change." + }, + { + "left": "pull_request:46154", + "right": "pull_request:46196", + "accept": false, + "reason": "T5 and SeamlessM4T/v2 have different attention implementations and fixes; too model-specific 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": 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-46152-2", + "nodes": [ + "pull_request:46152", + "pull_request:46207" + ], + "soft_pairs": [ + "pull_request:46152|pull_request:46207" + ], + "prepared_review_unit_hash": "869764d2688f6533e8a1a0cfb9b5f7521f06ba7cfdcc7d50e0847504fb6d40db", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4269, + "estimated_input_tokens": 1068, + "estimated_eval_tokens": 2392 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4269, + "estimated_input_tokens": 1068, + "estimated_eval_tokens": 2392 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs share a broad theme of removing source-file reads, but they target different code paths in different modules: `import_utils.py` vs `modeling_utils.py`. They are related refactors, not the same underlying bug/fix.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR is a clear duplicate/canonical representative; both are independent changes in separate modules with different implementation details and test impact.", + "best_issue_reason": null, + "best_pr_reason": "PR #46207 is slightly more representative of the cluster because it directly replaces a source-reading helper with introspection and includes an accompanying test, but it is still not a canonical duplicate of #46152.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46152", + "right": "pull_request:46207", + "accept": false, + "reason": "Both aim to avoid reading source files, but they fix different concrete behaviors in different subsystems (`import_utils` resource resolution vs `modeling_utils` attention-implementation detection). They are not mergeable as one PR without conflating separate problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/manifest.json b/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..d3e6d94a3de81d7a0b9c7dc07aa4ca97e1bf1f61 --- /dev/null +++ b/snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260526t180028z", + "artifacts": { + "hybrid": "snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-26T18:20:13Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260526T180028Z", + "variant": "hybrid" +} diff --git a/snapshots/20260526T180028Z/manifest.json b/snapshots/20260526T180028Z/manifest.json index 7d7538824acb7fff4f70dbc5ffc5d4ca6b6f19cf..b271e797dbdbd41be3e1a91eb9ae213d2f9bc9f9 100644 --- a/snapshots/20260526T180028Z/manifest.json +++ b/snapshots/20260526T180028Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 1716 }, "extracted_at": "2026-05-26T18:00:28Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260526t180028z", + "runs": { + "hybrid-model-20260526t180028z": { + "analysis_id": "hybrid-model-20260526t180028z", + "artifacts": { + "hybrid": "snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260526T180028Z/analysis-runs/hybrid-model-20260526t180028z/manifest.json", + "model": null, + "published_at": "2026-05-26T18:20:13Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260526T180028Z", "watermark": {