diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index 7d926bfaa7eb4545bbe789a712f9dbe685d10247..205448f901935280aa3b05542fcdb454f8039abb 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": "20260512T000156Z", - "generated_at": "2026-05-12T00:10:49Z", + "snapshot_id": "20260512T060024Z", + "generated_at": "2026-05-12T06:09:26Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1426,7 +1426,7 @@ "cluster_id": "cluster-43824-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", "status": "open", - "confidence": 0.75, + "confidence": 0.55, "canonical_issue_number": 43824, "canonical_pr_number": 43836, "issue_numbers": [ @@ -1437,8 +1437,7 @@ 43842 ], "evidence_types": [ - "closing_reference", - "shared_issue_target" + "closing_reference" ], "pr_comparisons": [ { @@ -1684,6 +1683,259 @@ } ] }, + { + "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": 44025, + "issue_numbers": [], + "pr_numbers": [ + 44001, + 44025 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44001, + "right_pr_number": 44025, + "code_similarity": 0.161, + "size_similarity": 0.44, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.486, + "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, + 44004 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44002, + "right_pr_number": 44004, + "code_similarity": 0.125, + "size_similarity": 0.398, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.304, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-45861-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 45861, + "issue_numbers": [], + "pr_numbers": [ + 45861, + 45903 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45861, + "right_pr_number": 45903, + "code_similarity": 0.617, + "size_similarity": 0.516, + "file_overlap": 1.0, + "area_overlap": 0.377, + "patch_similarity": 0.546, + "shared_filenames": [ + "src/transformers/models/qwen3_5/modeling_qwen3_5.py", + "src/transformers/models/qwen3_5_moe/modeling_qwen3_5_moe.py", + "src/transformers/models/qwen3_omni_moe/modeling_qwen3_omni_moe.py", + "src/transformers/models/qwen3_vl/modeling_qwen3_vl.py", + "src/transformers/models/qwen3_vl/modular_qwen3_vl.py", + "src/transformers/models/qwen3_vl_moe/modeling_qwen3_vl_moe.py", + "tests/models/qwen3_vl/test_modeling_qwen3_vl.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/qwen3_5/modeling_qwen3_5.py", + "left_ranges": [ + [ + 146, + 154 + ] + ], + "right_ranges": [ + [ + 146, + 154 + ], + [ + 161, + 183 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_5_moe/modeling_qwen3_5_moe.py", + "left_ranges": [ + [ + 142, + 150 + ] + ], + "right_ranges": [ + [ + 142, + 150 + ], + [ + 157, + 179 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_omni_moe/modeling_qwen3_omni_moe.py", + "left_ranges": [ + [ + 1315, + 1323 + ] + ], + "right_ranges": [ + [ + 1315, + 1323 + ], + [ + 1330, + 1352 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_vl/modeling_qwen3_vl.py", + "left_ranges": [ + [ + 354, + 362 + ] + ], + "right_ranges": [ + [ + 354, + 362 + ], + [ + 369, + 391 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_vl/modular_qwen3_vl.py", + "left_ranges": [ + [ + 294, + 302 + ] + ], + "right_ranges": [ + [ + 32, + 38 + ], + [ + 270, + 292 + ], + [ + 311, + 319 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_vl_moe/modeling_qwen3_vl_moe.py", + "left_ranges": [ + [ + 865, + 873 + ] + ], + "right_ranges": [ + [ + 865, + 873 + ], + [ + 880, + 902 + ] + ] + }, + { + "filename": "tests/models/qwen3_vl/test_modeling_qwen3_vl.py", + "left_ranges": [ + [ + 17, + 26 + ], + [ + 29, + 35 + ], + [ + 45, + 78 + ], + [ + 522, + 547 + ] + ], + "right_ranges": [ + [ + 17, + 26 + ], + [ + 29, + 35 + ], + [ + 45, + 79 + ], + [ + 523, + 582 + ] + ] + } + ] + } + ] + }, { "cluster_id": "cluster-44018-2", "summary": "Cluster of 2 related pull requests linked by soft_similarity.", @@ -2005,7 +2257,7 @@ 43842 ], "target_issue_number": 43824, - "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." + "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference evidence." }, { "cluster_id": "cluster-43979-11", @@ -2024,6 +2276,24 @@ "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": 44025, + "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": [ + 44004 + ], + "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, @@ -2059,6 +2329,15 @@ ], "target_issue_number": 45647, "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-45861-2", + "canonical_pr_number": 45861, + "duplicate_pr_numbers": [ + 45903 + ], + "target_issue_number": null, + "reason": "PRs in cluster-45861-2 are treated as duplicates because they share soft_similarity evidence." } ], "best_issue": { diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index fe42aacf7b4c8c02fe6b5642f92ae9316c6ef26d..d009789f9fdf2663363a7cb74c1448ea1a8d0eb0 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": "20260512T000156Z", - "generated_at": "2026-05-12T00:10:49Z", + "snapshot_id": "20260512T060024Z", + "generated_at": "2026-05-12T06:09:26Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -26,7 +26,7 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "0247d225baa8ae2f900d28338e3ef4363fbeb0a3a9116e002b07433cdd9e21d5", + "prepared_review_unit_hash": "e153ddec1352b53f10c71e2ea036241e882bc651ff08880d676e3ca583d3a804", "component_budget": { "node_count": 3, "item_count": 3, @@ -48,24 +48,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These three issues are not true duplicates; the only overlap is loose model/loading vocabulary. #16618 is the broadest model-loading report, while #13244 is about Tapas tokenization and #15980 is about an authentication/download error message.", - "confidence": 0.88, - "canonical_issue_reason": "#16618 is the best representative only by breadth: it is the most general model-loading complaint in the set. The other two concern different problems (tokenization behavior and a private-model download error).", + "summary": "These issues are not true duplicates: one is a Tapas tokenization mismatch, one is an auth/error-message problem for private model downloads, and one is a generic model-loading failure for bert-base-uncased. The closest pair still appears to be only superficially similar.", + "confidence": 0.89, + "canonical_issue_reason": "Issue #16618 is the broadest representative of the cluster because it concerns model loading, but it is still a separate failure mode from the other two.", "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the most central issue to this small cluster because its title is the broadest and closest to the shared model-loading theme, even though it is not a duplicate of the others.", + "best_issue_reason": "#16618 is the most central issue by title and scope, but the cluster does not contain a clear duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tapas tokenization mismatch is a different bug from failing to load bert-base-uncased; they involve different code paths and symptoms." + "reason": "Tapas tokenization mismatch vs. generic bert-base-uncased loading failure; different code paths and symptoms." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "A bad private-model download/auth error is unrelated to a generic inability to load bert-base-uncased; same general area, but not the same underlying issue." + "reason": "Private-model login/error-message behavior is unrelated to loading a public model like bert-base-uncased." } ] }, @@ -87,7 +87,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:24643", "issue:30277", @@ -197,423 +197,411 @@ "issue:43866|issue:44863", "issue:43854|issue:43866", "issue:39290|issue:43531", - "issue:43792|issue:45901", "issue:41093|issue:43638", + "issue:43792|issue:45901", "issue:43425|issue:45070", "issue:43596|issue:45800" ], - "prepared_review_unit_hash": "2ecaa8227c51b7f47704676efc4c8fd222de2f807ceba903a08693bd121ba6f1", + "prepared_review_unit_hash": "cdee891446d5bf3335a2413eae4d0837f15c581e7021225a975e9a65f1c64018", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 63, - "serialized_chars": 45922, - "estimated_input_tokens": 11481, - "estimated_eval_tokens": 23218 + "serialized_chars": 45920, + "estimated_input_tokens": 11480, + "estimated_eval_tokens": 23216 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly unrelated issues are mixed together here: model-specific runtime errors, docs cleanup, and a small DeepSpeed ZeRO-3 duplicate cluster. The only clear duplicate set is the repeated \"index 0 is out of bounds for dimension 0 with size 0\" failure during ZeRO-3 init/load on Bert/Gemma3 variants.", - "confidence": 0.93, - "canonical_issue_reason": "issue:43596 is the cleanest representative of the ZeRO-3 empty-tensor index-out-of-bounds bug; it states the core failure plainly and matches the duplicate cluster around the same error signature.", + "summary": "This cluster is mostly soft text-similarity noise across unrelated issues, with one clear duplicate family around DeepSpeed ZeRO-3 load/init IndexError failures. A small docs-only pair also shares a broad cleanup theme but not the same concrete change.", + "confidence": 0.78, + "canonical_issue_reason": "issue:43596 is the cleanest representative of the only clear duplicate family: a ZeRO-3 model-init/load failure causing 'index 0 is out of bounds for dimension 0 with size 0'. It is broad enough to cover the matching Bert/ZeRO-3 variants.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43596 is the best global issue representative because it captures the shared concrete failure mode most clearly and is central to the only true duplicate cluster in this set.", + "best_issue_reason": "issue:43596 best represents the shared ZeRO-3 index-out-of-bounds bug and is the strongest duplicate anchor among the issues provided.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different failures: missing config field vs streaming chat/completions error." + "reason": "Different failures: Qwen3.5 config attribute lookup vs streaming chat/completions behavior." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Different model/hardware problems; AMD GPU failure is not the same as an MPS int histogram error." + "reason": "Unrelated runtime paths: AMD GPU loading issue vs MPS histogram kernel limitation." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Both are model-specific, but the error signatures and code paths differ (dtype mismatch vs AMD GPU crash)." + "reason": "Different models and different device/dtype problems; no shared concrete bug." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Autocast dtype mismatch is a different bug from the AMD GPU execution failure." + "reason": "Autocast dtype mismatch for Phi MoE is unrelated to GPT-OSS running on AMD GPUs." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Unrelated model/runtime issues in different code paths." + "reason": "Different model families and failure modes; not the same bug." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Different model and failure mode; no shared underlying bug." + "reason": "Qwen NVFP4 load error is unrelated to AMD GPU execution failure." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch is unrelated to ModernBERT ONNX export." + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated code paths." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "ModernBERT ONNX export and Qwen3Moe FP8 are unrelated." + "reason": "ModernBERT ONNX export and Qwen3Moe FP8 config error are different issues." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "Different subsystems: ONNX export vs device-map CUDA assert." + "reason": "ONNX export failure vs CUDA assert during auto device mapping are not the same bug." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are docs regressions, but they reference different removed features and likely separate edits." + "reason": "Both are docs cleanups for v5 removals, but they reference different removed features and are not the same artifact." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "ONNX export error is unrelated to the GenerationMixin import breakage." + "reason": "ONNX export bug and GenerationMixin import error are unrelated." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Both mention shape/device issues, but the concrete failure modes and models differ." + "reason": "Mask/tensor shape mismatch is unrelated to Gemma4 PLE device placement." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Generic index/mask errors, but not the same concrete bug or repro." + "reason": "Both are IndexError-like titles, but one is ZeRO-3 init and the other is a mask indexing mismatch; different bugs." }, { "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "Both are index-style errors, but one is ZeRO-3 empty-tensor init and the other is a mask/tensor mismatch." + "reason": "Different failure types: ZeRO-3 empty-tensor init vs mask/index shape mismatch." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Different models and different failure types; no clear duplicate relationship." + "reason": "Mask shape mismatch and GPT-OSS tensor-parallel issue are different problems." }, { "left": "issue:44805", "right": "issue:44918", "accept": false, - "reason": "Mask/tensor shape mismatch is distinct from the SFT input-embedding unpacking issue." + "reason": "Different subsystems and error causes; not a duplicate pair." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "BarkProcessor voice preset bug is unrelated to ModernBERT export." + "reason": "BarkProcessor voice preset handling is unrelated to ModernBERT ONNX export." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Both involve distributed training, but the errors and affected paths differ." + "reason": "Collective mismatch during ZeRO-3 and Bert ZeRO-3 index error are distinct failures." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3 index-out-of-bounds-on-empty-tensor failure; both are the same concrete bug." + "reason": "Same ZeRO-3 load/init IndexError ('index 0 out of bounds' with size 0), just surfaced on closely related Bert model variants." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger Kernel cross_entropy behavior is unrelated to GPT-OSS tensor-parallel failure." + "reason": "Liger cross_entropy call and GPT-OSS TP failure do not point to the same code-path bug." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "DeepSeek detokenization and LoRA save/load mismatch are different bugs." + "reason": "Incorrect detokenization and LoRA merge/save inconsistency are unrelated." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "Different model/runtime problems with no shared code path." + "reason": "Qwen NVFP4 runtime error and LoRA weight merge/save mismatch are different issues." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "Both are shape-related, but the failing mechanisms are different (checkpointing/FSDP vs mask indexing)." + "reason": "Activation checkpointing/FSDP recomputation mismatch is unrelated to mask indexing errors." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "Training weight-dimension error is unrelated to the collective mismatch." + "reason": "DeepSpeed training weight-dimension error and collective mismatch are different bugs." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "ZeRO-3 Bert init failure is unrelated to GPT-OSS tensor-parallel behavior." + "reason": "ZeRO-3 Bert load failure and GPT-OSS tensor-parallel failure are unrelated." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "Activation-checkpointing shape mismatch and custom compute_loss signature break are unrelated." + "reason": "FSDP checkpointing shape mismatch and CustomTrainer signature mismatch are unrelated." }, { "left": "issue:43596", "right": "issue:45161", "accept": false, - "reason": "Different models and unrelated failures." + "reason": "Same DeepSpeed ZeRO-3 issue family? no; GPT-OSS TP problem is a different subsystem and symptom." }, { "left": "issue:43716", "right": "issue:45507", "accept": false, - "reason": "Model dtype mismatch and invalid-method call are different bugs." + "reason": "Different model-specific failures with no shared code path." }, { "left": "issue:39290", "right": "issue:45081", "accept": false, - "reason": "Gemma3 config attribute error is unrelated to the Mistral tokenizer regex crash." + "reason": "Gemma3/vLLM config mismatch and Mistral tokenizer patch crash are unrelated." }, { "left": "issue:45823", "right": "issue:45874", "accept": false, - "reason": "Both are Gemma4-related, but one is device placement and the other is reverse embedding lookup cost; not the same bug." + "reason": "Device-map forward mismatch and expensive reverse embedding lookup are different Gemma4 issues." }, { "left": "issue:43828", "right": "issue:45161", "accept": false, - "reason": "Autocast dtype mismatch is not the same as GPT-OSS TP failure." + "reason": "Autocast dtype mismatch for Phi MoE is unrelated to GPT-OSS TP failure." }, { "left": "issue:43425", "right": "issue:44292", "accept": false, - "reason": "Torch version incompatibility and Qwen-3-8B NVFP4 error are unrelated." + "reason": "Torch-version incompatibility and Qwen NVFP4 runtime error are not the same bug." }, { "left": "issue:34928", "right": "issue:41720", "accept": false, - "reason": "Different distributed/runtime failures with no common underlying issue." + "reason": "FSDP activation checkpointing mismatch and CUDA assert on Qwen3 auto device mapping are unrelated." }, { "left": "issue:44918", "right": "issue:45161", "accept": false, - "reason": "SFT embedding unpacking and GPT-OSS TP failure are different code paths." + "reason": "TRL SFT embedding unpacking failure and GPT-OSS TP failure are different issues." }, { "left": "issue:43541", "right": "issue:43716", "accept": false, - "reason": "Grouped_mm tracing failure and image-preprocessor dtype mismatch are unrelated." + "reason": "Dynamo tracing grouped_mm error and image preprocessor dtype mismatch are unrelated." }, { "left": "issue:43716", "right": "issue:45685", "accept": false, - "reason": "Different hardware/runtime issues; no duplicate evidence." + "reason": "Different model/device issues; no shared underlying bug." }, { "left": "issue:43828", "right": "issue:44292", "accept": false, - "reason": "Different model families and distinct dtype/runtime errors." - }, - { - "left": "issue:45507", - "right": "issue:45685", - "accept": false, - "reason": "Invalid-method model bug is unrelated to the MPS histogram int limitation." - }, - { - "left": "issue:43716", - "right": "issue:44292", - "accept": false, - "reason": "Different symptoms and model families." + "reason": "Different Qwen/Phi runtime paths and different error causes." }, { "left": "issue:44292", "right": "issue:44918", "accept": false, - "reason": "NVFP4 runtime error is unrelated to SFT embedding unpacking." + "reason": "Qwen NVFP4 runtime failure and TRL embedding unpacking failure are unrelated." }, { "left": "issue:43039", "right": "issue:44918", "accept": false, - "reason": "Liger Kernel cross_entropy issue is unrelated to the trainer embedding bug." + "reason": "Liger kernel cross-entropy routing and SFT embedding unpacking are not the same bug." }, { "left": "issue:41762", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3 index-out-of-bounds-on-size-0 failure, just on different models." + "reason": "Both are ZeRO-3 load/init IndexErrors ('index 0 out of bounds' with size 0), with different models exhibiting the same underlying initialization bug." }, { "left": "issue:43827", "right": "issue:44512", "accept": false, - "reason": "Both are v5 docs regressions, but they reference different removed docs topics and are not the same change." + "reason": "Both mention docs cleanup around removed v5 features, but they are different references and not the same concrete change." }, { "left": "issue:43716", "right": "issue:44560", "accept": false, - "reason": "Dtype mismatch in Mistral-3 is unrelated to the Qwen3-vl StopIteration video bug." + "reason": "Different multimodal/model issues with no shared failure path." }, { "left": "issue:43828", "right": "issue:45685", "accept": false, - "reason": "Autocast dtype mismatch and MPS histogram error are unrelated." + "reason": "Autocast dtype mismatch and MPS histogram limitation are unrelated." }, { "left": "issue:44918", "right": "issue:45685", "accept": false, - "reason": "Trainer embedding handling and MPS int histogram are different bugs." + "reason": "SFT trainer embedding issue and MPS int histogram limitation are unrelated." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Liger Kernel cross_entropy call and autocast dtype mismatch do not share the same underlying bug." + "reason": "Liger kernel usage issue and Phi MoE autocast dtype mismatch are different bugs." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed collective mismatch and custom trainer signature change are unrelated." + "reason": "DeepSpeed collective mismatch and trainer compute_loss signature break are unrelated." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "Checkpointing/FSDP shape mismatch is unrelated to the GenerationMixin import error." + "reason": "Checkpointing/FSDP shape mismatch and GenerationMixin import error are unrelated." }, { "left": "issue:43039", "right": "issue:44805", "accept": false, - "reason": "Different bugs: Liger Kernel cross_entropy vs mask/tensor shape mismatch." + "reason": "Different subsystems and symptoms; not a duplicate." }, { "left": "issue:41762", "right": "issue:43596", "accept": true, - "reason": "Same ZeRO-3 empty-tensor index-out-of-bounds failure; same concrete bug." + "reason": "Same ZeRO-3 index-0-out-of-bounds load/init failure, just on different model classes." }, { "left": "issue:43901", "right": "issue:44512", "accept": false, - "reason": "TextClassificationPipeline docs note and run-command docs note are separate documentation issues." + "reason": "Different docs issues: one is about return_all_scores wording, the other about removed run command docs." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Missing Gemma3 config field and Qwen3 device-map assert are unrelated." + "reason": "Different model/config bugs and different runtime failures." }, { "left": "issue:45237", "right": "issue:45901", "accept": false, - "reason": "AMD GPU model failure and table-question-answering crash are unrelated." + "reason": "GPT-OSS AMD GPU failure and table-question-answering crash are unrelated." }, { "left": "issue:44841", "right": "issue:45823", "accept": false, - "reason": "Processor failure for Voxtral and Gemma4 device mismatch are different issues." + "reason": "Processor failure for Voxtral and Gemma4 device-map mismatch are different bugs." }, { "left": "issue:43039", "right": "issue:44560", "accept": false, - "reason": "Liger Kernel cross_entropy and Qwen3-vl video StopIteration are unrelated." + "reason": "Liger kernel issue and Qwen3-vl StopIteration are unrelated." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Checkpoint corruption and NemotronH checkpoint-loading failure are different problems." + "reason": "Checkpoint corruption and NemotronH checkpoint loading issue are different problems." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "Unit-test load failure for GLM-4.7-Flash is not the same as a corrupted Ovis2 checkpoint." + "reason": "Model loading test failure and corrupted checkpoint report do not describe the same bug." }, { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Different model families and different sliding-window-related errors." + "reason": "Gemma3 sliding_window_pattern regression and Qwen3-MoE sliding_window issue are related only by name, not the same change." }, { - "left": "issue:43792", - "right": "issue:45901", + "left": "issue:41093", + "right": "issue:43638", "accept": false, - "reason": "Whisper load failure and table-question-answering crash are unrelated." + "reason": "Mask shape mismatch and ZeRO-3 empty-tensor IndexError are different failure modes." }, { - "left": "issue:41093", - "right": "issue:43638", + "left": "issue:43792", + "right": "issue:45901", "accept": false, - "reason": "Both mention index/shape errors, but the concrete bug and stack context differ." + "reason": "Whisper runtime failure and table QA crash are unrelated." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch-version incompatibility and pydantic PretrainedConfig field breakage are unrelated." + "reason": "Torch compatibility issue and pydantic PretrainedConfig field regression are unrelated." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "ZeRO-3 empty-tensor bug is unrelated to torch/transformers version incompatibility." + "reason": "ZeRO-3 model init bug and torch/transformers version incompatibility are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative about the soft edges. The ZeRO-3 out-of-bounds cluster is the only clearly supported duplicate set, and the accepted pairs are well supported by the issue titles and shared error signature." + "feedback": "The summary is grounded in the packet and stays conservative. The only clearly duplicated family is the ZeRO-3 index-out-of-bounds load/init issue across 43596, 43638, and 41762; the docs pair is reasonably treated as related in theme but not the same concrete change. I didn\u2019t see any soft-edge verdicts that overstate the evidence." }, "evaluator_used": true, "retried": false, @@ -632,7 +620,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36010", "issue:39186", @@ -704,8 +692,8 @@ "issue:43541|issue:45161", "issue:43828|issue:45464", "issue:44291|issue:45070", - "issue:43366|issue:45464", "issue:45020|issue:45800", + "issue:43366|issue:45464", "issue:43531|issue:45070", "issue:43541|issue:44589", "issue:41093|issue:43596", @@ -720,244 +708,244 @@ "issue:44530|issue:45005", "issue:44360|issue:44512" ], - "prepared_review_unit_hash": "39333065425eb3dece56489ecd54ce0084ad175b4b86bf1e222ca600e42cfbb6", + "prepared_review_unit_hash": "e9f50a6f38d9ea79408453dfc5c2ab946ac280fa0d2f76170c7ec18a877b20d4", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 37854, - "estimated_input_tokens": 9464, - "estimated_eval_tokens": 19184 + "serialized_chars": 37846, + "estimated_input_tokens": 9462, + "estimated_eval_tokens": 19180 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous bug reports across unrelated model families and regressions. No soft-edge pair is a strong duplicate match from titles alone; the broad open remote_code regression is the best umbrella issue, but not a clear duplicate target for the rest.", - "confidence": 0.41, - "canonical_issue_reason": "issue:45020 is the broadest open report in the set and best fits as an umbrella for recent-version regressions affecting remote_code/custom-model loading.", + "summary": "This cluster is mostly a collection of distinct Transformers regression reports. There is some broad overlap around v5/model-loading/runtime breakages, but the soft pairs do not look like true duplicates of the same underlying bug or change.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 45020 is the best umbrella candidate: it is broad, open, and centered on recent-version regressions breaking custom/remote-code models, which is the closest shared theme across many of the other reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the most representative and actionable issue: it is open, broadly scoped, and central to a class of version-regression reports.", + "best_issue_reason": "Issue 45020 is the most representative issue to keep as the cluster anchor because it describes a broad class of recent Transformers regressions rather than a single model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45859", "right": "issue:45902", "accept": false, - "reason": "Both are Qwen3.5-MoE rotary-embedding bugs, but one is about CPU offload compatibility and the other about uninitialized memory after meta->to_empty materialization; these look like different failure modes." + "reason": "Same model family, but different bugs: one is CPU-offload incompatibility in forward; the other is uninitialized-memory after meta->to_empty(cuda) materialization." }, { "left": "issue:43975", "right": "issue:45901", "accept": false, - "reason": "Unrelated symptoms and subsystems: incorrect detokenization in v5 vs a table-question-answering crash." + "reason": "Unrelated symptoms and code paths: detokenization regression vs table-question-answering crash." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "Whisper loading/runtime failure is unrelated to the PretrainedConfig pydantic regression." + "reason": "Different problems: Whisper loading/runtime failure vs a PretrainedConfig/pydantic regression." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Same model family, but different surfaces and failures: chat crash vs streaming chat/completions API failure; not enough evidence of one underlying bug." + "reason": "Both involve Qwen3.5 chat paths, but one is a crash in transformers chat and the other is a streaming inference API failure; not clearly the same bug." }, { "left": "issue:44292", "right": "issue:45901", "accept": false, - "reason": "Qwen NVFP4 runtime error and a table QA crash are unrelated." + "reason": "No meaningful overlap: Qwen-3-8B NVFP4 runtime error vs table-question-answering crash." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Different model bugs: untied lm_head weights in Mistral3 vs a corrupted Ovis2 checkpoint." + "reason": "Different models and failure modes: tied lm_head weights vs a corrupted Ovis2 checkpoint." }, { "left": "issue:39290", "right": "issue:45823", "accept": false, - "reason": "Gemma3 vLLM attribute regression and Gemma4 device-mismatch are different issues." + "reason": "Different models and bugs: missing Gemma3 config attribute under vLLM vs Gemma4 device mismatch during forward." }, { "left": "issue:45464", "right": "issue:45685", "accept": false, - "reason": "Streaming inference on Qwen3.5 and an MPS histogram kernel error are unrelated." + "reason": "Unrelated issues: Qwen3.5 streaming inference vs an MPS integer-kernel limitation." }, { "left": "issue:43541", "right": "issue:45685", "accept": false, - "reason": "Mixtral torch-dynamo grouped_mm failure is unrelated to the MPS Int histogram error." + "reason": "Different code paths and hardware backends: torch dynamo grouped_mm tracing vs MPS histogram support." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Both mention dtype-related problems, but they involve different models and code paths; not clearly the same bug." + "reason": "Both are runtime numeric issues, but one is grouped_mm tracing in Mixtral and the other is autocast dtype mismatch in Phi-tiny-MoE." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "ImportError for GenerationMixin and Gemma3 sliding_window_pattern are unrelated." + "reason": "Import error for GenerationMixin is unrelated to a Gemma3 config attribute missing in vLLM." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Voxtral processor failure and a template-node compilation error do not match." + "reason": "Different subsystems: processor loading for Voxtral vs a template compilation TypeError." }, { "left": "issue:41093", "right": "issue:41762", "accept": false, - "reason": "Both are index/shape errors, but one is a mask-vs-tensor mismatch and the other is a zero-size index error during Gemma3 + ZeRO-3 loading; too different to merge." + "reason": "Both are shape/indexing errors, but they affect different workflows and models; not enough evidence of the same bug." }, { "left": "issue:45800", "right": "issue:45823", "accept": false, - "reason": "Torch/transformers version incompatibility is not the same as Gemma4 PLE device mismatch." + "reason": "One is a general torch/Transformers incompatibility report; the other is a Gemma4 device-map mismatch." }, { "left": "issue:43296", "right": "issue:43366", "accept": false, - "reason": "PaddleOCR-VL loading in vLLM and GGUF gpt-oss support are different model-architecture issues." + "reason": "Completely different topics: PaddleOCR-VL loading failure vs GGUF gpt-oss support." }, { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "StableLmConfig pad_token_idx regression and a pydantic PretrainedConfig field breakage are related only at a very high level, not as the same concrete bug." + "reason": "Both are v5 config-related, but one is a missing pad_token_idx regression and the other is a pydantic field issue." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "Int4 quantization OOM and tied-weights translation-model issues are distinct." + "reason": "Different problems: int4 quantization memory growth vs tied-weights behavior on translation models." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Mixtral tracing failure and GPT-OSS MoE tensor-parallel issues are different code paths." + "reason": "Both mention MoE/GPT-OSS-adjacent behavior, but the concrete failures are different: dynamo tracing vs tensor-parallel support." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "Phi MoE autocast dtype mismatch is unrelated to Qwen3.5 streaming inference failure." + "reason": "Different failures: dtype mismatch under autocast vs streaming chat API failure." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized argument regression is unrelated to the PretrainedConfig pydantic issue." + "reason": "Both touch model loading, but one is an init_empty_weights argument regression and the other is a PretrainedConfig/pydantic breakage." }, { - "left": "issue:43366", - "right": "issue:45464", + "left": "issue:45020", + "right": "issue:45800", "accept": false, - "reason": "GGUF gpt-oss support and Qwen3.5 streaming API failure are unrelated." + "reason": "A broad remote_code regression is not the same underlying bug as a specific torch version incompatibility." }, { - "left": "issue:45020", - "right": "issue:45800", + "left": "issue:43366", + "right": "issue:45464", "accept": false, - "reason": "A broad remote_code regression and a specific torch-version incompatibility are not the same issue." + "reason": "GGUF gpt-oss support is unrelated to Qwen3.5 streaming inference." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and the pydantic PretrainedConfig regression are unrelated." + "reason": "Qwen3-MoE sliding_window behavior is unrelated to the pydantic PretrainedConfig regression." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Grouped_mm tracing failure and Float8 storage lookup error are separate runtime bugs." + "reason": "Different runtime failures: grouped_mm tracing vs missing Float8 storage type." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Both are deepspeed/shape-index failures, but the symptoms and models differ enough that they are not clearly one bug." + "reason": "Both are index-out-of-bounds style errors, but they arise in different models and initialization contexts." }, { "left": "issue:43054", "right": "issue:43994", "accept": false, - "reason": "Both involve SigLIP2, but one is a text-embedding quality complaint and the other is a nonsensical AutoModel/pipeline result; not enough evidence they are the same underlying defect." + "reason": "Both concern embeddings/representation quality, but the models and failure modes are different enough that they are not duplicates." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "TensorBoard-without-TensorFlow backend detection and a torch/transformers incompatibility are unrelated." + "reason": "TensorBoard-without-TensorFlow backend issue is unrelated to torch/Transformers incompatibility." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "High perplexity on gpt-oss and a GLM5 issue are different model-specific reports." + "reason": "High perplexity on GPT-OSS and a generic GLM5 issue are not the same bug." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Mistral-3 image-preprocessor dtype mismatch and Qwen3.5 embedding unpacking with TRL SFT are different bugs." + "reason": "Different model families and symptoms: image/text dtype mismatch vs embedding unpacking with trl SFT trainer." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP weight-dimension error and TRL input-embedding unpacking failure are unrelated." + "reason": "FSDP weight shape error and Qwen3.5 embedding unpacking failure are different code paths." }, { "left": "issue:45632", "right": "issue:45698", "accept": false, - "reason": "Both concern custom-module loading, but one is a leaf-directory cache collision for local models and the other is wrong-module loading after save_pretrained; too little evidence they are the same concrete bug." + "reason": "Both involve custom-module loading, but one is a cache-path collision and the other is loading the wrong module after save_pretrained; not the same defect." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Untied lm_head weights in Mistral3 and translation-model tied-weight issues are not the same concrete problem." + "reason": "Tied lm_head weights in Mistral3 and tied weights in translation models are related conceptually, but these are different model families and likely different fixes." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Custom model initialization in notebooks and flash-attn fallback gating are unrelated." + "reason": "Custom-model notebook initialization breakage is unrelated to flash-attn fallback logic." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "Qwen3.5 linear_attention crash and translation tied-weights regressions are different subsystems." + "reason": "PagedAttentionCache linear_attention crash is unrelated to tied-weights regressions." }, { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "DSA indexer ReLU discussion and removed docs run-command mention are unrelated." + "reason": "A technical discussion about the DSA indexer is unrelated to stale documentation." } ] }, @@ -979,7 +967,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36331", "issue:38175", @@ -1046,8 +1034,8 @@ "issue:41628|issue:45800", "issue:43872|issue:44589", "issue:43054|issue:45701", - "issue:38175|issue:43054", "issue:41553|issue:43883", + "issue:38175|issue:43054", "issue:44910|issue:45859", "issue:41553|issue:43881", "issue:42947|issue:44387", @@ -1060,17 +1048,17 @@ "issue:44403|issue:44488", "issue:41762|issue:42915", "issue:43782|issue:44960", - "issue:43881|issue:43883", - "issue:42491|issue:44368" + "issue:42491|issue:44368", + "issue:43881|issue:43883" ], - "prepared_review_unit_hash": "9e4f5a7396fda3b245c23cf8ad19a0b8819a0b942562d7ef80bb68f0634f0e66", + "prepared_review_unit_hash": "c62746840d5d5711e58dd213e4940021ca79779ed40aa9e135d1595190b4e1f4", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 47, @@ -1085,210 +1073,210 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a mix of unrelated Transformers/model regressions. The only clearly duplicated pocket is the non-persistent-buffer corruption reports; the SigLIP2-related edges are too weak to merge on titles alone.", - "confidence": 0.74, - "canonical_issue_reason": "issue:45020 is the broadest representative of the cluster\u2019s main regression theme: recent Transformers versions breaking model loading/remote-code flows. It is best as an umbrella anchor, but not a true duplicate of the more specific reports.", + "summary": "The cluster is about the Transformers v5 non-persistent-buffer corruption regression. Issue 43950 is the clearest anchor, with 43644 and 44534 as true duplicates; 43643 is related to remote-code loading but not the same bug.", + "confidence": 0.94, + "canonical_issue_reason": "43950 most directly names the shared regression (`from_pretrained()` corrupting `register_buffer(persistent=False)` buffers) and is the best representative of the duplicate buffer-corruption cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the best single issue to anchor the cluster because it is current, broad, and representative of the version-regression class present here. It should serve as the cluster\u2019s umbrella rather than a duplicate target.", + "best_issue_reason": "43950 is the strongest single issue to represent this cluster because it is the most specific and regression-focused report of the same non-persistent-buffer bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42915", "right": "issue:45399", "accept": false, - "reason": "Both are loading/fallback problems, but they are different concrete failures and model paths." + "reason": "Both are loading-related, but they describe different failures: Qwen3 MoE LoRA compatibility vs flash-attn2 fallback gating." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Quantization/offloading trouble vs tied-weights translation-model issues; same broad area, different bug." + "reason": "Quantization/offloading behavior is not the same as tied-weights warnings on translation models." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is unrelated to translation tied-weights behavior." + "reason": "NemotronH checkpoint loading failure is a different bug from tied-weights handling." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A cache-strategy typo and stale docs for a removed command are separate documentation issues." + "reason": "A cache-strategy typo is unrelated to outdated docs mentioning a removed command." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "Different model families and different code paths; not the same bug." + "reason": "Qwen3.5 embedding unpacking with TRL is a different code path from GraniteMoEHybrid calling an invalid method." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "Different symptoms and targets: detokenization regression vs load/runtime error." + "reason": "DeepSeek detokenization and Qwen NVFP4 loading are model-specific failures with different causes." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Same underlying regression: Transformers v5 fills/corrupts non-persistent buffers with junk during loading." + "reason": "Both report the same Transformers v5 non-persistent-buffer corruption/junk-buffer regression." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "Unrelated bugs in different models; no shared concrete code path." + "reason": "Qwen NVFP4 runtime failure is unrelated to GraniteMoEHybrid invalid-method behavior." }, { - "left": "issue:43643", - "right": "issue:45020", - "accept": false, - "reason": "Both touch remote_code/version regressions, but one is a specific AutoConfig field issue while the other is a broad umbrella report." + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Both describe the same non-persistent-buffer corruption regression in Transformers v5." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "Both involve SigLIP2, but one is a docs/example error and the other is an embedding-quality discrepancy." + "reason": "SigLIP2 docs-example errors with quantization failure are not the same as a text-embedding quality discrepancy." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Both mention precision/dtype symptoms, but the concrete failures differ." + "reason": "Phi autocast dtype mismatch and Qwen3.5 position_ids/SDPA issues are different failures." }, { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "Trainer compute_loss API mismatch vs ZeRO-3 Gemma3 loading failure; different stack and issue." + "reason": "A custom trainer kwarg error is unrelated to Gemma3 ZeRO-3 loading failure." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Corrupted checkpoint vs generic loading noise; related category, not duplicate." + "reason": "Corrupted checkpoint and generic loading noise are not the same underlying issue." }, { "left": "issue:41628", "right": "issue:45800", "accept": false, - "reason": "AutoImageProcessor import failure and torch/Transformers incompatibility are distinct problems." + "reason": "AutoImageProcessor import failure and torch/transformers incompatibility are distinct bugs." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "Different bitsandbytes/quantization compatibility errors with different missing symbols/storages." + "reason": "bitsandbytes kwarg incompatibility is different from missing Float8 storage type errors." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "Same broad model family, but the titles point to a quality/discrepancy theme, not the same concrete bug." + "reason": "SigLIP2 embedding quality and tokenizer changes across versions are related only broadly, not the same bug." }, { - "left": "issue:38175", - "right": "issue:43054", + "left": "issue:41553", + "right": "issue:43883", "accept": false, - "reason": "Both are SigLIP2-related, but unexpected zero probabilities and worse embeddings are not the same bug from the available evidence." + "reason": "Bad AutoTokenizer error messaging and missing `all_tied_weights_keys` are unrelated." }, { - "left": "issue:41553", - "right": "issue:43883", + "left": "issue:38175", + "right": "issue:43054", "accept": false, - "reason": "Bad AutoTokenizer error messaging for Voxtral vs Molmo tied-weights attribute error." + "reason": "Unexpected zero probabilities in SigLIP2 is not the same as broader text-embedding degradation." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "Different Qwen3.5 failures with different code paths and symptoms." + "reason": "Flash-attn illegal-memory-access on Qwen3.5 is different from CPU-offload incompatibility in rotary embedding." }, { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "Different model-loading problems with different models and failure modes." + "reason": "Voxtral AutoTokenizer error messaging and glm-4v loading failure are unrelated model-loading problems." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "Ineffective gradient checkpointing in PEFT LoRA is not the same as higher CUDA reserved memory under int4 quantization." + "reason": "Gradient-checkpointing ineffectiveness and int4 CUDA reserved-memory OOM are different performance bugs." }, { "left": "issue:43054", "right": "issue:43493", "accept": false, - "reason": "The SigLIP2 titles suggest a shared family and discrepancy theme, but not enough to confidently call them the same bug from titles alone." + "reason": "Both concern SigLIP2, but one is a quality complaint and the other is an HF-vs-JAX implementation discrepancy." }, { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "Generic loading noise vs a specific model failing to load; related category, not duplicate." + "reason": "Generic loading noise is not the same as inability to load a specific checkpoint." }, { - "left": "issue:43644", - "right": "issue:43950", - "accept": true, - "reason": "Same non-persistent-buffer regression in v5; both report buffers being filled or corrupted with junk on load." + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Missing fields with `trust_remote_code=True` is adjacent to, but not the same as, broader remote-code breakage." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "Detokenization regression vs Python 3.13 flash_attn import-utils KeyError; different code paths." + "reason": "Detokenization issues and Python 3.13 flash_attn import errors are unrelated." }, { "left": "issue:43975", "right": "issue:45237", "accept": false, - "reason": "Different failures entirely: detokenization vs AMD GPU compatibility." + "reason": "Detokenization issues and AMD GPU runtime failures are unrelated." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "Both concern memory, but one is ineffective gradient checkpointing and the other is general MoE training memory usage." + "reason": "Checkpointing/LoRA behavior is unrelated to Qwen3 MoE memory usage." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Both are load-time issues, but they involve different models and no shared bug signature." + "reason": "Both are loading-related, but one is generic noise and the other is a specific checkpoint load failure." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Gemma3 ZeRO-3 loading failure is unrelated to Qwen3Moe FP8 config failure." + "reason": "Gemma3 ZeRO-3 loading failure and Qwen3 MoE LoRA incompatibility are different model-specific issues." }, { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Qwen3VL weight_only load error vs GLM5 issue; different model and code path." + "reason": "Qwen3VL weight-only loading error is not the same as GLM5 loading/reporting issues." }, { - "left": "issue:43881", - "right": "issue:43883", + "left": "issue:42491", + "right": "issue:44368", "accept": false, - "reason": "Completely different model failures: glm-4v-9b load failure vs Molmo tied-weights attribute error." + "reason": "LoRA compatibility across hf versions and a tie-word-embeddings warning are not the same underlying bug." }, { - "left": "issue:42491", - "right": "issue:44368", + "left": "issue:43881", + "right": "issue:43883", "accept": false, - "reason": "Both mention Qwen3/Qwen3.5 and LoRA, but one is cross-version model incompatibility and the other is a warning about tie_word_embeddings." + "reason": "glm-4v loading failure and missing `all_tied_weights_keys` are different failures." } ] }, "evaluator_result": { "accept": false, - "feedback": "The non-persistent-buffer pair is well grounded, but the SigLIP2 verdict is a bit too strong for the packet evidence. The titles support a shared model family and a similar quality/discrepancy theme, but not enough to confidently call it the same bug/duplicate from titles alone. That makes the soft-edge handling not fully conservative, so I\u2019d reject." + "feedback": "The 43950/44534 match is grounded, but the accepted 43643/43950 soft edge is too strong for the packet: 43643 is only described as missing fields with `trust_remote_code=True`, and the packet does not clearly tie it to the non-persistent-buffer regression. Because that acceptance overstates the evidence, I can\u2019t approve the cluster as written." }, "evaluator_used": true, "retried": true, @@ -1307,7 +1295,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:24643", "issue:30064", @@ -1365,14 +1353,14 @@ "issue:44661|issue:45020", "issue:44991|issue:45399", "issue:43828|issue:45823", - "issue:45020|issue:45356", "issue:45081|issue:45399", "issue:43827|issue:44509", "issue:43950|issue:45902", + "issue:45020|issue:45356", "issue:43404|issue:43950", "issue:43742|issue:45399", - "issue:43257|issue:43866", "issue:42915|issue:45020", + "issue:43257|issue:43866", "issue:43638|issue:45823", "issue:43792|issue:44220", "issue:43872|issue:44291", @@ -1395,20 +1383,20 @@ "issue:44155|issue:45584", "issue:43366|issue:43531" ], - "prepared_review_unit_hash": "592171e140520192157b2e20e0593819de6f0cc79dadedfe1973ce8b7021f537", + "prepared_review_unit_hash": "e4eef7719deb7a488cc9d4a6d00c018a9c8dd8c394233139434d6b812d14469b", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 35, - "serialized_chars": 38553, + "serialized_chars": 38555, "estimated_input_tokens": 9639, "estimated_eval_tokens": 19534 }, @@ -1417,228 +1405,228 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous and contains several unrelated bug families. I found a few genuine duplicate-like pairs (docs cleanup, mask-shape IndexError, bitsandbytes/init_empty_weights TypeError, Whisper audio feature extraction, and Qwen video-input regression), but most soft edges are false positives.", - "confidence": 0.87, - "canonical_issue_reason": "No single issue cleanly represents the whole mixed cluster; if an anchor is required, issue 43872 is the cleanest concrete bug report because 44291 is the same _is_hf_initialized/init_empty_weights regression.", + "summary": "This cluster is mostly heterogeneous: most items are unrelated model-, tokenizer-, or docs-specific issues. Only a few clear duplicate pairs stand out, notably the v5 docs/pipeline regression, the `_is_hf_initialized` / `init_empty_weights` loading regression, the identical mask-shape IndexError reports, and the Qwen3-vl video regression.", + "confidence": 0.81, + "canonical_issue_reason": "No single issue cleanly represents the entire cluster, but issue 44291 is the strongest canonical candidate among the clear duplicates because it states the generalized `_is_hf_initialized` / `init_empty_weights` regression rather than only a downstream symptom.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43872 is the best representative among the duplicate-like candidates: it is a specific, actionable bug with a near-identical follow-up report in 44291.", + "best_issue_reason": "Issue 44291 is the best overall issue to anchor deduping here: it is the most generalized and actionable report among the true duplicates, while most other items are separate bugs that should not be collapsed together.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "Different failures: MPS histogram/int dtype issue vs Gemma4 PLE device mismatch." + "reason": "Different failures: MPS histogram/int support in MoE vs Gemma4 PLE device placement with device_map auto." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Unrelated: missing Qwen2.5-VL class import vs bitsandbytes _is_hf_initialized TypeError." + "reason": "Unrelated symptoms: missing Qwen2.5-VL import vs bitsandbytes/_is_hf_initialized incompatibility." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "Different bug families: remote_code breakage vs Gemma4 device placement during forward." + "reason": "Broad remote_code regression is not the same bug as Gemma4 PLE device mismatch." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Tokenizer mapping lookup bug is not the same as the remote_code regression." + "reason": "Tokenizer mapping edge case vs remote_code breakage; different code paths and fixes." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading failure vs flash-attn2 fallback gating; no shared code-path bug." + "reason": "Tokenizer loading regression vs flash-attn fallback gating; different subsystems." }, { - "left": "issue:43827", + "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Docs cleanup vs runtime device mismatch; not the same issue." - }, - { - "left": "issue:45020", - "right": "issue:45356", - "accept": false, - "reason": "Remote_code regressions and Kimi tokenizer codec/regex issues are different failures." + "reason": "Autocast dtype mismatch in Phi-MoE is not the same as Gemma4 device mismatch." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Mistral regex crash is unrelated to flash-attn fallback blocking." + "reason": "Mistral tokenizer regex crash and flash-attn fallback checks are unrelated." }, { "left": "issue:43827", "right": "issue:44509", "accept": true, - "reason": "Same docs cleanup: both say removed text2text/summarization/translation pipeline tasks are still referenced." + "reason": "Same docs regression: both report stale pipeline-task references removed in v5." }, { "left": "issue:43950", "right": "issue:45902", "accept": false, - "reason": "Both touch buffer/materialization, but these are not the same concrete bug or fix path." + "reason": "Non-persistent buffer corruption on from_pretrained is a different issue from Qwen3Moe inv_freq materialization." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer/model regressions; no shared concrete bug." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Unrelated model-weight tying bug vs non-persistent buffer corruption regression." + "reason": "lm_head weight tying bug is unrelated to non-persistent buffer handling." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "Model load key error vs flash-attn2 fallback gating; no duplicate signal." + "reason": "MobileLLM load failure and flash-attn fallback gating are distinct problems." }, { - "left": "issue:43257", - "right": "issue:43866", + "left": "issue:42915", + "right": "issue:45020", "accept": false, - "reason": "Different models and different symptoms: Qwen3 MoE loading vs Ovis2 checkpoint corruption." + "reason": "FineGrainedFP8Config failure is not the same as remote_code model breakage." }, { - "left": "issue:42915", - "right": "issue:45020", + "left": "issue:43257", + "right": "issue:43866", "accept": false, - "reason": "FineGrainedFP8Config failure is unrelated to remote_code loading regressions." + "reason": "Qwen3 MoE weight-conversion problem and Ovis2 checkpoint corruption are different bugs." }, { "left": "issue:43638", "right": "issue:45823", "accept": false, - "reason": "DeepSpeed ZeRO-3 empty-index error vs Gemma4 device mismatch; different bugs." + "reason": "Deepspeed ZeRO-3 empty-parameter loading failure is unrelated to Gemma4 device placement." }, { "left": "issue:43792", "right": "issue:44220", - "accept": true, - "reason": "Likely the same Whisper audio-feature path: 44220 names _torch_extract_fbank_features(), and 43792 reports Whisper-large-v2 cannot run." + "accept": false, + "reason": "Both are Whisper/audio-related, but the titles do not establish the same concrete root cause; too weak to merge." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Same unexpected _is_hf_initialized / init_empty_weights TypeError regression, just reported from different angles." + "reason": "Same underlying incompatibility around `_is_hf_initialized` / `init_empty_weights`; 44291 generalizes the bitsandbytes symptom." }, { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Both are ZeRO-3 weight-loading failures, but they affect different Qwen model families and submodules." + "reason": "Both mention DeepSpeed weight-loading issues, but they target different Qwen variants and do not clearly share one code-path bug." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "FineGrainedFP8Config failure is unrelated to the bitsandbytes _is_hf_initialized bug." + "reason": "FP8 config failure and bitsandbytes/_is_hf_initialized incompatibility are unrelated." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "Different model-loading problems for different architectures; not the same underlying bug." + "reason": "Different model-loading failures for different architectures." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer loading issues, but the models and failure modes are different." + "reason": "Bad error message for Voxtral tokenization is not the same as the est-roberta tokenizer failure." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "DeepSpeed appears in both, but one is missing Qwen3 MoE weights and the other is gradient averaging with GAS." + "reason": "Qwen3 MoE weight-conversion issue and DeepSpeed GAS gradient averaging regression are separate training bugs." }, { "left": "issue:45759", "right": "issue:45902", "accept": false, - "reason": "Composite-config handling vs uninitialized rotary embedding memory; different code paths." + "reason": "Composite config unwrapping issue is unrelated to Qwen3Moe rotary embedding materialization." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Different runtime errors: trainer signature mismatch vs mask/tensor shape mismatch." + "reason": "CustomTrainer kwarg mismatch and mask-shape IndexError are different training failures." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "Gradient explosion in RLHF is unrelated to a flash_attention s_aux=None crash." + "reason": "RLHF NaN/SDPA fallback issue is unrelated to flash_attention.py s_aux=None crash." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "bitsandbytes initialization bug is unrelated to CLIPTokenizer model_max_length." + "reason": "bitsandbytes/init_empty_weights incompatibility is unrelated to CLIPTokenizer max length." }, { "left": "issue:41093", "right": "issue:44805", "accept": true, - "reason": "Same mask-shape IndexError; the titles are essentially the same bug." + "reason": "Same generic mask-shape IndexError pattern; these look like duplicate reports of the same underlying indexing bug." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "PagedAttentionCache linear_attention crash is unrelated to NemotronH checkpoint loading." + "reason": "Qwen3.5 paged attention group-type crash is unrelated to NemotronH checkpoint loading." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Different tokenizer/model-loading issues with no clear shared bug." + "reason": "Different tokenizer-load failures for different models." }, { "left": "issue:44479", "right": "issue:44560", "accept": true, - "reason": "Same Qwen video-input regression family; 44560 is a specific StopIteration symptom of the 5.3.0 video-input breakage." + "reason": "Both describe the same Qwen video-input regression around 5.3.0, with 44560 as a specific instance of the broader issue." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "DeepSpeed training weight-dimension error vs image processor void-segmentation bug are unrelated." + "reason": "DeepSpeed training weight-shape error and void segmentation map processing are unrelated." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF gpt-oss support request vs autocast dtype mismatch; different issues." + "reason": "GGUF gpt-oss support and Phi-MoE autocast dtype mismatch are different problems." }, { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Gemma4 FSDP2 shared_kv_states bug is a different path from the device_map=\"auto\" device mismatch." + "reason": "Gemma4 FSDP2 shared_kv_states bug and Gemma4 PLE device mismatch are separate forward-path issues." }, { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "AudioFlamingo token/embedding leak is unrelated to Whisper empty-transcription generation failure." + "reason": "AudioFlamingo3 token/embedding leakage and Whisper empty-transcription handling are unrelated." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "gpt-oss GGUF support and Qwen3-MoE sliding_window are unrelated." + "reason": "GGUF gpt-oss support and Qwen3-MoE sliding_window behavior are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays appropriately conservative. The accepted soft edges are well supported by the titles, especially the exact/near-exact duplicates (43827/44509, 43872/44291, 41093/44805, 44479/44560) and the Whisper/audio-feature pair. The rejected edges also read as cautious and consistent with the packet. " + "feedback": "The cluster summary is grounded in the packet and stays conservative about unrelated issues. The accepted duplicates are well-supported by their titles and descriptions: 43827/44509, 43872/44291, 41093/44805, and 44479/44560. The rejected soft edges also read as appropriately cautious rather than overstated. " }, "evaluator_used": true, "retried": false, @@ -1657,7 +1645,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36010", "issue:38175", @@ -1714,8 +1702,8 @@ "issue:44560|issue:45685", "issue:43824|issue:43957", "issue:43645|issue:43646", - "issue:42915|issue:43957", "issue:43366|issue:44589", + "issue:42915|issue:43957", "issue:42617|issue:43366", "issue:44560|issue:44918", "issue:36010|issue:42915", @@ -1731,257 +1719,257 @@ "issue:43644|issue:44534", "issue:38175|issue:39692", "issue:44960|issue:44977", - "issue:45488|issue:45812", - "issue:45313|issue:45357", "issue:42491|issue:43720", + "issue:45313|issue:45357", + "issue:45488|issue:45812", "issue:44451|issue:44488", "issue:41720|issue:42915", - "issue:43854|issue:43931", "issue:43708|issue:44075", + "issue:43854|issue:43931", "issue:42491|issue:45276", - "issue:43257|issue:43854", "issue:42915|issue:44756", - "issue:39692|issue:43994", - "issue:42491|issue:43931" + "issue:43257|issue:43854", + "issue:42491|issue:43931", + "issue:39692|issue:43994" ], - "prepared_review_unit_hash": "56060f236db5ebb00331421c14fc2d952af44a0794ae22e64532f2cb89de1d2f", + "prepared_review_unit_hash": "369348f6034820a322d4a9b61b7c71daaf71a21f13d252c9be27aa5ff00c4519", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37807, - "estimated_input_tokens": 9452, - "estimated_eval_tokens": 19160 + "serialized_chars": 37802, + "estimated_input_tokens": 9451, + "estimated_eval_tokens": 19158 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous overall, with several small duplicate subclusters rather than one unified bug. The clearest duplicate themes are the non-persistent-buffer regression, the SigLIP2 bad-output reports, and the two BERT model-loading failures.", + "summary": "Mostly distinct Transformers v5/model-loading regressions; only a few soft pairs are true duplicates, chiefly around non-persistent buffers, custom model init, and SigLIP2 bad outputs.", "confidence": 0.84, - "canonical_issue_reason": "Issue 43644 is the best issue anchor: it is concrete, regression-focused, and has a near-identical duplicate in 44534 about the same non-persistent-buffer corruption.", + "canonical_issue_reason": "issue:43950 is the clearest root-cause report of the broad v5 regression in `from_pretrained` buffer handling (`register_buffer(persistent=False)`), which also matches the duplicate buffer-corruption reports.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43644 is the strongest representative issue because it states the bug crisply, maps to an exact duplicate, and is more general than the other issue titles in that subcluster.", + "best_issue_reason": "It has the most actionable and general bug statement in the cluster, and it describes a reusable loading-path regression rather than a model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "Both are model-loading failures, but one is a non-persistent-buffer regression and the other is a Kosmos2.5 OCR index error; different bugs." + "reason": "Buffer corruption during loading and a Kosmos2.5 OCR index error are unrelated failure modes." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Different code paths and symptoms: Bamba torch.compile/SDPA versus Qwen3.5 flash-attention illegal memory access." + "reason": "Both involve attention/kernel failures, but they affect different models and code paths with different symptoms." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Unrelated failures: Qwen3-VL video StopIteration versus MPS histogram support for Int tensors in MoE." + "reason": "Qwen3-VL video StopIteration and an MPS int-histogram limitation are unrelated bugs." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Different regressions: missing Qwen2.5-VL import versus meta-device model loading breakage." + "reason": "Importing Qwen2.5-VL and meta-device loading breakage are different model-loading issues." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "Both report Transformers 5 breaking custom model initialization; 43645 is just the notebook-specific manifestation of the same underlying bug." + "reason": "Both report the same Transformers v5 regression breaking custom model initialization; the notebook detail is just a context variant." }, { - "left": "issue:42915", - "right": "issue:43957", + "left": "issue:43366", + "right": "issue:44589", "accept": false, - "reason": "Qwen3MoE FP8 failure is unrelated to the meta-device loading regression." + "reason": "GGUF gpt-oss support and Float8 storage lookup failure are unrelated." }, { - "left": "issue:43366", - "right": "issue:44589", + "left": "issue:42915", + "right": "issue:43957", "accept": false, - "reason": "GGUF gpt-oss support and Float8 storage lookup failure are distinct issues." + "reason": "Qwen3Moe FP8 failure and meta-device loading issues do not share the same underlying bug." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "A 3D parallel script failure is unrelated to GGUF architecture support." + "reason": "3d_parallel.py execution failure is unrelated to GGUF architecture support." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Both involve Qwen3.5, but one is video inference and the other is TRL SFT embedding unpacking; not the same bug." + "reason": "Video StopIteration and TRL embedding unpacking are different Qwen3-VL/QLora training failures." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "ImportError for GenerationMixin is unrelated to the Qwen3MoE FP8 issue." + "reason": "GenerationMixin import error and Qwen3Moe FP8 failure are unrelated." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer mapping registration failure and Gemma4 device mismatch are different code paths." + "reason": "Tokenizer mapping/model registration bug and Gemma4 device mismatch are separate issues." }, { "left": "issue:38175", "right": "issue:43994", "accept": true, - "reason": "Both describe the same SigLIP2 model producing wrong/degenerate outputs for the same checkpoint, so they look like duplicate reports of one regression." + "reason": "Both describe the same SigLIP2 model producing wrong/degenerate outputs; the later issue is a broader symptom report." }, { "left": "issue:43632", "right": "issue:45834", "accept": false, - "reason": "_is_hf_initialized regression and Kosmos2.5 long-OCR index error are unrelated." + "reason": "_is_hf_initialized regression and Kosmos2.5 OCR index error are unrelated." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Different symptoms and models: video StopIteration versus mask-shape IndexError." + "reason": "These are different runtime errors with no shared concrete code path." }, { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Both mention config validation, but they affect different models and don\u2019t clearly point to one concrete duplicate bug." + "reason": "Strict config validation for granite_speech and tiny-random glm4v config loading are different problems." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "Zero3/Bert index error and TOKENIZER_MAPPING_NAMES add-new-model-like failure are different problems." + "reason": "DeepSpeed ZeRO-3 Bert indexing failure and add-new-model-like tokenizer mapping failure are unrelated." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Bert Zero3 index error is not the same as the tokenizer-mapping registration issue." + "reason": "Zero3/BertModel indexing failure is not the same bug as tokenizer mapping registration." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer mapping registration and tensor mask shape mismatch are unrelated." + "reason": "Tokenizer mapping registration and mask-shape mismatch are different bugs." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "Device-map offload load failure is not the same as Strix Halo mmap OOM." + "reason": "gpu+cpu offload loading failure and mmap OOM on Strix Halo are memory-related but not the same defect." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "These are the same non-persistent-buffer corruption regression, phrased with slightly different titles." + "reason": "These are the same v5 non-persistent-buffer corruption regression, just worded slightly differently." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "The SigLIP2 bad-output bug is different from the documentation-example mismatch/quantization failure report." + "reason": "Both mention SigLIP2, but one is wrong outputs and the other is documentation/example errors with model/processor mismatch." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "GLM5 and Qwen3.5 flash-attention issues are separate model-specific bugs." + "reason": "GLM5 and Qwen3.5 flash-attention failures are model-specific and different." }, { - "left": "issue:45488", - "right": "issue:45812", + "left": "issue:42491", + "right": "issue:43720", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different tokenization code paths and different model families." + "reason": "Qwen3_moe LoRA compatibility and BitNet packed-weight unpacking are separate accelerate-loading problems." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "ZeRO-3 loading of language_model weights and incorrect visual encoder save_pretrained keys are different bugs." + "reason": "ZeRO-3 weight loading for language_model and save_pretrained visual-key regression are unrelated." }, { - "left": "issue:42491", - "right": "issue:43720", + "left": "issue:45488", + "right": "issue:45812", "accept": false, - "reason": "Qwen3MoE LoRA incompatibility and BitNet packed-weight loading are different model-loading issues." + "reason": "Tokenizer pre-tokenizer override bug and Granite token-ID regression are different tokenizer issues." }, { "left": "issue:44451", "right": "issue:44488", - "accept": true, - "reason": "Both report the same model-loading regression for closely related BERT checkpoints, with the same failure mode after the version change." + "accept": false, + "reason": "They are similar Scandinavian BERT load failures, but not clearly the same underlying bug from the available evidence." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Auto device-mapping CUDA assert and Qwen3MoE FP8 failure are distinct issues." - }, - { - "left": "issue:43854", - "right": "issue:43931", - "accept": false, - "reason": "GLM-4.7-Flash test loading failure and Qwen3-VL weight-shape mismatch are unrelated." + "reason": "Qwen3 device-mapping assert and Qwen3Moe FP8 failure are distinct regressions." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Trainer resume max_steps calculation and SGD args not being used are unrelated trainer/optimizer bugs." + "reason": "Checkpoint max_steps recalculation and SGD args being ignored are unrelated trainer/optimizer bugs." }, { - "left": "issue:42491", - "right": "issue:45276", + "left": "issue:43854", + "right": "issue:43931", "accept": false, - "reason": "Qwen3MoE LoRA loading and Gemma4 embedding resize behavior are unrelated." + "reason": "GLM-4.7-Flash test loading failure and Qwen3-VL weight-shape mismatch are different model-loading issues." }, { - "left": "issue:43257", - "right": "issue:43854", + "left": "issue:42491", + "right": "issue:45276", "accept": false, - "reason": "Qwen3 MOE weight conversion during accelerate+deepspeed loading is different from the GLM-4.7-Flash unit-test load failure." + "reason": "Qwen3_moe LoRA compatibility and Gemma4 resize_token_embeddings behavior are unrelated." }, { "left": "issue:42915", "right": "issue:44756", "accept": false, - "reason": "Qwen3MoE FP8 failure and Strix Halo mmap OOM are unrelated." + "reason": "Qwen3Moe FP8 and Strix Halo mmap OOM are different problems." }, { - "left": "issue:39692", - "right": "issue:43994", + "left": "issue:43257", + "right": "issue:43854", "accept": false, - "reason": "The documentation-example bug is not the same as the SigLIP2 bad-output regression." + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed and GLM-4.7-Flash loading are unrelated." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Qwen3MoE HF4\u2192HF5 LoRA incompatibility and Qwen3-VL weight-shape mismatch are different model-loading failures." + "reason": "LoRA compatibility regression and Qwen3-VL weight mismatch are different bugs." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "SigLIP2 documentation example issues and wrong inference outputs are related only by model family, not clearly the same bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet and stays mostly conservative. The duplicate subclusters called out are supported by the titles and similarity scores, and the conservative false verdicts look reasonable. The accepted soft edges are not obviously overstated from the available evidence." + "feedback": "The clustering is conservative and well grounded in the packet. The three accepted soft pairs are reasonably supported by the titles and descriptions: non-persistent buffer junk (43644/44534), custom model initialization / notebook variant (43645/43646), and SigLIP2 wrong outputs (38175/43994). The rejected pairs are mostly framed cautiously as related but not clearly the same bug, which matches the available evidence. One small note: phrases like \"root-cause report\" for issue 43950 are a bit stronger than the packet alone proves, but not enough to invalidate the overall summary." }, "evaluator_used": true, "retried": false, @@ -2000,7 +1988,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36010", "issue:39404", @@ -2065,8 +2053,8 @@ "issue:44164|issue:44291", "issue:41720|issue:44155", "issue:44402|issue:44488", - "issue:39692|issue:44960", "issue:43425|issue:43957", + "issue:39692|issue:44960", "issue:42947|issue:45704", "issue:43873|issue:44387", "issue:43335|issue:45663", @@ -2080,255 +2068,252 @@ "issue:42947|issue:43381", "issue:43957|issue:44756", "issue:44743|issue:44960", - "issue:45684|issue:45698", "issue:45276|issue:45292", + "issue:45684|issue:45698", "issue:43381|issue:44928", "issue:45663|issue:45902", "issue:44164|issue:44756", "issue:43646|issue:43708" ], - "prepared_review_unit_hash": "69de8c5be2e0044beb14a0e30a85500ac350ff5636a03cfdb41f13f70730a7dc", + "prepared_review_unit_hash": "bf184a20eebd6e98d2902e7bbadfe4aad681027a72fadfad4ea0782907f8a7d4", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 38087, - "estimated_input_tokens": 9522, - "estimated_eval_tokens": 19300 + "serialized_chars": 38089, + "estimated_input_tokens": 9523, + "estimated_eval_tokens": 19302 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most items are unrelated bug reports across different models/features. The only clear duplicate cluster is the `resize_token_embeddings` regression affecting model-specific embeddings/output embeddings (Gemma4, T5Gemma, and the generic report).", - "confidence": 0.84, - "canonical_issue_reason": "issue:45292 is the most general formulation of the `resize_token_embeddings` bug and cleanly subsumes the Gemma4/T5Gemma variants.", + "summary": "The cluster is mostly a collection of distinct Transformers regressions that only share broad themes like loading, quantization, checkpointing, or embedding resize behavior. I did not find a true duplicate pair with enough evidence to merge.", + "confidence": 0.66, + "canonical_issue_reason": "No item is a clear duplicate hub; issue 45292 is the broadest, least model-specific resize_token_embeddings regression, so it is the best representative.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45292 is the strongest canonical representative because it describes the shared model-agnostic failure mode rather than a single architecture-specific instance.", + "best_issue_reason": "45292 is the most generic and reusable bug report in the set, making it the least arbitrary representative for the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Different problems: MoE training memory usage vs quantization/offloading behavior." + "reason": "Both mention memory/quantization, but one is Qwen3 MoE training inefficiency and the other is offloading failure; different bugs." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading failures, but they involve different models and likely different root causes." + "reason": "Both are tokenizer/model loading regressions, but for different models and different failure modes." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "Unrelated regressions: junk non-persistent buffers vs custom model initialization in notebooks." + "reason": "Shared Transformers 5.0 context, but one is non-persistent buffers and the other is Jupyter custom-model init; not the same bug." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Different model/runtime failures: Qwen chat crash vs Gemma4Processor missing `_tokenizer` in serve." + "reason": "Different models and different code paths: Qwen chat crash vs Gemma4Processor missing _tokenizer." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Different quantization-related symptoms and code paths; one is training memory use, the other int4 OOM." + "reason": "Both are memory-related, but one is training inefficiency and the other is int4 reserved-memory OOM; not the same underlying issue." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Different flash-attention bugs with different triggering conditions and failure modes." + "reason": "Both involve flash attention, but one is Qwen3.5 packed-sequence misparse and the other is s_aux=None AttributeError." }, { "left": "issue:42491", "right": "issue:45292", "accept": false, - "reason": "LoRA checkpoint compatibility is not the same bug as `resize_token_embeddings` not updating outputs." + "reason": "LoRA/qwen3_moe version-compatibility issue vs generic resize_token_embeddings propagation bug; unrelated root causes." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "ImportError for `GenerationMixin` is unrelated to Whisper pipeline `return_language` behavior." + "reason": "Import error for GenerationMixin vs Whisper pipeline return_language regression; different artifacts and failures." }, { "left": "issue:45276", "right": "issue:45335", - "accept": true, - "reason": "Both report the same `resize_token_embeddings` propagation bug affecting model-specific input/output embeddings; one fix could plausibly cover both." + "accept": false, + "reason": "Both are resize_token_embeddings bugs, but they affect different model families and different submodules." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Similar symptom (`lm_head` not tied) but different model classes and not clearly the same code-path bug." + "reason": "Both concern untied lm_head weights, but in different models and likely different tie-weight paths." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Different serialization/loading failures: `extra_state` handling vs unexpected `_is_hf_initialized` argument." + "reason": "save/from_pretrained extra_state handling vs init_empty_weights argument mismatch; different loading mechanisms." }, { "left": "issue:41720", "right": "issue:44155", "accept": false, - "reason": "Unrelated: device-map CUDA assert vs batched inference token/embedding leak." + "reason": "Qwen3 device-mapping crash vs AudioFlamingo3 batch contamination; no shared underlying bug." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Both concern tokenizer vocab issues, but they are different models and different failure mechanisms." + "reason": "Both tokenizer-related, but one is vocab-size inconsistency and the other is model loading failure." }, { - "left": "issue:39692", - "right": "issue:44960", + "left": "issue:43425", + "right": "issue:43957", "accept": false, - "reason": "Doc-example errors are not the same as the GLM5 model-loading issue." + "reason": "Torch 2.10 compatibility vs meta-device loading regression; different incompatibilities." }, { - "left": "issue:43425", - "right": "issue:43957", + "left": "issue:39692", + "right": "issue:44960", "accept": false, - "reason": "Torch version incompatibility is distinct from meta-device loading bugs." + "reason": "Documentation example errors vs a generic GLM5 issue; no same code-path bug." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Different subsystems: PEFT gradient checkpointing vs T5/apex RMSNorm memory leak." + "reason": "Gradient checkpointing/PEFT issue vs T5 apex RMSNorm leak; unrelated." }, { "left": "issue:43873", "right": "issue:44387", "accept": false, - "reason": "Both relate to quantization, but one is offloading not working and the other is reserved-memory/OOM behavior." + "reason": "Both mention quantization and memory, but one is offloading behavior and the other is OOM from reserved memory." }, { "left": "issue:43335", "right": "issue:45663", "accept": false, - "reason": "Different model families and failure modes; sparse-layer construction is unrelated to Gemma4 FSDP2 shared KV state." + "reason": "SwitchTransformers sparse-layer config bug vs Gemma4 FSDP2 shared_kv_states error; different systems." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "FSDP2 attention state bug is unrelated to composite config unwrapping in `from_config`." + "reason": "Gemma4 FSDP2 KeyError vs Qwen multimodal from_config text_config unwrapping; unrelated." }, { "left": "issue:45663", "right": "issue:45859", "accept": false, - "reason": "Different code paths: per-layer shared KV reconstruction vs CPU offload incompatibility in rotary embedding." + "reason": "Different Qwen/Gemma code paths; one is FSDP2 state rebuild, the other CPU-offload rotary embedding incompatibility." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "Unexpected init arg during meta loading is unrelated to disabling mmap to avoid OOM." + "reason": "init_empty_weights constructor mismatch vs mmap OOM workaround; not the same bug." }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "Different forward-pass bugs in different models; not the same underlying defect." + "reason": "AudioFlamingo3 track leakage vs Gemma4 device mismatch under auto device_map; different failures." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "Different memory problems with different causes; not a duplicate." + "reason": "Both are memory/OOM reports, but one is quantization-related reserved memory and the other is Strix Halo mmap behavior." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Different model-loading regressions affecting different models and APIs." + "reason": "Model load failure in unit tests vs save_pretrained checkpoint regression; different directions of the pipeline." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Both involve quantization formats, but the models and failure modes differ." + "reason": "Different quantized models and different symptoms: load error vs bf16 fallback." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Gradient checkpointing in PEFT is not the same as gradient checkpointing being disallowed in eval mode." + "reason": "Gradient checkpointing in PEFT vs gradient checkpointing in eval mode; distinct conditions and fixes." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "Meta-device loading bugs are unrelated to mmap/OOM issues." + "reason": "meta-device loading regression vs mmap/OOM workaround; different code paths." }, { "left": "issue:44743", "right": "issue:44960", "accept": false, - "reason": "Recurrent-state reset in Qwen3.5 code is unrelated to the GLM5 issue." + "reason": "Qwen3_5 recurrent-state reset bug vs generic GLM5 issue; not the same bug." }, { - "left": "issue:45684", - "right": "issue:45698", + "left": "issue:45276", + "right": "issue:45292", "accept": false, - "reason": "Save permissions propagation and wrong-module loading are different save/load bugs." + "reason": "Same general resize_token_embeddings theme, but the affected submodules and model scope differ enough that this is not a confirmed duplicate." }, { - "left": "issue:45276", - "right": "issue:45292", - "accept": true, - "reason": "45292 is the generic version of the same `resize_token_embeddings` bug; 45276 is a model-specific manifestation." + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load custom models, but one is permissions propagation and the other is wrong module loading." }, { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Eval-mode checkpointing restriction is unrelated to Qwen3.5 SDPA/math-fallback gradient explosion." + "reason": "Checkpointing eval-mode issue vs RLHF NaN from 3D position_ids and SDPA fallback; unrelated." }, { "left": "issue:45663", "right": "issue:45902", "accept": false, - "reason": "Shared-KV-state rebuild bug is not the same as uninitialized `inv_freq` after `to_empty(cuda)`." + "reason": "Gemma4 FSDP2 state bug vs Qwen3_5Moe rotary embedding uninitialized-memory bug; different code paths." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "Custom `extra_state` serialization and Strix Halo mmap/OOM are unrelated." + "reason": "save/from_pretrained extra_state issue vs Strix Halo mmap OOM; not the same underlying defect." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom-model initialization failures are unrelated to Trainer `resume_from_checkpoint` step \u0570\u0561\u0577\u057eculation." + "reason": "Custom model init regression vs Trainer resume_from_checkpoint max_steps miscalculation; unrelated." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative on the soft edges. The `resize_token_embeddings` cluster (45276/45335/45292) is a plausible single bugfix/PR group, and the other pair verdicts do not overclaim duplicate status based on titles alone." - }, - "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 }, @@ -2343,7 +2328,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36032", "issue:39404", @@ -2398,13 +2383,13 @@ "issue:44479|issue:44877", "issue:45588|issue:45663", "issue:45292|issue:45335", - "issue:43257|issue:44863", "issue:43645|issue:44164", + "issue:43257|issue:44863", "issue:44402|issue:44451", "issue:43828|issue:43957", "issue:43425|issue:43828", - "issue:39404|issue:45701", "issue:44589|issue:44756", + "issue:39404|issue:45701", "issue:44683|issue:45823", "issue:43931|issue:44863", "issue:43906|issue:44530", @@ -2416,27 +2401,27 @@ "issue:39404|issue:44912", "issue:44265|issue:44898", "issue:43299|issue:43931", - "issue:43994|issue:44079", "issue:44479|issue:44805", - "issue:39404|issue:44671", + "issue:43994|issue:44079", "issue:45005|issue:45902", + "issue:39404|issue:44671", "issue:44589|issue:45084", "issue:40990|issue:42947", - "issue:44671|issue:44991", "issue:43425|issue:44918", - "issue:36032|issue:43452", + "issue:44671|issue:44991", "issue:44164|issue:45759", "issue:43596|issue:44683", + "issue:36032|issue:43452", "issue:43856|issue:44756" ], - "prepared_review_unit_hash": "0b8f6d645ec7db48ca073804cd7ed9b4d9d95684d42421c75475b86e5318b7e2", + "prepared_review_unit_hash": "f0f5c5b12c71ece7d9c1c71e3e52b7af2a6b7a8a0d09e3912a79fc1b59575646", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, @@ -2451,216 +2436,216 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: many separate loading/runtime regressions that only share broad Transformers-v5 similarity. I\u2019d keep most items separate; the only clear duplicate-like pair is the resize_token_embeddings regression on output/decoder embeddings.", - "confidence": 0.76, - "canonical_issue_reason": "Issue 43611 is the broadest representative of the mixed set because it targets a concrete Transformers 5.0 model-loading regression. That said, the cluster is too diverse for a strong true canonical duplicate.", + "summary": "This cluster is mostly heterogeneous. The only clear duplicate-like pair is the resize_token_embeddings bug, where one report is the generic form and the other is a t5gemma-specific instance.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 45292 is the broader, more canonical report; 45335 is a model-specific manifestation of the same resize_token_embeddings not propagating to output/decoder embeddings.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43611 is the best umbrella issue for the cluster\u2019s dominant theme of v5 loading breakage, but it should be treated as a loose representative rather than a true duplicate anchor.", + "best_issue_reason": "Issue 45292 best represents the duplicate pair because it states the underlying bug more generally and is likely the better anchor for triage.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Both are v5-era loading regressions, but one is a video-input regression and the other is strict config loading; different code paths and fixes." + "reason": "Different failures: video-input regression in Qwen VL models vs strict config blocking granite_speech loading." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "Both mention attention/forward crashes, but the bugs are unrelated: sink-less flash attention vs Gemma4 FSDP2 shared_kv_states rebuilding." + "reason": "Unrelated code paths: flash_attention s_aux handling vs Gemma4 FSDP2 shared_kv_states reconstruction." }, { "left": "issue:45292", "right": "issue:45335", "accept": true, - "reason": "Same underlying bug: resize_token_embeddings does not propagate resized weights to downstream embedding modules. One report is generic, the other is the T5Gemma decoder.embed_tokens case." + "reason": "Same underlying bug: resize_token_embeddings not updating downstream embeddings; 45335 is the t5gemma-specific instance." }, { - "left": "issue:43257", - "right": "issue:44863", + "left": "issue:43645", + "right": "issue:44164", "accept": false, - "reason": "Both are model-loading failures, but for different architectures and failure modes: Qwen3 MoE conversion under accelerate/deepspeed vs NemotronH checkpoint compatibility." + "reason": "Custom-model initialization in notebooks is not the same as save/from_pretrained handling extra_state." }, { - "left": "issue:43645", - "right": "issue:44164", + "left": "issue:43257", + "right": "issue:44863", "accept": false, - "reason": "One is custom model initialization in notebooks, the other is save/from_pretrained handling of extra_state; related only at a very high level." + "reason": "Both are loading issues, but for different architectures and different root causes." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "Both are tokenizer-loading complaints, but they point to different models and likely different causes; not the same concrete defect." + "reason": "Both involve tokenizer/model loading, but the titles point to different models and no shared concrete bug." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Both are dtype/device-related regressions, but one is autocast mismatch in Phi MoE and the other is meta-device loading breakage across some models." + "reason": "Different mismatch scenarios: autocast dtype error vs meta-device loading failure." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch-version incompatibility is a dependency compatibility issue, not the same bug as the Phi autocast dtype mismatch." + "reason": "Torch version compatibility is too broad to equate with a specific autocast dtype mismatch bug." }, { - "left": "issue:39404", - "right": "issue:45701", + "left": "issue:44589", + "right": "issue:44756", "accept": false, - "reason": "Whisper return_language pipeline behavior and tokenization changes across versions are unrelated failures." + "reason": "Float8 storage lookup failure is unrelated to disabling mmap for OOM on Strix Halo." }, { - "left": "issue:44589", - "right": "issue:44756", + "left": "issue:39404", + "right": "issue:45701", "accept": false, - "reason": "Float8 storage lookup failure and mmap OOM on Strix Halo are separate environment/runtime issues." + "reason": "Whisper pipeline return_language regression is not the same as a general tokenization change report." }, { "left": "issue:44683", "right": "issue:45823", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 PLE device mismatch are different failures in different subsystems." + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device_map mismatch are different problems." }, { "left": "issue:43931", "right": "issue:44863", "accept": false, - "reason": "Both are load-time shape/compatibility errors, but they involve different model families and distinct checkpoint conversion logic." + "reason": "Qwen3-VL shape mismatch and NemotronH checkpoint-loading failure are distinct model-loading bugs." }, { "left": "issue:43906", "right": "issue:44530", "accept": false, - "reason": "An isolated reproduction of an older issue is not the same bug as the Qwen3.5 PagedAttentionCache linear_attention crash." + "reason": "The isolated reproduction of another issue is not the same as the Qwen3.5 PagedAttentionCache crash." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Both are v5 model-loading regressions, but one is about base_model_prefix handling and the other is about defining custom models in notebooks." + "reason": "base_model_prefix loading regression and notebook-defined custom model initialization are separate failures." }, { "left": "issue:43425", "right": "issue:45823", "accept": false, - "reason": "Generic torch incompatibility is not the same concrete defect as the Gemma4 PLE forward device mismatch." + "reason": "Torch 2.10 incompatibility is too broad and not the same as Gemma4 PLE device mismatch." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "PagedAttentionCache invalid group type and non-template-node compile errors are unrelated implementation problems." + "reason": "PagedAttentionCache linear_attention crash is unrelated to a compiler/template-node TypeError." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch version compatibility and image preprocessor/model dtype mismatch are different issues." + "reason": "Torch version incompatibility is not the same as a Mistral-3 image preprocessor dtype mismatch." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "Both are docs-related, but one is stale return_all_scores wording and the other is removed pipeline task documentation; not the same change." + "reason": "Both are docs-related, but one is about return_all_scores and the other about removed pipeline tasks." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline return_language and MXFP4 quantization fallback are unrelated regressions." + "reason": "Whisper pipeline language return regression and MXFP4 fallback behavior are different issues." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "torch.export with torch_compilable_check and Perceiver interpolation failure are different model/export bugs." + "reason": "torch.export failures with torch_compilable_check are unrelated to Perceiver non-default resolution handling." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "Both are Qwen3-VL loading problems, but one is a v5 breakage for Qwen3VL MoE models and the other is a specific weight-shape mismatch on a different checkpoint." - }, - { - "left": "issue:43994", - "right": "issue:44079", - "accept": false, - "reason": "SigLIP2 bad outputs and ModelOutput key assignment with None are unrelated bugs." + "reason": "Both concern Qwen3-VL models, but one is a v5 regression and the other is a checkpoint shape mismatch." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "A video-input regression and a mask/tensor shape mismatch are different runtime failures." + "reason": "Video-input regression and mask/index shape mismatch are different concrete failures." }, { - "left": "issue:39404", - "right": "issue:44671", + "left": "issue:43994", + "right": "issue:44079", "accept": false, - "reason": "Whisper pipeline behavior and CamemBERT masked LM prediction errors are unrelated model-specific issues." + "reason": "Incorrect SigLIP2 outputs and ModelOutput key assignment are separate bugs." }, { "left": "issue:45005", "right": "issue:45902", "accept": false, - "reason": "Tied-weights translation-model regressions and Qwen3_5Moe rotary embedding uninitialized memory are distinct bugs." + "reason": "Tied-weights loading and uninitialized-memory after to_empty are different model/materialization problems." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline behavior and CamemBERT masked LM predictions are unrelated." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "Float8 storage resolution and compile-node type errors do not share the same code path." + "reason": "Missing Float8 storage and non-template-node compilation errors do not share the same root cause." }, { "left": "issue:40990", "right": "issue:42947", "accept": false, - "reason": "High perplexity on gpt-oss and ineffective gradient checkpointing with LoRA are unrelated training/evaluation issues." - }, - { - "left": "issue:44671", - "right": "issue:44991", - "accept": false, - "reason": "CamemBERT prediction regression and EMBEDDIA/est-roberta tokenizer loading failure are different defects." + "reason": "High perplexity on gpt-oss-20b is not the same as gradient checkpointing being ineffective with LoRA." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch 2.10 incompatibility is not the same bug as Qwen3.5 input-embedding unpacking with trl SFTTrainer." + "reason": "General Torch incompatibility does not match the Qwen3.5 SFT unpacking failure." }, { - "left": "issue:36032", - "right": "issue:43452", + "left": "issue:44671", + "right": "issue:44991", "accept": false, - "reason": "T5Tokenizer add_special_tokens conflict and gguf_file breakage in from_pretrained are separate tokenizer/loading failures." + "reason": "CamemBERT prediction quality and tokenizer loading for est-roberta are different problems." }, { "left": "issue:44164", "right": "issue:45759", "accept": false, - "reason": "extra_state serialization and AutoModelForCausalLM.from_config text_config unwrapping are different save/load code paths." + "reason": "extra_state save/load handling is unrelated to from_config not unwrapping text_config." }, { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "deepspeed zero3 init IndexError and compiled flex_attention on torch>=2.9 are unrelated failures." + "reason": "Zero3/BertModel index error is unrelated to flex_attention compilation on newer torch." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5Tokenizer special-method conflict and gguf_file loading breaks are different tokenizer/model-loading bugs." }, { "left": "issue:43856", "right": "issue:44756", "accept": false, - "reason": "Qwen3 MoE memory usage and Strix Halo mmap OOM are both memory-related but not the same underlying bug." + "reason": "Qwen3 MoE training memory usage and disabling mmap for Strix Halo OOM are not the same bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analysis is grounded in the packet and stays conservative overall. The cluster is correctly characterized as mostly heterogeneous, and the one accepted soft pair (45292/45335) is the only clearly close duplicate-like match. The umbrella/canonical issue choice is framed as loose rather than overclaimed, which fits the evidence." + "feedback": "The assessment is grounded in the packet and stays conservative. The only accepted pair, issue:45292 and issue:45335, is plausibly the same resize_token_embeddings bug affecting different downstream embeddings, and the rest of the pairwise rejections do not overclaim shared root causes." }, "evaluator_used": true, "retried": false, @@ -2679,7 +2664,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:32090", "issue:34567", @@ -2741,8 +2726,8 @@ "issue:40990|issue:43421", "issue:43611|issue:43644", "issue:44488|issue:44987", - "issue:44206|issue:44220", "issue:43716|issue:45084", + "issue:44206|issue:44220", "issue:43643|issue:44530", "issue:43883|issue:44488", "issue:34567|issue:40444", @@ -2765,239 +2750,242 @@ "issue:43994|issue:44610", "issue:43645|issue:44534" ], - "prepared_review_unit_hash": "0326538829eb3793ad1e623cf48e91585bbe2ae57a3453891e5c1185c08fbc8c", + "prepared_review_unit_hash": "18f68080e309d48de7e48a3db55d59750bedacef0acd21018dd589c70fea169f", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37696, - "estimated_input_tokens": 9424, - "estimated_eval_tokens": 19104 + "serialized_chars": 37700, + "estimated_input_tokens": 9425, + "estimated_eval_tokens": 19106 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose collection of mostly unrelated Transformers issues. The soft-edge pairs are all different concrete bugs/regressions, so none should be merged as duplicates.", - "confidence": 0.87, - "canonical_issue_reason": "If a single issue must represent the cluster, issue #43646 is the broadest umbrella: it is a general Transformers v5 custom-model initialization regression, while the others are narrower, unrelated failures.", + "summary": "A heterogeneous set of issues with a few topical clusters; the strongest duplicate-like pairings are around custom-model initialization in v5 and GGUF loading regressions. Most other items appear to be distinct bugs in different models or code paths.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 43646 is the best canonical issue because it uses the broadest framing of the v5 custom-model initialization regression, which cleanly covers the paired buffer-junk report.", "canonical_pr_reason": null, - "best_issue_reason": "#43646 is the best single issue to anchor triage because it is the most general and representative of the v5 custom-model initialization breakage family in this set.", + "best_issue_reason": "Issue 43646 is the best representative overall because it captures the broad custom-model initialization regression, making it a good umbrella for the closest duplicate-like subcluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:32090", "right": "issue:39404", "accept": false, - "reason": "Different bugs: Trainer GPU broadcast NoneType error vs Whisper return_language pipeline regression." + "reason": "Different subsystems and failures: Trainer GPU broadcast NoneType error vs Whisper pipeline return_language behavior." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Different load paths and failures: est-roberta tokenizer load vs Mistral regex patch backend_tokenizer crash." + "reason": "Both are tokenizer-loading problems, but they involve different models and different failure modes." }, { "left": "issue:44737", "right": "issue:45859", "accept": false, - "reason": "Different code paths: XLNet relative position arange device bug vs Qwen3.5Moe CPU-offload embedding issue." + "reason": "Both mention offload/device behavior, but they are different models and distinct code paths." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "Unrelated problems: save/from_pretrained extra_state handling vs Qwen video-input regression." + "reason": "Unrelated regressions: save/from_pretrained extra_state handling vs video-input processing for Qwen VL models." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Different regressions: Apple Silicon caching_allocator_warmup TypeError vs _is_hf_initialized flag breakage." + "reason": "Different regressions: Apple Silicon allocator warmup TypeError vs _is_hf_initialized flag breakage." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Different model/loading failures: cjvt/sleng-bert load issue vs Mistral tokenizer regex patch crash." + "reason": "Shared Mistral/tokenizer theme is too broad; the concrete failure modes differ." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "Different subsystems: TOKENIZER_MAPPING_NAMES add-new-model-like failure vs compiled flex_attention on torch>=2.9." + "reason": "Unrelated areas: tokenizer mapping handling vs compiled flex_attention on torch >= 2.9." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "Different symptoms: perplexity regression on gpt-oss-20b vs runtime special-token post-processor update bug." + "reason": "Perplexity/LM evaluation problem vs tokenizer post-processor update bug; no shared code path." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer serialization; not the same bug." + "reason": "Both are v5 regressions, but they describe different concrete bugs." }, { "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Different model-specific load failures for different repositories." + "reason": "Both are model-loading failures, but they concern different models and likely different loader regressions." }, { - "left": "issue:44206", - "right": "issue:44220", + "left": "issue:43716", + "right": "issue:45084", "accept": false, - "reason": "Related audio area, but titles point to different failures: unsupported center arg vs _torch_extract_fbank_features issue." + "reason": "Different bugs: image preprocessor/model dtype mismatch vs template-node compilation error." }, { - "left": "issue:43716", - "right": "issue:45084", + "left": "issue:44206", + "right": "issue:44220", "accept": false, - "reason": "Different problems: image preprocessor/model dtype mismatch vs template compilation TypeError." + "reason": "Both touch audio feature extraction, but the titles indicate different failure points." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "Different issues: missing fields with trust_remote_code AutoConfig vs Qwen3.5 PagedAttentionCache linear_attention crash." + "reason": "Different behaviors: AutoConfig trust_remote_code field loss vs PagedAttentionCache linear_attention crash." }, { "left": "issue:43883", "right": "issue:44488", "accept": false, - "reason": "Different failures: missing all_tied_weights_keys on Molmo vs loading cjvt/sleng-bert." + "reason": "Different problems: missing all_tied_weights_keys on a model class vs a specific tokenizer/model loading failure." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "Different training issues: TrainerState token counter not updating vs Qwen2.5-VL iterable dataset multi-image finetuning failure." + "reason": "TrainerState token counting vs multi-image IterableDataset finetuning failure are unrelated." }, { "left": "issue:36032", "right": "issue:42915", "accept": false, - "reason": "Different model/config bugs: T5 tokenizer special-token conflict vs Qwen3Moe FineGrainedFP8Config failure." + "reason": "Tokenizer special-token conflict vs FineGrainedFP8Config failure on Qwen3Moe; different code paths." }, { "left": "issue:44811", "right": "issue:45584", "accept": false, - "reason": "Both Whisper-related, but one is batch_decode skip_special_tokens handling and the other is empty-transcription generation after align_special_tokens." + "reason": "Both Whisper-related, but batch_decode skip_special_tokens and empty-transcription after align_special_tokens are distinct symptoms." }, { "left": "issue:43644", "right": "issue:43646", - "accept": false, - "reason": "Both are v5 initialization regressions, but one is non-persistent buffer junk and the other is custom model initialization breaking; not the same defect." + "accept": true, + "reason": "These look like the same v5 custom-model initialization regression: 43644 is a specific symptom, while 43646 is the broader failure report." }, { "left": "issue:43541", "right": "issue:45084", "accept": false, - "reason": "Different runtime errors: Mixtral grouped_mm tracing failure vs non-template node compilation TypeError." + "reason": "Different failures in different paths: torch dynamo grouped_mm tracing vs template-node compilation." }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Different model load regressions for different checkpoints." + "reason": "Separate model-loading failures for different checkpoints." }, { "left": "issue:43452", "right": "issue:43482", - "accept": false, - "reason": "Different gguf-related failures: gguf_file compatibility vs Qwen2.5-GGUF loading on v5." + "accept": true, + "reason": "Both point to the same GGUF/from_pretrained loader regression; 43482 is a specific instance of the broader 43452 bug." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "Different bugs: Qwen3Moe FineGrainedFP8Config failure vs Qwen3.5 paged attention linear_attention crash." + "reason": "Qwen3Moe FP8 config failure vs Qwen3.5 paged-attention cache crash; not the same bug." }, { "left": "issue:44849", "right": "issue:45325", "accept": false, - "reason": "Different Qwen3.5 regressions: hidden_states output issue vs still-image rope_index scaling bug." + "reason": "Different Qwen-family issues: output_hidden_states bug vs rope index scaling bug in multimodal video handling." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "Different issues: device_map=auto dequantized offload failure vs Qwen2.5-GGUF load failure." + "reason": "Different loading contexts: device_map/offload dequantized model load vs GGUF model load failure." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Different regressions: tokenizer add_special_tokens conflict vs Jupyter custom model initialization breakage." + "reason": "Tokenizer special-token conflict vs Jupyter/custom model initialization regression; distinct issues." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Different model-specific load failures for different repositories." + "reason": "Both are version-related loading failures, but they affect different models and likely different tokenizer/model code paths." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Related to tied weights, but one is Mistral3 lm_head tying and the other is device-dependent serialization; not the same bug." + "reason": "Both involve lm_head/tied weights, but one is a missing tie in a specific model class and the other is device-dependent serialization." }, { "left": "issue:45084", "right": "issue:45507", "accept": false, - "reason": "Different failures: template compilation TypeError vs GraniteMoEHybrid invalid method call." + "reason": "Different failures: template compilation error vs GraniteMoEHybrid invalid method call." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "Different issues: Molmo tied-weights attribute error vs est-roberta tokenizer load failure." + "reason": "Unrelated: missing tied-weights metadata vs tokenizer loading regression for a specific model." }, { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Different audio/multimodal bugs: apply_chat_template sample-rate default vs MIMI encoder padding-mask inconsistency." + "reason": "Audio sampling-rate defaulting in apply_chat_template is unrelated to MIMI encoder batch-vs-single behavior." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Different symptoms in v5: custom model initialization breakage vs non-persistent buffer junk." + "reason": "Different v5 regressions: custom model initialization vs non-persistent buffer junk." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "Different model/processor mismatches: SigLIP2 nonsensical outputs vs OmDet-Turbo 640px vs 224px processor mismatch." + "reason": "Different vision/processor issues for different models with different expected input sizes and failure modes." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Different regressions: Jupyter custom model initialization vs non-persistent buffer junk in v5." + "reason": "Notebook/custom-model initialization bug vs non-persistent buffer junk regression; related theme, but not the same concrete issue." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, + "evaluator_result": { + "accept": false, + "feedback": "The pair judgments are conservative and the two accepted pairs are plausible, but the summary is slightly overconfident/inaccurate: the packet includes open issues as well, so describing the set as \u201cclosed transformer issues\u201d is not fully grounded. Please keep the top-level characterization at the level of \u201ca heterogeneous set of issues\u201d rather than asserting state." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -3012,7 +3000,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36032", "issue:40444", @@ -3069,14 +3057,14 @@ "issue:43377|issue:43819", "issue:42915|issue:45084", "issue:44451|issue:45081", - "issue:45216|issue:45357", "issue:44265|issue:44610", - "issue:44987|issue:45081", + "issue:45216|issue:45357", "issue:44220|issue:44683", + "issue:44987|issue:45081", "issue:43404|issue:45127", "issue:42915|issue:44291", - "issue:44062|issue:44987", "issue:43632|issue:44756", + "issue:44062|issue:44987", "issue:36032|issue:43742", "issue:43296|issue:43531", "issue:44479|issue:45325", @@ -3084,234 +3072,234 @@ "issue:43611|issue:44534", "issue:40444|issue:45325", "issue:43531|issue:44877", - "issue:36032|issue:41720", "issue:40990|issue:44811", + "issue:36032|issue:41720", "issue:43425|issue:44403", "issue:44079|issue:45663", "issue:43632|issue:44534", "issue:42175|issue:45542", + "issue:41553|issue:43582", "issue:44462|issue:45812", "issue:43421|issue:44568", - "issue:41553|issue:43582", "issue:43818|issue:45357" ], - "prepared_review_unit_hash": "2ca3ce531684128684cc577d6894a3cb0e17ce9c8ea0e5e8074fd79770e4981b", + "prepared_review_unit_hash": "761cf492ae8a443344de482b6b650ee59cadb82377cc12b6ab1dfcbec58281ef", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36711, - "estimated_input_tokens": 9178, - "estimated_eval_tokens": 18612 + "serialized_chars": 36715, + "estimated_input_tokens": 9179, + "estimated_eval_tokens": 18614 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of transformer regressions, with a small tokenizer/save_pretrained subcluster. I only found two clear duplicate pairs; most other soft matches are related by theme but not the same underlying bug.", - "confidence": 0.59, - "canonical_issue_reason": "45812 is the best anchor: it is a concrete, high-impact AutoTokenizer v4\u2192v5 regression with silent wrong token IDs, which is the strongest representative of the tokenizer-loading subset.", + "summary": "Mostly a mixed cluster of Transformers tokenizer/loading and model-regression reports, with a few genuine duplicate-like pockets. I kept the stronger same-path pairs (Qwen3.5 save_pretrained, Qwen2.5-VL video/position-id, and tokenizer special-token handling) and rejected the weaker AutoTokenizer/Granite link as too speculative.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45812 is still the best single anchor because it is the broadest, active AutoTokenizer regression in the set and has the clearest cluster-wide relevance. That said, not every tokenizer-loading issue here is a duplicate of it, so the linkage should stay conservative.", "canonical_pr_reason": null, - "best_issue_reason": "45812 is the most representative and actionable issue in the set because it describes a broad, user-visible tokenizer regression rather than a niche model-specific failure.", + "best_issue_reason": "issue:45812 is the strongest representative issue overall: broad impact, open regression, and the most central to the tokenizer-loading subcluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Different model families and failure modes: Llava Next load segfault vs Qwen3OmniMoe video-processing ValueError." + "reason": "Different multimodal families and failure modes; only the broad video/image-input area overlaps." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Generic loading-noise report vs a specific Mistral regex patch crash; not the same bug." + "reason": "One is generic loading noise, the other is a specific tokenizer patch crash; no same bug path." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "Different audio/code paths: MIMI padding-mask mismatch vs DAC latent/STE mismatch." + "reason": "Both are audio-related, but batching/padding-mask behavior and DAC latent decoding mismatch are separate bugs." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "FP8 configuration failure and template-node compile error are unrelated." + "reason": "Different runtime failures with no concrete shared code path." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "ScandiBERT load failure vs Mistral tokenizer backend crash; different root causes." + "reason": "Both mention loading, but ScandiBERT loading and Mistral regex patching are different paths." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "Unrelated areas: torch.export support vs an image processor size mismatch." }, { "left": "issue:45216", "right": "issue:45357", "accept": true, - "reason": "Both describe the same Qwen3.5 save_pretrained regression producing incorrect checkpoints; 45357 narrows it to wrong visual-encoder keys." + "reason": "Same Qwen3.5 save_pretrained regression; 45357 looks like a narrower manifestation of the same broken checkpoint-writing path." }, { - "left": "issue:44265", - "right": "issue:44610", + "left": "issue:44220", + "right": "issue:44683", "accept": false, - "reason": "torch.export/torch_compilable_check issue vs processor image-size mismatch; not the same bug." + "reason": "Different features and failure surfaces: fbank extraction vs compiled flex_attention on newer torch." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "Different failures: loading physical-intelligence/fast vs Mistral regex patch crash." - }, - { - "left": "issue:44220", - "right": "issue:44683", - "accept": false, - "reason": "Fbank feature extraction and compiled flex_attention are unrelated code paths." + "reason": "Both are loading regressions, but for different models and different tokenizer/config logic." }, { "left": "issue:43404", "right": "issue:45127", "accept": false, - "reason": "Tied lm_head bug vs LoRA-merge-with-extended-vocab collapse; different mechanisms." + "reason": "Both mention tied weights, but one is a missing tie in model init and the other is LoRA merge behavior with extended vocab." }, { "left": "issue:42915", "right": "issue:44291", "accept": false, - "reason": "Both are version-related, but one is FineGrainedFP8Config and the other is init_empty_weights/_is_hf_initialized; not the same issue." + "reason": "Different bugs: FP8 config handling vs init_empty_weights/_is_hf_initialized argument handling." }, { - "left": "issue:44062", - "right": "issue:44987", + "left": "issue:43632", + "right": "issue:44756", "accept": false, - "reason": "AddedToken keyword conflict vs model-loading regression; different bugs." + "reason": "Unrelated regressions: a Transformers v5 flag issue versus an Apple Silicon mmap/OOM workaround." }, { - "left": "issue:43632", - "right": "issue:44756", + "left": "issue:44062", + "right": "issue:44987", "accept": false, - "reason": "_is_hf_initialized regression vs Strix Halo mmap OOM workaround; unrelated." + "reason": "The AddedToken special-argument error and the physical-intelligence/fast loading failure do not share the same path." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "T5 tokenizer add_special_tokens conflict vs MobileLLM-125M key error; different failures." + "reason": "Both are load-time errors, but the T5 tokenizer method conflict and the MobileLLM key error are unrelated." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window issue are unrelated." + "reason": "Different model families and different failures; no shared concrete bug." }, { "left": "issue:44479", "right": "issue:45325", - "accept": false, - "reason": "Same broad Qwen video/temporal area, but 44479 is a multi-model video-input regression while 45325 is a specific still-image rope-index bug; not clearly one bug." + "accept": true, + "reason": "Both target the same Qwen2.5-VL temporal/video position-id regression; 45325 is a specific manifestation of the broader v5.3.0 video-input breakage." }, { "left": "issue:42915", "right": "issue:44589", "accept": false, - "reason": "FineGrainedFP8Config failure vs missing Float8 storage type; different symptoms and code paths." + "reason": "The config failure and missing storage-type error are distinct issues despite similar float8 terminology." }, { "left": "issue:43611", "right": "issue:44534", "accept": false, - "reason": "base_model_prefix load break vs non-persistent buffer junk; distinct regressions." + "reason": "Different v5 regressions: base_model_prefix loading breakage vs non-persistent buffer initialization junk." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "Multiple-images-per-prompt fine-tuning failure is not the same as the Qwen2.5-VL rope-index scaling bug." + "reason": "Both touch Qwen2.5-VL, but one is dataset/multi-image finetuning and the other is still-image temporal position scaling." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Qwen3-MoE sliding_window issue and granite_speech strict-config loading are unrelated." + "reason": "Separate model/config problems with no shared code path." }, { - "left": "issue:36032", - "right": "issue:41720", + "left": "issue:40990", + "right": "issue:44811", "accept": false, - "reason": "Tokenizer loading conflict vs auto device-mapping CUDA assert; different layers." + "reason": "Perplexity on GPT-OSS and Whisper batch_decode skip_special_tokens are unrelated." }, { - "left": "issue:40990", - "right": "issue:44811", + "left": "issue:36032", + "right": "issue:41720", "accept": false, - "reason": "High perplexity on GPT-OSS vs Whisper batch_decode skip_special_tokens bug; unrelated." + "reason": "Tokenizer load conflict versus device-mapping CUDA assert; no substantive overlap." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch version incompatibility vs noisy transformer-loading message; not the same underlying bug." + "reason": "Torch version compatibility and loading-noise are not the same bug." }, { "left": "issue:44079", "right": "issue:45663", "accept": false, - "reason": "ModelOutput key assignment issue vs Gemma-4 shared_kv_states KeyError; different code paths." + "reason": "ModelOutput key assignment and Gemma4 FSDP shared_kv_states are unrelated." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "Different v5 regressions with different failure surfaces." + "reason": "Different regressions in different parts of model initialization and buffer handling." }, { "left": "issue:42175", "right": "issue:45542", "accept": false, - "reason": "Both involve TensorFlow/backend packaging, but the reported failures differ enough that they do not look like one bug." + "reason": "Both are TensorFlow/backend packaging complaints, but they describe different concrete problems and fixes." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error message and Apple Silicon warmup TypeError are unrelated." }, { "left": "issue:44462", "right": "issue:45812", "accept": false, - "reason": "Both are AutoTokenizer regressions, but one is ignoring tokenizer.json while the other is producing wrong Granite token IDs; not enough evidence of a single root cause." + "reason": "Both involve AutoTokenizer/loading, but the symptoms differ ('ignores tokenizer.json' vs 'wrong token IDs for all Granite models') and the same bug path is not established." }, { "left": "issue:43421", "right": "issue:44568", "accept": true, - "reason": "Both point to the same special-token/post-processor regression: runtime special-token changes not reflected, causing BOS/EOS insertion to fail." - }, - { - "left": "issue:41553", - "right": "issue:43582", - "accept": false, - "reason": "Bad AutoTokenizer error for Voxtral vs Apple Silicon caching_allocator_warmup TypeError; unrelated." + "reason": "Both concern special-token/post-processor handling in tokenizers, and 44568 plausibly fits the same runtime special-token update gap." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Video-LLaVA temporal-attention issue vs Qwen3.5 save_pretrained regression; different models and bugs." + "reason": "Video-LLaVA tower architecture issues are unrelated to Qwen3.5 save_pretrained key serialization." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary stays grounded in the packet and the verdicts are conservative. The two accepted pairs both plausibly describe the same underlying tokenizer/post-processor and save_pretrained regressions, while the remaining soft matches are appropriately rejected as only theme-level similarities rather than clearly shared bugs. The canonical anchor on 45812 is also defensible given the issue set." + "accept": false, + "feedback": "The cluster summary is broadly grounded, but it is not conservative enough on every soft edge. In particular, the accepted link between issue:44462 and issue:45812 overstates the evidence: both involve AutoTokenizer/loading, but the titles only show different symptoms ('ignores tokenizer.json' vs 'wrong token IDs for all Granite models') and do not clearly establish the same bug path. A few other accepted pairs are plausible, but this one is too speculative for a precision pass." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -3327,7 +3315,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:33666", "issue:35707", @@ -3388,13 +3376,13 @@ "issue:43482|issue:45538", "issue:35707|issue:40444", "issue:44079|issue:44534", - "issue:43482|issue:43525", "issue:44291|issue:44589", + "issue:43482|issue:43525", "issue:43377|issue:45491", "issue:43749|issue:44079", "issue:41720|issue:45081", - "issue:43644|issue:44079", "issue:43531|issue:44291", + "issue:43644|issue:44079", "issue:40444|issue:45381", "issue:44265|issue:45072", "issue:43632|issue:45072", @@ -3411,226 +3399,226 @@ "issue:43701|issue:45325", "issue:44479|issue:45823" ], - "prepared_review_unit_hash": "c0d9bb2f363883ea908eb506ee1c3293ff92ad182cdda4308a04051d026f5aee", + "prepared_review_unit_hash": "da6ea750a1277fdc0355e6bd3fe37669a149519d7d29b8ae02294f631885d0c7", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36959, - "estimated_input_tokens": 9240, - "estimated_eval_tokens": 18736 + "serialized_chars": 36954, + "estimated_input_tokens": 9239, + "estimated_eval_tokens": 18734 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated Transformers regression reports. Only one soft edge looks like a true duplicate-style match: the Qwen2.5-VL position-id/rope-index bug across still-image and video inputs. Everything else is adjacent at best, but not the same underlying bug.", - "confidence": 0.58, - "canonical_issue_reason": "issue:45325 is the clearest root-cause report in the cluster: it names the concrete `get_rope_index` path and the specific bad scaling behavior, making it the best representative of the shared Qwen2.5-VL position-id bug.", + "summary": "Mostly a loose cluster of recent Transformers v5 regressions across model loading, device mapping, and multimodal position-id handling. Only one soft pair looks like the same underlying custom-model initialization breakage; the rest are adjacent but distinct bugs.", + "confidence": 0.65, + "canonical_issue_reason": "issue:45020 is the broadest umbrella in the set, covering the general class of recent Transformers-version breakages that many of the other issues are specific manifestations of.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45325 is the best global issue candidate because it is the most concrete, actionable, and root-cause-oriented report among the items; it also subsumes the related video-input symptom reported in issue:45381.", + "best_issue_reason": "issue:45020 is the best single representative for this cluster because it captures the widest shared theme of recent Transformers v5 regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "Different failures: device-map/offload loading vs training-time memory inefficiency." + "reason": "Both mention device map/memory, but one is dequantized-model loading and the other is Qwen3 MoE training OOM." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "Whisper runtime failure and float8 storage lookup error are unrelated code paths." + "reason": "Whisper runtime failure and Float8 storage lookup are different failure modes." }, { "left": "issue:44683", "right": "issue:45020", "accept": false, - "reason": "Torch>=2.9 flex_attention compile failure is not the same as remote_code loading breakage." + "reason": "Compiled flex_attention on torch>=2.9 and remote_code loading regressions are unrelated." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Multi-GPU training and multi-image iterable-dataset finetuning are different bugs." + "reason": "Same model family area, but multi-GPU training and multi-image iterable-dataset finetuning are distinct bugs." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "Loading noise and tokenizer load failure do not share the same underlying defect." + "reason": "Loading noise vs tokenizer loading failure for a specific model are not the same issue." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "Flash-attention training degeneration and num_labels=1 zero-loss behavior are separate classification issues." + "reason": "Both are training regressions, but FlashAttention-3 degeneration and single-label zero-loss are different code paths." }, { "left": "issue:43482", "right": "issue:45538", "accept": false, - "reason": "GGUF/v5 load regression and CLIPTokenizer max-length behavior are unrelated." + "reason": "GGUF/v5 tokenizer loading and CLIPTokenizer max_length behavior are unrelated." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "inputs_embeds/past_key_values generation bug is not the same as Qwen2.5-VL multi-image dataset failure." + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image finetuning." }, { "left": "issue:44079", "right": "issue:44534", "accept": false, - "reason": "ModelOutput key assignment and non-persistent buffer junk are different internal regressions." + "reason": "ModelOutput key assignment and non-persistent buffer junk are separate internals." }, { - "left": "issue:43482", - "right": "issue:43525", + "left": "issue:44291", + "right": "issue:44589", "accept": false, - "reason": "GGUF loading failure and missing `pad_token_id` on Llama4Config are distinct errors." + "reason": "init_empty_weights/_is_hf_initialized and Float8 storage lookup are different bugs." }, { - "left": "issue:44291", - "right": "issue:44589", + "left": "issue:43482", + "right": "issue:43525", "accept": false, - "reason": "`_is_hf_initialized` init argument handling and float8 storage resolution are unrelated." + "reason": "Tokenizer loading failure and missing pad_token_id on Llama4Config are unrelated." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "MIMI padding-mask mismatch and Gemma3 sliding-window NaNs are different model-specific bugs." + "reason": "MIMI padding-mask behavior and Gemma3 sliding-window NaNs are different model paths." }, { "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP CPU RAM-efficient loading is not the same as ModelOutput key handling." + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are unrelated." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "CUDA assert under auto device mapping and Mistral tokenizer regex patch failure are unrelated." + "reason": "Qwen3 auto device-map cuda asserts and Mistral regex patch crashes are unrelated." }, { - "left": "issue:43644", - "right": "issue:44079", + "left": "issue:43531", + "right": "issue:44291", "accept": false, - "reason": "Non-persistent buffer junk and ModelOutput key assignment are separate regression classes." + "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights argument handling are separate issues." }, { - "left": "issue:43531", - "right": "issue:44291", + "left": "issue:43644", + "right": "issue:44079", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior does not match the init_empty_weights `_is_hf_initialized` error." + "reason": "Non-persistent buffer serialization and ModelOutput key assignment are not the same bug." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Multi-image training failure is not the same bug as Qwen2.5-VL video position_ids being wrong." + "reason": "Multi-image finetuning failure and Qwen2.5-VL video position-id regression are distinct." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "torch.export/torch_compilable_check failure and dtype mismatch in bf16 inference are different issues." + "reason": "torch.export/torch_compilable_check and bfloat16 dtype mismatches are different failures." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "`_is_hf_initialized` flag regression and bf16 dtype mismatch are unrelated." + "reason": "_is_hf_initialized flag breakage and bfloat16 inference dtype mismatch are unrelated." }, { "left": "issue:43611", "right": "issue:43646", - "accept": false, - "reason": "Base-model-prefix loading regression and custom model initialization regression are adjacent but not the same code-path bug." + "accept": true, + "reason": "Both are Transformers 5.0 model-initialization/custom-model loading regressions and appear to stem from the same breakage." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "Packaging/backend omission and PaddleOCR-VL load failure are unrelated." + "reason": "Missing TensorFlow in a torch extra and PaddleOCR-VL loading failure are unrelated." }, { "left": "issue:45325", "right": "issue:45381", - "accept": true, - "reason": "Both report the same Qwen2.5-VL position-id/rope-index regression in 5.3.0; one is the still-image manifestation and the other is the video-input manifestation." + "accept": false, + "reason": "Both involve Qwen2.5-VL position ids, but one is still-image scaling and the other is video vision ids; too different to merge confidently." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "SigLIP2 nonsensical outputs and Perceiver non-default-resolution failure are different model-specific bugs." + "reason": "SigLIP2 nonsensical outputs and Perceiver resolution handling are different model bugs." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "Missing lm_head tie and inconsistent serialization of tied weights are related in theme but not the same concrete bug." + "reason": "Both mention lm_head tying, but one is a generation bug and the other is serialization inconsistency; not clearly the same bug." }, { "left": "issue:45325", "right": "issue:45834", "accept": false, - "reason": "Qwen2.5-VL position-id bug and Kosmos2.5 long-OCR index error are unrelated." + "reason": "Qwen2.5-VL position-id regression and Kosmos2.5 OCR index error are unrelated." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Whisper runtime failure and meta-device model loading breakage do not share the same root cause." + "reason": "Whisper loading/runtime failure and meta-device loading regressions are different issues." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Qwen3MoE FP8 config failure and Qwen2.5-GGUF v5 loading failure are different incompatibilities." + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-GGUF tokenizer loading are unrelated." }, { "left": "issue:44387", "right": "issue:44617", "accept": false, - "reason": "Int4 quantization memory growth and Sam3Video OOM are not the same bug." + "reason": "Int4 quantization memory regression and SAM3Video OOM are different causes." }, { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "PaddleOCR-VL/vLLM loading regression and torch 2.4.1 vs transformers 5.8 incompatibility are unrelated." + "reason": "PaddleOCR-VL loading failure and torch/transformers incompatibility are not the same bug." }, { "left": "issue:43701", "right": "issue:45325", "accept": false, - "reason": "Checkpoint key mismatch and Qwen2.5-VL position-id scaling are different failures." + "reason": "Checkpoint key mismatch and Qwen2.5-VL position-id scaling are unrelated." }, { "left": "issue:44479", "right": "issue:45823", "accept": false, - "reason": "Qwen video-input regression and Gemma4 device mismatch are unrelated model-path bugs." + "reason": "Qwen2.5-VL video regression and Gemma4 device mismatch are different model-specific bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet, and the soft-edge decisions stay conservative. The one accepted duplicate-style pair (45325/45381) is well supported by the titles, while the other rejections avoid overclaiming shared root cause from weak or only thematic similarity." + "feedback": "The cluster summary stays within the packet: it treats the set as a loose collection of recent Transformers v5 regressions, and the lone accepted soft pair (issue:43611 / issue:43646) is plausibly the same model-initialization breakage. The other soft-edge rejections are conservative given the differing titles, and the representative choice of issue:45020 is a reasonable broad umbrella for the group." }, "evaluator_used": true, "retried": false, @@ -3649,7 +3637,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:34634", "issue:35707", @@ -3716,251 +3704,251 @@ "issue:41720|issue:45823", "issue:43377|issue:44610", "issue:43454|issue:45072", - "issue:43377|issue:44898", "issue:43572|issue:45759", "issue:39692|issue:40444", + "issue:43377|issue:44898", "issue:43526|issue:43883", "issue:43749|issue:44534", "issue:44466|issue:45357", "issue:43454|issue:43720", - "issue:43296|issue:44877", "issue:43881|issue:44991", + "issue:43296|issue:44877", "issue:41720|issue:43322", "issue:41720|issue:44977", - "issue:44008|issue:45823", "issue:40990|issue:45701", + "issue:44008|issue:45823", "issue:43404|issue:45357", "issue:45632|issue:45684", "issue:42617|issue:42915", "issue:44186|issue:45072", "issue:43577|issue:43708" ], - "prepared_review_unit_hash": "2b6746cb107cabd6e0d90573ac11268789abf6c176cae4f600cc6a3673b210a8", + "prepared_review_unit_hash": "3c1e8b7365b2467b938d557c008f5bec6985b12aeedda8952639de2978cebdee", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37824, - "estimated_input_tokens": 9456, - "estimated_eval_tokens": 19168 + "serialized_chars": 37820, + "estimated_input_tokens": 9455, + "estimated_eval_tokens": 19166 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated, model-specific bug reports rather than one duplicate cluster. The closest overlaps are around loading/offloading/device-map behavior, but each still points to a different concrete failure path, so no soft pair should be merged.", - "confidence": 0.89, - "canonical_issue_reason": "issue:43873 is the broadest and most central runtime bug report here: it has the most discussion/inbound references and covers offloading + quantization, which is the closest shared theme among the nearby device/offload reports.", + "summary": "This cluster is a loose semantic grouping of model-loading, device-map, tokenizer, quantization, and weight-tying issues; none of the soft pairs look like exact duplicates.", + "confidence": 0.8, + "canonical_issue_reason": "No single exact duplicate spans the cluster, but issue 43873 is the broadest representative of the offloading/quantization subgroup and has the strongest activity.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the best single anchor for triage because it is broad, actively discussed, and most likely to absorb related offloading regressions if any existed.", + "best_issue_reason": "Issue 43873 is the best standalone anchor because it is the most general loading/offloading report in the set and has the most discussion/inbound attention, though the cluster is not a true duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43881", "right": "issue:44488", "accept": false, - "reason": "Both are loading failures, but one is a specific multimodal model load crash and the other is a tokenizer/model compatibility problem for a different model." + "reason": "Different models and different loading failures; only the broad \"load fails\" theme overlaps." }, { "left": "issue:44291", "right": "issue:44877", "accept": false, - "reason": "Different failure points: unexpected _is_hf_initialized arg in init_empty_weights vs strict config rejection for granite_speech." + "reason": "One is an init_empty_weights argument mismatch, the other is strict config parsing for granite_speech." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Both involve audio-related models, but one is apply_chat_template sampling-rate defaulting and the other is local checkpoint loading with PEFT adapters." + "reason": "Audio chat-template sample-rate defaults vs PEFT checkpoint loading are unrelated bugs." }, { "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "Device-mismatch CPU offload for Bark-small is unrelated to torch.export failures with torch_compilable_check." + "reason": "CPU-offload device mismatch for Bark is unrelated to torch.export failures around torch_compilable_check." }, { "left": "issue:40990", "right": "issue:45584", "accept": false, - "reason": "Perplexity regression on gpt-oss is not the same as Whisper empty-transcription generation after align_special_tokens." + "reason": "High perplexity during eval and Whisper empty-transcription generation failure are different code paths." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "Bark voice_preset failure and progressive generation with inputs_embeds/past_key_values are different code paths and symptoms." + "reason": "BarkProcessor voice_preset and progressive generation with inputs_embeds/past_key_values are unrelated." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Offloading/quantization behavior is a different problem from version-dependent tokenization changes." + "reason": "Offloading/quantization behavior does not match a tokenization-change regression." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "Tokenizer padding/truncation crash is unrelated to export-time torch_compilable_check behavior." + "reason": "Tokenizer padding/truncation crash is unrelated to torch.export and torch_compilable_check." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "Both mention offload/device_map, but one is dequantized-model loading on gpu+cpu offload and the other is a broader quantization/offloading issue." + "reason": "Both mention offload, but one is dequantized device_map loading and the other is a broader quantization/offloading report." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "inputs_embeds/past_key_values generation bugs and Qwen3 auto device-map cuda asserts are distinct failures." + "reason": "Progressive generation with cached inputs is unrelated to a Qwen3 auto-device-map cuda assert." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "CPU offload device mismatch and DAC.from_latents missing STE are unrelated model behaviors." + "reason": "Bark CPU offload mismatch and DAC.from_latents missing STE are different model behaviors." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "Tied lm_head weights and torch.compile SDPA failures are different bugs in different models." + "reason": "Weight tying in AyaVision is unrelated to Bamba torch.compile/SDPA failure." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Both are device_map issues, but they involve different models and different symptoms: cudaErrorAssert vs forward-time device mismatch." + "reason": "Both involve device_map auto, but the failing models and underlying mismatches are different." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "MIMI padding-mask batching bug is not the same as OmDet processor/model resolution mismatch." + "reason": "MIMI batching/padding-mask bug is unrelated to OmDet-Turbo processor image-size mismatch." }, { "left": "issue:43454", "right": "issue:45072", "accept": false, - "reason": "Weight tying and dtype mismatch regressions are different failure classes." - }, - { - "left": "issue:43377", - "right": "issue:44898", - "accept": false, - "reason": "Missing padding-mask support and Perceiver resolution/interpolate_pos_encoding are unrelated bugs." + "reason": "A missing lm_head tie is not the same as dtype mismatches in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "One is a missing pad_token_idx config field; the other is from_config not unwrapping text_config for composite multimodal configs." + "reason": "Missing pad_token_idx in config and composite config unwrapping are separate config-handling bugs." }, { "left": "issue:39692", "right": "issue:40444", "accept": false, - "reason": "Both are multimodal, but one is a SigLIP2 docs/model-processor mismatch and the other is Qwen2.5-VL fine-tuning with multi-image IterableDataset." + "reason": "SigLIP2 doc example errors are unrelated to Qwen2.5-VL finetuning on iterable multi-image prompts." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "MIMI padding-mask inconsistency is unrelated to Perceiver resolution/interpolation failure." }, { "left": "issue:43526", "right": "issue:43883", "accept": false, - "reason": "BEiT image label reduction and Molmo missing all_tied_weights_keys are unrelated implementation bugs." + "reason": "BeitImageProcessorFast label reduction and Molmo missing all_tied_weights_keys are unrelated." }, { "left": "issue:43749", "right": "issue:44534", "accept": false, - "reason": "FSDP CPU RAM-efficient loading and non-persistent buffer junk are both loading-related, but not the same bug." + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer serialization are different mechanisms." }, { "left": "issue:44466", "right": "issue:45357", "accept": false, - "reason": "Both involve serialization, but one is lm_head.weight device-dependent serialization and the other is incorrect visual encoder keys for Qwen3.5 save_pretrained." + "reason": "lm_head serialization inconsistency is not the same as incorrect visual encoder keys in Qwen3.5 save_pretrained." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "Tied-weight handling in a vision-language model is not the same as unpacking packed weights during accelerate loading." + "reason": "Weight tying bug in AyaVision is unrelated to BitNet packed-weight unpacking during loading." }, { - "left": "issue:43296", - "right": "issue:44877", + "left": "issue:43881", + "right": "issue:44991", "accept": false, - "reason": "PaddleOCR-VL load failure in vLLM and strict granite_speech config loading are different model-specific issues." + "reason": "Model load failure for glm-4v-9b is unrelated to tokenizer loading for EMBEDDIA/est-roberta." }, { - "left": "issue:43881", - "right": "issue:44991", + "left": "issue:43296", + "right": "issue:44877", "accept": false, - "reason": "A multimodal model load failure and a tokenizer-loading regression for est-roberta do not share the same code path." + "reason": "PaddleOCR-VL loading in vLLM and strict granite_speech config parsing are distinct failures." }, { "left": "issue:41720", "right": "issue:43322", "accept": false, - "reason": "Qwen3 auto device-map cuda assert and Llava Next segfaults are different models and different failure modes." + "reason": "Qwen3 auto device-map cuda assert and Llava Next segmentation fault are different bugs." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "Same model family, but the bugs differ: auto device mapping crash vs flash-attention generation behavior." + "reason": "Auto device mapping crash and flash-attention generation bug are different Qwen3 issues." }, { - "left": "issue:44008", - "right": "issue:45823", + "left": "issue:40990", + "right": "issue:45701", "accept": false, - "reason": "Gemma 3n variable-name collision in forward is unrelated to Gemma4 PLE device mismatch." + "reason": "Perplexity regression and tokenization changes are not the same defect." }, { - "left": "issue:40990", - "right": "issue:45701", + "left": "issue:44008", + "right": "issue:45823", "accept": false, - "reason": "Perplexity anomaly and tokenization changes are not the same underlying defect." + "reason": "Gemma 3n forward variable collision and Gemma4 PLE device mismatch are unrelated." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "lm_head weight tying in Mistral3 is unrelated to incorrect visual encoder keys in Qwen3.5 save_pretrained." + "reason": "Missing lm_head tying in Mistral3 differs from bad visual encoder key serialization in Qwen3.5." }, { "left": "issue:45632", "right": "issue:45684", "accept": false, - "reason": "Cache-path collisions for trust_remote_code and read-only permission propagation from save_pretrained are separate filesystem issues." + "reason": "Cache-path collisions and read-only permission propagation are different save/load issues." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "3d_parallel.py execution failure and FineGrainedFP8Config failure in Qwen3Moe are unrelated." + "reason": "3d_parallel launch failure and Qwen3Moe FP8 config failure are unrelated." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Tokenizer crash on NER padding/truncation is not the same as dtype mismatches in inference." + "reason": "Tokenizer crash and bfloat16 dtype mismatch are different subsystems." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "Blip2 dtype propagation and Trainer resume_from_checkpoint step-count calculation are different subsystems and bugs." + "reason": "Blip2 dtype loading bug and Trainer resume max_steps calculation bug are unrelated." } ] }, @@ -3982,7 +3970,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:30064", "issue:33357", @@ -4040,246 +4028,255 @@ "issue:44877|issue:44991", "issue:36331|issue:42617", "issue:36331|issue:42915", - "issue:43550|issue:43720", "issue:43450|issue:45701", + "issue:43550|issue:43720", "issue:44610|issue:44898", "issue:44186|issue:44610", "issue:44479|issue:44918", "issue:42915|issue:43317", - "issue:43550|issue:43606", "issue:41720|issue:42617", + "issue:43550|issue:43606", "issue:43316|issue:44913", - "issue:45081|issue:45812", "issue:43295|issue:45701", + "issue:45081|issue:45812", "issue:44671|issue:44743", "issue:43526|issue:43881", "issue:41720|issue:45161", "issue:43531|issue:43572", "issue:43421|issue:45812", - "issue:43540|issue:43782", "issue:36010|issue:42617", + "issue:43540|issue:43782", "issue:44186|issue:44361", "issue:42915|issue:43322", "issue:43388|issue:45059", "issue:45406|issue:45464", - "issue:43421|issue:45701", "issue:30064|issue:34634", + "issue:43421|issue:45701", "issue:33357|issue:35707" ], - "prepared_review_unit_hash": "e7c50f2b9dea5fbea9a915713f01ab4c1c2b44a72409d4fa21e62be09be38d2f", + "prepared_review_unit_hash": "bce1ba19d30af66e5b3326d5a6d05d18eb955a46457d88f0b462324d9ed87ca0", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36878, - "estimated_input_tokens": 9220, - "estimated_eval_tokens": 18696 + "serialized_chars": 36873, + "estimated_input_tokens": 9219, + "estimated_eval_tokens": 18694 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly noise: the issues cover unrelated models, processors, tokenizers, config bugs, and serving/runtime failures. None of the soft pairs look like the same underlying bug or change, so I would not merge any of them.", - "confidence": 0.95, - "canonical_issue_reason": "issue:43873 is the closest thing to an umbrella issue because it is broad, has the most inbound references, and centers on offloading/quantization behavior, but it still does not actually subsume the others.", + "summary": "This cluster is mostly a collection of unrelated Transformer bugs. The serve-related pair `issue:44423` and `issue:45406` should not be treated as duplicates: they hit different model paths and fail with different concrete exceptions.", + "confidence": 0.93, + "canonical_issue_reason": "`issue:45406` is the clearest standalone issue in the cluster because it names the exact `Gemma4Processor` `_tokenizer` crash; `issue:44423` is a separate Qwen3.5 continuous-batching serve failure and should remain distinct.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the best representative only in the loose sense of being broad and high-signal; the rest are distinct, model-specific reports.", + "best_issue_reason": "`issue:45406` is the strongest representative issue: specific, reproducible, and tied to an exact exception/path, unlike the broader serve crash reports around it.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43873", "right": "issue:44756", "accept": false, - "reason": "Both are offloading-related, but one is a quantization/offload behavior report and the other is a Strix Halo mmap/OOM workaround; different root causes." + "reason": "Quantization/offloading behavior vs a Strix Halo mmap/OOM workaround; different bugs." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "Int4 quantization OOM from Transformers 5.x is not the same bug as a T5 apex.FusedRMSNorm memory leak." + "reason": "Int4 OOM under Transformers 5.x vs an apex RMSNorm memory leak; not the same failure." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Both affect serving multimodal models, but the failures are different AttributeErrors in different processor paths." + "reason": "Both are serve-related, but one is a Qwen3.5 continuous-batching `str.to()` crash and the other is a Gemma4Processor `_tokenizer` crash." }, { "left": "issue:44877", "right": "issue:44991", "accept": false, - "reason": "One is strict config loading for granite_speech; the other is tokenizer loading regression for est-roberta." + "reason": "Different tokenizer/loading regressions affecting different model paths." }, { "left": "issue:36331", "right": "issue:42617", "accept": false, - "reason": "A Trainer compute_loss signature change is unrelated to a 3d_parallel.py execution failure." + "reason": "Trainer `compute_loss` API mismatch vs a `3d_parallel.py` runtime failure; unrelated." }, { "left": "issue:36331", "right": "issue:42915", "accept": false, - "reason": "CustomTrainer kwarg incompatibility is unrelated to Qwen3MoE FineGrainedFP8 loading." + "reason": "Trainer API mismatch vs Qwen3MoE FP8 load failure; different code paths." }, { - "left": "issue:43550", - "right": "issue:43720", + "left": "issue:43450", + "right": "issue:45701", "accept": false, - "reason": "torch.compile+SDPA on Bamba is a different code path than packed-weight unpacking during accelerate loading." + "reason": "Video batching shape bug vs a tokenization/version regression; not the same issue." }, { - "left": "issue:43450", - "right": "issue:45701", + "left": "issue:43550", + "right": "issue:43720", "accept": false, - "reason": "Video batch shape bugs are unrelated to a tokenizer/version regression." + "reason": "Bamba torch.compile/SDPA issue vs BitNet packed-weight unpacking during loading; distinct bugs." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "Both involve image sizes, but the model/preprocessing failures are different and not the same defect." + "reason": "Processor output size mismatch vs a Perceiver non-default-resolution failure; different symptoms and causes." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "LayoutLMv2 NER/padding crashes and OmDet-Turbo resolution mismatch are distinct tokenizer vs image-processor bugs." + "reason": "LayoutLMv2 tokenizer crash vs an image processor shape bug; not the same bug." }, { "left": "issue:44479", "right": "issue:44918", "accept": false, - "reason": "A video-input regression in several Qwen VL models is not the same as unpacking Qwen3.5 embeddings with TRL SFT." + "reason": "Video-input regression across Qwen VL models vs an embeddings unpacking/trainer issue." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "These are separate loading failures: one is Qwen3MoE FP8 config, the other dequantized model offload with device_map=auto." + "reason": "Qwen3Moe FP8 load failure vs dequantized model offload loading failure; too different." }, { - "left": "issue:43550", - "right": "issue:43606", + "left": "issue:41720", + "right": "issue:42617", "accept": false, - "reason": "torch.compile SDPA failure and CPU-offload device mismatch are different runtime bugs." + "reason": "Qwen3 auto-device-map CUDA assert vs a generic parallel script failure." }, { - "left": "issue:41720", - "right": "issue:42617", + "left": "issue:43550", + "right": "issue:43606", "accept": false, - "reason": "Qwen3 auto device mapping cudaErrorAssert is unrelated to a 3d_parallel.py failure." + "reason": "Different models and failure modes: SDPA/torch.compile vs CPU offload device mismatch." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Config API discrepancy for Gemma3TextConfig is not the same bug as GPTNeoX rotary_pct not persisting on reload." + "reason": "Config API discrepancy vs a rotary_pct reload regression; not the same issue." }, { - "left": "issue:45081", - "right": "issue:45812", + "left": "issue:43295", + "right": "issue:45701", "accept": false, - "reason": "Mistral regex patch crash and Granite token-ID regression are different tokenizer problems with different failure modes." + "reason": "Processor/tokenizer regression in custom model code vs a broader tokenization change report." }, { - "left": "issue:43295", - "right": "issue:45701", + "left": "issue:45081", + "right": "issue:45812", "accept": false, - "reason": "Processor.tokenizer regression and version-dependent tokenization changes are not the same underlying issue." + "reason": "Mistral regex patch crash vs Granite token ID regression; different tokenizer bugs." }, { "left": "issue:44671", "right": "issue:44743", "accept": false, - "reason": "CamemBERT masked LM predictions and Qwen3.5 recurrent-state reset are unrelated model bugs." + "reason": "CamemBERT masked-LM prediction bug vs Qwen3.5 recurrent-state reset in modular code." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "BeitImageProcessorFast reduce_labels bug and glm-4v-9b load failure are not the same issue." + "reason": "BeitImageProcessorFast label reduction bug vs a glm-4v-9b loading failure; unrelated." }, { "left": "issue:41720", "right": "issue:45161", "accept": false, - "reason": "These are both Qwen3-family, but one is device-map CUDA assert and the other is tensor-parallel not working for GPT-OSS MoE." + "reason": "Both are Qwen/MoE-related, but the concrete errors and affected setups differ." }, { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE and a missing pad_token_idx in StableLmConfig are separate config/model bugs." + "reason": "Sliding-window Qwen3-MoE behavior vs a StableLm config field regression; different issues." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Runtime post-processor updates for special tokens are a different tokenizer behavior than Granite token-ID misgeneration." + "reason": "Special-token post-processor update bug vs wrong token IDs in AutoTokenizer; same broad area, but not the same bug." }, { - "left": "issue:43540", - "right": "issue:43782", + "left": "issue:36010", + "right": "issue:42617", "accept": false, - "reason": "Video input validation errors and weight_only load errors are different failure surfaces." + "reason": "GenerationMixin import error vs a parallel script runtime issue; unrelated." }, { - "left": "issue:36010", - "right": "issue:42617", + "left": "issue:43540", + "right": "issue:43782", "accept": false, - "reason": "GenerationMixin import failure is unrelated to a 3d_parallel.py runtime problem." + "reason": "Video-processing regression vs a `from_pretrained(weight_only=True)` loading error; different code paths." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "Two different tokenizer failures on different models and tasks; no shared concrete bug." + "reason": "Different tokenizer/model crashes with different symptoms and models." }, { "left": "issue:42915", "right": "issue:43322", "accept": false, - "reason": "Qwen3MoE FP8 loading and Llava Next segfault are separate model-loading failures." + "reason": "FP8 loading failure vs a Llava Next segmentation fault; not the same bug." }, { "left": "issue:43388", "right": "issue:45059", "accept": false, - "reason": "Metric-gathering label truncation and SAM3 text+box odd behavior are different subsystems and bugs." + "reason": "Metric-gathering label truncation vs SAM3 text/bbox behavior; separate issues." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Gemma4Processor missing _tokenizer and Qwen3.5 streaming inference failure are different serving issues." + "reason": "Both mention serve, but one is a Gemma4Processor attribute crash and the other is a Qwen3.5 streaming inference failure." }, { "left": "issue:30064", "right": "issue:34634", "accept": false, - "reason": "Void segmentation-map processing and BarkProcessor voice_preset are unrelated processor bugs." + "reason": "Void segmentation map processing vs BarkProcessor voice preset handling; unrelated." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Runtime special-token update bug vs a broader version-to-version tokenization change report." }, { "left": "issue:33357", "right": "issue:35707", "accept": false, - "reason": "MacOS CLIP bus error and progressive generation with inputs_embeds/past_key_values are unrelated problems." + "reason": "MacOS CLIP bus error vs a progressive-generation `inputs_embeds`/`past_key_values` issue; unrelated." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The summary overstates the evidence for a duplicate pair. In the packet, `issue:44423` is a continuous-batching crash on Qwen3.5 with `AttributeError: 'str' object has no attribute 'to'`, while `issue:45406` is a Gemma4Processor `_tokenizer` attribute crash. They are both serve-related, but the concrete failures and models differ, so treating them as the same bug is not grounded enough. The rest of the soft-edge rejections are generally conservative, but the single accepted pair should be rejected." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -4295,7 +4292,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:34567", "issue:34634", @@ -4361,14 +4358,14 @@ "issue:34567|issue:35707", "issue:44368|issue:45357", "issue:43782|issue:45381", - "issue:44451|issue:44991", "issue:44898|issue:45072", + "issue:44451|issue:44991", "issue:44077|issue:44625", "issue:44987|issue:45042", - "issue:44062|issue:44451", "issue:43531|issue:44589", - "issue:43421|issue:43653", "issue:45759|issue:45859", + "issue:44062|issue:44451", + "issue:43421|issue:43653", "issue:44918|issue:44936", "issue:45588|issue:45759", "issue:39692|issue:44610", @@ -4376,214 +4373,214 @@ "issue:42886|issue:44843", "issue:43421|issue:44186" ], - "prepared_review_unit_hash": "f741ed75461dcd30bfbb2a739816065028b53d7f784e58da0dca8e6085bf85dc", + "prepared_review_unit_hash": "521265de539230fa462e3424f8798d2984655bfe92859cfc9a3fb6d0494008ea", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 36034, - "estimated_input_tokens": 9009, - "estimated_eval_tokens": 18274 + "serialized_chars": 36032, + "estimated_input_tokens": 9008, + "estimated_eval_tokens": 18272 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of unrelated, similarity-only false positives across tokenizer, model-loading, and training issues. The only clear duplicate pair is the Qwen2_5_VLProcessor batched `apply_chat_template` crash with `padding=False`.", - "confidence": 0.87, - "canonical_issue_reason": "issue:44545 is the clearest representative of the true duplicate pair: it states the exact Qwen2_5_VLProcessor batched-input crash with `padding=False` and matches issue:44514.", + "summary": "This set is mostly a heterogeneous mix of unrelated issue reports; only two soft pairs look like true duplicates. There is no single cluster-wide canonical issue or PR.", + "confidence": 0.9, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:44545 is the best issue to keep as the canonical anchor because it cleanly names the concrete failure mode and is an exact duplicate of issue:44514.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44492", "right": "issue:44509", "accept": false, - "reason": "Different docs-only changes: a typo fix in cache strategies vs obsolete pipeline-task mentions." + "reason": "Both touch docs, but one is a typo and the other is stale pipeline-task documentation; not the same bug." }, { "left": "issue:41720", "right": "issue:43746", "accept": false, - "reason": "Different bugs and code paths: Qwen3 auto device mapping CUDA assert vs GraniteSpeech PEFT checkpoint loading." + "reason": "Different models and failures: Qwen3 device-mapping CUDA assert vs GraniteSpeech local-checkpoint/PEFT loading." }, { "left": "issue:43606", "right": "issue:43720", "accept": false, - "reason": "Both involve loading/offload, but one is Bark CPU device mismatch and the other is BitNet packed-weight unpacking." + "reason": "Both are loading/offload related, but Bark CPU offload device mismatch and BitNet packed-weight unpacking are different code paths." }, { "left": "issue:44779", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different models and symptoms; no clear same underlying defect." + "reason": "Both are tokenizer regressions, but for different model families and symptoms; not the same underlying bug." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "Unrelated: torch.compile/SDPA model failure vs BigBirdTokenizer special-token decode issue." + "reason": "Model compile/SDPA failure vs tokenizer special-token registration/empty decode issue." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Different subsystems: quantization/offloading behavior vs a T5 apex RMSNorm memory leak." + "reason": "Quantization/offloading behavior and a T5 Apex RMSNorm memory leak are unrelated bugs." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Same concrete crash: Qwen2_5_VLProcessor.apply_chat_template fails on batched input when `padding=False`." + "reason": "Same Qwen2_5_VLProcessor.apply_chat_template batched-input crash with padding=False; titles and failure mode match." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Both mention classification settings, but one is config propagation and the other is a zero-loss problem across models." + "reason": "One is Qwen3.5 config propagation for num_labels; the other is a broader sequence-classification loss degeneration issue across models." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "Different issues: Bark CPU offload device mismatch vs tokenizer mask-token registration/decode behavior." + "reason": "Bark CPU offload device mismatch is unrelated to BigBirdTokenizer special-token decode behavior." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and multimodal config unwrapping are distinct bugs." + "reason": "Both mention Qwen3.x, but sliding_window behavior and text_config unwrapping are separate configuration bugs." }, { "left": "issue:34634", "right": "issue:41720", "accept": false, - "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping are unrelated." + "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping are entirely different problems." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Both are token-related, but one is runtime special-token post-processing and the other is save/load custom token IDs." + "reason": "Different tokenizer issues: runtime post-processor refresh vs DiaConfig losing custom token IDs on save/load." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "TrainerState metric updating and progressive generation with inputs_embeds/past_key_values are unrelated." + "reason": "TrainerState token counting and progressive generation with inputs_embeds/past_key_values are unrelated." }, { "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "Different Qwen issues: a warning about tied embeddings vs incorrect visual encoder keys on save_pretrained." + "reason": "One is a warning about tie_word_embeddings during LoRA fine-tuning; the other is a save_pretrained regression for visual encoder keys." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Different Qwen multimodal failures: weight_only loading error vs wrong video vision_position_ids." + "reason": "Both are Qwen VL-related, but one is a from_pretrained weight_only load error and the other is a video vision_position_ids bug." }, { - "left": "issue:44451", - "right": "issue:44991", + "left": "issue:44898", + "right": "issue:45072", "accept": false, - "reason": "Both are model/tokenizer loading failures, but the affected models and failure modes differ." + "reason": "Perceiver image-size interpolation and bf16 dtype mismatches in SwitchTransformers/TimmWrapperModel are different issues." }, { - "left": "issue:44898", - "right": "issue:45072", + "left": "issue:44451", + "right": "issue:44991", "accept": false, - "reason": "Perceiver image-size handling and dtype mismatch in bfloat16 inference are unrelated." + "reason": "Both are model/tokenizer loading failures, but they affect different checkpoints and likely different root causes." }, { "left": "issue:44077", "right": "issue:44625", "accept": false, - "reason": "PatchTSMixer post-init validation and Qwen3.5 num_labels propagation are distinct configuration bugs." + "reason": "Optional post_init policy for patchtsmixer is unrelated to Qwen3.5 num_labels propagation." }, { "left": "issue:44987", "right": "issue:45042", "accept": false, - "reason": "Different problems: loading a specific model vs PIL image processors incorrectly requiring torchvision." + "reason": "One is a specific model load failure; the other is an image-processor dependency regression on PIL backends." }, { - "left": "issue:44062", - "right": "issue:44451", + "left": "issue:43531", + "right": "issue:44589", "accept": false, - "reason": "AddedToken constructor error and ScandiBERT loading failure do not point to the same root cause." + "reason": "Sliding-window behavior for Qwen3-MoE and a Float8 storage lookup error are unrelated." }, { - "left": "issue:43531", - "right": "issue:44589", + "left": "issue:45759", + "right": "issue:45859", "accept": false, - "reason": "Qwen3-MoE sliding_window and missing Float8 storage type are unrelated." + "reason": "Config unwrapping for composite Qwen multimodal models and CPU-offload incompatibility in rotary embedding are different bugs." }, { - "left": "issue:43421", - "right": "issue:43653", + "left": "issue:44062", + "right": "issue:44451", "accept": false, - "reason": "Same broad tokenizer area, but runtime post-processor updates and BigBird mask-token registration are different defects." + "reason": "AddedToken construction error and ScandiBERT loading failure are not the same underlying problem." }, { - "left": "issue:45759", - "right": "issue:45859", + "left": "issue:43421", + "right": "issue:43653", "accept": false, - "reason": "Different Qwen 3.5 issues: config unwrapping vs CPU-offload incompatibility in rotary embedding." + "reason": "Both involve special tokens, but runtime post-processor updates and BigBird mask-token registration are distinct failures." }, { "left": "issue:44918", "right": "issue:44936", "accept": false, - "reason": "Different trainer failures: embedding unpacking in SFT vs evaluate-after-train regression." + "reason": "TRL SFT unpacking for Qwen3.5 embeddings and trainer.evaluate() failing after train() are different trainer issues." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "Flash-attention sinkless-model crash and Qwen config unwrapping are unrelated." + "reason": "Flash-attention sinkless-model AttributeError and Qwen config unwrapping are unrelated." }, { "left": "issue:39692", "right": "issue:44610", "accept": false, - "reason": "Both are processor/model mismatch issues, but the affected models and incorrect image sizes are different." + "reason": "Both mention processor/model mismatches, but for different models and different concrete failures." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Gradient checkpointing in eval mode and ZeRO-3 gradient growth are different training behaviors." + "reason": "Gradient checkpointing in eval mode and gradient blow-up under ZeRO-3 are separate training behaviors." }, { "left": "issue:42886", "right": "issue:44843", - "accept": false, - "reason": "Both involve offline/tokenizer loading, but one is cache fallback and the other is an unconditional model_info() call in a Mistral patch." + "accept": true, + "reason": "Both describe HF_HUB_OFFLINE failures when loading tokenizer assets; 44843 pinpoints the same offline-mode network call via model_info()." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "TokenizersBackend special-token updates and LayoutLMv2Tokenizer NER/padding crashes are distinct bugs." + "reason": "Tokenizer post-processor refresh and LayoutLMv2 NER/batched padding crashes are different tokenizer bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet, and the one accepted duplicate pair (issue:44514 / issue:44545) is strongly supported by the titles. The remaining soft-edge verdicts stay conservative and do not overclaim duplicate status from similarity alone." + "feedback": "The summary is grounded in the packet: the set is heterogeneous, the two accepted soft pairs are strongly supported by the titles/body themes, and the claim that there is no cluster-wide canonical issue or PR is conservative. I did not see any soft-edge verdict that overstates the evidence." }, "evaluator_used": true, "retried": false, @@ -4602,7 +4599,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:30064", "issue:36010", @@ -4641,7 +4638,6 @@ "issue:44671", "issue:44811", "issue:44843", - "issue:44877", "issue:44898", "issue:45072", "issue:45081", @@ -4651,31 +4647,33 @@ "issue:45685", "issue:45704", "issue:45834", - "issue:45859" + "issue:45859", + "issue:45907" ], "soft_pairs": [ "issue:43994|issue:44671", "issue:43525|issue:43531", - "issue:45081|issue:45356", "issue:45704|issue:45859", + "issue:45081|issue:45356", "issue:41720|issue:45704", + "issue:45356|issue:45907", "issue:39692|issue:43873", "issue:43596|issue:44220", "issue:43746|issue:43873", "issue:40444|issue:43746", "issue:42915|issue:43746", - "issue:43540|issue:44008", "issue:44220|issue:44661", + "issue:43540|issue:44008", "issue:30064|issue:36010", "issue:43720|issue:43819", - "issue:45183|issue:45479", "issue:43618|issue:43697", - "issue:43335|issue:43756", + "issue:45183|issue:45479", "issue:43653|issue:43720", - "issue:43716|issue:44008", + "issue:43335|issue:43756", "issue:43295|issue:45834", - "issue:44062|issue:44488", + "issue:43716|issue:44008", "issue:43550|issue:45072", + "issue:44062|issue:44488", "issue:43550|issue:43819", "issue:43322|issue:45685", "issue:44186|issue:44898", @@ -4683,223 +4681,222 @@ "issue:43577|issue:43818", "issue:43531|issue:43643", "issue:43421|issue:44811", - "issue:43653|issue:43819", - "issue:43643|issue:44877" + "issue:43653|issue:43819" ], - "prepared_review_unit_hash": "bcbacb0cebf66255bde511fdb8214dcb7a3f4ed87df351209233ab85f889573d", + "prepared_review_unit_hash": "eaed07aaf41249208937961e5af799853d5b8006e10066cdae0a63050c6aeb05", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37395, - "estimated_input_tokens": 9349, - "estimated_eval_tokens": 18954 + "serialized_chars": 37427, + "estimated_input_tokens": 9357, + "estimated_eval_tokens": 18970 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: most pairs share only broad subsystem keywords (tokenizers, multimodal models, config, quantization) but not the same concrete failure mode. I do not see a defensible canonical issue or PR for the cluster as a whole.", - "confidence": 0.97, - "canonical_issue_reason": "No single issue is a strong canonical representative because the items span unrelated bugs across tokenization, vision-language models, config loading, quantization, and runtime/offload paths.", + "summary": "The set is highly heterogeneous: tokenizer regressions, vision/multimodal bugs, dtype/offload issues, config/model-loading regressions, and CI/documentation problems. None of the soft pairs look like the same underlying bug, so no duplicate merges are justified.", + "confidence": 0.96, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "No global best issue stands out; the cluster is not a near-duplicate set around one underlying bug.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different models and symptoms: SigLIP2 inference nonsense vs CamemBERT masked-LM prediction errors. Same broad area, not the same bug." + "reason": "Both involve model output quality, but one is SigLIP2 inference/pipeline misuse and the other is a CamemBERT masked-LM regression in v5; different models and failure modes." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "One is a missing config attribute (`pad_token_id`), the other is a sliding-window issue in Qwen3-MoE. Distinct code paths." + "reason": "Llama4Config missing pad_token_id and Qwen3-MoE sliding_window behavior are unrelated config/model bugs." }, { - "left": "issue:45081", - "right": "issue:45356", + "left": "issue:45704", + "right": "issue:45859", "accept": false, - "reason": "Both involve tokenizer regex handling, but one crashes on `backend_tokenizer` access while the other is a codec/regression warning issue. Not the same concrete bug." + "reason": "T5 Apex RMSNorm memory leak and Qwen3_5Moe CPU offload incompatibility affect different code paths and components." }, { - "left": "issue:45704", - "right": "issue:45859", + "left": "issue:45081", + "right": "issue:45356", "accept": false, - "reason": "T5 RMSNorm memory leak and Qwen3 rotary embedding CPU-offload incompatibility are unrelated failures." + "reason": "Both touch mistral regex handling, but 45081 is a tokenizer crash on backend_tokenizer access while 45356 is a Kimi-K2.5 regression about codec handling and warning text; not the same bug." }, { "left": "issue:41720", "right": "issue:45704", "accept": false, - "reason": "Auto device-mapping CUDA assert is unrelated to an apex RMSNorm memory leak." + "reason": "Qwen3 auto device-map cuda assert and T5 RMSNorm memory leak are unrelated runtime issues." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Kimi-K2.5 tokenizer regression is about Mistral regex/codec behavior; list_repo_files revision forwarding is a hub API bug." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "Doc-example model/processor mismatch and quantization failure is not the same as offloading behavior with quantization." + "reason": "SigLIP2 doc example errors and quantization failure are about example/model usage, while 43873 is a general offloading-with-quantization issue with no matching model/path shown." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "BertModel zero3 init index error and `_torch_extract_fbank_features()` are different failures." + "reason": "Both cause runtime failures, but deepspeed zero3 init with BertModel and _torch_extract_fbank_features are different subsystems and symptoms." }, { "left": "issue:43746", "right": "issue:43873", "accept": false, - "reason": "Loading PEFT adapters from local checkpoints is unrelated to quantized offloading semantics." + "reason": "GraniteSpeech PEFT checkpoint loading and offloading with quantization are different loading/offload bugs." }, { "left": "issue:40444", "right": "issue:43746", "accept": false, - "reason": "Multi-image IterableDataset finetuning failure and GraniteSpeech checkpoint loading are different model/training paths." + "reason": "Qwen2.5-VL iterable dataset with multiple images and GraniteSpeech PEFT local checkpoint loading do not share the same code path." }, { "left": "issue:42915", "right": "issue:43746", "accept": false, - "reason": "FineGrainedFP8 loading failure is unrelated to PEFT adapter checkpoint loading." + "reason": "Qwen2.5 MoE FP8 config failure and GraniteSpeech adapter loading are unrelated." }, { - "left": "issue:43540", - "right": "issue:44008", + "left": "issue:44220", + "right": "issue:44661", "accept": false, - "reason": "Qwen3OmniMoe video-processing ValueError and Gemma3n audio mask variable collision are different multimodal bugs." + "reason": "Audio feature extraction and add-new-model-like TOKENIZER_MAPPING_NAMES handling are different tokenizer/model utilities." }, { - "left": "issue:44220", - "right": "issue:44661", + "left": "issue:43540", + "right": "issue:44008", "accept": false, - "reason": "Audio feature extraction issue and tokenizer-mapping model addition failure do not share the same bug." + "reason": "Qwen3OmniMoe video-input ValueError and Gemma3n audio_mel_mask name collision are separate multimodal bugs." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Void segmentation-map processing and a `GenerationMixin` import error are unrelated." + "reason": "Void segmentation-map processing and the GenerationMixin import error are entirely unrelated." }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "Accelerate loading/unpacked weights bug and DAC STE mismatch are different implementation errors." - }, - { - "left": "issue:45183", - "right": "issue:45479", - "accept": false, - "reason": "Input validation error-message logic and single-label zero-loss classification are distinct bugs." + "reason": "BitNet packed-weight unpacking during accelerate loading and DAC from_latents vs forward mismatch are different model internals." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "CLIP output attentions regression and RTDetrV2 differing outputs are separate model regressions." + "reason": "CLIPOutput attentions assignment and RTDetrV2 differing outputs are unrelated model regressions." }, { - "left": "issue:43335", - "right": "issue:43756", + "left": "issue:45183", + "right": "issue:45479", "accept": false, - "reason": "Sparse-layer creation in SwitchTransformers and RoPE-layer dropping in Smollm3 are unrelated architecture bugs." + "reason": "XOR validation for input_ids/inputs_embeds errors and single-label classification with num_labels=1 zero-loss behavior are different validation vs loss bugs." }, { "left": "issue:43653", "right": "issue:43720", "accept": false, - "reason": "BigBird tokenizer special-token registration and BitNet packed-weight loading are unrelated." + "reason": "BigBirdTokenizer special-token registration and BitNet packed-weight loading are different issues." }, { - "left": "issue:43716", - "right": "issue:44008", + "left": "issue:43335", + "right": "issue:43756", "accept": false, - "reason": "Mistral-3 dtype mismatch and Gemma3n variable-name collision are different issues." + "reason": "SwitchTransformers sparse layer creation and Smollm3 RoPE layer dropping are unrelated model-configuration bugs." }, { "left": "issue:43295", "right": "issue:45834", "accept": false, - "reason": "Processor/tokenizer regression and Kosmos2.5 long-OCR index error are unrelated." + "reason": "processor.tokenizer regression and Kosmos2.5 long OCR index error are different multimodal/tokenization failures." }, { - "left": "issue:44062", - "right": "issue:44488", + "left": "issue:43716", + "right": "issue:44008", "accept": false, - "reason": "`AddedToken` special-argument duplication is not the same as failing to load `cjvt/sleng-bert`." + "reason": "Mistral image preprocessor dtype mismatch and Gemma3n audio variable collision are unrelated model-specific bugs." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba and bfloat16 dtype mismatches in other models are different problems." + "reason": "Both mention SDPA/dtype/runtime, but Bamba torch.compile failure and SwitchTransformers/TimmWrapperModel bfloat16 mismatch are different code paths." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken special-argument conflict and inability to load cjvt/sleng-bert are not the same underlying tokenizer bug." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "Bamba SDPA compile failure and DAC forward/from_latents mismatch are unrelated." + "reason": "Bamba torch.compile+SDPA failure and DAC from_latents mismatch are unrelated model/runtime issues." }, { "left": "issue:43322", "right": "issue:45685", "accept": false, - "reason": "Llava-Next segfault and MPS histogram-on-int error in moe are different runtime bugs." + "reason": "Llava Next segmentation fault and MPS histogram not implemented for Int in MoE are different backend/model problems." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "LayoutLMv2 tokenizer padding/NER crash and Perceiver non-default resolution failure are not the same bug." + "reason": "LayoutLMv2 tokenizer crashes on NER/padding versus Perceiver non-default resolution classification failure are unrelated." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Both touch `_patch_mistral_regex`, but one is an offline `model_info()` call and the other is a backend-tokenizer attribute crash. Different concrete failures." + "reason": "Both involve tokenizer regex/hub behavior, but one is unconditional model_info() breaking offline mode and the other is a tokenizer backend attribute crash; different fixes." }, { "left": "issue:43577", "right": "issue:43818", "accept": false, - "reason": "BLIP2 dtype propagation and Video-LLaVA temporal-attention/weight-sharing issues are unrelated." + "reason": "BLIP2 dtype propagation and Video-LLaVA missing temporal attention/shared weights are unrelated multimodal architecture bugs." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and `trust_remote_code` missing-fields config loading are different bugs." + "reason": "Qwen3-MoE sliding_window and trust_remote_code AutoConfig missing fields are different configuration issues." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Runtime special-token post-processor refresh and Whisper `batch_decode` skip-special-tokens behavior are separate tokenizer issues." + "reason": "TokenizersBackend post-processor refresh on special-token changes and Whisper batch_decode skip_special_tokens behavior are different tokenizer APIs." }, { "left": "issue:43653", "right": "issue:43819", "accept": false, - "reason": "BigBird special-token registration and DAC latent/forward mismatch do not share an underlying cause." - }, - { - "left": "issue:43643", - "right": "issue:44877", - "accept": false, - "reason": "Both concern config loading, but one is missing fields from `trust_remote_code=True` and the other is strict config rejection for GraniteSpeech; not the same defect." + "reason": "BigBirdTokenizer special-token registration and DAC forward/from_latents mismatch are unrelated." } ] }, @@ -4921,7 +4918,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:30064", "issue:34634", @@ -4934,14 +4931,13 @@ "issue:43577", "issue:43582", "issue:43606", + "issue:43643", "issue:43644", - "issue:43650", "issue:43720", "issue:43749", "issue:43782", "issue:43825", "issue:43827", - "issue:43906", "issue:43994", "issue:44060", "issue:44186", @@ -4957,7 +4953,7 @@ "issue:44671", "issue:44805", "issue:44821", - "issue:44857", + "issue:44877", "issue:44936", "issue:44977", "issue:44991", @@ -4973,12 +4969,13 @@ "issue:45834" ], "soft_pairs": [ + "issue:43643|issue:44877", "issue:43540|issue:45381", "issue:44448|issue:44671", "issue:43782|issue:44977", "issue:45584|issue:45834", - "issue:44561|issue:45020", "issue:43644|issue:43749", + "issue:44561|issue:45020", "issue:43825|issue:43994", "issue:44485|issue:44509", "issue:44821|issue:45084", @@ -4999,218 +4996,204 @@ "issue:43720|issue:45072", "issue:45081|issue:45406", "issue:43749|issue:44291", - "issue:44060|issue:44368", - "issue:43650|issue:43906", - "issue:43582|issue:44857" + "issue:44060|issue:44368" ], - "prepared_review_unit_hash": "2c65e415db7bfaa447d8dba6a8e77d8b2db2cb9a18218f8755066308188819f6", + "prepared_review_unit_hash": "bebac7435379fda6964eeee8a05a66da5814ddd5a78e9a888179d4ca86619093", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36471, - "estimated_input_tokens": 9118, - "estimated_eval_tokens": 18492 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35675, + "estimated_input_tokens": 8919, + "estimated_eval_tokens": 18094 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated bug reports across different models, loaders, trainers, and docs. The only strong duplicate-like pair is the Qwen2.5-VL position-id regression in v5.3.0, where two reports appear to describe the same underlying video/image position encoding bug.", - "confidence": 0.87, - "canonical_issue_reason": "issue:45325 is the clearest, most root-cause-oriented report in the only likely duplicate pair: it names the shared Qwen2.5-VL `get_rope_index` / position-id bug directly and is specific enough to anchor triage.", + "summary": "The cluster is mostly a set of unrelated Transformers bugs with only loose thematic overlap around v5 regressions, loading, and processor/tokenizer issues. I do not see any soft pair that is clearly the same underlying bug or change.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45020 is the best broad umbrella candidate because it covers the recurring theme of recent-version breakages around remote_code/model loading, but it is still only a partial fit and not a true duplicate of the whole set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45325 is the best overall issue candidate because it is the most precise representative of the cluster\u2019s only true duplicate-style bug and is more actionable than the broader follow-up report.", + "best_issue_reason": "issue:45020 is the most representative open issue for the cluster\u2019s shared theme of v5 regressions affecting model loading and remote-code models.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config/loading behavior, but one is about missing fields from trust_remote_code and the other is strict config blocking granite_speech; different failure modes and targets." + }, { "left": "issue:43540", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen video-input failures, but they involve different model families and symptoms; too broad to treat as the same concrete bug." + "reason": "Different Qwen model families and different bugs: video processing failure vs still-image RoPE/position_id scaling." }, { "left": "issue:44448", "right": "issue:44671", "accept": false, - "reason": "Both are version-vs-v5 behavior regressions, but they affect different models and different outputs; not the same underlying defect." + "reason": "Both are output regressions, but they affect different models and tasks (Pegasus generation vs CamemBERT masked LM)." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Different Qwen models and different failure modes (`from_pretrained` weight_only error vs flash-attention generation issue); not mergeable as one bug." + "reason": "Different code paths: from_pretrained weight_only loading error vs flash-attention generation issue." }, { "left": "issue:45584", "right": "issue:45834", "accept": false, - "reason": "Whisper empty-transcription handling and Kosmos2.5 OCR index errors are unrelated model-specific bugs." + "reason": "Whisper empty transcription handling and Kosmos2.5 long-OCR index errors are unrelated bugs." }, { - "left": "issue:44561", - "right": "issue:45020", + "left": "issue:43644", + "right": "issue:43749", "accept": false, - "reason": "Both mention `trust_remote_code`, but one is a specific removed helper (`is_torch_fx_available`) while the other is a broad recent-regression report; not enough to prove the same code-path bug." + "reason": "Both concern loading/state handling, but junk non-persistent buffers and FSDP CPU RAM-efficient loading are not the same concrete bug." }, { - "left": "issue:43644", - "right": "issue:43749", + "left": "issue:44561", + "right": "issue:45020", "accept": false, - "reason": "A junk non-persistent-buffer initialization issue and an FSDP CPU RAM-efficient loading bug are different loading problems." + "reason": "44561 is a specific regression from removing is_torch_fx_available; 45020 is a broader umbrella for remote_code breakages, not the same concrete issue." }, { "left": "issue:43825", "right": "issue:43994", "accept": false, - "reason": "Pipeline task-removal messaging and SigLIP2 model/processor mismatch are unrelated." + "reason": "One is a pipeline error message around removed translation tasks; the other is a SigLIP2 docs/model mismatch plus quantization failure." }, { "left": "issue:44485", "right": "issue:44509", "accept": false, - "reason": "Both concern GLM/docs-style discussion around RoPE or removed pipeline tasks, but they are not the same underlying bug or change." + "reason": "GLM-5 RoPE implementation is unrelated to stale docs that still mention removed pipeline tasks." }, { "left": "issue:44821", "right": "issue:45084", "accept": false, - "reason": "AutoImageProcessor URL loading and template-node compilation errors are unrelated." + "reason": "AutoImageProcessor URL loading and a template compilation TypeError are unrelated." }, { "left": "issue:39692", "right": "issue:45834", "accept": false, - "reason": "SigLIP2 docs errors and Kosmos2.5 OCR index errors are separate model issues." + "reason": "SigLIP2 documentation errors and Kosmos2.5 long OCR index errors are different problems." }, { "left": "issue:30064", "right": "issue:36331", "accept": false, - "reason": "Image processor segmentation-map handling and CustomTrainer loss signature mismatch are unrelated." + "reason": "Image processor void segmentation maps and CustomTrainer compute_loss kwargs are unrelated." }, { "left": "issue:41720", "right": "issue:44991", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert and tokenizer loading for est-roberta are unrelated." + "reason": "Qwen3 device-mapping CUDA assert and tokenizer loading for EMBEDDIA/est-roberta are different failures." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "LayoutLMv2 tokenizer padding/NER crashes and FastSpeech2Conformer tokenizer loading failure are separate tokenizer bugs." + "reason": "Different tokenizer/model issues: LayoutLMv2 NER/padding crash versus AutoTokenizer failing FastSpeech2ConformerTokenizer." }, { "left": "issue:43825", "right": "issue:43827", "accept": false, - "reason": "One is an incorrect error message, the other is stale docs; same broad area but not the same concrete bug/change." + "reason": "Both mention removed v5 pipeline tasks, but one is an incorrect runtime message and the other is stale docs; related, not the same bug." }, { "left": "issue:44479", "right": "issue:45834", "accept": false, - "reason": "Qwen VL video regression and Kosmos2.5 OCR index error are different model families and failure paths." + "reason": "Qwen video-input regression and Kosmos2.5 OCR index errors are separate model/input bugs." }, { "left": "issue:43577", "right": "issue:43582", "accept": false, - "reason": "Blip2 dtype propagation and Apple Silicon allocator warmup TypeError are unrelated." + "reason": "One is a dtype propagation bug in Blip2 loading; the other is an Apple Silicon TypeError in caching_allocator_warmup." }, { "left": "issue:44805", "right": "issue:44936", "accept": false, - "reason": "Mask shape IndexError and post-train evaluation failure are different training/runtime issues." + "reason": "Mask shape mismatch IndexError and trainer.evaluate() failing after train are not the same issue." }, { "left": "issue:44671", "right": "issue:45701", "accept": false, - "reason": "CamemBERT masked-LM regression and generic tokenization changes are not the same bug." + "reason": "CamemBERT masked-LM regressions and general tokenization changes are not the same concrete bug." }, { "left": "issue:43606", "right": "issue:45072", "accept": false, - "reason": "CPU offload device mismatch and bfloat16 dtype mismatch are different runtime/device issues." + "reason": "CPU-offload device mismatch for bark-small and bfloat16 dtype mismatches in other models are distinct failures." }, { "left": "issue:34634", "right": "issue:36010", "accept": false, - "reason": "BarkProcessor voice_preset and GenerationMixin import failure are unrelated." + "reason": "BarkProcessor voice_preset behavior and a GenerationMixin import error are unrelated." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "OmDet-Turbo processor size mismatch and dtype mismatch in inference are different bugs." + "reason": "OmDet-Turbo processor size mismatch and bfloat16 dtype mismatch in inference are different bugs." }, { "left": "issue:43782", "right": "issue:45325", "accept": false, - "reason": "Both are Qwen-related, but one is a `from_pretrained` weight-only error and the other is a position-id regression in Qwen2.5-VL; different code paths." + "reason": "Different Qwen-VL bugs: weight_only loading failure versus still-image temporal position_id scaling." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "Missing TensorFlow backend and Mistral regex patch crash are unrelated." + "reason": "Backend dependency packaging and a Mistral tokenizer regex crash are unrelated." }, { "left": "issue:43720", "right": "issue:45072", "accept": false, - "reason": "BitNet packed-weight loading and dtype mismatch issues are different loading/inference bugs." + "reason": "Packed-weight unpacking during accelerate loading is unrelated to dtype mismatch regressions." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "A Mistral tokenizer regex patch crash and Gemma4Processor attribute error are unrelated processor/tokenizer bugs." + "reason": "Both are attribute errors in tokenizer/processor internals, but they affect different components and causes." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "FSDP loading failure and `_is_hf_initialized` init-empty-weights TypeError are distinct model-loading regressions." + "reason": "Both involve loading/empty-weights paths, but FSDP CPU RAM-efficient loading and an unexpected _is_hf_initialized argument are distinct regressions." }, { "left": "issue:44060", "right": "issue:44368", "accept": false, - "reason": "Both mention tied-weights warnings, but they describe different models and different warning causes; not the same underlying defect." - }, - { - "left": "issue:43650", - "right": "issue:43906", - "accept": false, - "reason": "Placeholder issue text and an isolated reproduction report are not a duplicate pair." - }, - { - "left": "issue:43582", - "right": "issue:44857", - "accept": false, - "reason": "Apple Silicon allocator TypeError and LwDetrImageLoss AMP/CUDA crash are unrelated." - }, - { - "left": "issue:45325", - "right": "issue:45381", - "accept": true, - "reason": "These look like the same Qwen2.5-VL position-id / rope-index regression: one reports still-image temporal position scaling, the other reports wrong video vision_position_ids in the same v5.3.0 area." + "reason": "Both are tied-weights warnings, but one is an incorrect internal tying bug and the other is a user-facing config warning on a different model." } ] }, @@ -5232,7 +5215,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:34634", "issue:36010", @@ -5248,26 +5231,27 @@ "issue:43531", "issue:43550", "issue:43577", + "issue:43582", "issue:43638", "issue:43645", + "issue:43650", "issue:43653", "issue:43696", "issue:43697", "issue:43720", "issue:43742", "issue:43746", - "issue:43749", "issue:43819", "issue:43854", + "issue:43906", "issue:43927", "issue:44479", "issue:44554", "issue:44568", "issue:44589", "issue:44610", - "issue:44756", "issue:44811", - "issue:44849", + "issue:44857", "issue:44912", "issue:44936", "issue:44977", @@ -5280,23 +5264,24 @@ "issue:45488", "issue:45538", "issue:45600", - "issue:45701", "issue:45803" ], "soft_pairs": [ + "issue:43650|issue:43906", + "issue:43582|issue:44857", "issue:43262|issue:43819", "issue:43526|issue:43697", "issue:43526|issue:44554", "issue:45459|issue:45803", "issue:34634|issue:36331", "issue:45084|issue:45538", - "issue:43329|issue:45600", "issue:43742|issue:45020", + "issue:43329|issue:45600", "issue:43653|issue:44912", "issue:43638|issue:44936", "issue:43452|issue:44991", - "issue:43257|issue:43329", "issue:43746|issue:44811", + "issue:43257|issue:43329", "issue:44589|issue:45042", "issue:43257|issue:43696", "issue:43854|issue:44977", @@ -5304,214 +5289,230 @@ "issue:36010|issue:43645", "issue:39692|issue:44912", "issue:43819|issue:43927", - "issue:43720|issue:44610", "issue:43454|issue:43577", + "issue:43720|issue:44610", "issue:43550|issue:44912", "issue:44568|issue:45488", "issue:43531|issue:45042", - "issue:44568|issue:45356", "issue:43262|issue:44811", "issue:43329|issue:44479", "issue:36010|issue:36331", - "issue:43749|issue:44756", - "issue:44849|issue:45701" + "issue:44568|issue:45356" ], - "prepared_review_unit_hash": "20ef366be25be0683cbcdbc076db174b308a47f7810721dc1b235371519b07ac", + "prepared_review_unit_hash": "ea0bb5d84edaf897c24d727d7d33b49f4b7bb21f96ccdbea8c321e294b20f758", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37176, - "estimated_input_tokens": 9294, - "estimated_eval_tokens": 18844 + "serialized_chars": 37228, + "estimated_input_tokens": 9307, + "estimated_eval_tokens": 18870 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: most items are separate Transformers regressions across tokenizers, loading, audio/vision processors, training, and quantization. I did not find any soft pair that looks like the same underlying bug/change.", - "confidence": 0.78, - "canonical_issue_reason": "issue:45020 is the broadest umbrella among the set and best matches the dominant theme of recent-version breakages around loading/remote_code, but the cluster overall is not a tight duplicate set.", + "summary": "The soft pairs mostly overlap only at a broad subsystem level (tokenizers, audio, vision, loading, training) but describe different concrete failures, so none look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.92, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the best single representative because it is the most general, high-signal open issue describing version-induced breakage; it can subsume the broadest share of the nearby loading-regression reports, though not all of them.", + "best_issue_reason": "No single issue is a clear global canonical here; the set spans many unrelated bugs, so any choice would be arbitrary.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Completely unrelated: a vague request vs an isolated reproduction of a different upstream issue." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Different failures and code paths: Apple Silicon allocator TypeError vs CUDA AMP image-loss crash." + }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Both are audio-related, but one is a sampling-rate default in apply_chat_template and the other is a DAC latent reconstruction mismatch; different code paths and symptoms." + "reason": "Both audio-related, but one is chat-template sampling rate and the other is DAC latent decoding mismatch." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "Image processor label reduction bug vs RTDetrV2 output divergence in v5; both are vision issues but not the same defect." + "reason": "Different vision bugs in different models; no shared root cause is evident." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "Unrelated: BEiT image processor label handling vs MPS attention correctness when value/query head dims differ." + "reason": "Unrelated model families and failures; a processor label bug is not the same as an attention correctness issue." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Both involve broad exception handling, but they affect different components and failure modes; not the same bug." + "reason": "Both mention exception handling, but they are different bugs in different functions and should not be merged." }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "BarkProcessor voice_preset issue is unrelated to CustomTrainer.compute_loss signature mismatch." + "reason": "Different APIs and failure modes: Bark voice preset vs trainer compute_loss signature." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "Template-node compilation error vs CLIPTokenizer max length constant bug; different subsystems and failure types." + "reason": "Unrelated issues: template compilation error vs tokenizer max_length misconfiguration." }, { - "left": "issue:43329", - "right": "issue:45600", + "left": "issue:43742", + "right": "issue:45020", "accept": false, - "reason": "Video multimodal token counting bug vs stale auto_mappings config reference; no shared code-path." + "reason": "Both involve loading, but one is a specific MobileLLM key error and the other is a broad remote_code regression." }, { - "left": "issue:43742", - "right": "issue:45020", + "left": "issue:43329", + "right": "issue:45600", "accept": false, - "reason": "Both mention loading problems, but 43742 is a specific KeyError for one model while 45020 is a broad remote_code regression; too different to merge." + "reason": "Different areas: multimodal token counting vs stale auto_mapping references in CI." }, { "left": "issue:43653", "right": "issue:44912", "accept": false, - "reason": "Tokenizer special-token registration issue vs MXFP4 quantization loading/fallback; unrelated." + "reason": "Tokenizer special-token registration is unrelated to MXFP4 quantization loading fallback." }, { "left": "issue:43638", "right": "issue:44936", "accept": false, - "reason": "DeepSpeed ZeRO-3 / non-pretrained BERT index error vs trainer.evaluate() after train() failure; different behaviors and likely different root causes." + "reason": "Different trainer/deepspeed failures with different triggers and symptoms." }, { "left": "issue:43452", "right": "issue:44991", "accept": false, - "reason": "Both are from_pretrained/tokenizer loading regressions, but one is gguf_file handling and the other is a specific tokenizer load failure; not the same underlying bug." + "reason": "Both are model-loading/tokenizer issues, but the affected paths and reported bugs differ." }, { - "left": "issue:43257", - "right": "issue:43329", + "left": "issue:43746", + "right": "issue:44811", "accept": false, - "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed is unrelated to multimodal token counting in the video branch." + "reason": "Unrelated: PEFT local checkpoint loading vs Whisper batch_decode skip_special_tokens behavior." }, { - "left": "issue:43746", - "right": "issue:44811", + "left": "issue:43257", + "right": "issue:43329", "accept": false, - "reason": "Local checkpoint loading with PEFT adapters vs Whisper batch_decode skip_special_tokens handling; different models and code paths." + "reason": "Different bugs: Qwen3 MoE weight conversion/loading vs undefined video-token helper names." }, { "left": "issue:44589", "right": "issue:45042", "accept": false, - "reason": "Float8 storage lookup failure is unrelated to PIL backend requiring torchvision." + "reason": "Different incompatibilities: missing Float8 storage vs torchvision requirement in PIL image processors." }, { "left": "issue:43257", "right": "issue:43696", "accept": false, - "reason": "MoE weight conversion bug vs GPU OOM on GPT-oss-20b; not duplicates." + "reason": "Different Qwen3/OOM-loading issues with no shared root cause shown." }, { "left": "issue:43854", "right": "issue:44977", "accept": false, - "reason": "Model loading/test setup issue for GLM-4.7-Flash vs Qwen3.5 flash-attention generation bug; different models and root causes." + "reason": "Same broad generation/loading area, but different models and failure mechanisms." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "SigLIP2 zero probabilities and OmDet processor size mismatch are both vision issues, but they are distinct bugs." + "reason": "Both are vision-related, but one is zero probabilities and the other is processor/model input-size mismatch." }, { "left": "issue:36010", "right": "issue:43645", "accept": false, - "reason": "ImportError for GenerationMixin and Jupyter custom-model initialization breakage are separate compatibility problems." + "reason": "Different compatibility regressions: GenerationMixin import failure vs Jupyter custom-model initialization." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "Doc example/model-processor mismatch and quantization failure vs MXFP4 loading fallback; not the same issue." + "reason": "Documentation/example errors are not the same as MXFP4 quantization fallback behavior." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "DAC latent/forward mismatch is unrelated to DiaConfig losing custom token IDs on save/load." + "reason": "Different components and failures: DAC latent conversion vs Dia config save/load token IDs." }, { - "left": "issue:43720", - "right": "issue:44610", + "left": "issue:43454", + "right": "issue:43577", "accept": false, - "reason": "Packed-weight unpacking during accelerate loading vs OmDet input-size mismatch; no shared underlying defect." + "reason": "One is weight tying causing bad generation; the other is dtype propagation on load." }, { - "left": "issue:43454", - "right": "issue:43577", + "left": "issue:43720", + "right": "issue:44610", "accept": false, - "reason": "AyaVision lm_head tying bug vs BLIP2 dtype propagation bug; both loading/model-setup related but clearly different." + "reason": "Completely different subsystems: packed-weight loading vs image processor resolution mismatch." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "Qwen3-MoE sliding-window bug is unrelated to quantization fallback for git-oss-20b." + "reason": "Different model/runtime problems: torch.compile+SDPA vs quantization loading fallback." }, { "left": "issue:44568", "right": "issue:45488", "accept": false, - "reason": "Both are tokenizer regressions, but one concerns add_special_tokens/BOS-EOS behavior and the other changes pre-tokenizer selection; different root causes." + "reason": "Both tokenizer regressions, but different tokenizer classes and different broken behaviors." }, { "left": "issue:43531", "right": "issue:45042", "accept": false, - "reason": "Qwen3-MoE sliding-window issue and PIL/torchvision requirement regression are unrelated." - }, - { - "left": "issue:44568", - "right": "issue:45356", - "accept": false, - "reason": "Both are tokenizer regressions, but they affect different models and different mechanisms (special tokens vs codec/regex handling)." + "reason": "Unrelated model sliding-window bug vs image processor torchvision dependency regression." }, { "left": "issue:43262", "right": "issue:44811", "accept": false, - "reason": "Audio chat-template sampling-rate default and Whisper batch_decode skip_special_tokens are different audio-processing bugs." + "reason": "Both audio, but sampling-rate defaults and decode special-token handling are distinct bugs." }, { "left": "issue:43329", "right": "issue:44479", "accept": false, - "reason": "Both touch multimodal/video paths, but 43329 is an undefined-variable bug in token counting while 44479 is a broader v5 video-input regression across models." + "reason": "Possible thematic overlap on video VLMs, but the reports describe different regressions and are not clearly the same bug." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Different breakages: import path change vs trainer method signature change." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both tokenizer regressions, but on different models and different underlying tokenizer handling." } ] }, @@ -5533,12 +5534,10 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:28282", "issue:33357", "issue:34567", - "issue:34689", "issue:38175", "issue:40990", "issue:41720", @@ -5556,9 +5555,9 @@ "issue:43643", "issue:43697", "issue:43742", + "issue:43749", "issue:43756", "issue:43824", - "issue:43906", "issue:43927", "issue:43931", "issue:44062", @@ -5566,8 +5565,9 @@ "issue:44479", "issue:44488", "issue:44560", - "issue:44737", + "issue:44756", "issue:44821", + "issue:44849", "issue:44898", "issue:44912", "issue:44938", @@ -5580,15 +5580,18 @@ "issue:45381", "issue:45405", "issue:45538", - "issue:45588", + "issue:45701", "issue:45759", - "issue:45859" + "issue:45859", + "issue:45907" ], "soft_pairs": [ + "issue:43749|issue:44756", + "issue:44849|issue:45701", "issue:43643|issue:45759", "issue:34567|issue:40990", - "issue:43257|issue:43931", "issue:43329|issue:43450", + "issue:43257|issue:43931", "issue:43606|issue:45859", "issue:43257|issue:43756", "issue:43697|issue:45357", @@ -5597,239 +5600,237 @@ "issue:42915|issue:43742", "issue:43452|issue:43582", "issue:42915|issue:44821", + "issue:44987|issue:45907", "issue:33357|issue:34567", - "issue:44479|issue:45381", "issue:41720|issue:43540", + "issue:44479|issue:45381", "issue:42915|issue:45538", "issue:43927|issue:44912", "issue:42175|issue:43824", "issue:43317|issue:45538", "issue:43577|issue:45072", - "issue:43540|issue:44560", "issue:43540|issue:44479", + "issue:43540|issue:44560", "issue:44062|issue:44991", "issue:42175|issue:44938", "issue:45137|issue:45405", "issue:42175|issue:44488", - "issue:38175|issue:44898", - "issue:28282|issue:34689", - "issue:44737|issue:45588", - "issue:43906|issue:45381" + "issue:38175|issue:44898" ], - "prepared_review_unit_hash": "873d91a113fb041f078e12d7ffeb26db088a3584f7558b03c545b32a7cbd5e90", + "prepared_review_unit_hash": "1f59b41624637a42b01bf872abbbc812e7ff0642a4933cc8a809d5e35f04c3a7", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36815, - "estimated_input_tokens": 9204, - "estimated_eval_tokens": 18664 + "serialized_chars": 36619, + "estimated_input_tokens": 9155, + "estimated_eval_tokens": 18566 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly unrelated Transformers bug reports; only the Qwen2.5-VL video-input regression pair looks like a true duplicate.", - "confidence": 0.78, - "canonical_issue_reason": "issue:44479 is the best umbrella issue here: it clearly describes the broad version-specific video-input regression and names the affected Qwen model families.", + "summary": "Most pairs are clearly unrelated despite superficial theme overlap (often just the same subsystem/model family). One soft duplicate stands out: the Qwen video-input regression report and the qwen2.5-vl vision_position_ids report look like the same underlying bug.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44479 is the broadest, clearest report of the Qwen v5.3.0 video-input regression; issue:45381 appears to be the same bug narrowed to qwen2.5-vl/vision_position_ids.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the strongest standalone report, with the clearest regression framing and the broadest impact surface among the set.", + "best_issue_reason": "issue:44479 is the best canonical issue because it captures the full regression scope across affected Qwen video models, while still matching the specific qwen2.5-vl symptom in issue:45381.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Different loading problems: FSDP CPU/RAM-efficient loading vs Apple Silicon mmap/OOM mitigation." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Different bugs: Qwen3.5 output_hidden_states regression vs a tokenizer/version change report." + }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "Both involve config/model-loading behavior, but one is AutoConfig field loss and the other is AutoModelForCausalLM text_config unwrapping; different bugs." + "reason": "Different config-loading failures: missing fields from trust_remote_code vs composite Qwen text_config unwrapping." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "Unrelated symptoms: trainer token counting versus absurd perplexity on a model eval run." + "reason": "Unrelated: TrainerState token counter vs high perplexity on a specific model/dataset." }, { - "left": "issue:43257", - "right": "issue:43931", + "left": "issue:43329", + "right": "issue:43450", "accept": false, - "reason": "Both are Qwen3 loading issues, but one is MoE weight conversion with accelerate/deepspeed and the other is a Qwen3-VL shape mismatch; different code paths." + "reason": "Both are video-related, but one is a multimodal token-counting code bug and the other is batched processor shape handling." }, { - "left": "issue:43329", - "right": "issue:43450", + "left": "issue:43257", + "right": "issue:43931", "accept": false, - "reason": "Both touch video handling, but one is an undefined-variable bug in token counting and the other is batched processor output shape; not the same defect." + "reason": "Both involve Qwen3 loading, but one is accelerate/deepspeed weight conversion and the other is a weight-shape mismatch for Qwen3-VL." }, { "left": "issue:43606", "right": "issue:45859", "accept": false, - "reason": "Both mention CPU offload/device issues, but they affect different models and likely different modules; not enough evidence of one root cause." + "reason": "Same general CPU-offload area, but different models and concrete failures." }, { "left": "issue:43257", "right": "issue:43756", "accept": false, - "reason": "Distinct Qwen3-related problems: MoE weight conversion versus RoPE layer retention." + "reason": "Different model-specific issues: Qwen3 MOE weight conversion vs Smollm3 RoPE layer dropping." }, { "left": "issue:43697", "right": "issue:45357", "accept": false, - "reason": "One is an inference-output regression in RTDetrV2, the other is a save_pretrained key serialization problem for Qwen3.5." + "reason": "Different subsystems: RTDetrV2 output regression vs Qwen3.5 save_pretrained key naming." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "A tokenizer/model load regression for a specific repo versus an unrelated CLIPTokenizer max-length bug." + "reason": "Different tokenizer/model-loading problems; only loosely related by loading behavior." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "init_empty_weights argument handling and PIL backend torchvision dependency are separate failures." + "reason": "Different failures: init_empty_weights signature mismatch vs PIL backend torchvision dependency handling." }, { "left": "issue:42915", "right": "issue:43742", "accept": false, - "reason": "Different failures: FineGrainedFP8Config on Qwen3Moe versus a key error loading MobileLLM." + "reason": "Different model/config bugs: FineGrainedFP8Config vs MobileLLM loading key error." }, { "left": "issue:43452", "right": "issue:43582", "accept": false, - "reason": "GGUF loading breakage versus an Apple Silicon caching_allocator_warmup TypeError; unrelated." + "reason": "Different domains: GGUF loader breakage vs AppleSilicon allocator warmup TypeError." }, { "left": "issue:42915", "right": "issue:44821", "accept": false, - "reason": "Different areas: quantization/config handling versus AutoImageProcessor URL loading." + "reason": "Different issues: Qwen3Moe quantization/config vs loading AutoImageProcessor from a URL." }, { - "left": "issue:33357", - "right": "issue:34567", + "left": "issue:44987", + "right": "issue:45907", "accept": false, - "reason": "MacOS bus error on CLIP model loading is unrelated to TrainerState token counting." + "reason": "Different code paths: model load failure vs list_repo_files failing to forward revision." }, { - "left": "issue:44479", - "right": "issue:45381", - "accept": true, - "reason": "Same version and same Qwen2.5-VL video-input path; 45381's wrong vision_position_ids appears to be the same underlying video regression described more broadly in 44479." + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Completely unrelated: MacOS CLIP bus error vs TrainerState token counting." }, { "left": "issue:41720", "right": "issue:43540", "accept": false, - "reason": "Both are Qwen-related runtime failures, but one is a cudaErrorAssert under auto device mapping and the other is a video-input ValueError." + "reason": "Both mention Qwen and CUDA/video, but one is device mapping on A800 and the other is video-input processing in Qwen3OmniMoe." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Both describe the same Qwen video-input regression; 45381 is the specific qwen2.5-vl manifestation of the broader bug in 44479." }, { "left": "issue:42915", "right": "issue:45538", "accept": false, - "reason": "No meaningful overlap beyond being model-related bugs." + "reason": "Unrelated: Qwen3Moe FP8 config failure vs CLIPTokenizer max_length issue." }, { "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "Custom token IDs lost on save/load is a tokenizer/config persistence bug; MXFP4 quantization fallback is a separate model-loading issue." + "reason": "Different loading/config bugs: DiaConfig save/load token IDs vs MXFP4 quantization fallback." }, { "left": "issue:42175", "right": "issue:43824", "accept": false, - "reason": "Packaging/backend dependency issue versus an import failure for a specific Qwen VL class." + "reason": "Unrelated: TensorFlow extra installation problem vs missing Qwen2_5_VL import." }, { "left": "issue:43317", "right": "issue:45538", "accept": false, - "reason": "Device-map offload loading failure and CLIPTokenizer max_length behavior are unrelated." + "reason": "Different issues: device_map/offload loading failure vs tokenizer max_length default." }, { "left": "issue:43577", "right": "issue:45072", "accept": false, - "reason": "Both are dtype complaints, but they concern different models and different failure modes." + "reason": "Both are dtype-related, but different models and different failure modes; not the same concrete bug." }, { "left": "issue:43540", - "right": "issue:44560", + "right": "issue:44479", "accept": false, - "reason": "Both involve video input, but one is a ValueError in Qwen3OmniMoe and the other is a StopIteration in Qwen3-vl-embedding; not clearly the same bug." + "reason": "Both are video-input reports, but the model and failure mode differ; not enough evidence of one underlying bug." }, { "left": "issue:43540", - "right": "issue:44479", + "right": "issue:44560", "accept": false, - "reason": "Shared theme of video processing, but the model families and reported symptoms differ; not enough evidence of one concrete duplicate." + "reason": "Different Qwen video-input failures affecting different models and error paths." }, { "left": "issue:44062", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading problems, but one is an AddedToken keyword conflict and the other is a repo-specific est-roberta failure." + "reason": "Different tokenizer-loading issues; the model-specific symptom is not the same as the AddedToken keyword bug." }, { "left": "issue:42175", "right": "issue:44938", "accept": false, - "reason": "Missing TensorFlow backend in a torch extra and Python 3.14 load failure are different environment issues." + "reason": "Unrelated: backend installation issue vs Python 3.14 load failure." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "DeepSpeed ZeRO3 deque error versus an unreleased PEFT version bump; unrelated." + "reason": "Completely unrelated: DeepSpeed ZeRO3 deque error vs PEFT version pin mismatch." }, { "left": "issue:42175", "right": "issue:44488", "accept": false, - "reason": "Packaging/backend dependency issue versus a model load failure for cjvt/sleng-bert." + "reason": "Unrelated: TensorFlow backend packaging vs a specific model load failure." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "Different image-processing bugs: unexpected zero probabilities versus Perceiver non-default resolution failure." - }, - { - "left": "issue:28282", - "right": "issue:34689", - "accept": false, - "reason": "Old PyTorch-import error versus a newer Llama 3.2 vision model-loading breakage; unrelated." - }, - { - "left": "issue:44737", - "right": "issue:45588", - "accept": false, - "reason": "CPU-side XLNet position encoding bug versus a flash_attention sinkless-model AttributeError." - }, - { - "left": "issue:43906", - "right": "issue:45381", - "accept": false, - "reason": "Isolated reproduction of another issue versus a specific Qwen2.5-VL video regression; no direct match." + "reason": "Different vision-model bugs: zero probabilities on SigLIP2 vs Perceiver non-default resolution failure." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The one accepted pair, issue:44479 vs issue:45381, is plausibly the same Qwen2.5-VL video regression based on the titles alone, while the other pairwise rejections are cautious rather than overstated." + "feedback": "The canonicalization is grounded in the packet: issue:44479 is the broad Qwen v5.3.0 video-input regression, and issue:45381 is a narrower qwen2.5-vl manifestation of the same symptom. The soft-edge verdicts are generally conservative and stay within what the titles support; no pair is overstated as a duplicate without evidence." }, "evaluator_used": true, "retried": false, @@ -5848,12 +5849,12 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:24643", "issue:28282", "issue:29127", "issue:34567", + "issue:34689", "issue:36331", "issue:41762", "issue:42915", @@ -5862,7 +5863,6 @@ "issue:43526", "issue:43531", "issue:43540", - "issue:43577", "issue:43582", "issue:43643", "issue:43688", @@ -5872,6 +5872,7 @@ "issue:43749", "issue:43756", "issue:43782", + "issue:43906", "issue:43994", "issue:44062", "issue:44291", @@ -5880,11 +5881,10 @@ "issue:44514", "issue:44561", "issue:44589", - "issue:44625", "issue:44704", + "issue:44737", "issue:44792", "issue:44821", - "issue:44877", "issue:44898", "issue:44936", "issue:44964", @@ -5896,21 +5896,25 @@ "issue:45381", "issue:45405", "issue:45479", + "issue:45588", "issue:45600", "issue:45823" ], "soft_pairs": [ - "issue:42915|issue:43749", + "issue:28282|issue:34689", + "issue:44737|issue:45588", "issue:43742|issue:44291", - "issue:43756|issue:45325", + "issue:42915|issue:43749", + "issue:43906|issue:45381", "issue:43526|issue:45479", "issue:28282|issue:29127", "issue:43540|issue:45823", + "issue:43756|issue:45325", "issue:43582|issue:43782", "issue:43493|issue:43994", "issue:34567|issue:36331", - "issue:44062|issue:45081", "issue:44291|issue:44821", + "issue:44062|issue:45081", "issue:43643|issue:45375", "issue:43452|issue:44488", "issue:44792|issue:44964", @@ -5918,213 +5922,210 @@ "issue:43742|issue:44589", "issue:43531|issue:44821", "issue:45405|issue:45600", - "issue:43688|issue:43749", "issue:43697|issue:45216", + "issue:43688|issue:43749", "issue:44484|issue:44704", - "issue:44514|issue:45381", "issue:43720|issue:44898", + "issue:44514|issue:45381", "issue:41762|issue:44936", - "issue:43643|issue:44561", - "issue:24643|issue:29127", - "issue:43452|issue:43577", - "issue:44625|issue:44877" + "issue:43643|issue:44561" ], - "prepared_review_unit_hash": "aa28384cadb56ce22f245ad58e0cd5e19ee0535c3d13a6c8e341e6a59dfefc61", + "prepared_review_unit_hash": "6d3eca9783ad63ca7a1d855bbf362c4b485c454df9fd189ef54724c4456ff49c", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36325, - "estimated_input_tokens": 9082, - "estimated_eval_tokens": 18420 + "serialized_chars": 36379, + "estimated_input_tokens": 9095, + "estimated_eval_tokens": 18446 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose mix of unrelated Transformers issues across model loading, configuration, training, image/video processing, and distributed/runtime behavior. None of the soft pairs appear to describe the same underlying bug or a PR-worthy mergeable duplicate.", - "confidence": 0.96, - "canonical_issue_reason": "No single issue is a safe canonical: the items span distinct models, code paths, and failure modes, so none clearly subsumes the others.", + "summary": "This cluster is heterogeneous: the proposed pairs mostly share only broad areas like loading, config, trainer, or multimodal code, but not the same concrete bug/change. I would not merge any of the soft edges.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43749 is the highest-signal issue in the set, with the most discussion and inbound references, and it represents a broad, user-impacting regression more than the other reports.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a strong global representative; the cluster is too heterogeneous to pick one as a reliable canonical exemplar.", + "best_issue_reason": "issue:43749 is the best representative issue here because it is broad, well-discussed, and likely to anchor triage better than the narrower one-off reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:42915", - "right": "issue:43749", + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Both are model-loading failures, but one is a missing PyTorch dependency message and the other is a specific Llama 3.2 Vision breakage; different bugs." + }, + { + "left": "issue:44737", + "right": "issue:45588", "accept": false, - "reason": "Different problems: Qwen3Moe FP8 config failure vs FSDP CPU RAM-efficient loading regression." + "reason": "Different code paths: XLNet CPU tensor placement vs. flash_attention sink/s_aux handling." }, { "left": "issue:43742", "right": "issue:44291", "accept": false, - "reason": "Different load-time bugs: MobileLLM key error vs init_empty_weights passing an unexpected argument." + "reason": "A key-error while loading a specific model is not the same as an init_empty_weights signature regression." }, { - "left": "issue:43756", - "right": "issue:45325", + "left": "issue:42915", + "right": "issue:43749", + "accept": false, + "reason": "Both involve advanced loading/runtime settings, but one is Qwen3Moe FP8 behavior and the other is FSDP CPU RAM-efficient loading; distinct failures." + }, + { + "left": "issue:43906", + "right": "issue:45381", "accept": false, - "reason": "Different models and behaviors: Smollm3 RoPE layer drop vs Qwen2.5-VL still-image RoPE scaling." + "reason": "The first is an isolated reproduction of an existing issue; the second is a Qwen2.5-VL vision position-id bug. No concrete match." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "One is BEiT image processor label reduction; the other is sequence-classification loss degeneracy." + "reason": "BEiT image label reduction and sequence-classification loss degeneracy are unrelated behaviors." }, { "left": "issue:28282", "right": "issue:29127", "accept": false, - "reason": "Different issues: missing PyTorch import vs clearer LayoutLMv3 box-count error messaging." + "reason": "ImportError for missing PyTorch is unrelated to LayoutLMv3 box-validation error messaging." }, { "left": "issue:43540", "right": "issue:45823", "accept": false, - "reason": "Different models and code paths: Qwen3OmniMoe video processing vs Gemma4 PLE device placement." + "reason": "Different models and different failures: Qwen3OmniMoe video processing vs Gemma4 device placement mismatch." }, { - "left": "issue:43582", - "right": "issue:43782", + "left": "issue:43756", + "right": "issue:45325", "accept": false, - "reason": "Different runtime/model bugs: Apple Silicon warmup TypeError vs Qwen3VL weight_only load error." + "reason": "Both mention RoPE/position handling, but they affect different models and different bugs (layer dropping vs. temporal scaling)." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError is unrelated to Qwen3VL weight_only loading." }, { "left": "issue:43493", "right": "issue:43994", "accept": false, - "reason": "Both involve SigLIP2, but one is HF-vs-JAX output discrepancy and the other is AutoModel/pipeline nonsense outputs; not the same concrete bug." + "reason": "Both concern SigLIP2, but one is a HF-vs-JAX discrepancy and the other is bad outputs with AutoModel/pipeline; not clearly the same defect." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "Trainer state token counting bug vs CustomTrainer compute_loss signature mismatch." + "reason": "TrainerState token counting not updating is not the same as CustomTrainer.compute_loss receiving an unexpected kwarg." }, { - "left": "issue:44062", - "right": "issue:45081", + "left": "issue:44291", + "right": "issue:44821", "accept": false, - "reason": "Tokenizers AddedToken duplicate-special bug is unrelated to the Mistral regex patch crash." + "reason": "init_empty_weights/_is_hf_initialized and loading AutoImageProcessor from URL are different failure modes." }, { - "left": "issue:44291", - "right": "issue:44821", + "left": "issue:44062", + "right": "issue:45081", "accept": false, - "reason": "Different loading paths: init_empty_weights argument error vs AutoImageProcessor URL loading." + "reason": "Tokenizer AddedToken kwarg collision and Mistral regex patch crashing on backend_tokenizer are unrelated tokenizer bugs." }, { "left": "issue:43643", "right": "issue:45375", "accept": false, - "reason": "Generic trust_remote_code config passthrough issue is not the same as Qwen3_5MoeVisionConfig missing one field under @strict." + "reason": "Both involve config fields, but one is AutoConfig losing fields under trust_remote_code and the other is a specific Qwen3_5MoeVisionConfig field being dropped by strict parsing." }, { "left": "issue:43452", "right": "issue:44488", "accept": false, - "reason": "GGUF auto-loading regression is unrelated to a specific model load failure for cjvt/sleng-bert." + "reason": "GGUF loading regression and a model-specific load failure are too different to be duplicates." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "Janus test failure on image generation and Phi-4 multimodal loading are different model-specific problems." + "reason": "Both are multimodal load/test failures, but they target different models and different symptoms." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "PIL backend torchvision requirement regression is unrelated to the Mistral tokenizer regex crash." + "reason": "PIL image processors requiring torchvision and a Mistral tokenizer regex crash are unrelated." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "MobileLLM key error and missing Float8 storage are different loading/runtime failures." + "reason": "A MobileLLM key error and missing Float8 storage support are different loading/runtime issues." }, { "left": "issue:43531", "right": "issue:44821", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to AutoImageProcessor URL loading." + "reason": "Qwen3-MoE sliding_window behavior and AutoImageProcessor URL loading are unrelated." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "One is PEFT version pinning; the other is stale auto_mappings references to removed configs." + "reason": "A version pin on PEFT and stale auto_mappings references to removed configs are different maintenance issues." }, { - "left": "issue:43688", - "right": "issue:43749", + "left": "issue:43697", + "right": "issue:45216", "accept": false, - "reason": "Auxiliary-loss normalization bug is unrelated to the FSDP CPU RAM-efficient loading regression." + "reason": "RTDetrV2 output divergence and Qwen3.5 save_pretrained regression are unrelated." }, { - "left": "issue:43697", - "right": "issue:45216", + "left": "issue:43688", + "right": "issue:43749", "accept": false, - "reason": "RTDetrV2 output drift and Qwen3.5 save_pretrained checkpoint corruption are separate regressions." + "reason": "Aux-loss normalization in OLMoE/GPT Oss is unrelated to FSDP CPU RAM-efficient loading." }, { "left": "issue:44484", "right": "issue:44704", "accept": false, - "reason": "save_pretrained shard-size question is unrelated to AutoProcessor not forwarding kwargs to cached_file." + "reason": "save_pretrained shard-size behavior and AutoProcessor kwarg forwarding are different API issues." }, { - "left": "issue:44514", - "right": "issue:45381", + "left": "issue:43720", + "right": "issue:44898", "accept": false, - "reason": "Both touch Qwen2.5-VL, but one crashes in apply_chat_template batching and the other miscomputes video vision position ids." + "reason": "BitNet packed-weight unpacking during accelerate loading and Perceiver non-default-resolution classification are unrelated." }, { - "left": "issue:43720", - "right": "issue:44898", + "left": "issue:44514", + "right": "issue:45381", "accept": false, - "reason": "BitNet packed-weight loading bug is unrelated to Perceiver non-default resolution failure." + "reason": "Both are Qwen2.5-VL-related, but one is batched chat-template padding and the other is video vision_position_ids; not the same bug." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "Gemma3 ZeRO-3 loading index error and trainer.evaluate() after train() are different code paths." + "reason": "Gemma3 ZeRO-3 loading index error and trainer.evaluate() after train() are different failures." }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "Both mention trust_remote_code, but the roots differ: missing config fields vs removal of is_torch_fx_available." - }, - { - "left": "issue:24643", - "right": "issue:29127", - "accept": false, - "reason": "DeepSpeed weight dimensionality error is unrelated to LayoutLMv3 box-validation messaging." - }, - { - "left": "issue:43452", - "right": "issue:43577", - "accept": false, - "reason": "GGUF auto-loading breakage is unrelated to BLIP2 dtype propagation." - }, - { - "left": "issue:44625", - "right": "issue:44877", - "accept": false, - "reason": "Qwen3.5 num_labels propagation and granite_speech strict config loading are distinct config issues." + "reason": "Missing config fields under trust_remote_code and removal of is_torch_fx_available breaking remote-code models are separate compatibility problems." } ] }, @@ -6146,9 +6147,11 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ + "issue:24643", "issue:28282", + "issue:29127", "issue:30064", "issue:32090", "issue:33357", @@ -6156,7 +6159,6 @@ "issue:35141", "issue:38175", "issue:41720", - "issue:43122", "issue:43295", "issue:43329", "issue:43452", @@ -6176,14 +6178,13 @@ "issue:44442", "issue:44464", "issue:44466", - "issue:44479", "issue:44514", - "issue:44554", "issue:44568", "issue:44625", "issue:44743", "issue:44811", "issue:44843", + "issue:44877", "issue:44936", "issue:44977", "issue:44991", @@ -6198,266 +6199,252 @@ "issue:45823" ], "soft_pairs": [ + "issue:24643|issue:29127", + "issue:43452|issue:43577", + "issue:44625|issue:44877", "issue:43452|issue:44843", - "issue:43295|issue:45356", "issue:44466|issue:45005", + "issue:43295|issue:45356", "issue:44514|issue:45290", "issue:43819|issue:44811", - "issue:43653|issue:44568", "issue:44464|issue:44743", - "issue:43688|issue:45440", + "issue:43653|issue:44568", "issue:44936|issue:45823", "issue:30064|issue:33666", + "issue:43688|issue:45440", "issue:38175|issue:43295", - "issue:43688|issue:45704", "issue:44361|issue:44442", + "issue:43688|issue:45704", "issue:43653|issue:44361", - "issue:41720|issue:43906", "issue:28282|issue:32090", - "issue:43577|issue:43697", + "issue:41720|issue:43906", "issue:28282|issue:33357", + "issue:43577|issue:43697", "issue:43646|issue:43749", - "issue:43688|issue:45701", "issue:28282|issue:35141", + "issue:43688|issue:45701", "issue:44843|issue:44991", - "issue:44977|issue:45356", "issue:43531|issue:43742", "issue:43653|issue:43927", - "issue:43329|issue:45325", "issue:43550|issue:43927", "issue:44464|issue:44977", - "issue:43577|issue:45588", - "issue:43577|issue:44554", - "issue:44479|issue:44625", - "issue:43122|issue:43906", - "issue:43550|issue:44361" + "issue:43329|issue:45325", + "issue:43577|issue:45588" ], - "prepared_review_unit_hash": "b13921e73955c4f936a95f3cb9959daf1fb56b646bdef169b6566ea689146ccd", + "prepared_review_unit_hash": "28c4afded6bdf549430a6140a208ba05460ceeea05d35ef782c05e6932d4b538", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37796, - "estimated_input_tokens": 9449, - "estimated_eval_tokens": 19154 + "soft_pair_count": 31, + "serialized_chars": 37184, + "estimated_input_tokens": 9296, + "estimated_eval_tokens": 18848 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No soft edges look like true duplicates. Most pairs share only a broad theme (tokenization, multimodal, training, or v5 regressions) but fail on concrete symptom/code-path overlap. The most representative issue in this set is the broad v5 custom-model initialization regression (43646).", - "confidence": 0.79, - "canonical_issue_reason": "issue:43646 is the broadest and most upstream-looking regression report here, centered on custom model initialization breakage in v5, so it is the best single representative issue for this mixed set.", + "summary": "This looks like a noisy mix of mostly unrelated issue reports, with only loose thematic overlap around tokenizer/config/processor regressions in v5. I do not see any soft pair that is clearly the same underlying bug or change.", + "confidence": 0.69, + "canonical_issue_reason": "issue:44843 is the clearest concrete regression in a shared high-impact code path (`AutoTokenizer.from_pretrained` / tokenizer patching) and is representative of the broader v5 tokenizer-loading theme in this set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 has the clearest generalized regression framing and can serve as the most useful umbrella representative among otherwise unrelated reports.", + "best_issue_reason": "issue:44843 is the most central and actionable issue among the loosely related tokenizer/config regressions, with a specific failure mode and an obvious shared entry point.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "Different domains and failure modes: DeepSpeed training weight-shape error vs LayoutLMv3 box/clarity issue." + }, { "left": "issue:43452", - "right": "issue:44843", + "right": "issue:43577", "accept": false, - "reason": "Both are tokenizer/model loading regressions, but one is gguf_file handling and the other is an offline-mode _patch_mistral_regex bug; different failure points." + "reason": "One is gguf/AutoTokenizer-Model loading breakage; the other is dtype propagation in BLIP2. Not the same bug." }, { - "left": "issue:43295", - "right": "issue:45356", + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config propagation/loading, but they are different fields and different failure paths." + }, + { + "left": "issue:43452", + "right": "issue:44843", "accept": false, - "reason": "Both are tokenizer-related, but one is custom processor.tokenizer/image passthrough and the other is Kimi codec / warning behavior; not the same bug." + "reason": "Both touch tokenizer loading, but one is gguf_file support and the other is an offline-mode Mistral regex/model_info regression." }, { "left": "issue:44466", "right": "issue:45005", "accept": false, - "reason": "Both mention tied weights, but one is device-dependent lm_head serialization and the other is translation-model weight tying behavior; different code paths." + "reason": "Related tied-weights theme, but one is device-dependent lm_head.weight serialization and the other is broader translation-model tied-weight behavior; not clearly one concrete bug." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Both are regressions, but one is processor/tokenizer API breakage and the other is Kimi codec/regex warnings. Different code paths." }, { "left": "issue:44514", "right": "issue:45290", "accept": false, - "reason": "Different apply_chat_template crash cases: batched padding=False versus assistant tool-call messages with no content." + "reason": "Both crash in chat-template handling, but the triggers are different (batched padding vs tool-call messages with no content)." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "Unrelated functionality: DAC latent decoding mismatch versus Whisper processor.batch_decode skip_special_tokens handling." - }, - { - "left": "issue:43653", - "right": "issue:44568", - "accept": false, - "reason": "Both involve special tokens, but one is BigBird mask-token registration and the other is MDeBERTa BOS/EOS insertion; different bugs." + "reason": "Different components entirely: DAC latent decoding vs Whisper processor batch_decode behavior." }, { "left": "issue:44464", "right": "issue:44743", "accept": false, - "reason": "Both are generation-related, but chunked compiled-forward inconsistency is not the same as recurrent-state reset with cache in Qwen3-MoE." + "reason": "Both concern generation behavior, but one is compiled forward inconsistency and the other is recurrent-state reset with cache. Different bugs." }, { - "left": "issue:43688", - "right": "issue:45440", + "left": "issue:43653", + "right": "issue:44568", "accept": false, - "reason": "Both are MoE-related, but one is auxiliary-loss normalization and the other is divergence from the remote DeepSeekV3 implementation." + "reason": "Both are special-token-related tokenizer issues, but they affect different tokenizers and different code paths." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "A train/eval lifecycle failure and a Gemma4 PLE device-mismatch forward bug are different problems." + "reason": "Training/eval lifecycle bug vs device-mapping forward mismatch in Gemma4 PLE. Not the same issue." }, { "left": "issue:30064", "right": "issue:33666", "accept": false, - "reason": "Image-processor segmentation handling is unrelated to Qwen2-VL multi-GPU training." + "reason": "Both are multimodal-related at a high level, but one is segmentation map processing and the other is Qwen2-VL multi-GPU training." }, { - "left": "issue:38175", - "right": "issue:43295", + "left": "issue:43688", + "right": "issue:45440", "accept": false, - "reason": "A SigLIP zero-probability issue is not the same as a processor.tokenizer regression in custom model code." + "reason": "Both are MoE-adjacent, but one is auxiliary-loss normalization and the other is DeepSeekV3 implementation divergence." }, { - "left": "issue:43688", - "right": "issue:45704", + "left": "issue:38175", + "right": "issue:43295", "accept": false, - "reason": "Auxiliary-loss normalization in MoE models is unrelated to T5's apex.FusedRMSNorm memory leak." + "reason": "Different symptoms and subsystems: SigLIP2 zero probabilities vs processor/tokenizer regression." }, { "left": "issue:44361", "right": "issue:44442", "accept": false, - "reason": "Different tokenizer failures affecting different tokenizer classes and loading paths." + "reason": "Both are tokenizer-loading failures, but for different tokenizer classes and likely different parsing issues." }, { - "left": "issue:43653", - "right": "issue:44361", + "left": "issue:43688", + "right": "issue:45704", "accept": false, - "reason": "Shared tokenizer theme only; mask-token special-token registration and MLukeTokenizer AttributeError are different failures." + "reason": "Aux-loss normalization bug vs T5 silently using apex RMSNorm memory-leak path. Not the same underlying problem." }, { - "left": "issue:41720", - "right": "issue:43906", + "left": "issue:43653", + "right": "issue:44361", "accept": false, - "reason": "Qwen3 auto-device-map cuda assert is not the same concrete bug as an isolated reproduction of issue 38071." + "reason": "Special-token registration bug vs MLukeTokenizer attribute error. Too different to merge." }, { "left": "issue:28282", "right": "issue:32090", "accept": false, - "reason": "Missing-PyTorch ImportError and NoneType _gpu_broadcast_one TypeError are unrelated." + "reason": "Both error on missing/unsupported types, but one is missing PyTorch import and the other is `_gpu_broadcast_one` with NoneType in Trainer." }, { - "left": "issue:43577", - "right": "issue:43697", + "left": "issue:41720", + "right": "issue:43906", "accept": false, - "reason": "BLIP2 dtype propagation is unrelated to RTDetrV2 output divergence in v5." + "reason": "Both mention runtime failures on large models, but the concrete causes are unrelated (cudaErrorAssert vs isolated reproduction of another issue)." }, { "left": "issue:28282", "right": "issue:33357", "accept": false, - "reason": "Missing-PyTorch ImportError and a Mac bus error on CLIP are different environment/model failures." + "reason": "ImportError for missing PyTorch vs Mac bus error in CLIP model usage. Different failure classes." }, { - "left": "issue:43646", - "right": "issue:43749", + "left": "issue:43577", + "right": "issue:43697", "accept": false, - "reason": "Custom model initialization breakage and FSDP_CPU_RAM_EFFICIENT_LOADING are different regressions." + "reason": "BLIP2 dtype loading bug vs RTDetrV2 output divergence in v5. Not the same code path." }, { - "left": "issue:43688", - "right": "issue:45701", + "left": "issue:43646", + "right": "issue:43749", "accept": false, - "reason": "Auxiliary-loss normalization in MoE models is unrelated to a generic tokenization-version change report." + "reason": "Both are v5 regressions, but one is custom model initialization and the other is FSDP CPU RAM efficient loading." }, { "left": "issue:28282", "right": "issue:35141", "accept": false, - "reason": "ImportError for PyTorch and output embedding reinitialization after resizing token embeddings are unrelated." + "reason": "Missing PyTorch import vs post_init reinitializing output embeddings after resizing. Unrelated bugs." }, { - "left": "issue:44843", - "right": "issue:44991", + "left": "issue:43688", + "right": "issue:45701", "accept": false, - "reason": "Offline model_info patching is a different bug from a general tokenizer-loading failure for EMBEDDIA/est-roberta." + "reason": "Aux-loss normalization vs generic tokenization changes. Too broad and not the same issue." }, { - "left": "issue:44977", - "right": "issue:45356", + "left": "issue:44843", + "right": "issue:44991", "accept": false, - "reason": "Qwen3.5 flash-attention generation issues and Kimi-K2.5 tokenizer codec regressions are different code paths." + "reason": "Both are tokenizer-loading regressions, but one is offline-mode model_info behavior and the other is a specific model tokenizer load failure; not enough evidence of one bug." }, { "left": "issue:43531", "right": "issue:43742", "accept": false, - "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to the MobileLLM-125M key error." + "reason": "Sliding-window Qwen3-MoE bug vs MobileLLM key error during load. Different concrete failures." }, { "left": "issue:43653", "right": "issue:43927", "accept": false, - "reason": "BigBird mask-token registration and DiaConfig losing custom token IDs after save/load are different token-handling bugs." - }, - { - "left": "issue:43329", - "right": "issue:45325", - "accept": false, - "reason": "Video token counting in multimodal processors is not the same as rope-index temporal scaling for still images." + "reason": "BigBird special-token registration issue vs DiaConfig losing custom token IDs on save/load." }, { "left": "issue:43550", "right": "issue:43927", "accept": false, - "reason": "torch.compile + SDPA failure in Bamba-9B-v2 is unrelated to DiaConfig token ID persistence." + "reason": "torch.compile+SDPA failure vs config persistence bug. Different layers of the stack." }, { "left": "issue:44464", "right": "issue:44977", "accept": false, - "reason": "Compiled chunked-generation inconsistency and Qwen3.5 flash-attention generation failure are different mechanisms." + "reason": "Compiled-forward chunked generation inconsistency vs Qwen3.5 flash-attention generation bug. Same general area, but different problems." }, { - "left": "issue:43577", - "right": "issue:45588", + "left": "issue:43329", + "right": "issue:45325", "accept": false, - "reason": "BLIP2 dtype propagation is unrelated to the flash_attention.py s_aux=None crash." + "reason": "Both are multimodal/VL issues, but one is undefined helper usage in token counting and the other is RoPE position-id scaling." }, { "left": "issue:43577", - "right": "issue:44554", - "accept": false, - "reason": "BLIP2 dtype propagation and the MPS attention correctness issue are different bugs." - }, - { - "left": "issue:44479", - "right": "issue:44625", - "accept": false, - "reason": "A video-input regression in Qwen models is not the same as num_labels propagation in Qwen3.5 config." - }, - { - "left": "issue:43122", - "right": "issue:43906", - "accept": false, - "reason": "Tokenization changes across versions are not shown to be the same as the unrelated reproduction issue." - }, - { - "left": "issue:43550", - "right": "issue:44361", + "right": "issue:45588", "accept": false, - "reason": "torch.compile SDPA failure and MLukeTokenizer AttributeError are unrelated." + "reason": "BLIP2 dtype issue vs flash_attention crash on `s_aux=None`. Different models and code paths." } ] }, @@ -6479,7 +6466,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:28218", "issue:32090", @@ -6490,11 +6477,10 @@ "issue:36331", "issue:39692", "issue:41720", - "issue:43257", + "issue:43122", "issue:43262", "issue:43278", "issue:43295", - "issue:43299", "issue:43334", "issue:43452", "issue:43493", @@ -6503,6 +6489,7 @@ "issue:43540", "issue:43550", "issue:43572", + "issue:43577", "issue:43606", "issue:43688", "issue:43720", @@ -6510,273 +6497,280 @@ "issue:43756", "issue:43825", "issue:43844", + "issue:43906", "issue:43927", "issue:44361", "issue:44451", "issue:44464", - "issue:44488", + "issue:44479", + "issue:44554", "issue:44568", "issue:44610", "issue:44625", "issue:44821", - "issue:44843", "issue:44849", "issue:44913", "issue:44964", "issue:44977", - "issue:45083", "issue:45357", "issue:45405", "issue:45584", "issue:45812" ], "soft_pairs": [ + "issue:43577|issue:44554", + "issue:44479|issue:44625", + "issue:43550|issue:44361", + "issue:43122|issue:43906", "issue:32090|issue:34567", - "issue:43504|issue:43550", "issue:41720|issue:44464", + "issue:43504|issue:43550", "issue:43504|issue:43720", "issue:43504|issue:44610", "issue:32090|issue:33666", "issue:44849|issue:45357", "issue:43452|issue:44451", - "issue:44568|issue:45812", - "issue:43278|issue:43688", "issue:43742|issue:44821", + "issue:43278|issue:43688", + "issue:44568|issue:45812", "issue:33666|issue:36010", "issue:43493|issue:43825", "issue:43262|issue:43295", "issue:43525|issue:43572", - "issue:43756|issue:44913", "issue:43606|issue:43927", "issue:43720|issue:43927", + "issue:43756|issue:44913", "issue:28218|issue:33357", "issue:33666|issue:36331", "issue:43493|issue:43844", - "issue:39692|issue:43493", "issue:43720|issue:44361", + "issue:39692|issue:43493", "issue:43278|issue:43844", "issue:43540|issue:44977", "issue:44964|issue:45405", "issue:43334|issue:43572", - "issue:43257|issue:43299", - "issue:44625|issue:45584", - "issue:44488|issue:44843", - "issue:43756|issue:45083" + "issue:44625|issue:45584" ], - "prepared_review_unit_hash": "c2af94df7eaf9e201071621be51b83e6207ccae0ae707a07e66b6e854b0c1864", + "prepared_review_unit_hash": "c3b41160e4405c98d3140544511072dee6ba99e8a4ff06064ced3d2e126fc6fd", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37058, - "estimated_input_tokens": 9265, - "estimated_eval_tokens": 18786 + "soft_pair_count": 32, + "serialized_chars": 37393, + "estimated_input_tokens": 9349, + "estimated_eval_tokens": 18954 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose similarity cluster of unrelated Transformers bugs (tokenizer regressions, config/load failures, training/runtime issues). I don\u2019t see any soft pair that is clearly the same underlying bug. The best anchor issue is the Granite tokenizer regression because it is broad and directly about a silent tokenizer breakage.", - "confidence": 0.33, - "canonical_issue_reason": "issue:45812 is the broadest, most central tokenizer-regression report in the set: it affects all Granite models, describes a silent v4\u2192v5 behavior change, and has the most direct relevance to duplicate-triage for tokenizer output bugs.", + "summary": "This cluster is largely heterogeneous; most items are distinct model-, trainer-, or config-specific bugs rather than true duplicates. No soft pair looks safely mergeable into one fix. The broadest representative issue is the Granite tokenizer regression.", + "confidence": 0.41, + "canonical_issue_reason": "Issue 45812 is the strongest representative of the tokenization-regression theme: broad impact, clear v4\u2192v5 breakage, and a concrete tokenizer symptom.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45812 is the strongest cluster representative because it is model-family-wide, concrete, and likely to attract adjacent tokenizer bug reports; the other items are mostly unrelated load/training/config regressions.", + "best_issue_reason": "Issue 45812 is the best standalone issue in this set because it is specific, high-impact, and most likely to attract or anchor related tokenizer fixes.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:32090", - "right": "issue:34567", + "left": "issue:43577", + "right": "issue:44554", "accept": false, - "reason": "Different trainer failures: GPU broadcast of NoneType vs TrainerState token counting not updating." + "reason": "Different failures: Blip2 dtype casting vs MPS attention correctness." }, { - "left": "issue:43504", - "right": "issue:43550", + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Qwen video-input regression and Qwen3.5 num_labels propagation are different code paths." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Unrelated: torch.compile/SDPA issue vs tokenizer AttributeError." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "One is a tokenization regression; the other is a reproduction of a separate issue with no clear overlap." + }, + { + "left": "issue:32090", + "right": "issue:34567", "accept": false, - "reason": "Unrelated bugs: legacy preset field on BEiT loading vs torch.compile+SDPA failure in Bamba." + "reason": "Trainer broadcast TypeError and token-count tracking are unrelated." }, { "left": "issue:41720", "right": "issue:44464", "accept": false, - "reason": "Different code paths: auto device mapping cuda assert vs chunked generation with compiled forward." + "reason": "Different inference bugs: auto device mapping assert vs compiled-forward chunked generation." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Legacy-field loading bug vs SDPA compile bug in a different model." }, { "left": "issue:43504", "right": "issue:43720", "accept": false, - "reason": "BEiT legacy-field load bug is unrelated to BitNet packed-weight unpacking during accelerate loading." + "reason": "Different subsystems: model loading preset vs BitNet packed-weight loading." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "Different subsystems: BEiT pretrained loading vs OmDet-Turbo processor image-size mismatch." + "reason": "Pretrained loading failure and processor image-size mismatch are not the same bug." }, { "left": "issue:32090", "right": "issue:33666", "accept": false, - "reason": "Trainer broadcast error and Qwen2-VL multi-GPU training are different failures." + "reason": "Trainer broadcast error is unrelated to Qwen2-VL multi-GPU training." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Qwen3.5 hidden-state output bug is distinct from incorrect visual-encoder keys on save_pretrained." + "reason": "Different Qwen3.5 issues: hidden-states output vs save_pretrained visual-key regression." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "Generic gguf/AutoModel loading breakage is not the same as a specific ScandiBERT load failure." + "reason": "GGUF loading breakage and ScandiBERT load failure do not look like the same defect." }, { - "left": "issue:44568", - "right": "issue:45812", + "left": "issue:43742", + "right": "issue:44821", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and different symptoms; no evidence of one shared bug." + "reason": "MobileLLM key error and AutoImageProcessor URL loading are separate problems." }, { "left": "issue:43278", "right": "issue:43688", "accept": false, - "reason": "Evaluate dtype drift and auxiliary-loss normalization are separate training issues." + "reason": "Mixed precision dtype drift and auxiliary-loss normalization are unrelated." }, { - "left": "issue:43742", - "right": "issue:44821", + "left": "issue:44568", + "right": "issue:45812", "accept": false, - "reason": "MobileLLM key error and AutoImageProcessor URL loading are unrelated load-path bugs." + "reason": "Both are tokenizer regressions, but they affect different models and concrete behaviors." }, { "left": "issue:33666", "right": "issue:36010", "accept": false, - "reason": "Multi-GPU training support issue is unrelated to GenerationMixin import failure." + "reason": "Qwen2-VL training issue vs GenerationMixin import error are unrelated." }, { "left": "issue:43493", "right": "issue:43825", "accept": false, - "reason": "SigLIP2 implementation discrepancy and pipeline translation error messaging are different issues." + "reason": "SigLIP2 implementation mismatch and pipeline translation-message bug are different concerns." }, { "left": "issue:43262", "right": "issue:43295", "accept": false, - "reason": "Audio chat-template sample-rate default is unrelated to processor.tokenizer/image-handling regression." + "reason": "Audio chat-template sampling-rate default and processor/tokenizer regression are not the same bug." }, { "left": "issue:43525", "right": "issue:43572", "accept": false, - "reason": "Both mention missing pad-token fields, but they involve different configs/models and different missing attributes." - }, - { - "left": "issue:43756", - "right": "issue:44913", - "accept": false, - "reason": "RoPE-layer-count bug and rotary_pct reload regression are distinct configuration issues." + "reason": "Both mention missing pad token fields, but they hit different configs and identifiers (id vs idx)." }, { "left": "issue:43606", "right": "issue:43927", "accept": false, - "reason": "CPU offload device mismatch is not the same as config token IDs being lost on save/load." + "reason": "CPU offload device mismatch and DiaConfig save/load token-ID loss are unrelated." }, { "left": "issue:43720", "right": "issue:43927", "accept": false, - "reason": "Packed-weight unpacking during accelerate loading is unrelated to DiaConfig token-ID persistence." + "reason": "BitNet packed-weight loading and DiaConfig token-ID persistence are different failures." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "RoPE-layer truncation bug and rotary_pct reload regression do not share a concrete code path." }, { "left": "issue:28218", "right": "issue:33357", "accept": false, - "reason": "Tokenizer added-space behavior and MacOS CLIP bus error are clearly different bugs." + "reason": "Tokenizer added-space behavior and MacOS CLIP bus error are clearly unrelated." }, { "left": "issue:33666", "right": "issue:36331", "accept": false, - "reason": "Qwen2-VL multi-GPU training and custom compute_loss keyword mismatch are unrelated trainer issues." + "reason": "Multi-GPU training issue vs custom compute_loss signature break are different problems." }, { "left": "issue:43493", "right": "issue:43844", "accept": false, - "reason": "SigLIP2 discrepancy is not the same as gradient explosion under ZeRO-3." + "reason": "SigLIP2 discrepancy and ZeRO-3 gradient explosion are not the same bug." }, { - "left": "issue:39692", - "right": "issue:43493", + "left": "issue:43720", + "right": "issue:44361", "accept": false, - "reason": "Documentation example errors are not the same as the underlying SigLIP2 implementation discrepancy." + "reason": "BitNet accelerate loading and MLukeTokenizer task AttributeError are unrelated." }, { - "left": "issue:43720", - "right": "issue:44361", + "left": "issue:39692", + "right": "issue:43493", "accept": false, - "reason": "BitNet loading with packed weights and MLukeTokenizer task AttributeError are unrelated." + "reason": "Docs-example errors and implementation discrepancy in SigLIP2 are different issue types." }, { "left": "issue:43278", "right": "issue:43844", "accept": false, - "reason": "Embedding dtype mismatch and abnormal gradient growth are different training regressions." + "reason": "Training/evaluate dtype mismatch is unrelated to gradient growth under ZeRO-3." }, { "left": "issue:43540", "right": "issue:44977", "accept": false, - "reason": "Qwen3OmniMoe video-input processing and Qwen3.5 flash-attention generation are different code paths." + "reason": "Video-input processing failure and flash-attention generation bug are different code paths." }, { "left": "issue:44964", "right": "issue:45405", "accept": false, - "reason": "Model loading failure and an unreleased PEFT version pin are unrelated." + "reason": "Model load regression and unreleased PEFT minimum-version bump are unrelated." }, { "left": "issue:43334", "right": "issue:43572", "accept": false, - "reason": "Both involve pad-token metadata, but they are different model configs with different missing fields and symptoms." - }, - { - "left": "issue:43257", - "right": "issue:43299", - "accept": false, - "reason": "These are both Qwen3 MoE-related, but one is accelerate+deepspeed weight conversion and the other is a dev load regression in Qwen3VL; not the same concrete bug." + "reason": "Qwen3-VL pad_token_id attribute error and StableLm pad_token_idx issue are different configs." }, { "left": "issue:44625", "right": "issue:45584", "accept": false, - "reason": "num_labels propagation and Whisper empty-transcription handling are unrelated." - }, - { - "left": "issue:44488", - "right": "issue:44843", - "accept": false, - "reason": "A model load failure on sleng-bert is not the same as the offline-mode mistral regex patch bug." - }, - { - "left": "issue:43756", - "right": "issue:45083", - "accept": false, - "reason": "Smollm3 RoPE-layer truncation and qwen3_omni_moe feature-length helper behavior are different bugs." + "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription generation are unrelated." } ] }, @@ -6798,7 +6792,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:28218", "issue:29942", @@ -6808,19 +6802,20 @@ "issue:34567", "issue:39692", "issue:43232", + "issue:43257", "issue:43278", "issue:43295", + "issue:43299", "issue:43334", "issue:43504", "issue:43572", "issue:43575", - "issue:43582", "issue:43606", "issue:43646", "issue:43653", "issue:43701", + "issue:43756", "issue:43824", - "issue:43844", "issue:43927", "issue:43994", "issue:44112", @@ -6829,35 +6824,36 @@ "issue:44423", "issue:44464", "issue:44466", + "issue:44488", "issue:44493", "issue:44521", - "issue:44554", "issue:44589", "issue:44734", "issue:44792", + "issue:44843", "issue:44849", - "issue:44964", - "issue:44977", - "issue:45084", + "issue:45083", "issue:45200", "issue:45229", "issue:45290", "issue:45405", - "issue:45446", "issue:45520", "issue:45584", "issue:45759", "issue:45823" ], "soft_pairs": [ + "issue:43257|issue:43299", + "issue:43756|issue:45083", + "issue:44488|issue:44843", "issue:43334|issue:45759", "issue:45200|issue:45229", "issue:43646|issue:44466", "issue:43824|issue:44589", "issue:39692|issue:43295", "issue:45229|issue:45823", - "issue:33357|issue:33666", "issue:44589|issue:45520", + "issue:33357|issue:33666", "issue:43572|issue:44291", "issue:43504|issue:43606", "issue:43927|issue:44361", @@ -6872,202 +6868,192 @@ "issue:29942|issue:30333", "issue:44521|issue:45290", "issue:28218|issue:34567", - "issue:43232|issue:44849", - "issue:43844|issue:44964", - "issue:45084|issue:45520", - "issue:44554|issue:45446", - "issue:43582|issue:44977" + "issue:43232|issue:44849" ], - "prepared_review_unit_hash": "2b06e20157c7f24ddf76f6edf1d5029f76dc1d8e1abe8dbe762bcbf808f36ac1", + "prepared_review_unit_hash": "853688ee1cbf145803a8e7f2a6f775323ca49f07f18e4fc442a4fe721e971256", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 35791, - "estimated_input_tokens": 8948, - "estimated_eval_tokens": 18152 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 34989, + "estimated_input_tokens": 8748, + "estimated_eval_tokens": 17752 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the items mostly share broad Transformers/model-loading themes, but none of the soft pairs look like the same underlying bug or change. I found no convincing duplicate issue or PR candidate.", - "confidence": 0.92, - "canonical_issue_reason": null, + "summary": "This cluster is mostly a grab bag of unrelated Transformers issues that share broad keywords like model loading, multimodal support, generation, or tokenizer behavior. The soft pairs are topical lookalikes, but they do not appear to be the same underlying bug/change.", + "confidence": 0.41, + "canonical_issue_reason": "issue:43646 is the broadest representative of the cluster: a general Transformers 5.0 regression affecting custom model initialization, which overlaps with several other loading/init-style issues here.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:43646 is the best overall issue candidate because it is the most general and central to the cluster\u2019s common theme of regression in model initialization/loading.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen3/MoE loading, but one is about accelerate+deepspeed weight conversion and the other about multimodal config unwrapping; different failure modes." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "They are both model-architecture issues, but the reported bugs are unrelated: RoPE layer dropping vs a feature-extraction helper behaving unexpectedly." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "One is a specific model load failure, the other is an offline-hub regression in tokenizer patching; not the same code path." + }, { "left": "issue:43334", "right": "issue:45759", "accept": false, - "reason": "Both involve Qwen multimodal configs, but one is a missing pad_token_id on load and the other is from_config failing to unwrap text_config; different code paths and symptoms." + "reason": "Both touch Qwen VL/multimodal loading, but one is a missing pad_token_id error and the other is from_config not unwrapping text_config; related area, different bug." }, { "left": "issue:45200", "right": "issue:45229", "accept": false, - "reason": "Gemma4-related, but one is a training fine-tuning mm_token_type_ids default issue and the other is multi-GPU inference OOM." + "reason": "Both mention Gemma 4, but one is a training input-type default issue and the other is a multi-GPU inference OOM; not the same underlying problem." }, { "left": "issue:43646", "right": "issue:44466", "accept": false, - "reason": "Both mention v5/main regressions, but one is custom model initialization and the other is lm_head.weight serialization depending on device." + "reason": "General version regressions, but custom model initialization and tied-weight serialization are distinct behaviors and code paths." }, { "left": "issue:43824", "right": "issue:44589", "accept": false, - "reason": "Completely different failures: Qwen2.5-VL import error versus Float8 storage lookup TypeError." + "reason": "Import error for a Qwen VL class and a missing Float8 storage type are unrelated bugs." }, { "left": "issue:39692", "right": "issue:43295", "accept": false, - "reason": "Both are regression reports, but one is a SigLIP2 docs example issue and the other is custom code breaking around processor.tokenizer / images-to-tokenizer handling." + "reason": "Both are model/example regressions, but one is a SigLIP2 doc example problem while the other is a custom multimodal tokenizer API breakage." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "Same Gemma4 family, but OOM from multi-GPU inference is not the same bug as a device mismatch during forward with device_map=auto." + "reason": "Both concern Gemma4 multi-GPU inference, but one is OOM and the other is a device mismatch during forward; different concrete failures." }, { - "left": "issue:33357", - "right": "issue:33666", + "left": "issue:44589", + "right": "issue:45520", "accept": false, - "reason": "Different models, platforms, and failures: MacOS bus error on CLIP versus Qwen2-VL multi-GPU training." + "reason": "Storage-type lookup failure and flash_attn import key error are unrelated infrastructure bugs." }, { - "left": "issue:44589", - "right": "issue:45520", + "left": "issue:33357", + "right": "issue:33666", "accept": false, - "reason": "Unrelated runtime issues: Float8 storage object error versus flash_attn import KeyError on Python 3.13." + "reason": "Both are multimodal/model-related, but CLIP bus error on macOS and Qwen2-VL multi-GPU training are not the same issue." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "Both are model-loading/version issues, but one is a missing pad_token_idx in StableLmConfig and the other is an unexpected _is_hf_initialized argument with init_empty_weights." + "reason": "Both surfaced around the 5.0 transition, but missing pad_token_idx and unexpected _is_hf_initialized are separate API regressions." }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Different subsystems and bugs: legacy-field model loading for BEiT versus a device mismatch with CPU offload for Bark." + "reason": "Different models and different failure modes: legacy field load issue vs CPU offload device mismatch." }, { "left": "issue:43927", "right": "issue:44361", "accept": false, - "reason": "One is DiaConfig save/load losing custom token IDs and causing generation IndexError; the other is MLukeTokenizer AttributeError on tasks." + "reason": "DiaConfig token IDs being lost on save/load is unrelated to MLukeTokenizer AttributeError failures." }, { "left": "issue:44423", "right": "issue:44734", "accept": false, - "reason": "Both are serve-related, but continuous batching with multimodal models and KV-cache continuation tensor indexing are distinct crash paths." + "reason": "Both are server-side crashes, but one is multimodal input handling and the other is KV-cache continuation indexing; not the same bug." }, { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "No overlap beyond token/model loading: BEiT legacy preset loading versus BigBirdTokenizer mask token registration and decode output." + "reason": "Unrelated model-loading issue versus tokenizer special-token registration bug." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "OOM on loading a large Qwen2 model is unrelated to a PEFT minimum-version bump not yet on PyPI." + "reason": "Large-model tensor-parallel OOM and a PEFT version bump problem are entirely different." }, { "left": "issue:44464", "right": "issue:45584", "accept": false, - "reason": "Different generation issues: compiled-forward chunked generation inconsistency versus Whisper empty-transcription failure after align_special_tokens." + "reason": "Compiled-forward chunked generation inconsistency and Whisper empty-transcription handling after token alignment are different generation bugs." }, { "left": "issue:43994", "right": "issue:44493", "accept": false, - "reason": "Different symptoms and likely causes: SigLIP2 nonsensical outputs versus unexpected key with position id across many models." + "reason": "SigLIP2 nonsensical outputs and unexpected position-id keys are distinct symptoms with different likely causes." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "BF16-to-FP32 dtype change in evaluation is unrelated to resume_from_checkpoint key mismatch." + "reason": "A dtype drift in evaluation and a resume_from_checkpoint key mismatch are not the same underlying defect." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "A real model/device bug versus a CI failure from a stale device override test; not the same underlying problem." + "reason": "One is a real CPU-offload device mismatch, the other is a stale CI test; they are not the same bug." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "Janus image-generation test failure and a PEFT version bump are unrelated." + "reason": "A janus model test failure and a PEFT minimum-version bump are unrelated." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Flash Attention 2 test failures and MLflow not reporting failed training jobs are unrelated." + "reason": "Flash Attention 2 test failures and MLFlow reporting after job failure are unrelated." }, { "left": "issue:44521", "right": "issue:45290", "accept": false, - "reason": "Both use apply_chat_template, but all-zero assistant masks for multimodal inputs is a different bug from crashing on assistant tool-call messages with no content." + "reason": "Both involve apply_chat_template, but one is all-zero assistant masks for multimodal inputs while the other is a crash on tool-call assistant messages; different edge cases." }, { "left": "issue:28218", "right": "issue:34567", "accept": false, - "reason": "Tokenizer spacing after added tokens and TrainerState num_input_tokens_seen not updating are unrelated." + "reason": "Tokenizer spacing after added tokens and TrainerState token counters are unrelated." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation sync_gpus keyword update and Qwen3.5 output_hidden_states behavior are separate bugs." - }, - { - "left": "issue:43844", - "right": "issue:44964", - "accept": false, - "reason": "ZeRO-3 gradient growth and a Phi-4 multimodal loading failure are different issues." - }, - { - "left": "issue:45084", - "right": "issue:45520", - "accept": false, - "reason": "A template compilation TypeError is unrelated to flash_attn import KeyError on Python 3.13." - }, - { - "left": "issue:44554", - "right": "issue:45446", - "accept": false, - "reason": "MPS attention correctness with mismatched head dims is separate from a PyTorch version check bug in flex_attention." - }, - { - "left": "issue:43582", - "right": "issue:44977", - "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and Qwen3.5 flash-attention generation problems are unrelated." + "reason": "One concerns update_model_kwargs after sync_gpus, the other output_hidden_states in Qwen3.5; no shared concrete bug." } ] }, @@ -7089,7 +7075,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:15354", "issue:28218", @@ -7097,7 +7083,6 @@ "issue:37428", "issue:38175", "issue:42915", - "issue:43278", "issue:43295", "issue:43334", "issue:43388", @@ -7107,19 +7092,16 @@ "issue:43526", "issue:43540", "issue:43572", + "issue:43582", "issue:43701", "issue:43824", "issue:43844", - "issue:43856", "issue:43873", "issue:43957", "issue:43975", "issue:44315", - "issue:44442", "issue:44464", "issue:44466", - "issue:44514", - "issue:44521", "issue:44554", "issue:44568", "issue:44610", @@ -7127,21 +7109,30 @@ "issue:44849", "issue:44898", "issue:44936", + "issue:44964", + "issue:44977", "issue:44987", "issue:45072", + "issue:45084", "issue:45127", "issue:45198", "issue:45200", "issue:45325", "issue:45356", "issue:45412", + "issue:45446", + "issue:45520", "issue:45563", "issue:45701", "issue:45823" ], "soft_pairs": [ - "issue:44568|issue:45701", + "issue:43844|issue:44964", + "issue:45084|issue:45520", + "issue:44554|issue:45446", + "issue:43582|issue:44977", "issue:15354|issue:38175", + "issue:44568|issue:45701", "issue:43540|issue:45200", "issue:37428|issue:43957", "issue:45072|issue:45198", @@ -7159,239 +7150,236 @@ "issue:45200|issue:45325", "issue:43572|issue:43957", "issue:43844|issue:44936", - "issue:43334|issue:43525", "issue:43295|issue:43450", + "issue:43334|issue:43525", "issue:43824|issue:43975", "issue:43295|issue:43873", "issue:43388|issue:43526", "issue:42915|issue:43824", "issue:38175|issue:45412", "issue:28218|issue:35141", - "issue:38175|issue:43493", - "issue:44442|issue:45198", - "issue:43278|issue:43856", - "issue:44514|issue:44521" + "issue:38175|issue:43493" ], - "prepared_review_unit_hash": "13a75d251a5ba847c83b70780b130f0373b0223de1c7dc203bf27bad7cce02c3", + "prepared_review_unit_hash": "d29a5f1708e952429fe81e1fcfa32ee484f707c95c8c45e266928ac5fbc2dbb4", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36711, - "estimated_input_tokens": 9178, - "estimated_eval_tokens": 18612 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37531, + "estimated_input_tokens": 9383, + "estimated_eval_tokens": 19022 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous set of issues with no broad cluster-wide duplicate theme. The only credible duplicate-style link is the SigLIP2 correctness pair; the rest are adjacent at best but describe different bugs, models, or code paths.", - "confidence": 0.72, - "canonical_issue_reason": "Issue 43493 is the broader SigLIP2 implementation discrepancy; issue 38175 looks like a narrower symptom of that same model behavior.", + "summary": "This cluster is mostly a set of unrelated transformer bugs. The only clear duplicate-like pair is the missing `pad_token_id` config regression affecting two different model configs; all other soft pairs should stay separate.", + "confidence": 0.88, + "canonical_issue_reason": "issue:43334 is the clearest representative of the shared `pad_token_id`-missing regression and has the most explicit loading error; it also matches issue:43525 closely enough to treat as the same bug.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43493 is the best representative of the only real duplicate family here because it states the underlying HF-vs-JAX discrepancy more generally.", + "best_issue_reason": "issue:43334 is the best issue to keep as the canonical anchor: it is specific, reproducible, and captures the shared config-attribute failure more cleanly than the nearby duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44568", - "right": "issue:45701", + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "Different failures: DeepSpeed/ZeRO gradient growth vs model-loading breakage for Phi-4 multimodal." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Unrelated code paths: compile error on template nodes vs Python 3.13 flash-attn import lookup." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "Different bugs in different attention utilities: MPS correctness issue vs a version-check/import bug." + }, + { + "left": "issue:43582", + "right": "issue:44977", "accept": false, - "reason": "Both mention tokenization regressions, but one is a missing BOS/EOS insertion bug and the other is a broad version-related tokenization change; not the same concrete defect." + "reason": "Apple Silicon allocator warmup TypeError is unrelated to Qwen3.5 flash-attention generation behavior." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "Completely different failures: TorchScript export on ViT versus SigLIP2 zero-probability output." + "reason": "JIT scripting/export failure and SigLIP2 zero-probability issue are not the same bug." + }, + { + "left": "issue:44568", + "right": "issue:45701", + "accept": false, + "reason": "Both involve tokenization, but one is a specific special-token bug while the other is a broad version-regression report." }, { "left": "issue:43540", "right": "issue:45200", "accept": false, - "reason": "Different subsystems and symptoms: Qwen3Omni video input handling versus Gemma4 multimodal token-type defaults." + "reason": "Video-input processing error in Qwen3OmniMoe vs Gemma 4 text-only fine-tuning token-type handling." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "An import error for a missing flash-attention helper is unrelated to meta-device model loading failures." + "reason": "Different import/load failures: missing `_flash_supports_window_size` vs meta-device loading breakage." }, { "left": "issue:45072", "right": "issue:45198", "accept": false, - "reason": "Different code paths: bfloat16 dtype mismatch during inference versus Wav2Vec2 save/tokenization failures." + "reason": "Different subsystems: bfloat16 dtype mismatch in inference vs Wav2Vec2 save/tokenization failure." }, { "left": "issue:45200", "right": "issue:45823", "accept": false, - "reason": "Both are Gemma4 issues, but one is missing/default mm_token_type_ids and the other is a device-placement mismatch in forward; not the same bug." + "reason": "Gemma 4 token-type-id defaulting and device-map forward mismatch are separate issues." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger Kernel application in model_init is unrelated to the Qwen3.5 hidden-states bug." + "reason": "Model-init/Liger Kernel application issue is unrelated to Qwen3.5 hidden-state output bug." }, { "left": "issue:44554", "right": "issue:45356", "accept": false, - "reason": "An MPS attention correctness issue is unrelated to a tokenizer regression in Kimi-K2.5." + "reason": "MPS attention correctness and tokenizer codec regression are unrelated." }, { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "SigLIP2 model discrepancy and resume_from_checkpoint key mismatch are different failures." + "reason": "SigLIP2 implementation discrepancy vs checkpoint resume key mismatch are different problems." }, { "left": "issue:43295", "right": "issue:44610", "accept": false, - "reason": "Both involve processors, but one is processor.tokenizer/image passing regression and the other is a bad image-size output from OmDet-Turbo." + "reason": "Processor/tokenizer API regression is unrelated to OmDet-Turbo image-size mismatch." }, { "left": "issue:43873", "right": "issue:44464", "accept": false, - "reason": "Quantization/offloading behavior is unrelated to compiled-forward chunked generation outputs." + "reason": "Quantization offloading behavior and compiled-forward chunked generation are different code-path bugs." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "Both touch tied weights/lm_head, but one is serialization-by-device and the other is LoRA merge collapse after vocab extension; different bugs." + "reason": "Both mention weights, but one is serialization/device-dependent and the other is LoRA merge collapse with extended vocab." }, { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Perceiver resolution handling and RT-DETR memory release are unrelated." + "reason": "Perceiver resize failure and RT-DETR memory leak are unrelated." }, { "left": "issue:44792", "right": "issue:45563", "accept": false, - "reason": "A failed image-generation test for Janus is unrelated to a stale paged-generate warning." + "reason": "A Janus test failure is not the same as a stale paged-generate warning." }, { "left": "issue:37428", "right": "issue:43824", "accept": false, - "reason": "Different import failures for different model classes; no shared code path is evident." + "reason": "Both are import-related, but they target different missing symbols/classes and different failure modes." }, { "left": "issue:43572", "right": "issue:44987", "accept": false, - "reason": "Both are loading/config regressions, but they concern different models and symptoms, so they are not the same underlying bug." + "reason": "StableLm pad-token config regression is unrelated to loading `physical-intelligence/fast` on newer transformers." }, { "left": "issue:45200", "right": "issue:45325", "accept": false, - "reason": "Gemma4 token-type defaults and Qwen2.5-VL temporal position scaling are unrelated." + "reason": "Token-type-id defaults and Qwen2.5-VL rope-position scaling are separate multimodal bugs." }, { "left": "issue:43572", "right": "issue:43957", "accept": false, - "reason": "A missing config attribute after update is not the same as meta-device loading breakage across models." + "reason": "Config attribute regression and meta-device loading breakage do not share the same underlying fix." }, { "left": "issue:43844", "right": "issue:44936", "accept": false, - "reason": "Training gradient explosion under ZeRO-3 and trainer.evaluate() failure after train are different issues." - }, - { - "left": "issue:43334", - "right": "issue:43525", - "accept": false, - "reason": "Both are missing pad_token_id AttributeErrors, but they affect different config classes and model families; too weak to call duplicates." + "reason": "Training-gradient anomaly and trainer.evaluate() failing after train are different issues." }, { "left": "issue:43295", "right": "issue:43450", "accept": false, - "reason": "Custom processor.tokenizer access regression and batched video shape bug are separate processor problems." + "reason": "Processor regression with `processor.tokenizer` is not the same as batched video shape handling." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": true, + "reason": "Both report the same concrete `AttributeError` for missing `pad_token_id` on config objects during model loading; a shared fix is plausible." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "Importing a missing Qwen2.5-VL class is unrelated to DeepSeek detokenization behavior." + "reason": "Missing Qwen2_5_VL import and Deepseek tokenizer detokenization regression are unrelated." }, { "left": "issue:43295", "right": "issue:43873", "accept": false, - "reason": "Processor API regression and quantization/offloading behavior are unrelated." + "reason": "Processor API breakage and quantization offloading behavior are separate problems." }, { "left": "issue:43388", "right": "issue:43526", "accept": false, - "reason": "Trainer last-batch label dropping and BeitImageProcessorFast label reduction are different label-handling bugs." + "reason": "Different label-handling bugs in different utilities: metric gathering vs Beit image processor reduction." }, { "left": "issue:42915", "right": "issue:43824", "accept": false, - "reason": "Fine-grained FP8 model failure is unrelated to a Qwen2.5-VL import error." + "reason": "FineGrainedFP8Config failure on Qwen3Moe is unrelated to missing Qwen2_5_VL import." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 output correctness and RT-DETR memory cleanup are unrelated." + "reason": "SigLIP2 probability anomaly and RT-DETR memory release issue are unrelated." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing after added tokens and embedding reinitialization after resize are different defects." - }, - { - "left": "issue:38175", - "right": "issue:43493", - "accept": true, - "reason": "Both are SigLIP2 correctness problems; 38175 is a specific symptom, while 43493 describes the broader HF-vs-JAX implementation discrepancy." - }, - { - "left": "issue:44442", - "right": "issue:45198", - "accept": false, - "reason": "Different speech-model tokenization/load failures with no shared concrete bug." - }, - { - "left": "issue:43278", - "right": "issue:43856", - "accept": false, - "reason": "Embedding dtype drift in eval and Qwen3 MoE memory inefficiency are unrelated." - }, - { - "left": "issue:44514", - "right": "issue:44521", - "accept": false, - "reason": "Both are apply_chat_template multimodal bugs, but one is a batched-padding crash and the other is all-zero assistant masks; not clearly the same root cause." + "reason": "Tokenizer adding an extra space and output embeddings reinitialized after resize are distinct bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet, and the soft-edge calls stay conservative. The SigLIP2 pair is the only clearly supported duplicate-style link, while the rest are reasonably separated by different models, symptoms, or code paths." + "feedback": "Grounded overall. The canonical anchor choice for issue:43334 vs issue:43525 is conservative and supported by the titles, and the remaining soft-edge verdicts mostly stay on the safe side by rejecting only on clear topical separation. I don\u2019t see an overstatement that would require rejection." }, "evaluator_used": true, "retried": false, @@ -7410,9 +7398,8 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:29127", "issue:29942", "issue:32090", "issue:37428", @@ -7423,7 +7410,6 @@ "issue:43425", "issue:43450", "issue:43493", - "issue:43504", "issue:43526", "issue:43550", "issue:43575", @@ -7433,15 +7419,19 @@ "issue:43819", "issue:43825", "issue:43827", + "issue:43856", "issue:43901", "issue:43931", "issue:44112", "issue:44206", "issue:44351", "issue:44360", + "issue:44442", "issue:44448", "issue:44462", "issue:44493", + "issue:44514", + "issue:44521", "issue:44561", "issue:44610", "issue:44743", @@ -7449,19 +7439,20 @@ "issue:44857", "issue:45083", "issue:45127", + "issue:45198", "issue:45200", "issue:45245", "issue:45290", - "issue:45310", "issue:45381", - "issue:45478", "issue:45584", "issue:45588", "issue:45593", - "issue:45823", - "issue:45859" + "issue:45823" ], "soft_pairs": [ + "issue:44442|issue:45198", + "issue:43278|issue:43856", + "issue:44514|issue:44521", "issue:43653|issue:44112", "issue:43827|issue:43901", "issue:43450|issue:43575", @@ -7471,14 +7462,14 @@ "issue:44360|issue:44561", "issue:43819|issue:45083", "issue:43262|issue:43450", - "issue:43819|issue:44112", "issue:44610|issue:44857", + "issue:43819|issue:44112", "issue:37428|issue:43425", "issue:43278|issue:43825", "issue:43335|issue:43550", "issue:43606|issue:45083", - "issue:44448|issue:44743", "issue:44857|issue:45593", + "issue:44448|issue:44743", "issue:45290|issue:45381", "issue:45200|issue:45588", "issue:29942|issue:32090", @@ -7490,248 +7481,235 @@ "issue:44561|issue:44779", "issue:43335|issue:43653", "issue:43819|issue:44493", - "issue:43550|issue:44112", - "issue:45310|issue:45478", - "issue:29127|issue:32090", - "issue:43335|issue:43504", - "issue:45588|issue:45859" + "issue:43550|issue:44112" ], - "prepared_review_unit_hash": "baaecdcebda82995284d626830332d3e746962bf04307b01f1d6f3dcf928ef0d", + "prepared_review_unit_hash": "2a7a48602d9b848041ccee4dbf742de184eb6ec0a3b0dfe0aaaf53744378afb1", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37606, - "estimated_input_tokens": 9402, - "estimated_eval_tokens": 19060 + "soft_pair_count": 32, + "serialized_chars": 37283, + "estimated_input_tokens": 9321, + "estimated_eval_tokens": 18898 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly heterogeneous and the soft edges are largely false positives. The only clear duplicate is the Qwen3.5 MoE from_pretrained regression pair (45310/45478).", - "confidence": 0.91, - "canonical_issue_reason": "Issue 45310 is the best canonical choice because it is the clearest, earlier report of the same concrete regression as 45478: `transformers>=5.4.0` causing `Qwen3.5 Moe from_pretrained` to fail.", + "summary": "The cluster is mostly heterogeneous: the soft pairs share broad subsystems or keywords but do not describe the same underlying bug/change closely enough to merge as duplicates. No soft edge is strong enough to accept. The best anchor issue is the multimodal `apply_chat_template` regression (#44521), which is the most central and discussed concrete user-facing bug in the set.", + "confidence": 0.58, + "canonical_issue_reason": "#44521 is the clearest central issue: it targets a concrete multimodal `apply_chat_template` bug, has the most inbound references/discussion among the set, and is more representative than the narrower or unrelated regressions.", "canonical_pr_reason": null, - "best_issue_reason": "45310 is the most suitable global representative here: it is specific, reproducible, and directly matches the only strong duplicate candidate in the cluster.", + "best_issue_reason": "#44521 is the strongest global issue candidate because it describes a specific, reproducible API failure with broader applicability than the other items and appears to be the most actively referenced issue here.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Both are tokenizer/loading problems, but they affect different models and failure modes (`AutoTokenizer` load vs save_pretrained/tokenization)." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "One is a dtype regression between train/eval; the other is a training memory issue. Same area, different bug." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both involve `apply_chat_template`, but one is a batched-input crash and the other is wrong assistant masks; not the same defect." + }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "Different bugs: tokenizer special-token decode issue vs stale device-override CI failure." + "reason": "Unrelated issues: BigBird tokenizer special-token decoding vs a GraniteSpeech CI device-override test." }, { "left": "issue:43827", "right": "issue:43901", "accept": false, - "reason": "Both are docs-related, but they concern different API changes (`pipeline()` removal vs `return_all_scores`)." + "reason": "Both are docs-related, but they cover different pipeline APIs and different deprecations/behavior changes." }, { "left": "issue:43450", "right": "issue:43575", "accept": false, - "reason": "Different domains: batched video processor shape bug vs Qwen2-57B tensor-parallel OOM." + "reason": "Video processor shape bug vs OOM when loading a large model with tensor parallelism; no shared code-path." }, { "left": "issue:43450", "right": "issue:43493", "accept": false, - "reason": "Video batched-shape issue and SigLIP2 HF/JAX discrepancy are unrelated." + "reason": "Different model families and failures: batched video processor shape vs SigLIP2 implementation mismatch." }, { "left": "issue:44206", "right": "issue:45584", "accept": false, - "reason": "Different failure modes: unsupported `center` arg in audio feature extraction vs Whisper empty transcription after token alignment." + "reason": "Feature extractor argument regression vs Whisper empty-transcription failure; different processing paths." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA merge collapse with tied embeddings is unrelated to the 2^24 category limit error." + "reason": "LoRA/tied-embeddings model collapse is unrelated to the category-count runtime error." }, { "left": "issue:44360", "right": "issue:44561", "accept": false, - "reason": "A discussion about a missing ReLU in DSA indexer is unrelated to `is_torch_fx_available` removal breakage." + "reason": "Completely different topics: DSA indexer ReLU discussion vs v5 `is_torch_fx_available` removal breakage." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "DAC latent/forward mismatch is a different bug from `_get_feat_extract_output_lengths` behavior in qwen3_omni_moe." + "reason": "DAC latent/forward mismatch and a Qwen3-Omni helper-length bug are unrelated implementation issues." }, { "left": "issue:43262", "right": "issue:43450", "accept": false, - "reason": "Audio chat-template sampling-rate default and video batched-shape handling are separate processor issues." + "reason": "Audio chat-template sampling-rate default vs batched video processor output shape." }, { - "left": "issue:43819", - "right": "issue:44112", + "left": "issue:44610", + "right": "issue:44857", "accept": false, - "reason": "Different components and symptoms: DAC mismatch vs GraniteSpeech stale device-override CI failure." + "reason": "Processor size mismatch vs AMP/CUDA crash in a different loss module." }, { - "left": "issue:44610", - "right": "issue:44857", + "left": "issue:43819", + "right": "issue:44112", "accept": false, - "reason": "OmDet processor/model size mismatch is unrelated to LwDetrImageLoss AMP crash." + "reason": "No overlap beyond both being model-related; the bugs are entirely different." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "Import error for `_flash_supports_window_size` is not the same as a general Torch 2.10 incompatibility." + "reason": "Importing a removed flash-attention helper is not the same as a broad Torch 2.10 compatibility report." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "Embedding dtype drift in eval is unrelated to the pipeline translation-task error message." + "reason": "Embedding dtype regression and a pipeline error-message/docs issue are distinct." }, { "left": "issue:43335", "right": "issue:43550", "accept": false, - "reason": "Sparse-layer construction in SwitchTransformers and Bamba torch.compile/SDPA failure are distinct code-path problems." + "reason": "SwitchTransformers config layer-count bug vs Bamba SDPA/torch.compile failure; different models and code paths." }, { "left": "issue:43606", "right": "issue:45083", "accept": false, - "reason": "CPU offload device mismatch in bark-small is unrelated to qwen3_omni_moe length helper behavior." + "reason": "CPU offload device mismatch is unrelated to the Qwen3-Omni feature-length helper behavior." }, { - "left": "issue:44448", - "right": "issue:44743", + "left": "issue:44857", + "right": "issue:45593", "accept": false, - "reason": "Pegasus output differences and qwen3 recurrent-state reset are different model-specific regressions." + "reason": "AMP crash in LwDetrImageLoss vs missing auxiliary losses in D-FINE; not the same underlying bug." }, { - "left": "issue:44857", - "right": "issue:45593", + "left": "issue:44448", + "right": "issue:44743", "accept": false, - "reason": "Different detection-model bugs: AMP crash vs missing auxiliary losses when denoising is off." + "reason": "Different regressions: Pegasus output changes across versions vs recurrent state reset in modular Qwen3." }, { "left": "issue:45290", "right": "issue:45381", "accept": false, - "reason": "Tool-call chat-template crash is unrelated to qwen2.5-vl video vision_position_ids being wrong." + "reason": "One is chat-template tool-call crashing, the other is wrong video vision position ids; different failures." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma4 text-only `mm_token_type_ids` defaulting and flash-attention `s_aux=None` crash are separate issues." + "reason": "Gemma4 multimodal token-type defaults and flash_attention sinkless-model crash are unrelated." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention 2 test failures and Trainer `_gpu_broadcast_one` NoneType errors do not describe the same bug." + "reason": "Flash Attention test failures and `_gpu_broadcast_one` NoneType errors are different runtime problems." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Different import failures: flash attention utility symbol vs missing `HybridCache` export." + "reason": "Both are import errors, but for different symbols and packages; not the same breakage." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "SigLIP2 example issues are unrelated to BeitImageProcessorFast `reduce_labels` returning the wrong shape." + "reason": "SigLIP2 docs/model example problems are unrelated to BeitImageProcessorFast label reduction." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "Base-model-prefix loading breakage and Qwen3-VL weight-shape mismatch are distinct loading problems." + "reason": "Base-model-prefix loading breakage and Qwen3-VL weight-shape mismatch are distinct loading failures." }, { "left": "issue:44206", "right": "issue:45823", "accept": false, - "reason": "Both are device-related, but one is an audio feature-extractor arg bug and the other is Gemma4 PLE forward device mismatch." + "reason": "Both mention device mismatch, but they involve different models, setups, and code paths." }, { "left": "issue:44462", "right": "issue:44561", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json is unrelated to `is_torch_fx_available` removal fallout." + "reason": "Tokenizer.json precedence is unrelated to the v5 `is_torch_fx_available` removal regression." }, { "left": "issue:44561", "right": "issue:44779", "accept": false, - "reason": "Both are v5 breakages, but they affect different subsystems: remote-code FX helper removal vs Deepseek tokenizer results." + "reason": "Different breakages: remote-code import helper removal vs Deepseek tokenizer output regression." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "Sparse-layer config bug and BigBirdTokenizer special-token registration issue are unrelated." + "reason": "Sparse-layer config bug and BigBird tokenizer special-token issue are unrelated." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "DAC latent mismatch is unrelated to unexpected position-id key warnings across many models." + "reason": "DAC latent mismatch is unrelated to position-id key warnings across models." }, { "left": "issue:43550", "right": "issue:44112", "accept": false, - "reason": "Bamba torch.compile/SDPA failure is unrelated to the GraniteSpeech stale CI device override test." - }, - { - "left": "issue:45310", - "right": "issue:45478", - "accept": true, - "reason": "Same concrete bug: both report `transformers>=5.4.0` breaking `Qwen3.5 Moe from_pretrained`; 45478 is effectively a duplicate of 45310." - }, - { - "left": "issue:29127", - "right": "issue:32090", - "accept": false, - "reason": "LayoutLMv3 box-content error handling and Trainer `_gpu_broadcast_one` NoneType type error are different issues." - }, - { - "left": "issue:43335", - "right": "issue:43504", - "accept": false, - "reason": "SwitchTransformers sparse-layer creation and Beit semantic-segmentation legacy-field loading are unrelated." - }, - { - "left": "issue:45588", - "right": "issue:45859", - "accept": false, - "reason": "Both involve flash/offload paths, but `s_aux=None` AttributeError and Qwen3_5Moe rotary embedding CPU-offload incompatibility are different code paths." + "reason": "Bamba torch.compile/SDPA failure and GraniteSpeech CI stale test are different issues." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The duplicate judgment for 45310/45478 is strongly supported by the identical issue titles and matching regression description, and the rest of the pair verdicts do not overstate similarity." - }, - "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 }, @@ -7746,22 +7724,20 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:28218", + "issue:29127", "issue:29942", "issue:32090", - "issue:33357", "issue:34689", "issue:35141", "issue:37428", "issue:38175", "issue:39692", "issue:40444", - "issue:43278", - "issue:43329", "issue:43335", - "issue:43412", + "issue:43504", "issue:43526", "issue:43550", "issue:43606", @@ -7785,9 +7761,10 @@ "issue:45083", "issue:45198", "issue:45229", - "issue:45245", + "issue:45310", "issue:45372", "issue:45459", + "issue:45478", "issue:45491", "issue:45520", "issue:45563", @@ -7795,10 +7772,15 @@ "issue:45593", "issue:45698", "issue:45712", - "issue:45803" + "issue:45803", + "issue:45859" ], "soft_pairs": [ + "issue:43335|issue:43504", + "issue:45310|issue:45478", + "issue:29127|issue:32090", "issue:44855|issue:45083", + "issue:45588|issue:45859", "issue:43335|issue:45083", "issue:39692|issue:44493", "issue:44292|issue:45520", @@ -7808,263 +7790,255 @@ "issue:43335|issue:45593", "issue:43720|issue:44112", "issue:44977|issue:45229", - "issue:43723|issue:44554", "issue:40444|issue:43526", "issue:34689|issue:35141", - "issue:44448|issue:44977", + "issue:43723|issue:44554", "issue:43606|issue:44857", - "issue:44568|issue:45491", + "issue:44448|issue:44977", "issue:44857|issue:45072", - "issue:43927|issue:45698", + "issue:44568|issue:45491", "issue:28218|issue:32090", + "issue:43927|issue:45698", "issue:44977|issue:45563", - "issue:45459|issue:45712", "issue:45198|issue:45803", - "issue:43701|issue:45083", "issue:29942|issue:35141", - "issue:45372|issue:45588", + "issue:43701|issue:45083", + "issue:45459|issue:45712", + "issue:43873|issue:44493", "issue:37428|issue:44987", "issue:43550|issue:45083", - "issue:43873|issue:44493", - "issue:32090|issue:33357", - "issue:43412|issue:45588", - "issue:43873|issue:45229", - "issue:43278|issue:43329", - "issue:45245|issue:45563" + "issue:45372|issue:45588" ], - "prepared_review_unit_hash": "270f4d743cb6aafb37efc86925439812f896f9016be6a4528ec4e01f0563c9f0", + "prepared_review_unit_hash": "7a7984a3a8d71bd48e759aa74516c38a527fb39c169b2f9ffd21896de852ae3f", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37886, - "estimated_input_tokens": 9472, - "estimated_eval_tokens": 19200 + "soft_pair_count": 32, + "serialized_chars": 37529, + "estimated_input_tokens": 9383, + "estimated_eval_tokens": 19022 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous: the soft pairs span unrelated tokenizer, attention, loading, offload, multimodal, and CI failures. I don\u2019t see any pair that clearly shares the same underlying bug/change, so no duplicates should be merged here.", - "confidence": 0.98, - "canonical_issue_reason": null, + "summary": "This cluster is mostly a bag of unrelated Transformers bug reports. The only clear duplicate pair is the Qwen3.5 MoE from_pretrained regression: 45310 and 45478. All other soft matches are superficial topic/subsystem similarity and should be rejected.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45310 is the original report in the only obvious duplicate pair; it names the concrete Qwen3.5 MoE from_pretrained regression and predates issue:45478.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:45310 is the best representative issue because it is specific, concrete, and has a true duplicate counterpart in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "Different bugs in different BEiT/SwitchTransformers code paths; only broad model-family similarity." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same Qwen3.5 MoE from_pretrained failure, same title, and 45478 is a later duplicate report of the same regression." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 error-message clarity vs Trainer/_gpu_broadcast_one NoneType crash; unrelated failures." + }, { "left": "issue:44855", "right": "issue:45083", "accept": false, - "reason": "Python 3.13 import/script parsing bug vs qwen3_omni_moe feature-length helper behavior; unrelated code paths." + "reason": "Python 3.13 IndentationError in DebertaV2 import vs qwen3_omni_moe feature-length helper behavior; different code paths." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both involve offload/attention-related areas, but one is a flash_attention crash on s_aux=None and the other is a rotary embedding CPU-offload incompatibility." }, { "left": "issue:43335", "right": "issue:45083", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug vs qwen3_omni_moe length calculation; different models and failures." + "reason": "Different models and defects; one is sparse-layer config creation, the other is a helper-length calculation bug." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 doc/example errors vs generic position-id key warnings; different symptoms and roots." + "reason": "SigLIP2 docs example errors vs unexpected position-id keys across many models; not the same underlying bug." }, { "left": "issue:44292", "right": "issue:45520", "accept": false, - "reason": "Qwen-3-8B-NVFP4 runtime failure vs flash_attn import KeyError on Python 3.13; not the same bug." + "reason": "Qwen-3-8B-NVFP4 runtime error vs Python 3.13 flash_attn import KeyError; different failure modes." }, { "left": "issue:44448", "right": "issue:44779", "accept": false, - "reason": "Different model-specific output regressions in v4/v5; too broad to be one concrete change." + "reason": "Pegasus v4/v5 output mismatch vs Deepseek tokenizer regression; both tokenizer/generation related but not the same bug." }, { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "Zero probabilities in SigLIP2 vs unexpected position-id keys; unrelated model behavior." + "reason": "Unexpected zero probabilities in SigLIP2 vs generic unexpected position-id keys; different symptoms and likely causes." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "Config creates sparse layer at zero layers vs bfloat16 dtype mismatch in inference; different defects." + "reason": "Sparse-layer config bug vs dtype mismatch in bfloat16 inference; unrelated issues." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "SwitchTransformers config bug vs D-FINE auxiliary-loss behavior; no shared underlying issue." + "reason": "SwitchTransformers sparse-layer creation vs D-FINE auxiliary-loss behavior; different subsystems and outcomes." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "Packed-weight loading failure vs stale GraniteSpeech CI test; different subsystems and failures." + "reason": "Both CI-related, but one is packed-weight loading with accelerate and the other is a stale device override test; not the same bug." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Flash-attention generation bug in Qwen3.5 vs multi-GPU CUDA OOM in Gemma4; not the same fix." - }, - { - "left": "issue:43723", - "right": "issue:44554", - "accept": false, - "reason": "Tokenizer loading regression in v5 vs MPS attention correctness issue; unrelated paths." + "reason": "Qwen3.5 flash-attention generation issue vs Gemma4 multi-GPU CUDA OOM; different concrete problems." }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "IterableDataset multi-image finetuning failure vs BeitImageProcessorFast reduce_labels bug; different components." + "reason": "IterableDataset multi-image finetuning failure vs BeitImageProcessorFast reduce_labels bug; unrelated." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Llama 3.2 model loading breakage vs embedding reinit after resize; distinct model-init issues." + "reason": "Llama 3.2 Vision model loading breakage vs embedding reinitialization after resize; both model-loading related but distinct root causes." }, { - "left": "issue:44448", - "right": "issue:44977", + "left": "issue:43723", + "right": "issue:44554", "accept": false, - "reason": "Pegasus output drift vs Qwen3.5 flash-attention generation bug; different models and code paths." + "reason": "AutoTokenizer v5 loading issue vs MPS attention correctness when value head dim differs; unrelated bugs." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "CPU offload device mismatch vs LwDetrImageLoss AMP crash; unrelated failure modes." + "reason": "CPU offload device mismatch in Bark vs LwDetrImageLoss AMP/CUDA crash; different code paths and symptoms." }, { - "left": "issue:44568", - "right": "issue:45491", + "left": "issue:44448", + "right": "issue:44977", "accept": false, - "reason": "Tokenizer special-token regression vs Gemma3 NaN embeddings from sliding-window attention; no shared root cause." + "reason": "Different models and regressions: Pegasus output mismatch vs Qwen3.5 flash-attention generation failure." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "CUDA AMP loss crash vs dtype mismatch in inference; different bugs." + "reason": "AMP/CUDA loss crash vs bfloat16 dtype mismatch in inference; not the same underlying issue." }, { - "left": "issue:43927", - "right": "issue:45698", + "left": "issue:44568", + "right": "issue:45491", "accept": false, - "reason": "Custom token IDs lost on save/load vs wrong custom module loaded after save_pretrained; persistence-related but not the same concrete bug." + "reason": "Tokenizer add_special_tokens regression vs Gemma3 NaN embeddings from sliding-window attention; different components." }, { "left": "issue:28218", "right": "issue:32090", "accept": false, - "reason": "Tokenizer spacing issue vs Trainer _gpu_broadcast_one TypeError; completely unrelated." + "reason": "Tokenizer spacing bug vs Trainer GPU broadcast NoneType error; unrelated." }, { - "left": "issue:44977", - "right": "issue:45563", + "left": "issue:43927", + "right": "issue:45698", "accept": false, - "reason": "Flash-attention generation failure vs stale warning for num_return_sequences; not the same underlying issue." + "reason": "DiaConfig losing custom token IDs after save/load vs from_pretrained loading wrong custom module; both persistence-related but different failures." }, { - "left": "issue:45459", - "right": "issue:45712", + "left": "issue:44977", + "right": "issue:45563", "accept": false, - "reason": "Tokenizer error masking from import_protobuf_decode_error vs leftover dummy classes/check_repo cleanup; unrelated." + "reason": "Flash-attention generation failure vs a stale warning in paged generate; not the same bug." }, { "left": "issue:45198", "right": "issue:45803", "accept": false, - "reason": "Wav2Vec2 save/tokenization failure vs bare except swallowing errors in FuyuBatchFeature; different code paths." - }, - { - "left": "issue:43701", - "right": "issue:45083", - "accept": false, - "reason": "resume_from_checkpoint key mismatch vs qwen3_omni_moe helper bug; no shared defect." + "reason": "Wav2Vec2 save/tokenization failure vs bare except swallowing errors in FuyuBatchFeature; different models and error mechanisms." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Flash Attention 2 test failures vs embedding reinitialization after resize; unrelated." - }, - { - "left": "issue:45372", - "right": "issue:45588", - "accept": false, - "reason": "Gemma 4 processor import dependency break vs flash_attention s_aux=None AttributeError; different import/runtime issues." + "reason": "Flash Attention 2 test failures vs output embedding reinitialization after resizing; unrelated." }, { - "left": "issue:37428", - "right": "issue:44987", + "left": "issue:43701", + "right": "issue:45083", "accept": false, - "reason": "Missing flash_attention_utils symbol vs model loading failure for physical-intelligence/fast; too different to merge." + "reason": "resume_from_checkpoint key mismatch vs qwen3_omni_moe feature-length helper behavior; distinct issues." }, { - "left": "issue:43550", - "right": "issue:45083", + "left": "issue:45459", + "right": "issue:45712", "accept": false, - "reason": "torch.compile+SDPA bug in Bamba vs qwen3_omni_moe length helper issue; unrelated." + "reason": "Tokenizer error hiding when protobuf is absent vs leftover dummy classes in dummy_pt_objects.py; unrelated." }, { "left": "issue:43873", "right": "issue:44493", "accept": false, - "reason": "Quantization/offloading behavior vs unexpected position-id key warnings; not the same bug." - }, - { - "left": "issue:32090", - "right": "issue:33357", - "accept": false, - "reason": "Trainer broadcast NoneType error vs MacOS bus error on CLIP loading; different platforms and causes." - }, - { - "left": "issue:43412", - "right": "issue:45588", - "accept": false, - "reason": "Executorch export/erfinv training-guard issue vs flash_attention s_aux=None crash; separate failures." + "reason": "Quantization/offloading behavior issue vs unexpected position-id keys; only broad loading/runtime similarity." }, { - "left": "issue:43873", - "right": "issue:45229", + "left": "issue:37428", + "right": "issue:44987", "accept": false, - "reason": "Offloading with quantization vs Gemma4 multi-GPU OOM; different resource-management problems." + "reason": "Missing flash-support import in Python 3.13 vs transformers>=5.1.0 model loading failure; different causes." }, { - "left": "issue:43278", - "right": "issue:43329", + "left": "issue:43550", + "right": "issue:45083", "accept": false, - "reason": "Embedding dtype drift vs undefined multimodal-token helper variables; unrelated training/eval bugs." + "reason": "torch.compile + SDPA failure in Bamba vs qwen3_omni_moe helper-length bug; unrelated." }, { - "left": "issue:45245", - "right": "issue:45563", + "left": "issue:45372", + "right": "issue:45588", "accept": false, - "reason": "Category-count runtime error vs stale generate warning; no common underlying change." + "reason": "ReasoningEffort import breakage in Gemma4 processor loading vs flash_attention s_aux=None crash; same broad area, different concrete failures." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet. The Qwen3.5 MoE pair (45310/45478) has identical titles and close timestamps, so treating 45310 as the canonical/original report is reasonable. The rest of the soft-edge rejections are conservative and do not overclaim beyond broad topic similarity." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -8079,7 +8053,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:25251", "issue:28218", @@ -8087,10 +8061,7 @@ "issue:29942", "issue:30064", "issue:32090", - "issue:33290", "issue:33357", - "issue:34567", - "issue:39692", "issue:41720", "issue:42915", "issue:42994", @@ -8098,10 +8069,12 @@ "issue:43066", "issue:43257", "issue:43278", + "issue:43329", "issue:43381", + "issue:43412", "issue:43421", "issue:43653", - "issue:43756", + "issue:43873", "issue:43976", "issue:43994", "issue:44186", @@ -8113,13 +8086,13 @@ "issue:44462", "issue:44466", "issue:44479", - "issue:44610", "issue:44743", "issue:44857", "issue:44871", "issue:44977", "issue:45198", "issue:45229", + "issue:45245", "issue:45372", "issue:45406", "issue:45412", @@ -8127,10 +8100,16 @@ "issue:45459", "issue:45491", "issue:45520", + "issue:45563", "issue:45588", "issue:45823" ], "soft_pairs": [ + "issue:32090|issue:33357", + "issue:43412|issue:45588", + "issue:43873|issue:45229", + "issue:43278|issue:43329", + "issue:45245|issue:45563", "issue:41720|issue:45229", "issue:43976|issue:45440", "issue:28218|issue:29127", @@ -8142,8 +8121,8 @@ "issue:43278|issue:43381", "issue:44448|issue:44466", "issue:43065|issue:45412", - "issue:25251|issue:32090", "issue:45588|issue:45823", + "issue:25251|issue:32090", "issue:43653|issue:44743", "issue:44186|issue:45198", "issue:43994|issue:45412", @@ -8152,218 +8131,213 @@ "issue:42915|issue:42994", "issue:44361|issue:45198", "issue:44871|issue:44977", - "issue:43421|issue:45491", - "issue:44265|issue:45198", "issue:29942|issue:30064", - "issue:43756|issue:45440", - "issue:43257|issue:43278", - "issue:33357|issue:39692", - "issue:29127|issue:34567", - "issue:32090|issue:33290", - "issue:44610|issue:45412" + "issue:44265|issue:45198", + "issue:43421|issue:45491", + "issue:43257|issue:43278" ], - "prepared_review_unit_hash": "abf85833db1e49d7b5a91cf1f4be3f31db46eee9b84dbe3926b0c58e79c887bb", + "prepared_review_unit_hash": "3a32fc2f34823bf731ce44e59b2359f1c46298d98362b50e612e36019dc4c7fa", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36666, - "estimated_input_tokens": 9167, - "estimated_eval_tokens": 18590 + "serialized_chars": 36679, + "estimated_input_tokens": 9170, + "estimated_eval_tokens": 18596 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is not a duplicate set; it\u2019s a heterogeneous mix of unrelated tokenizer, model, training, and inference bugs. No soft pair looks like the same underlying issue or change.", - "confidence": 0.95, - "canonical_issue_reason": "No single canonical issue fits the cluster well because the items describe distinct bugs across different components. If a representative is needed, issue 45372 is one of the clearest concrete regression reports, but it does not subsume the others.", + "summary": "This set is largely a grab-bag of unrelated Transformers bugs rather than one tight duplicate cluster. I\u2019d use issue 45372 as the representative issue only because it is a clear, active Gemma4 regression with concrete repro context; otherwise most pairs should be kept separate.", + "confidence": 0.82, + "canonical_issue_reason": "Issue 45372 is the strongest representative because it is open, well-scoped, and has a concrete Gemma4 processor-loading failure with version-specific context.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45372 is the most concrete and actionable representative among the set, with a specific failure mode and visible impact, but it is still not a good duplicate anchor for the rest of the items.", + "best_issue_reason": "45372 is the best overall issue to anchor the cluster: it is actionable, reproducible, and more central than the other candidates.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Different failures: trainer broadcast TypeError vs MacOS bus error in a CLIP model." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export failure and flash-attention sink handling are separate code paths and symptoms." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization/offloading behavior is not the same bug as Gemma4 multi-GPU CUDA OOM." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Training/eval dtype drift is unrelated to the Qwen3.5 recurrent-state reset bug." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count runtime error and a stale generation warning are unrelated." + }, { "left": "issue:41720", "right": "issue:45229", "accept": false, - "reason": "Different problems: Qwen3 auto device mapping hits cudaErrorAssert, while Gemma4 multi-GPU inference hits CUDA OOM." + "reason": "Auto device-mapping assert and Gemma4 OOM are different model/runtime failures." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "One is a Python-version compatibility issue; the other is a model implementation divergence for DeepSeekV3MoE." + "reason": "Python version compatibility issue is unrelated to DeepSeekV3MoE divergence from remote impl." }, { "left": "issue:28218", "right": "issue:29127", "accept": false, - "reason": "Tokenizer extra-space behavior and LayoutLMv3 error-message clarity are unrelated bugs." + "reason": "Added-token spacing bug is not the same as a LayoutLMv3 error-message clarity issue." }, { "left": "issue:45372", "right": "issue:45406", "accept": false, - "reason": "Both involve Gemma4 processors, but one is an import error from mistral_common and the other is a missing _tokenizer attribute in serve; not the same bug." + "reason": "Both are Gemma4-related, but one is a mistral_common import failure and the other is a missing _tokenizer attribute in serve." }, { "left": "issue:45372", "right": "issue:45459", "accept": false, - "reason": "Import failure for ReasoningEffort and tokenizer error masking are distinct tokenizer-loading issues." + "reason": "Gemma4 processor import breakage is distinct from protobuf-masked tokenizer error handling." }, { "left": "issue:43065", "right": "issue:43994", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d and SigLIP2 nonsensical outputs are unrelated model issues." + "reason": "Dummy Conv2d placeholder in Sam3PixelDecoder is unrelated to Siglip2 bad outputs." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Wrong decoder type in v5 and AutoTokenizer ignoring tokenizer.json are different tokenizer-loading/serialization bugs." + "reason": "Tokenizer decoder type mismatch and AutoTokenizer ignoring tokenizer.json are different tokenizer-loading bugs." }, { "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "AMP/CUDA loss crash and flash-attention s_aux=None crash affect different code paths." + "reason": "AMP loss crash and flash_attention s_aux=None crash do not share the same failure mechanism." }, { "left": "issue:43278", "right": "issue:43381", "accept": false, - "reason": "Embedding dtype drift and gradient-checkpointing-in-eval-mode are separate evaluation/training-state problems." + "reason": "Embedding dtype regression is unrelated to the eval-mode gradient-checkpointing restriction." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Pegasus output differences across versions and lm_head.weight serialization inconsistency are not the same defect." + "reason": "Pegasus output mismatch and lm_head.weight serialization inconsistency are separate issues." }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "A dummy convolution in Sam3PixelDecoder is unrelated to an RT-DETR memory leak." + "reason": "Sam3PixelDecoder dummy layer bug is unrelated to RT-DETR memory not being released." }, { - "left": "issue:25251", - "right": "issue:32090", + "left": "issue:45588", + "right": "issue:45823", "accept": false, - "reason": "Pipeline top_k nesting behavior and Trainer _gpu_broadcast_one NoneType errors are unrelated." + "reason": "Flash-attention sink-less crash and Gemma4 PLE device mismatch are different forward-path problems." }, { - "left": "issue:45588", - "right": "issue:45823", + "left": "issue:25251", + "right": "issue:32090", "accept": false, - "reason": "Flash-attention auxiliary-state crash and Gemma4 PLE device mismatch are different forward-pass issues." + "reason": "Pipeline top_k shape change is unrelated to Trainer broadcast of NoneType." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "BigBirdTokenizer special-token decoding and Qwen3.5 recurrent state resetting are unrelated." + "reason": "Tokenizer special-token decode failure is unrelated to Qwen3.5 recurrent-state reset." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "LayoutLMv2Tokenizer NER/padding crashes and Wav2Vec2 save/tokenization failures are different tokenizer/model paths." + "reason": "LayoutLMv2 tokenizer crashes and Wav2Vec2 save/tokenization failures affect different components." }, { "left": "issue:44206", "right": "issue:44479", "accept": false, - "reason": "Feature extractor center-arg crash and video-input regression are separate processor bugs." + "reason": "Unsupported center arg in an extractor is not the same regression as Qwen video input handling." }, { "left": "issue:44451", "right": "issue:45520", "accept": false, - "reason": "ScandiBERT loading failure and flash_attn import on Python 3.13 are unrelated." + "reason": "Cannot load ScandiBERT and flash_attn KeyError on Python 3.13 are unrelated." }, { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed and quantized model saving are different quantization/loading problems." + "reason": "MOE weight conversion during loading is a different code path from quantized model saving." }, { "left": "issue:44361", "right": "issue:45198", "accept": false, - "reason": "MLukeTokenizer task AttributeError and Wav2Vec2 save/tokenization failure are unrelated." + "reason": "MLukeTokenizer AttributeError is unrelated to Wav2Vec2 save_pretrained/tokenization failure." }, { "left": "issue:44871", "right": "issue:44977", "accept": false, - "reason": "Gemma eos_token_id inconsistency and Qwen3.5 flash-attention generation failure are different issues." + "reason": "Gemma eos_token_id inconsistency is not the same as the Qwen3.5 flash-attention generation bug." }, { - "left": "issue:43421", - "right": "issue:45491", + "left": "issue:29942", + "right": "issue:30064", "accept": false, - "reason": "Runtime special-token post-processor updates and Gemma3 NaN embeddings do not share the same bug." + "reason": "Flash Attention 2 test failures and void segmentation-map processing are different issues." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "torch.export failure with torch_compilable_check is unrelated to Wav2Vec2 save/tokenization failure." - }, - { - "left": "issue:29942", - "right": "issue:30064", - "accept": false, - "reason": "Flash Attention 2 test failures and void segmentation map processing are different problems." + "reason": "torch.export guard failures are unrelated to Wav2Vec2 save/tokenization failures." }, { - "left": "issue:43756", - "right": "issue:45440", + "left": "issue:43421", + "right": "issue:45491", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and DeepSeekV3MoE divergence are unrelated model-architecture bugs." + "reason": "Runtime special-token post-processor updates and Gemma3 NaN embeddings are different bugs." }, { "left": "issue:43257", "right": "issue:43278", "accept": false, - "reason": "MoE weight conversion/loading and embedding dtype changes are separate concerns." - }, - { - "left": "issue:33357", - "right": "issue:39692", - "accept": false, - "reason": "CLIP bus error on macOS and SigLIP2 documentation/model mismatch are not the same underlying bug." - }, - { - "left": "issue:29127", - "right": "issue:34567", - "accept": false, - "reason": "Error-message clarity for LayoutLMv3 boxes and TrainerState token counter not updating are unrelated." - }, - { - "left": "issue:32090", - "right": "issue:33290", - "accept": false, - "reason": "NoneType broadcast in Trainer and AdaFactor OOM in DeepSpeed are distinct training failures." - }, - { - "left": "issue:44610", - "right": "issue:45412", - "accept": false, - "reason": "OmDet-Turbo processor image-size mismatch and RT-DETR memory retention are unrelated." + "reason": "Qwen3 MoE loading with deepspeed is unrelated to embedding dtype changes between train and eval." } ] }, @@ -8385,13 +8359,17 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:29127", "issue:29942", + "issue:32090", + "issue:33290", "issue:33357", + "issue:34567", "issue:35141", "issue:36010", + "issue:39692", "issue:42915", "issue:43232", "issue:43262", @@ -8402,41 +8380,42 @@ "issue:43526", "issue:43531", "issue:43575", - "issue:43646", "issue:43653", "issue:43701", - "issue:43723", + "issue:43756", "issue:43761", "issue:43824", "issue:43931", - "issue:44077", - "issue:44079", + "issue:44062", "issue:44186", - "issue:44188", "issue:44206", "issue:44279", - "issue:44387", "issue:44442", "issue:44464", + "issue:44610", "issue:44743", "issue:44811", "issue:44857", "issue:44977", - "issue:45003", "issue:45072", "issue:45103", "issue:45245", "issue:45372", + "issue:45412", "issue:45440", - "issue:45479", "issue:45491", "issue:45588", "issue:45593", - "issue:45803", "issue:45834", - "issue:45859" + "issue:45859", + "issue:45907" ], "soft_pairs": [ + "issue:43756|issue:45440", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:32090|issue:33290", + "issue:44610|issue:45412", "issue:45103|issue:45372", "issue:43824|issue:44279", "issue:45440|issue:45593", @@ -8449,226 +8428,214 @@ "issue:29127|issue:33357", "issue:43334|issue:43531", "issue:29127|issue:35141", - "issue:44977|issue:45245", "issue:44464|issue:45491", + "issue:44977|issue:45245", "issue:42915|issue:43931", "issue:44442|issue:45072", "issue:43262|issue:44206", "issue:43526|issue:44857", "issue:43232|issue:43388", + "issue:44062|issue:45907", "issue:43441|issue:45588", "issue:44743|issue:44811", - "issue:43575|issue:43701", - "issue:43646|issue:44077", - "issue:43575|issue:44387", - "issue:45003|issue:45440", - "issue:43761|issue:44079", - "issue:43723|issue:45479", - "issue:44442|issue:45803", - "issue:43761|issue:44188" + "issue:43575|issue:43701" ], - "prepared_review_unit_hash": "82cbbab1e83eafb6628b13e4faeee4cc14a10109dceac60f8580b8fb7a21eb33", + "prepared_review_unit_hash": "59bff6e8367c5337cea820e5853cae93e0737886a39b3c1c68d0f0cf2dd8cfd3", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36518, - "estimated_input_tokens": 9130, - "estimated_eval_tokens": 18516 + "soft_pair_count": 28, + "serialized_chars": 36186, + "estimated_input_tokens": 9047, + "estimated_eval_tokens": 18350 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is not a duplicate cluster. The issues cover many unrelated regressions across tokenizers, generation, audio/vision processors, model loading, quantization, and training utilities, so there is no single canonical bug/change to merge around.", - "confidence": 0.97, - "canonical_issue_reason": "No clear canonical issue: the items are largely unrelated, and the soft pairs do not describe the same underlying defect.", + "summary": "The set is heterogeneous: the soft pairs span unrelated bugs in training, model loading, processors, generation, and docs. All soft-edge candidates should be rejected as duplicate matches.", + "confidence": 0.94, + "canonical_issue_reason": "issue:29127 is the most central of the weakly related items and is a concrete, self-contained bug report, but the batch is not a true duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a strong global representative; the cluster is heterogeneous, so any single issue would be arbitrary.", + "best_issue_reason": "If forced to pick a representative issue, issue:29127 has the clearest failure description; still, there is no strong global canonical because the items are unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:45103", - "right": "issue:45372", + "left": "issue:43756", + "right": "issue:45440", "accept": false, - "reason": "Both are import/annotation-related crashes, but they fail for different reasons in different code paths: auto_docstring kwargs parsing vs mistral_common ReasoningEffort import." + "reason": "Different bugs: RoPE layer selection in Smollm3 vs a divergence between native and remote DeepSeekV3 implementations." }, { - "left": "issue:43824", + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error on CLIP loading is unrelated to a SigLIP2 doc example/model-processor mismatch and quantization failure." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity is unrelated to TrainerState's num_input_tokens_seen not updating." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "One is a NoneType broadcast error in Trainer; the other is an OOM issue with Adafactor in DeepSpeed." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor output-size mismatch is unrelated to RT-DETR memory not being released on deletion." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation parsing and a ReasoningEffort import break are distinct code paths and failure modes." + }, + { + "left": "issue:43824", "right": "issue:44279", "accept": false, - "reason": "Both mention loading/dependency problems, but one is a missing Qwen2.5-VL symbol and the other is a generic transformer dependency issue; not the same bug." + "reason": "Missing Qwen2.5-VL export/import is not the same as a generic dependency issue." }, { "left": "issue:45440", "right": "issue:45593", "accept": false, - "reason": "Different model-specific behavior: DeepseekV3MoE parity divergence vs D-FINE auxiliary-loss handling when denoising is off." + "reason": "DeepSeekV3 implementation divergence is unrelated to D-FINE auxiliary-loss behavior when denoising is off." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "Both concern tokenizers, but one is BigBird special-token registration/empty decode and the other is AutoTokenizer failing to load FastSpeech2ConformerTokenizer." + "reason": "BigBirdTokenizer special-token registration and AutoTokenizer loading FastSpeech2ConformerTokenizer are different tokenizer bugs." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Unrelated problems: gradient checkpointing in eval mode vs resume_from_checkpoint key mismatch." + "reason": "Gradient checkpointing in eval mode is unrelated to a resume_from_checkpoint key mismatch." }, { "left": "issue:43761", "right": "issue:45859", "accept": false, - "reason": "Different model and subsystem: CLIPVisionModel hidden_states regression vs Qwen3_5MoeTextRotaryEmbedding CPU offload incompatibility." + "reason": "CLIPVision hidden_states being None is unrelated to Qwen3_5MoeTextRotaryEmbedding CPU-offload compatibility." }, { "left": "issue:43526", "right": "issue:45834", "accept": false, - "reason": "Different processors and failures: BEiT reduce_labels output vs Kosmos2.5 OCR long-input index error." + "reason": "BEiT reduce_labels returning one label and Kosmos2.5 long-ocr index errors are different failures." }, { "left": "issue:29942", "right": "issue:36010", "accept": false, - "reason": "Flash Attention 2 test failures are not the same as a GenerationMixin import error; unrelated regressions." + "reason": "Flash Attention test failures are unrelated to GenerationMixin import resolution." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "Both are preprocessing bugs, but BEiT reduce_labels and LayoutLMv2Tokenizer NER padding/truncation are distinct code paths." + "reason": "A BEiT label-reduction bug is not the same as LayoutLMv2Tokenizer crashing on NER/padding inputs." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 box-information error handling is unrelated to the MacOS bus error in a community CLIP model." + "reason": "LayoutLMv3 error-message wording is unrelated to a CLIP MacOS bus error." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Both are Qwen3-family issues, but one is a missing pad_token_id on Qwen3-VL loading and the other is a sliding_window bug in Qwen3-MoE." + "reason": "Missing pad_token_id in Qwen3-VL text config is different from a sliding_window issue in Qwen3-MoE." }, { "left": "issue:29127", "right": "issue:35141", "accept": false, - "reason": "Different defects in different areas: LayoutLMv3 error messaging vs token-embedding resizing reinitialization in post_init." + "reason": "Poor error messaging in LayoutLMv3 has no overlap with token-embedding reinitialization after resize." }, { - "left": "issue:44977", - "right": "issue:45245", + "left": "issue:44464", + "right": "issue:45491", "accept": false, - "reason": "Qwen3.5 flash-attention generation issues are unrelated to the 2^24 category-count limit error." + "reason": "Chunked generation with compiled forward and Gemma3 NaNs from sliding-window/all-padding behavior are different bugs." }, { - "left": "issue:44464", - "right": "issue:45491", + "left": "issue:44977", + "right": "issue:45245", "accept": false, - "reason": "Both involve generation/attention behavior, but one is compiled chunked generation inconsistency and the other is Gemma3 NaNs from sliding-window all-padding windows." + "reason": "Qwen3.5 flash-attention generation issues are unrelated to the 2^24 category limit runtime error." }, { "left": "issue:42915", "right": "issue:43931", "accept": false, - "reason": "Same broad model family name, but different failures: FineGrainedFP8Config compatibility vs Qwen3-VL weight-shape mismatch." + "reason": "FineGrainedFP8Config on Qwen3Moe and Qwen3-VL weight-shape mismatch are separate model-loading problems." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "Tokenizer loading failure and bfloat16 dtype mismatch are unrelated bugs." + "reason": "Tokenizer load failure and bf16 dtype mismatches are unrelated failures." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting is unrelated to the unsupported center argument in a feature extractor." + "reason": "Audio chat-template sample-rate defaults are unrelated to LasrFeatureExtractor passing an unsupported center argument." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "BEiT reduce_labels output bug and LwDetrImageLoss float16 CUDA crash are different subsystems and failure modes." + "reason": "BEiT reduce_labels returning one label is unrelated to LwDetrImageLoss crashing under float16 AMP on CUDA." }, { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Generation kwargs handling after sync_gpus is unrelated to gather_for_metrics dropping label elements in the last batch." + "reason": "Generation kwargs after sync_gpus and gather_for_metrics dropping tuple labels are different subsystems and bugs." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken special-argument duplication is unrelated to list_repo_files not forwarding revision." }, { "left": "issue:43441", "right": "issue:45588", "accept": false, - "reason": "Both mention flash attention, but they appear to be different failures in different integrations and model assumptions." + "reason": "Ministral-3 flash-attention failure and s_aux=None in flash_attention.py are separate flash-attention issues." }, { "left": "issue:44743", "right": "issue:44811", "accept": false, - "reason": "Qwen3_5 recurrent-state reset and Whisper batch_decode skip_special_tokens are unrelated model/processor bugs." + "reason": "Recurrent states resetting in modular_qwen3_5.py is unrelated to Whisper batch_decode ignoring skip_special_tokens." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "Tensor-parallel OOM when loading a model is unrelated to a checkpoint key mismatch." - }, - { - "left": "issue:43646", - "right": "issue:44077", - "accept": false, - "reason": "Both involve initialization/post_init semantics, but one is a broad Transformers 5.0 custom model init breakage and the other is a specific patchtsmixer rule change." - }, - { - "left": "issue:43575", - "right": "issue:44387", - "accept": false, - "reason": "Both are OOM-related, but one is tensor-parallel load OOM for Qwen2-57B and the other is increased reserved memory during int4 quantization." - }, - { - "left": "issue:45003", - "right": "issue:45440", - "accept": false, - "reason": "Unsafe sys.modules access in modeling_utils is unrelated to DeepseekV3MoE output divergence." - }, - { - "left": "issue:43761", - "right": "issue:44079", - "accept": false, - "reason": "ModelOutput key assignment rules do not match the CLIPVisionModel hidden_states regression; different layers of the stack." - }, - { - "left": "issue:43723", - "right": "issue:45479", - "accept": false, - "reason": "Tokenizer loading in v5 and degenerate zero-loss classification with num_labels=1 are unrelated issues." - }, - { - "left": "issue:44442", - "right": "issue:45803", - "accept": false, - "reason": "AutoTokenizer load failure for one tokenizer is unrelated to a bare except swallowing errors in FuyuBatchFeature.convert_to_tensors()." - }, - { - "left": "issue:43761", - "right": "issue:44188", - "accept": false, - "reason": "Hidden-states regression in CLIPVisionModel is unrelated to attention-kernel divergence under torch.compile." + "reason": "Tensor-parallel OOM when loading Qwen2-57B-A14B is unrelated to a resume_from_checkpoint key mismatch." } ] }, @@ -8690,10 +8657,8 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:25251", - "issue:28282", "issue:33290", "issue:34567", "issue:34689", @@ -8702,297 +8667,303 @@ "issue:36331", "issue:39692", "issue:41628", - "issue:42175", "issue:42907", "issue:43316", "issue:43381", "issue:43493", "issue:43525", - "issue:43540", "issue:43550", + "issue:43575", "issue:43611", "issue:43643", - "issue:43673", + "issue:43646", "issue:43720", - "issue:43742", + "issue:43723", "issue:43749", + "issue:43761", "issue:43827", "issue:43856", "issue:43873", "issue:43931", "issue:44077", + "issue:44079", + "issue:44188", "issue:44190", + "issue:44387", "issue:44442", "issue:44479", "issue:44496", - "issue:44514", "issue:44743", - "issue:44855", "issue:44871", - "issue:44877", "issue:44898", "issue:44913", - "issue:45137", + "issue:45003", "issue:45216", "issue:45290", "issue:45372", + "issue:45440", + "issue:45479", "issue:45491", "issue:45698", - "issue:45759" + "issue:45759", + "issue:45803" ], "soft_pairs": [ + "issue:43575|issue:44387", + "issue:43646|issue:44077", + "issue:45003|issue:45440", + "issue:43761|issue:44079", + "issue:43723|issue:45479", + "issue:44442|issue:45803", + "issue:43761|issue:44188", "issue:43316|issue:43525", "issue:44479|issue:45290", "issue:42907|issue:45698", - "issue:33290|issue:34567", "issue:44442|issue:44898", + "issue:33290|issue:34567", "issue:34689|issue:43611", "issue:39692|issue:45491", "issue:33290|issue:35141", "issue:33290|issue:34689", "issue:43381|issue:43873", "issue:43931|issue:45216", - "issue:43550|issue:44743", "issue:43493|issue:43827", + "issue:43550|issue:44743", "issue:44077|issue:44479", - "issue:41628|issue:45372", - "issue:43316|issue:45759", "issue:43720|issue:44442", + "issue:43316|issue:45759", + "issue:41628|issue:45372", "issue:43643|issue:44913", "issue:43749|issue:43931", "issue:33290|issue:36331", - "issue:43873|issue:44871", "issue:34689|issue:36010", - "issue:44190|issue:44496", + "issue:43873|issue:44871", "issue:43381|issue:43856", - "issue:44855|issue:45137", - "issue:43381|issue:43742", - "issue:43316|issue:44877", - "issue:43540|issue:44514", - "issue:42175|issue:43316", - "issue:43673|issue:44743", - "issue:25251|issue:28282" + "issue:44190|issue:44496" ], - "prepared_review_unit_hash": "987bd375532995b07c2a9973ffda7a5aebfdf9a00d7de26b7a690d0ba323d351", + "prepared_review_unit_hash": "8f3c3f0d7d5e431e1c56b7493e4968526eef2978f8a964173f419a233b577682", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36571, - "estimated_input_tokens": 9143, - "estimated_eval_tokens": 18542 + "serialized_chars": 37229, + "estimated_input_tokens": 9308, + "estimated_eval_tokens": 18872 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are not one duplicate cluster; they cover unrelated bugs across training, loading, configs, multimodal processors, docs, and saving behavior. None of the soft pairs look like the same underlying issue/change.", - "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue: the set is heterogeneous and the soft pairs are mostly false positives, so collapsing them would mix unrelated bugs.", + "summary": "Most pairs are still best treated as non-duplicates. The one previously over-accepted edge, issue:43761 vs issue:44079, is related by symptom and mechanism, but the packet only supports a plausible connection\u2014not a confident same-bug match\u2014so it should stay rejected.", + "confidence": 0.86, + "canonical_issue_reason": "issue:44079 is the best representative of the ModelOutput key-assignment bug family because it states the framework-level mechanism directly; issue:43761 looks like a possible downstream symptom, but not enough to collapse the two into one issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the strongest triage anchor only because it is open and has the most inbound references/discussion, but it does not represent the rest of the set.", + "best_issue_reason": "issue:44079 is the strongest cluster representative: it describes the underlying ModelOutput bug in its most general form, while the CLIPVisionModel report is narrower and less conclusive as a duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is tensor-parallel loading and the other is int4/CUDA reserved-memory behavior; different code paths and fixes." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Both involve initialization semantics, but they point to different model-specific regressions rather than the same bug." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils is unrelated to DeepSeekV3MoE implementation divergence." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "The CLIPVisionModel symptom is plausibly related to the ModelOutput bug, but the packet only supports inference, not a confident same-underlying-bug duplicate." + }, + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer loading in v5 and a zero-loss sequence-classification bug are unrelated subsystems and failure modes." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "A tokenizer load failure is unrelated to FuyuBatchFeature's bare-except error swallowing." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "ModelOutput handling and attention-kernel divergence under torch.compile are different bugs." + }, { "left": "issue:43316", "right": "issue:43525", "accept": false, - "reason": "Different config/API mismatches: Gemma3TextConfig discrepancy vs missing pad_token_id in Llama4Config." + "reason": "Both are config API issues, but they concern different models and different missing/discrepant fields." }, { "left": "issue:44479", "right": "issue:45290", "accept": false, - "reason": "Separate multimodal chat-template bugs with different triggers and model families." + "reason": "Video-input regression and chat-template tool-call crash are separate code paths." }, { "left": "issue:42907", "right": "issue:45698", "accept": false, - "reason": "One is save/dequantize failure; the other is loading the wrong custom module after save." + "reason": "Saving dequantized models and loading the wrong custom module after save_pretrained are different persistence bugs." }, { - "left": "issue:33290", - "right": "issue:34567", + "left": "issue:44442", + "right": "issue:44898", "accept": false, - "reason": "Different training bugs: Adafactor OOM in DeepSpeed vs num_input_tokens_seen not updating." + "reason": "Tokenizer loading failure is unrelated to Perceiver non-default-resolution image classification." }, { - "left": "issue:44442", - "right": "issue:44898", + "left": "issue:33290", + "right": "issue:34567", "accept": false, - "reason": "Tokenizer-loading failure is unrelated to Perceiver image classification resizing/interpolation." + "reason": "DeepSpeed/Adafactor OOM and TrainerState token-count tracking are unrelated." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are loading regressions, but for different causes and model-loading code paths." + "reason": "Both are model-loading regressions, but they involve different release changes and different root causes." }, { "left": "issue:39692", "right": "issue:45491", "accept": false, - "reason": "SigLIP2 docs errors are unrelated to Gemma3 NaN embeddings during mixed-length batching." + "reason": "Documentation example errors and Gemma3 NaN embeddings are unrelated." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "Different mechanisms: DeepSpeed Adafactor memory blowup vs embedding reinit on resize." + "reason": "Optimizer OOM and embedding reinitialization in post_init are unrelated." }, { "left": "issue:33290", "right": "issue:34689", "accept": false, - "reason": "Training OOM under DeepSpeed is not the same as a Llama 3.2 model-loading breakage." + "reason": "Optimizer memory blow-up and Llama model-loading breakage are different failures." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Eval-mode gradient checkpointing and quantization offloading are distinct behaviors." + "reason": "Gradient checkpointing in eval mode and quantization offloading are unrelated issues." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Weight-shape mismatch on load is unrelated to Qwen3.5 save_pretrained checkpoint corruption." + "reason": "A Qwen3-VL weight-shape mismatch and a Qwen3.5 save_pretrained regression are not the same bug." }, { - "left": "issue:43550", - "right": "issue:44743", + "left": "issue:43493", + "right": "issue:43827", "accept": false, - "reason": "torch.compile SDPA failure and recurrent-state reset in modular_qwen3_5 are different bugs." + "reason": "SigLIP2 implementation mismatch and docs still referencing pipeline() are unrelated." }, { - "left": "issue:43493", - "right": "issue:43827", + "left": "issue:43550", + "right": "issue:44743", "accept": false, - "reason": "SigLIP2 HF/JAX discrepancy is not the same as stale pipeline() docs after v5 removals." + "reason": "torch.compile+SDPA failure in Bamba and recurrent-state reset in modular_qwen3_5 are different model-path bugs." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "Optional post_init restriction for patchtsmixer is unrelated to video-input regression in Qwen VL models." + "reason": "PatchTSTMixer post_init allowance and Qwen video-input regression do not share a concrete code path." }, { - "left": "issue:41628", - "right": "issue:45372", + "left": "issue:43720", + "right": "issue:44442", "accept": false, - "reason": "AutoImageProcessor import failure and Gemma 4 processor loading failure involve different missing symbols." + "reason": "BitNet accelerate-loading unpacking bug is unrelated to AutoTokenizer loading FastSpeech2ConformerTokenizer." }, { "left": "issue:43316", "right": "issue:45759", "accept": false, - "reason": "Gemma3TextConfig API mismatch is unrelated to AutoModelForCausalLM unwrapping composite text_config." + "reason": "Both involve config behavior, but one is a Gemma3TextConfig API discrepancy and the other is Qwen multimodal text_config unwrapping." }, { - "left": "issue:43720", - "right": "issue:44442", + "left": "issue:41628", + "right": "issue:45372", "accept": false, - "reason": "BitNet unpacked-weight loading bug has no connection to tokenizer class loading." + "reason": "Both are import errors, but they stem from different dependencies and different processor-loading paths." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "trust_remote_code config field loss and GPTNeoX rotary_pct reload reset are different config issues." + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct resetting on reload are different serialization/reload bugs." }, { "left": "issue:43749", "right": "issue:43931", "accept": false, - "reason": "FSDP CPU/RAM-efficient loading and Qwen3-VL weight mismatch are unrelated loading paths." + "reason": "FSDP CPU RAM efficient loading and Qwen3-VL shape mismatch are unrelated loading problems." }, { "left": "issue:33290", "right": "issue:36331", "accept": false, - "reason": "DeepSpeed OOM is not the same as CustomTrainer compute_loss signature breakage." - }, - { - "left": "issue:43873", - "right": "issue:44871", - "accept": false, - "reason": "Quantization offloading issue and Gemma-3 eos_token_id inconsistency are separate bugs." + "reason": "OOM during optimizer use and CustomTrainer compute_loss signature mismatch are unrelated training issues." }, { "left": "issue:34689", "right": "issue:36010", "accept": false, - "reason": "Llama 3.2 Vision loading regression is unrelated to GenerationMixin import failure." + "reason": "Llama model-loading regression and GenerationMixin import failure are separate API breakages." }, { - "left": "issue:44190", - "right": "issue:44496", + "left": "issue:43873", + "right": "issue:44871", "accept": false, - "reason": "Local dataset loading failure has nothing to do with unrecognized model/config loading." + "reason": "Quantization offloading behavior and Gemma-3 eos_token_id inconsistency are unrelated." }, { "left": "issue:43381", "right": "issue:43856", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction and Qwen3 MoE memory inefficiency are different problems." + "reason": "Eval-mode gradient checkpointing and Qwen3 MoE memory inefficiency are different training/memory concerns." }, { - "left": "issue:44855", - "right": "issue:45137", - "accept": false, - "reason": "Python 3.13 IndentationError in DebertaV2 import is unrelated to ZeRO3 deque underflow." - }, - { - "left": "issue:43381", - "right": "issue:43742", - "accept": false, - "reason": "Gradient checkpointing behavior is not the same as MobileLLM key-error model loading." - }, - { - "left": "issue:43316", - "right": "issue:44877", - "accept": false, - "reason": "Gemma3TextConfig API discrepancy is unrelated to strict config blocking granite_speech." - }, - { - "left": "issue:43540", - "right": "issue:44514", - "accept": false, - "reason": "Qwen3OmniMoe video processing error and Qwen2_5_VL batched chat-template crash are different code paths." - }, - { - "left": "issue:42175", - "right": "issue:43316", - "accept": false, - "reason": "Backend packaging for pip install '.[torch]' is unrelated to Gemma3TextConfig API mismatch." - }, - { - "left": "issue:43673", - "right": "issue:44743", - "accept": false, - "reason": "Missing GenerationMixin cache in v5.0.0 and Qwen3.5 recurrent-state reset are different regressions." - }, - { - "left": "issue:25251", - "right": "issue:28282", + "left": "issue:44190", + "right": "issue:44496", "accept": false, - "reason": "Pipeline top_k nesting bug and AutoModel PyTorch ImportError are completely unrelated." + "reason": "Local dataset loading in an example script and an unrecognized model/config issue are unrelated." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The summary is mostly grounded, but one soft-edge verdict is too strong: it marks issue:43761 vs issue:44079 as a match even though the packet labels that pair deterministic_accept=false. From the packet alone, the CLIPVisionModel symptom may be compatible with the ModelOutput bug, but that is still an inference, not enough to override the conservative label. The other negatives look appropriately cautious." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -9008,304 +8979,276 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:16998", "issue:22355", - "issue:32090", - "issue:35141", + "issue:25251", + "issue:28282", "issue:41950", + "issue:42175", "issue:42617", "issue:43065", "issue:43295", + "issue:43316", + "issue:43381", "issue:43388", "issue:43404", "issue:43441", "issue:43452", "issue:43475", "issue:43504", + "issue:43540", "issue:43550", "issue:43575", "issue:43606", "issue:43646", + "issue:43673", "issue:43688", "issue:43701", "issue:43742", "issue:43761", "issue:43825", - "issue:43873", - "issue:43931", - "issue:44060", "issue:44077", "issue:44162", - "issue:44242", - "issue:44464", "issue:44479", "issue:44496", - "issue:44521", + "issue:44514", "issue:44534", - "issue:44610", "issue:44617", "issue:44734", + "issue:44743", "issue:44792", + "issue:44855", "issue:44871", + "issue:44877", "issue:44913", - "issue:44977", "issue:45127", + "issue:45137", "issue:45200", - "issue:45381", "issue:45406", - "issue:45563", "issue:45584", "issue:45698" ], "soft_pairs": [ + "issue:44855|issue:45137", + "issue:43381|issue:43742", + "issue:43316|issue:44877", + "issue:42175|issue:43316", + "issue:43540|issue:44514", + "issue:43673|issue:44743", + "issue:25251|issue:28282", "issue:43404|issue:43441", - "issue:43388|issue:43688", "issue:43065|issue:44617", "issue:44162|issue:44792", - "issue:41950|issue:43475", + "issue:43388|issue:43688", "issue:43295|issue:43825", + "issue:41950|issue:43475", "issue:16998|issue:22355", "issue:44077|issue:44534", - "issue:45127|issue:45200", "issue:44871|issue:45584", + "issue:45127|issue:45200", "issue:43550|issue:43701", - "issue:43761|issue:44479", "issue:43606|issue:43701", + "issue:43761|issue:44479", "issue:43295|issue:44871", - "issue:43452|issue:44496", - "issue:43575|issue:43742", "issue:42617|issue:43575", + "issue:43575|issue:43742", + "issue:43452|issue:44496", "issue:43646|issue:44913", "issue:44734|issue:45406", - "issue:43504|issue:45698", - "issue:43575|issue:43873", - "issue:43931|issue:44060", - "issue:44617|issue:45584", - "issue:43761|issue:44242", - "issue:32090|issue:35141", - "issue:45563|issue:45584", - "issue:44464|issue:44871", - "issue:44792|issue:44977", - "issue:44479|issue:44734", - "issue:43065|issue:44610", - "issue:44521|issue:45381" + "issue:43504|issue:45698" ], - "prepared_review_unit_hash": "5810b8eb9bf28b6e34f3d07f0eb54f0fad8542c5d593a1067f9faed19ac55f93", + "prepared_review_unit_hash": "9b8b8c4d93af672243b96922fd06fe48e57df1548026215c56917ec9eca0ce03", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36934, - "estimated_input_tokens": 9234, - "estimated_eval_tokens": 18724 + "soft_pair_count": 27, + "serialized_chars": 35714, + "estimated_input_tokens": 8929, + "estimated_eval_tokens": 18114 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is not a duplicate set: it contains many unrelated Transformers issues spanning model loading, multimodal regressions, trainer behavior, and serving bugs. All proposed soft edges are false positives based on superficial wording overlap rather than the same underlying defect.", - "confidence": 0.97, - "canonical_issue_reason": "No canonical issue stands out; the items are heterogeneous and the soft matches do not point to one shared bug.", + "summary": "This set is heterogeneous: mostly unrelated Transformers bug reports spanning different models, subsystems, and failure modes. I did not find any soft pair that clearly represents the same underlying bug/change, so all soft edges are rejected.", + "confidence": 0.35, + "canonical_issue_reason": "issue:43646 is the broadest and most umbrella-like report in the set, centered on a general v5 custom model initialization regression rather than a model-specific symptom.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a good global representative of this cluster; the strongest candidates are still unrelated to the rest.", + "best_issue_reason": "issue:43646 is the best representative because it describes a wide API-level regression that can subsume multiple narrower loading/init failures, even though the cluster is not a true duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43404", - "right": "issue:43441", - "accept": false, - "reason": "Both are model-specific failures, but one is a tied-weights bug and the other is a FlashAttention regression; different code paths." - }, - { - "left": "issue:43388", - "right": "issue:43688", - "accept": false, - "reason": "One is a metric gathering label-drop bug, the other is auxiliary-loss normalization; unrelated training logic." - }, - { - "left": "issue:43065", - "right": "issue:44617", + "left": "issue:44855", + "right": "issue:45137", "accept": false, - "reason": "Sam3 pixel-decoder dummy Conv2d vs Sam3Video OOM; same model family, different failures." + "reason": "Python 3.13 import/parsing failure vs DeepSpeed ZeRO3 deque underflow; unrelated code paths." }, { - "left": "issue:44162", - "right": "issue:44792", + "left": "issue:43381", + "right": "issue:43742", "accept": false, - "reason": "ESM2 breakage and a janus image-generation test failure are unrelated." + "reason": "Gradient checkpointing in eval mode vs MobileLLM config loading KeyError; different bugs." }, { - "left": "issue:41950", - "right": "issue:43475", + "left": "issue:43316", + "right": "issue:44877", "accept": false, - "reason": "Both involve video/SAM3-style multimodal components, but one is a pipeline processor lookup and the other is a missing output attribute." + "reason": "Gemma3TextConfig API mismatch vs granite_speech strict-config loading; both config-related but not the same failure." }, { - "left": "issue:43295", - "right": "issue:43825", + "left": "issue:42175", + "right": "issue:43316", "accept": false, - "reason": "One is a processor.tokenizer regression in custom model code; the other is an error-message mismatch for translation pipelines." + "reason": "Packaging backend omission vs Gemma3 config API discrepancy; unrelated." }, { - "left": "issue:16998", - "right": "issue:22355", + "left": "issue:43540", + "right": "issue:44514", "accept": false, - "reason": "DeBERTa model_max_length question and missing transformers.onnx module are unrelated." + "reason": "Video-input processing error vs batched chat template padding crash; different functions and symptoms." }, { - "left": "issue:44077", - "right": "issue:44534", + "left": "issue:43673", + "right": "issue:44743", "accept": false, - "reason": "Both are v5 initialization-related, but one is about optional post_init being disallowed and the other about non-persistent buffers being corrupted." + "reason": "Chunked prefill cache missing vs recurrent-state reset with cache; both cache-related but different concrete code paths." }, { - "left": "issue:45127", - "right": "issue:45200", + "left": "issue:25251", + "right": "issue:28282", "accept": false, - "reason": "LoRA/extended-vocab weight tying and Gemma 4 mm_token_type_ids defaults are separate bugs." + "reason": "Pipeline top_k nesting bug vs missing PyTorch ImportError; unrelated." }, { - "left": "issue:44871", - "right": "issue:45584", + "left": "issue:43404", + "right": "issue:43441", "accept": false, - "reason": "Token ID config mismatch vs Whisper empty-transcription behavior after align_special_tokens; different models and symptoms." + "reason": "Weight tying bug vs FlashAttention failure in a related model family, but not the same underlying defect." }, { - "left": "issue:43550", - "right": "issue:43701", + "left": "issue:43065", + "right": "issue:44617", "accept": false, - "reason": "torch.compile/SDPA OOM in Bamba is unrelated to a resume_from_checkpoint key mismatch." + "reason": "Dummy Conv2d implementation vs CUDA OOM in Sam3Video; not the same bug." }, { - "left": "issue:43761", - "right": "issue:44479", + "left": "issue:44162", + "right": "issue:44792", "accept": false, - "reason": "CLIPVision hidden_states regression and Qwen VL video-input regression are different model/code-path issues." + "reason": "ESM2 breakage vs janus image-generation test failure; different models and issues." }, { - "left": "issue:43606", - "right": "issue:43701", + "left": "issue:43388", + "right": "issue:43688", "accept": false, - "reason": "CPU offload device mismatch is unrelated to checkpoint key mismatch on resume." + "reason": "Last-batch metric gathering bug vs auxiliary-loss normalization bug; different training logic." }, { "left": "issue:43295", - "right": "issue:44871", - "accept": false, - "reason": "Custom processor/tokenizer regression and Gemma eos_token_id inconsistency do not share a bug." - }, - { - "left": "issue:43452", - "right": "issue:44496", - "accept": false, - "reason": "GGUF loading breaks for tokenizer/model from_pretrained, while the other is an unrecognized model_type config problem." - }, - { - "left": "issue:43575", - "right": "issue:43742", + "right": "issue:43825", "accept": false, - "reason": "Tensor-parallel OOM on Qwen2-57B and MobileLLM key-error loading failure are different load-time problems." + "reason": "Processor/tokenizer regression vs incorrect pipeline error text; both regressions but distinct code paths." }, { - "left": "issue:42617", - "right": "issue:43575", + "left": "issue:41950", + "right": "issue:43475", "accept": false, - "reason": "3d_parallel.py execution failure and Qwen2-57B TP OOM are unrelated." + "reason": "Video-classification processor selection bug vs SAM3 vision output attribute error; unrelated." }, { - "left": "issue:43646", - "right": "issue:44913", + "left": "issue:16998", + "right": "issue:22355", "accept": false, - "reason": "Custom model init breakage in v5 vs GPTNeoX rotary_pct reload default are separate config/model-loading bugs." + "reason": "model_max_length question vs missing transformers.onnx module; no overlap." }, { - "left": "issue:44734", - "right": "issue:45406", + "left": "issue:44077", + "right": "issue:44534", "accept": false, - "reason": "Serve KV-cache continuation crash and Gemma4Processor missing _tokenizer are unrelated." + "reason": "patchtsmixer post_init validation vs non-persistent buffers junk fill; unrelated." }, { - "left": "issue:43504", - "right": "issue:45698", + "left": "issue:44871", + "right": "issue:45584", "accept": false, - "reason": "Legacy field loading for BEiT semantic segmentation and wrong custom module loading after save_pretrained are different serialization issues." + "reason": "Gemma eos_token_id mismatch vs Whisper empty-transcription generation failure; different model-specific bugs." }, { - "left": "issue:43575", - "right": "issue:43873", + "left": "issue:45127", + "right": "issue:45200", "accept": false, - "reason": "Qwen TP OOM and offloading-with-quantization behavior are both memory-related but not the same concrete failure." + "reason": "LoRA merge/tied embeddings collapse vs Gemma 4 mm_token_type_ids defaulting; separate issues." }, { - "left": "issue:43931", - "right": "issue:44060", + "left": "issue:43550", + "right": "issue:43701", "accept": false, - "reason": "Weight-shape mismatch in Qwen3-VL and tied-weights warning in Qwen3-Next are unrelated." + "reason": "torch.compile/SDPA failure vs checkpoint key mismatch; unrelated." }, { - "left": "issue:44617", - "right": "issue:45584", + "left": "issue:43606", + "right": "issue:43701", "accept": false, - "reason": "Sam3Video OOM and Whisper empty transcription after align_special_tokens are unrelated." + "reason": "CPU offload device mismatch vs checkpoint key mismatch; unrelated." }, { "left": "issue:43761", - "right": "issue:44242", + "right": "issue:44479", "accept": false, - "reason": "CLIPVision hidden_states regression and load-balancing-loss omission are distinct bugs." + "reason": "CLIPVisionModel hidden_states regression vs Qwen video-input regression; different model families and failures." }, { - "left": "issue:32090", - "right": "issue:35141", + "left": "issue:43295", + "right": "issue:44871", "accept": false, - "reason": "Trainer _gpu_broadcast_one NoneType error and output embedding reinitialization after resizing embeddings are unrelated." + "reason": "Custom processor/tokenizer regression vs Gemma eos_token_id inconsistency; different APIs." }, { - "left": "issue:45563", - "right": "issue:45584", + "left": "issue:42617", + "right": "issue:43575", "accept": false, - "reason": "Stale num_return_sequences warning and Whisper empty-transcription failure are different generation-time issues." + "reason": "3d_parallel launch issue vs tensor-parallel OOM while loading a model; not the same bug." }, { - "left": "issue:44464", - "right": "issue:44871", + "left": "issue:43575", + "right": "issue:43742", "accept": false, - "reason": "Chunked generation inconsistency with compiled forward is unrelated to eos_token_id config mismatch." + "reason": "Model loading OOM vs MobileLLM config KeyError; unrelated." }, { - "left": "issue:44792", - "right": "issue:44977", + "left": "issue:43452", + "right": "issue:44496", "accept": false, - "reason": "Janus test failure for image generation and Qwen3.5 flash-attention generation failure are model-specific and distinct." + "reason": "gguf_file/from_pretrained breakage vs unrecognized model_type in config; both loading-related but not the same concrete issue." }, { - "left": "issue:44479", - "right": "issue:44734", + "left": "issue:43646", + "right": "issue:44913", "accept": false, - "reason": "Qwen VL video-input regression and serve KV-cache indexing crash are different code paths." + "reason": "Broad custom model initialization regression vs GPTNeoXConfig rotary_pct reload issue; different scopes and symptoms." }, { - "left": "issue:43065", - "right": "issue:44610", + "left": "issue:44734", + "right": "issue:45406", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d and OmDet-Turbo processor image-size mismatch are unrelated vision issues." + "reason": "KV-cache continuation tensor indexing bug vs Gemma4Processor missing _tokenizer; both serve bugs but unrelated." }, { - "left": "issue:44521", - "right": "issue:45381", + "left": "issue:43504", + "right": "issue:45698", "accept": false, - "reason": "All-zero assistant masks for multimodal inputs and wrong vision_position_ids in Qwen2.5-VL are separate multimodal bugs." + "reason": "Legacy field blocking BEiT preset load vs wrong custom module after save/load; different pretrained-loading failures." } ] }, @@ -9327,59 +9270,69 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:36246", - "issue:41628", + "issue:32090", + "issue:35141", "issue:41720", - "issue:41950", - "issue:43116", - "issue:43295", + "issue:43065", "issue:43335", "issue:43388", - "issue:43479", - "issue:43540", - "issue:43550", + "issue:43575", "issue:43582", - "issue:43644", - "issue:43650", + "issue:43761", "issue:43827", + "issue:43873", "issue:43906", - "issue:43976", + "issue:43931", "issue:43994", - "issue:44016", - "issue:44077", - "issue:44079", - "issue:44112", + "issue:44060", "issue:44190", - "issue:44220", + "issue:44242", + "issue:44462", "issue:44464", - "issue:44496", + "issue:44479", + "issue:44521", "issue:44534", + "issue:44610", + "issue:44617", "issue:44734", "issue:44737", "issue:44792", "issue:44855", + "issue:44871", "issue:44913", "issue:44933", "issue:44938", "issue:44964", + "issue:44977", "issue:45127", "issue:45245", - "issue:45276", "issue:45290", "issue:45357", "issue:45362", - "issue:45375", + "issue:45381", "issue:45542", "issue:45563", "issue:45584", "issue:45588", "issue:45600", - "issue:45803" + "issue:45803", + "issue:45907" ], "soft_pairs": [ + "issue:43575|issue:43873", + "issue:44617|issue:45584", + "issue:43931|issue:44060", + "issue:43761|issue:44242", + "issue:32090|issue:35141", + "issue:45563|issue:45584", + "issue:44464|issue:44871", + "issue:44792|issue:44977", + "issue:43065|issue:44610", + "issue:44479|issue:44734", "issue:43827|issue:43994", + "issue:44521|issue:45381", "issue:44534|issue:44913", "issue:44464|issue:45563", "issue:43906|issue:45290", @@ -9387,237 +9340,198 @@ "issue:44190|issue:44964", "issue:41720|issue:45245", "issue:44792|issue:45600", - "issue:44737|issue:45803", "issue:44855|issue:45588", + "issue:44737|issue:45803", "issue:43388|issue:43582", + "issue:44462|issue:45907", "issue:45127|issue:45357", - "issue:44938|issue:45542", "issue:43335|issue:44855", - "issue:44077|issue:44079", - "issue:43976|issue:44855", - "issue:43644|issue:44913", - "issue:43550|issue:44190", - "issue:44496|issue:45803", - "issue:44112|issue:45600", - "issue:43540|issue:44734", - "issue:45276|issue:45584", - "issue:43335|issue:44190", - "issue:43650|issue:44220", - "issue:43116|issue:44190", - "issue:45245|issue:45584", - "issue:43295|issue:45276", - "issue:43479|issue:45375", - "issue:36246|issue:41628", - "issue:41950|issue:44016" + "issue:44938|issue:45542" ], - "prepared_review_unit_hash": "872d363bdd2dde7b2d8c7c8b8a8e6d9bd323d1f31609e5506a06798b139bcbcc", + "prepared_review_unit_hash": "84f3ac0c9ffd8d9519d1b84777bcea945d06711389c328f3b8d357c1560acc9c", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36884, - "estimated_input_tokens": 9221, - "estimated_eval_tokens": 18698 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35068, + "estimated_input_tokens": 8767, + "estimated_eval_tokens": 17790 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is largely heterogeneous: most items are unrelated bug reports spanning configs, generation, CI, docs, and environment-specific failures. The only loose theme is import/export regressions around image processor APIs, but none of the soft pairs look like the same underlying bug with enough confidence to merge.", - "confidence": 0.23, - "canonical_issue_reason": "issue:41628 is the broadest and most representative of the small import/export regression theme, since it concerns a public top-level transformers import failure rather than a model-specific or one-off error.", + "summary": "The proposed soft pairs are mostly superficial similarities across different models/features rather than true duplicates. I did not find any pair that clearly shares the same concrete bug or change path.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43873 is the strongest representative of this set if a single issue must be chosen: it has the broadest user impact, the most discussion, and inbound references. The rest of the items are mostly isolated, unrelated bugs.", "canonical_pr_reason": null, - "best_issue_reason": "issue:41628 is the best fit as a cluster representative because it is the most general and user-visible of the import failures; however, it is still only a partial thematic match to the rest of the set.", + "best_issue_reason": "issue:43873 is the best overall issue candidate because it is the most active and central report in the list, while the other issues are largely one-off model- or feature-specific problems.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43827", - "right": "issue:43994", + "left": "issue:43575", + "right": "issue:43873", "accept": false, - "reason": "Both mention pipeline, but one is a docs/removal issue and the other is a model behavior problem; different bugs." + "reason": "Both concern memory/quantization behavior, but one is a TP OOM on a specific model and the other is an offloading bug; different failure modes and likely different fixes." }, { - "left": "issue:44534", - "right": "issue:44913", + "left": "issue:44617", + "right": "issue:45584", "accept": false, - "reason": "One reports junk non-persistent buffers, the other a config field reverting on reload; related area, not same defect." + "reason": "Sam3Video CUDA OOM and Whisper empty-transcription generation failure are unrelated model/code-path bugs." }, { - "left": "issue:44464", - "right": "issue:45563", + "left": "issue:43931", + "right": "issue:44060", "accept": false, - "reason": "Both involve generation, but one is compiled-forward inconsistency and the other is a stale warning; not the same code-path failure." + "reason": "Different Qwen variants and different problems: a load-time shape mismatch vs an incorrect tied-weights warning." }, { - "left": "issue:43906", - "right": "issue:45290", + "left": "issue:43761", + "right": "issue:44242", "accept": false, - "reason": "Both are chat/template-related, but the reported failures differ and there is no clear shared bug mechanism." + "reason": "CLIP hidden_states regression and MoE load-balancing-loss behavior are separate features and code paths." }, { - "left": "issue:44933", - "right": "issue:45362", + "left": "issue:32090", + "right": "issue:35141", "accept": false, - "reason": "An import-from-image_utils problem is not the same as a Qwen3.5 chat crash." + "reason": "Trainer GPU broadcast NoneType error and embedding reinit after resize are unrelated training/model-init issues." }, { - "left": "issue:44190", - "right": "issue:44964", + "left": "issue:45563", + "right": "issue:45584", "accept": false, - "reason": "Different failure modes: local dataset loading in an example script vs loading a specific multimodal model." + "reason": "A stale warning in paged generate is not the same bug as Whisper crashing on empty transcription after align_special_tokens." }, { - "left": "issue:41720", - "right": "issue:45245", - "accept": false, - "reason": "Qwen3 device-mapping CUDA assert and category-count limit are unrelated." - }, - { - "left": "issue:44792", - "right": "issue:45600", - "accept": false, - "reason": "Both are CI/test failures, but they target different models and different underlying issues." - }, - { - "left": "issue:44737", - "right": "issue:45803", - "accept": false, - "reason": "XLNet CPU device placement bug and Fuyu exception handling bug are unrelated." - }, - { - "left": "issue:44855", - "right": "issue:45588", - "accept": false, - "reason": "Python parsing/import error in DebertaV2 and a flash-attention sinkless-model crash are different bugs." - }, - { - "left": "issue:43388", - "right": "issue:43582", + "left": "issue:44464", + "right": "issue:44871", "accept": false, - "reason": "Metric gathering label truncation and Apple Silicon warmup TypeError are unrelated." + "reason": "Chunked generation/compiled forward inconsistency and Gemma eos_token config mismatch are unrelated." }, { - "left": "issue:45127", - "right": "issue:45357", + "left": "issue:44792", + "right": "issue:44977", "accept": false, - "reason": "Both touch model save/weight handling, but one is LoRA vocab merge collapse and the other is wrong visual encoder keys in save_pretrained." + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation issue are different model paths and symptoms." }, { - "left": "issue:44938", - "right": "issue:45542", + "left": "issue:43065", + "right": "issue:44610", "accept": false, - "reason": "Python 3.14 load failure and missing TensorFlow backend handling are different environment/config issues." + "reason": "A dummy Conv2d in Sam3PixelDecoder and an OmDet-Turbo processor size mismatch are different bugs." }, { - "left": "issue:43335", - "right": "issue:44855", + "left": "issue:44479", + "right": "issue:44734", "accept": false, - "reason": "SwitchTransformers sparse-layer initialization and a Python 3.13 import parse error are unrelated." + "reason": "Both touch multimodal/runtime behavior, but one is a video-input regression and the other is a KV-cache indexing crash in serve." }, { - "left": "issue:44077", - "right": "issue:44079", + "left": "issue:43827", + "right": "issue:43994", "accept": false, - "reason": "A post_init policy bug and ModelOutput key assignment bug are distinct internals." + "reason": "Docs still referencing pipeline() and SigLIP producing nonsense with AutoModel/pipeline are not the same underlying issue." }, { - "left": "issue:43976", - "right": "issue:44855", + "left": "issue:44521", + "right": "issue:45381", "accept": false, - "reason": "Python version support regression and a DebertaV2 import parse error are not the same issue." + "reason": "Both are multimodal chat/template problems, but the assistant-mask bug and wrong vision_position_ids are distinct processing failures." }, { - "left": "issue:43644", + "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "Non-persistent buffer junk and rotary_pct reload behavior are different state-handling bugs." + "reason": "Non-persistent buffer junk-fill and GPTNeoX rotary_pct reload loss are unrelated configuration/runtime bugs." }, { - "left": "issue:43550", - "right": "issue:44190", + "left": "issue:44464", + "right": "issue:45563", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba and a dataset-loading example issue are unrelated." + "reason": "Different generate-related symptoms: compiled-forward inconsistency versus a stale warning about num_return_sequences." }, { - "left": "issue:44496", - "right": "issue:45803", + "left": "issue:43906", + "right": "issue:45290", "accept": false, - "reason": "Unrecognized model/config handling and a bare-except bug in FuyuBatchFeature are separate problems." + "reason": "The first is only a reproduction of an earlier issue; there is not enough evidence that it is the same concrete assistant-message/tool-call crash." }, { - "left": "issue:44112", - "right": "issue:45600", + "left": "issue:44933", + "right": "issue:45362", "accept": false, - "reason": "Both are CI-related, but they concern different tests and different root causes." + "reason": "Missing image_utils import and Qwen3.5 chat crash are unrelated." }, { - "left": "issue:43540", - "right": "issue:44734", + "left": "issue:44190", + "right": "issue:44964", "accept": false, - "reason": "Qwen3OmniMoe video-input validation and serve KV-cache indexing are different code paths." + "reason": "Local dataset loading failure and model loading failure for Phi-4 multimodal are different failure surfaces." }, { - "left": "issue:45276", - "right": "issue:45584", + "left": "issue:41720", + "right": "issue:45245", "accept": false, - "reason": "Token embedding resize propagation and Whisper empty-transcription generation are unrelated." + "reason": "CUDA assert during auto device mapping and the 2^24 categories limit error are unrelated." }, { - "left": "issue:43335", - "right": "issue:44190", + "left": "issue:44792", + "right": "issue:45600", "accept": false, - "reason": "SwitchTransformers config initialization and a local dataset loading failure do not match." + "reason": "Janus image-generation test failure and stale auto_mappings references to removed configs are different problems." }, { - "left": "issue:43650", - "right": "issue:44220", + "left": "issue:44855", + "right": "issue:45588", "accept": false, - "reason": "The generic 'ADD THE DATA' issue is not the same as an fbank feature extraction bug." + "reason": "Python 3.13 IndentationError from torch.jit parsing and a flash-attention None-aux crash are unrelated." }, { - "left": "issue:43116", - "right": "issue:44190", + "left": "issue:44737", + "right": "issue:45803", "accept": false, - "reason": "Example-script multi-label classification output handling and local dataset loading are different bugs." + "reason": "XLNet CPU allocation bug and Fuyu bare-except error handling are unrelated code paths." }, { - "left": "issue:45245", - "right": "issue:45584", + "left": "issue:43388", + "right": "issue:43582", "accept": false, - "reason": "Category cardinality limit and Whisper empty transcription generation are unrelated." + "reason": "Metric-gather label dropping and Apple Silicon warmup TypeError are unrelated." }, { - "left": "issue:43295", - "right": "issue:45276", + "left": "issue:44462", + "right": "issue:45907", "accept": false, - "reason": "Processor/tokenizer regression and resize_token_embeddings propagation are not the same underlying issue." + "reason": "Tokenizer loading ignores tokenizer.json, while the other issue is about forwarding revision in list_repo_files; different APIs and fixes." }, { - "left": "issue:43479", - "right": "issue:45375", + "left": "issue:45127", + "right": "issue:45357", "accept": false, - "reason": "Both are multimodal config bugs, but they affect different models and different missing/default fields." + "reason": "LoRA merge collapse with extended vocab and Qwen3.5 visual encoder key saving are different model-state serialization bugs." }, { - "left": "issue:36246", - "right": "issue:41628", + "left": "issue:43335", + "right": "issue:44855", "accept": false, - "reason": "Both are import errors, but one is a missing class export in a specific qwen2_5_vl submodule and the other is a top-level AutoImageProcessor import failure." + "reason": "SwitchTransformers sparse-layer creation and DebertaV2 import parsing on Python 3.13 are unrelated." }, { - "left": "issue:41950", - "right": "issue:44016", + "left": "issue:44938", + "right": "issue:45542", "accept": false, - "reason": "Video-classification pipeline processor lookup and a notebook syntax error are unrelated." + "reason": "Python 3.14 load failure and tensorboard-without-TensorFlow backend error are different environment/setup issues." } ] }, @@ -9639,280 +9553,305 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36246", "issue:38175", "issue:38617", + "issue:41628", + "issue:41950", "issue:42175", "issue:42907", "issue:43065", + "issue:43116", "issue:43295", - "issue:43299", - "issue:43381", + "issue:43335", "issue:43404", "issue:43441", - "issue:43526", - "issue:43531", + "issue:43479", + "issue:43540", + "issue:43550", "issue:43643", - "issue:43673", - "issue:43824", - "issue:43854", - "issue:43901", + "issue:43644", + "issue:43650", "issue:43976", "issue:44016", - "issue:44062", - "issue:44075", + "issue:44077", + "issue:44079", "issue:44112", "issue:44186", + "issue:44190", "issue:44220", "issue:44246", "issue:44279", - "issue:44336", - "issue:44368", "issue:44466", "issue:44496", "issue:44561", "issue:44683", "issue:44734", + "issue:44855", "issue:44913", - "issue:44933", "issue:44964", - "issue:44987", "issue:45003", - "issue:45042", "issue:45216", - "issue:45335", + "issue:45245", + "issue:45276", + "issue:45375", "issue:45406", "issue:45446", "issue:45584", - "issue:45593", "issue:45600", - "issue:45632" + "issue:45632", + "issue:45803" ], "soft_pairs": [ + "issue:44077|issue:44079", + "issue:43976|issue:44855", + "issue:43644|issue:44913", + "issue:43550|issue:44190", + "issue:43540|issue:44734", + "issue:44112|issue:45600", + "issue:44496|issue:45803", + "issue:45276|issue:45584", + "issue:43335|issue:44190", + "issue:43650|issue:44220", + "issue:43116|issue:44190", + "issue:45245|issue:45584", + "issue:43295|issue:45276", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:41950|issue:44016", "issue:36246|issue:38617", "issue:44186|issue:44734", "issue:38175|issue:43065", "issue:44683|issue:45446", - "issue:42175|issue:44279", - "issue:44734|issue:45632", "issue:44466|issue:44913", + "issue:42175|issue:44279", "issue:44016|issue:44220", - "issue:44561|issue:45632", + "issue:44734|issue:45632", "issue:43404|issue:45216", + "issue:44561|issue:45632", "issue:44246|issue:45003", "issue:43643|issue:44496", "issue:45406|issue:45632", "issue:44964|issue:45600", "issue:44112|issue:44964", - "issue:42907|issue:43441", - "issue:43854|issue:44964", - "issue:44016|issue:44062", - "issue:43295|issue:45335", - "issue:43976|issue:44987", - "issue:44496|issue:45042", - "issue:43673|issue:44336", - "issue:43531|issue:45600", - "issue:43526|issue:43901", - "issue:43824|issue:44933", - "issue:43299|issue:45216", - "issue:45335|issue:45584", - "issue:44075|issue:44368", - "issue:43976|issue:44279", - "issue:43901|issue:44496", - "issue:43381|issue:45593" + "issue:42907|issue:43441" ], - "prepared_review_unit_hash": "f49bfd565b1b9e51ec3c05c974619246dfb03ff857b30ef67bbc2d848c008203", + "prepared_review_unit_hash": "c9b04c6b9931812b2041cd33ac30e161a5bb00b2b2ce887552d55d5bb6e90cff", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37046, - "estimated_input_tokens": 9262, - "estimated_eval_tokens": 18780 + "soft_pair_count": 32, + "serialized_chars": 37403, + "estimated_input_tokens": 9351, + "estimated_eval_tokens": 18958 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly heterogeneous: many issues are about unrelated import/export regressions, model-specific load/save bugs, or generic docs/runtime problems. None of the soft edges are close enough to treat as duplicates under strict triage. Issue 43824 is the strongest representative because it is a concrete, well-discussed import failure with external references.", - "confidence": 0.72, - "canonical_issue_reason": "43824 is the most concrete and best-supported report in the set: a specific runtime import failure, with multiple inbound references and substantial discussion, making it the best anchor issue.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers bugs (imports, configs, model-specific regressions, pipelines, and notebooks). None of the suggested soft edges look like true duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "issue:43644 is the broadest release-level regression in the set and best captures the shared \"v5 breakage\" theme, while most other issues are narrower model-, pipeline-, or environment-specific bugs.", "canonical_pr_reason": null, - "best_issue_reason": "43824 is the strongest overall issue candidate because it is precise, widely corroborated, and more representative than the other mostly one-off reports.", + "best_issue_reason": "issue:43644 is the strongest representative issue because it describes a general Transformers v5 regression rather than a single model or example-script failure.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:36246", - "right": "issue:38617", + "left": "issue:44077", + "right": "issue:44079", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different modules, so they are not the same bug." + "reason": "Different bugs: one is about `patchtsmixer` `post_init`, the other about `ModelOutput` key handling." }, { - "left": "issue:44186", - "right": "issue:44734", + "left": "issue:43976", + "right": "issue:44855", "accept": false, - "reason": "Different code paths: tokenizer padding/NER crash vs serve KV-cache continuation indexing bug." + "reason": "Both are version/runtime failures, but one is a Python version compatibility issue and the other is a DebertaV2 import/parser problem on Python 3.13." }, { - "left": "issue:38175", - "right": "issue:43065", + "left": "issue:43644", + "right": "issue:44913", "accept": false, - "reason": "Completely different models and failure modes; no shared underlying bug." + "reason": "Both touch v5 serialization/config behavior, but one is about non-persistent buffers and the other is a GPTNeoX config reload bug." }, { - "left": "issue:44683", - "right": "issue:45446", + "left": "issue:43550", + "right": "issue:44190", "accept": false, - "reason": "Same broad flex_attention area, but one is a compiled flex_attention failure and the other is a version-check/import issue." + "reason": "Unrelated: torch.compile/SDPA failure in Bamba vs a local dataset loading issue in an image-classification example." }, { - "left": "issue:42175", - "right": "issue:44279", + "left": "issue:43540", + "right": "issue:44734", "accept": false, - "reason": "One is a backend packaging issue, the other is a generic dependency complaint; too vague and unrelated." + "reason": "Different code paths: Qwen3OmniMoe video-input validation vs transformers serve KV-cache continuation indexing." }, { - "left": "issue:44734", - "right": "issue:45632", + "left": "issue:44112", + "right": "issue:45600", "accept": false, - "reason": "Serve KV-cache crash and trust_remote_code cache-path collision are different problems." + "reason": "Both affect CI, but one is a GraniteSpeech stale-test failure and the other is a broken auto_mappings reference to removed configs." }, { - "left": "issue:44466", - "right": "issue:44913", + "left": "issue:44496", + "right": "issue:45803", "accept": false, - "reason": "One is tied-weight serialization behavior, the other is GPTNeoX config reload defaulting; different bugs." + "reason": "Different failures: unrecognized model/config loading vs a bare-except bug in Fuyu tensor conversion." }, { - "left": "issue:44016", - "right": "issue:44220", + "left": "issue:45276", + "right": "issue:45584", "accept": false, - "reason": "Notebook syntax error vs audio feature extraction issue; unrelated." + "reason": "Both are generation-related, but one is Gemma4 embedding resizing and the other is Whisper empty-transcription handling after token alignment." }, { - "left": "issue:44561", - "right": "issue:45632", + "left": "issue:43335", + "right": "issue:44190", "accept": false, - "reason": "Both mention trust_remote_code, but one is removed API usage and the other is a cache-path collision." + "reason": "Different subsystems: SwitchTransformers config construction vs an example script failing to load a local dataset." }, { - "left": "issue:43404", - "right": "issue:45216", + "left": "issue:43650", + "right": "issue:44220", "accept": false, - "reason": "Both concern model weight handling, but the affected models and failure modes differ." + "reason": "Unrelated issues in different areas: a data-related request vs a torch fbank feature extraction bug." }, { - "left": "issue:44246", - "right": "issue:45003", + "left": "issue:43116", + "right": "issue:44190", "accept": false, - "reason": "Both touch import-time behavior, but one is slow imports and the other is unsafe sys.modules access; not the same defect." + "reason": "Both are example-script problems, but they affect different scripts and different failure modes." }, { - "left": "issue:43643", - "right": "issue:44496", + "left": "issue:45245", + "right": "issue:45584", "accept": false, - "reason": "Both are config/loading related, but one returns incomplete config objects and the other is an unrecognized model/config mismatch." + "reason": "Different problems: category-cardinality limit vs Whisper generation on empty transcription." }, { - "left": "issue:42907", - "right": "issue:43441", + "left": "issue:43295", + "right": "issue:45276", "accept": false, - "reason": "Same model family, but dequantized save failure and FlashAttention load failure are distinct issues." + "reason": "One is a processor/tokenizer regression, the other is a Gemma4 resize-token-embeddings bug." }, { - "left": "issue:43854", - "right": "issue:44964", + "left": "issue:43479", + "right": "issue:45375", "accept": false, - "reason": "Different models and different load failures; only broad multimodal-loading similarity." + "reason": "Both are config-related, but they concern different multimodal model families and different missing/default fields." }, { - "left": "issue:44112", - "right": "issue:44964", + "left": "issue:36246", + "right": "issue:41628", "accept": false, - "reason": "CI device-override failure is unrelated to a model load regression." + "reason": "Both are import errors, but they involve different symbols and different API exposure problems." }, { - "left": "issue:44016", - "right": "issue:44062", + "left": "issue:41950", + "right": "issue:44016", "accept": false, - "reason": "Notebook syntax error vs token AddedToken argument bug; unrelated." + "reason": "Different issues entirely: video-classification pipeline behavior vs a notebook syntax error." }, { - "left": "issue:43295", - "right": "issue:45335", + "left": "issue:36246", + "right": "issue:38617", "accept": false, - "reason": "Both are regression-style reports, but they affect different APIs and model components." + "reason": "Both are import failures, but for different missing names and different call sites." }, { - "left": "issue:43976", - "right": "issue:44987", + "left": "issue:44186", + "right": "issue:44734", "accept": false, - "reason": "Platform compatibility issue vs model-loading failure; not the same underlying bug." + "reason": "Different bug classes: LayoutLMv2 tokenizer padding/NER crash vs server KV-cache continuation indexing." }, { - "left": "issue:44496", - "right": "issue:45042", + "left": "issue:38175", + "right": "issue:43065", "accept": false, - "reason": "Unrecognized-model config error is unrelated to PIL image-processor torchvision requirements." + "reason": "Different models and failures: SigLIP2 zero probabilities vs a dummy Conv2d in Sam3PixelDecoder." }, { - "left": "issue:43673", - "right": "issue:44336", + "left": "issue:44683", + "right": "issue:45446", "accept": false, - "reason": "Generation cache missing and ANSI output formatting are unrelated." + "reason": "Both touch flex_attention, but one is a compiled flex_attention failure on torch >= 2.9 and the other is a version-check/import bug for AuxRequest." }, { - "left": "issue:43531", - "right": "issue:45600", + "left": "issue:44466", + "right": "issue:44913", "accept": false, - "reason": "Different subsystems: sliding-window MoE behavior vs auto_mappings config reference cleanup." + "reason": "Both involve serialization/config state, but one is tied `lm_head.weight` serialization and the other is GPTNeoX `rotary_pct` reloading." }, { - "left": "issue:43526", - "right": "issue:43901", + "left": "issue:42175", + "right": "issue:44279", "accept": false, - "reason": "ImageProcessorFast label reduction bug and pipeline docs mismatch are unrelated." + "reason": "Packaging/dependency complaints, but not the same dependency or failure mode." }, { - "left": "issue:43824", - "right": "issue:44933", + "left": "issue:44016", + "right": "issue:44220", "accept": false, - "reason": "Both are missing-import style reports, but they reference different symbols and different modules." + "reason": "A notebook syntax error and a feature-extraction bug are unrelated." }, { - "left": "issue:43299", + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve KV-cache tensor indexing and `trust_remote_code` cache-path collision are unrelated." + }, + { + "left": "issue:43404", "right": "issue:45216", "accept": false, - "reason": "Different Qwen model families and different failure modes; too broad to merge." + "reason": "Both mention weight tying/serialization, but one is Mistral3 lm_head tying and the other is Qwen3.5 checkpoint save correctness." }, { - "left": "issue:45335", - "right": "issue:45584", + "left": "issue:44561", + "right": "issue:45632", "accept": false, - "reason": "Embedding resize bug and Whisper empty-transcription generation bug are unrelated." + "reason": "Both involve `trust_remote_code`, but one is a removed helper breaking remote models and the other is a local cache path collision." }, { - "left": "issue:44075", - "right": "issue:44368", + "left": "issue:44246", + "right": "issue:45003", "accept": false, - "reason": "Optimizer argument handling and tie_word_embeddings warning are not the same code-path problem." + "reason": "Different import-related issues: slow `import transformers` vs unsafe `sys.modules` access in modeling_utils." }, { - "left": "issue:43381", - "right": "issue:45593", + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "A Gemma4Processor missing `_tokenizer` and a trust_remote_code cache collision are unrelated." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Different model-loading failures: Phi-4-multimodal loading vs stale Sam3LiteText references in auto_mappings." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI test failure in GraniteSpeech and a Phi-4-multimodal loading issue are not duplicates." + }, + { + "left": "issue:42907", + "right": "issue:43441", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction and D-FINE auxiliary-loss behavior are unrelated." + "reason": "Different model families and bugs: saving dequantized models vs Ministral-3 FlashAttention failure." } ] }, @@ -9934,283 +9873,303 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:33290", "issue:38175", "issue:39692", "issue:41950", - "issue:42994", - "issue:43065", "issue:43295", "issue:43299", - "issue:43317", - "issue:43441", - "issue:43450", + "issue:43381", "issue:43479", "issue:43525", + "issue:43526", + "issue:43531", "issue:43577", - "issue:43650", + "issue:43673", + "issue:43824", "issue:43854", "issue:43901", "issue:43976", "issue:44016", + "issue:44062", + "issue:44075", "issue:44242", - "issue:44261", - "issue:44263", "issue:44279", - "issue:44291", - "issue:44297", + "issue:44336", "issue:44351", - "issue:44462", + "issue:44368", "issue:44496", "issue:44521", "issue:44617", "issue:44683", "issue:44779", - "issue:44898", + "issue:44933", + "issue:44964", + "issue:44987", "issue:45020", - "issue:45081", + "issue:45042", "issue:45200", "issue:45216", "issue:45278", "issue:45325", + "issue:45335", "issue:45357", "issue:45405", "issue:45542", + "issue:45584", + "issue:45593", "issue:45600", - "issue:45656", - "issue:45712", "issue:45759", - "issue:45823", - "issue:45834" + "issue:45823" ], "soft_pairs": [ + "issue:43854|issue:44964", + "issue:43295|issue:45335", + "issue:44016|issue:44062", + "issue:43976|issue:44987", + "issue:43673|issue:44336", + "issue:44496|issue:45042", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:43824|issue:44933", + "issue:43299|issue:45216", + "issue:45335|issue:45584", + "issue:44075|issue:44368", + "issue:43976|issue:44279", + "issue:43901|issue:44496", + "issue:43381|issue:45593", "issue:43299|issue:45357", - "issue:44351|issue:45278", "issue:44496|issue:45759", - "issue:44521|issue:45325", + "issue:44351|issue:45278", "issue:41950|issue:45020", + "issue:44521|issue:45325", "issue:44242|issue:45200", "issue:43976|issue:45405", "issue:43479|issue:43525", "issue:41950|issue:45823", - "issue:44683|issue:45542", "issue:43577|issue:45216", "issue:38175|issue:44617", + "issue:44683|issue:45542", "issue:44279|issue:45405", "issue:43299|issue:43854", "issue:39692|issue:43901", - "issue:43295|issue:44779", - "issue:44462|issue:45081", - "issue:41950|issue:43650", - "issue:44297|issue:44462", - "issue:33290|issue:45656", - "issue:45600|issue:45712", - "issue:44016|issue:44291", - "issue:44462|issue:44779", - "issue:43441|issue:45834", - "issue:43450|issue:44279", - "issue:42994|issue:43317", - "issue:44261|issue:44263", - "issue:43065|issue:44898" + "issue:43295|issue:44779" ], - "prepared_review_unit_hash": "d6d9a625fe7b206c8faa9b5a4938cc8818653ac3606712c9ac66c1122aba898e", + "prepared_review_unit_hash": "d7c1721ae71f2baebce8f8b267a9a49eed8de544436f21457ce4338d6909656d", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36020, - "estimated_input_tokens": 9005, - "estimated_eval_tokens": 18266 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36355, + "estimated_input_tokens": 9089, + "estimated_eval_tokens": 18434 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly a grab bag of unrelated Transformers bug reports, with a loose common theme of version regressions, model-loading issues, tokenizer/config mismatches, and multimodal pipeline bugs. I do not see any pair that should be merged as true duplicates.", - "confidence": 0.36, - "canonical_issue_reason": "issue:45020 is the broadest and most representative issue in the set: it frames a general regression class around recent Transformers versions breaking remote-code models, which fits the overall cluster theme better than the narrower per-model reports.", + "summary": "The cluster is heterogeneous: the soft pairs share broad transformer/modeling themes, but they are not the same concrete bug or change. I rejected all soft edges because the titles point to different code paths, models, or failure modes.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue stands out; these reports are too diverse to safely collapse into one duplicate hub.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the best single representative because it is a high-level regression report with broader scope than the other issue-specific failures, so it is the most plausible anchor for triage.", + "best_issue_reason": "No issue is a strong global representative for the whole cluster; the closest broad umbrella is still too general to serve as a true duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43299", - "right": "issue:45357", + "left": "issue:43854", + "right": "issue:44964", "accept": false, - "reason": "Both concern Qwen3.5/Qwen3VL, but one is a load-time MoE model failure and the other is a save_pretrained checkpoint-key regression. Different code paths and different concrete bugs." + "reason": "Both are model-loading failures, but for different checkpoints and likely different root causes." }, { - "left": "issue:44351", - "right": "issue:45278", + "left": "issue:43295", + "right": "issue:45335", "accept": false, - "reason": "The second is a broad import-regression report after upgrading Transformers; the first is a specific missing HybridCache export. Related symptom class, but not the same underlying bug." + "reason": "One is a processor/tokenizer regression; the other is an embedding resize bug in t5gemma." }, { - "left": "issue:44496", - "right": "issue:45759", + "left": "issue:44016", + "right": "issue:44062", "accept": false, - "reason": "Both are model-loading/config issues, but they affect different model families and different failure modes: unrecognized config/model_type versus not unwrapping text_config for composite multimodal configs." + "reason": "Notebook syntax error vs AddedToken argument conflict; unrelated failure modes." }, { - "left": "issue:44521", - "right": "issue:45325", + "left": "issue:43976", + "right": "issue:44987", "accept": false, - "reason": "Both are multimodal, but one is apply_chat_template assistant mask generation and the other is Qwen2.5-VL rope index scaling. Separate subsystems and bugs." + "reason": "A Python version compatibility issue and a model-loading failure are not the same bug." }, { - "left": "issue:41950", - "right": "issue:45020", + "left": "issue:43673", + "right": "issue:44336", "accept": false, - "reason": "The pipeline processor lookup bug is specific to video-classification, while the other issue is a broad remote_code compatibility regression. Too general to treat as the same defect." + "reason": "Cache handling in generation vs ANSI formatting in loading_report are unrelated." }, { - "left": "issue:44242", - "right": "issue:45200", + "left": "issue:44496", + "right": "issue:45042", "accept": false, - "reason": "Different model internals and different symptoms: missing load-balancing loss when router logits are off versus Gemma 4 multimodal token type IDs defaulting incorrectly." + "reason": "Unrecognized model config vs PIL/torchvision dependency handling are different issues." }, { - "left": "issue:43976", - "right": "issue:45405", + "left": "issue:43531", + "right": "issue:45600", "accept": false, - "reason": "Completely unrelated: one is a Python-version compatibility issue, the other is a dependency pin bump to an unreleased PEFT version." + "reason": "Qwen3-MoE sliding-window behavior and auto_mappings cleanup are unrelated." }, { - "left": "issue:43479", - "right": "issue:43525", + "left": "issue:43526", + "right": "issue:43901", "accept": false, - "reason": "Both involve config defaults, but they are for different models and different missing/default fields. No evidence they share the same code-path bug." + "reason": "ImageProcessorFast label reduction bug vs text-classification docs mismatch." }, { - "left": "issue:41950", - "right": "issue:45823", + "left": "issue:43824", + "right": "issue:44933", "accept": false, - "reason": "Both touch vision-related pipelines/models, but one is processor selection and the other is device placement in Gemma4 PLE forward. Not the same issue." + "reason": "Different import errors in different modules with different missing symbols." }, { - "left": "issue:44683", - "right": "issue:45542", + "left": "issue:43299", + "right": "issue:45216", "accept": false, - "reason": "No substantive overlap: compiled flex_attention on newer torch versus a backend error caused by tensorboard being installed without TensorFlow." + "reason": "Both involve Qwen models, but one is a load failure and the other is a bad save_pretrained regression." }, { - "left": "issue:43577", - "right": "issue:45216", + "left": "issue:45335", + "right": "issue:45584", "accept": false, - "reason": "One is dtype propagation in BLIP-2 loading, the other is incorrect save_pretrained checkpoint contents for Qwen3.5. Different lifecycle stages and different bugs." + "reason": "Embedding resize behavior and Whisper empty-transcription generation are unrelated." }, { - "left": "issue:38175", - "right": "issue:44617", + "left": "issue:44075", + "right": "issue:44368", "accept": false, - "reason": "Unrelated model-specific failures: zero probabilities in SigLIP2 versus CUDA OOM in Sam3Video." + "reason": "SGD argument handling and a tie_word_embeddings warning are different problems." }, { - "left": "issue:44279", - "right": "issue:45405", + "left": "issue:43976", + "right": "issue:44279", "accept": false, - "reason": "A vague dependency issue is not the same as the specific unreleased PEFT minimum-version bump." + "reason": "Python version support and a generic dependency issue are not the same bug." }, { - "left": "issue:43299", - "right": "issue:43854", + "left": "issue:43901", + "right": "issue:44496", "accept": false, - "reason": "Both are model loading failures, but they are for different models and different root causes; no sign they are the same bug." + "reason": "Docs for return_all_scores versus model config loading failure." }, { - "left": "issue:39692", - "right": "issue:43901", + "left": "issue:43381", + "right": "issue:45593", "accept": false, - "reason": "Both mention docs/examples, but one is a broken SigLIP2 example and the other is stale TextClassificationPipeline documentation. Different underlying problems." + "reason": "Gradient checkpointing eval-mode behavior and D-FINE auxiliary losses are unrelated." }, { - "left": "issue:43295", - "right": "issue:44779", + "left": "issue:43299", + "right": "issue:45357", "accept": false, - "reason": "Both are tokenizer-related regressions, but one is about processor.tokenizer/image passing in custom code and the other is Deepseek tokenizer correctness. Not the same defect." + "reason": "Both are Qwen3.5-related, but one is a loading regression and the other is an incorrect save_pretrained key layout." }, { - "left": "issue:44462", - "right": "issue:45081", + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Different config-loading regressions affecting different model families and code paths." + }, + { + "left": "issue:44351", + "right": "issue:45278", "accept": false, - "reason": "Both concern tokenizers, but one is AutoTokenizer ignoring tokenizer.json and the other is a Mistral regex patch crash. Different entry points and failures." + "reason": "A specific missing import and a broad upgrade-related import breakage are not the same concrete issue." }, { "left": "issue:41950", - "right": "issue:43650", + "right": "issue:45020", "accept": false, - "reason": "No meaningful relation; the second issue title is unrelated and provides no evidence of a shared bug." + "reason": "Video-classification processor lookup and remote_code model breakage are too broad to equate." }, { - "left": "issue:44297", - "right": "issue:44462", + "left": "issue:44521", + "right": "issue:45325", "accept": false, - "reason": "Both involve tokenizer save/load metadata, but one is tokenizer_class mismatch on save_pretrained while the other is repository tokenizer.json being ignored. Similar area, different bug." + "reason": "Chat-template assistant masks and Qwen2.5-VL rope indexing are different multimodal bugs." }, { - "left": "issue:33290", - "right": "issue:45656", + "left": "issue:44242", + "right": "issue:45200", "accept": false, - "reason": "Both mention DeepSpeed and optimizers, but one is an OOM with Adafactor and the other is optimizer.step() being called twice. Different concrete failures." + "reason": "MoE load-balancing loss logic vs mm_token_type_ids defaulting are unrelated." }, { - "left": "issue:45600", - "right": "issue:45712", + "left": "issue:43976", + "right": "issue:45405", "accept": false, - "reason": "Both are cleanup/CI-adjacent, but one is removed config references in auto_mappings and the other is leftover dummy classes leaking into dir(transformers). Distinct issues." + "reason": "Python compatibility and an unreleased dependency pin are different release issues." }, { - "left": "issue:44016", - "right": "issue:44291", + "left": "issue:43479", + "right": "issue:43525", "accept": false, - "reason": "A notebook syntax error and an init_empty_weights TypeError are unrelated failures." + "reason": "Multimodal config default initialization and missing pad_token_id on Llama4Config are different config bugs." }, { - "left": "issue:44462", - "right": "issue:44779", + "left": "issue:41950", + "right": "issue:45823", "accept": false, - "reason": "Both are tokenizer regressions, but the symptoms and likely fixes differ: repository tokenizer.json precedence versus Deepseek tokenizer output changes." + "reason": "Processor lookup for video classification and Gemma4 device placement are unrelated." }, { - "left": "issue:43441", - "right": "issue:45834", + "left": "issue:43577", + "right": "issue:45216", "accept": false, - "reason": "Different model families and different failure modes: FlashAttention incompatibility for Ministral-3 versus long-input OCR index errors in Kosmos2.5." + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint saving are unrelated." }, { - "left": "issue:43450", - "right": "issue:44279", + "left": "issue:38175", + "right": "issue:44617", "accept": false, - "reason": "No relation between batched video processor shape bugs and a generic dependency issue." + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are completely different failure modes." }, { - "left": "issue:42994", - "right": "issue:43317", + "left": "issue:44683", + "right": "issue:45542", "accept": false, - "reason": "Both are quantization/dequantization-related, but one is saving a quantized model and the other is loading a dequantized model with device_map auto offload. Not the same bug." + "reason": "Torch flex_attention compilation and tensorboard/TensorFlow backend setup are unrelated." }, { - "left": "issue:44261", - "right": "issue:44263", + "left": "issue:44279", + "right": "issue:45405", "accept": false, - "reason": "Completely different internals: MLA layernorm epsilon handling versus torch.split return handling in GlmMoeDsaIndexer." + "reason": "A generic dependency issue and a minimum-version bump are not the same bug." }, { - "left": "issue:43065", - "right": "issue:44898", + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Different model families and different failure points in loading." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "A broken docs example for SigLIP2 and a text-classification docs note are not the same issue." + }, + { + "left": "issue:43295", + "right": "issue:44779", "accept": false, - "reason": "Different model components and failures: a dummy Conv2d in Sam3PixelDecoder versus Perceiver image classification failing on non-default resolution." + "reason": "Processor/tokenizer regression and Deepseek tokenizer output regression are different code paths." } ] }, @@ -10232,58 +10191,70 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:41628", + "issue:33290", + "issue:41950", "issue:42175", - "issue:42491", - "issue:43122", + "issue:42994", + "issue:43065", "issue:43262", - "issue:43295", - "issue:43299", + "issue:43317", "issue:43441", - "issue:43525", - "issue:43643", + "issue:43450", "issue:43650", "issue:43653", "issue:43673", "issue:43723", "issue:43761", "issue:43784", - "issue:43824", - "issue:43881", "issue:43901", "issue:43976", "issue:43994", "issue:44016", "issue:44162", - "issue:44188", - "issue:44242", - "issue:44246", - "issue:44297", - "issue:44336", - "issue:44361", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44361", + "issue:44462", "issue:44466", "issue:44521", - "issue:44589", - "issue:44617", "issue:44623", "issue:44671", "issue:44683", "issue:44749", "issue:44779", + "issue:44898", "issue:44987", + "issue:45081", "issue:45276", "issue:45290", - "issue:45362", "issue:45397", "issue:45542", - "issue:45561", - "issue:45563", "issue:45593", - "issue:45823" + "issue:45600", + "issue:45656", + "issue:45712", + "issue:45823", + "issue:45834", + "issue:45907" ], "soft_pairs": [ + "issue:44462|issue:45081", + "issue:41950|issue:43650", + "issue:45081|issue:45907", + "issue:44297|issue:44462", + "issue:33290|issue:45656", + "issue:44016|issue:44291", + "issue:45600|issue:45712", + "issue:43441|issue:45834", + "issue:43450|issue:44279", + "issue:42994|issue:43317", + "issue:43065|issue:44898", + "issue:44261|issue:44263", "issue:44466|issue:45276", "issue:43441|issue:44683", "issue:43650|issue:45290", @@ -10291,241 +10262,219 @@ "issue:44623|issue:44749", "issue:43653|issue:45593", "issue:43723|issue:44162", - "issue:43262|issue:44521", "issue:43784|issue:45542", + "issue:43262|issue:44521", "issue:44671|issue:44779", "issue:43673|issue:43761", - "issue:44016|issue:45823", "issue:44361|issue:45593", + "issue:44016|issue:45823", "issue:42175|issue:43976", "issue:43901|issue:43994", - "issue:44987|issue:45542", - "issue:43122|issue:43650", - "issue:43824|issue:43976", - "issue:43525|issue:43881", - "issue:44297|issue:45397", - "issue:43525|issue:43643", - "issue:44188|issue:44336", - "issue:43295|issue:44617", - "issue:42491|issue:43299", - "issue:44589|issue:45362", - "issue:43901|issue:44246", - "issue:45561|issue:45563", - "issue:41628|issue:43976", - "issue:44242|issue:45593" + "issue:44987|issue:45542" ], - "prepared_review_unit_hash": "8415316f5011c188709f328069a4582b40f5f60c0cbb09a6aa1c978139e19b09", + "prepared_review_unit_hash": "614aac9c4b28002158c76b58aa773ce448e2fb83392d68db2c3a33d7d28d4ebc", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36216, - "estimated_input_tokens": 9054, - "estimated_eval_tokens": 18364 + "soft_pair_count": 28, + "serialized_chars": 36048, + "estimated_input_tokens": 9012, + "estimated_eval_tokens": 18280 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a grab-bag of unrelated issues; only a small config-loading subcluster looks like a true duplicate. Most other pairs share a broad area (v5 regressions, tokenizer/model loading, chat templates) but not the same concrete bug.", - "confidence": 0.67, - "canonical_issue_reason": "Issue #43643 is the broadest and most central of the near-duplicate loading/config reports: it describes fields being dropped from `AutoConfig.from_pretrained(..., trust_remote_code=True)`, which plausibly underlies the Llama4 `pad_token_id` missing-field error in #43525.", + "summary": "This set is highly heterogeneous: most pairs are only superficially similar (often both about tokenizers, processors, or v5 regressions) but describe different code paths and fixes. I do not see a true duplicate cluster; all soft edges should be rejected.", + "confidence": 0.9, + "canonical_issue_reason": "No single issue cleanly represents the cluster because the items span unrelated tokenizer-loading, serialization, vision/audio processor, quantization, backend, and CI problems. If an anchor is required, issue 44462 is the closest broad tokenizer-loading regression, but it does not cover the rest.", "canonical_pr_reason": null, - "best_issue_reason": "#43643 is the best issue anchor because it captures a general config-deserialization regression rather than a model-specific symptom, making it the cleanest representative of the only credible duplicate pair in this set.", + "best_issue_reason": "Issue 44462 is the most central and actionable among the tokenizer-related reports: it has a concrete reproducible failure around AutoTokenizer and repository tokenizer files. It is still only a partial fit for the overall set, which is too mixed to have a strong canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44466", - "right": "issue:45276", + "left": "issue:44462", + "right": "issue:45081", "accept": false, - "reason": "Different symptoms and code paths: serialization of tied `lm_head.weight` vs `resize_token_embeddings` not updating Gemma4 embeddings." + "reason": "Both involve tokenizers, but one is AutoTokenizer ignoring tokenizer.json while the other is a Mistral regex crash during tokenizer loading. Different bugs and likely different fixes." }, { - "left": "issue:43441", - "right": "issue:44683", + "left": "issue:41950", + "right": "issue:43650", "accept": false, - "reason": "Both mention attention/flash issues, but one is Ministral-3 with FlashAttention and the other is compiled flex_attention on torch>=2.9; not the same bug." + "reason": "Unrelated: video-classification processor lookup vs a vague data request issue. No shared bug path." }, { - "left": "issue:43650", - "right": "issue:45290", + "left": "issue:45081", + "right": "issue:45907", "accept": false, - "reason": "Unrelated: one is a low-content misc issue, the other is an `apply_chat_template` crash on tool-call assistant messages." + "reason": "Tokenizer regex crash and list_repo_files revision forwarding are unrelated subsystems." }, { - "left": "issue:44623", - "right": "issue:45397", + "left": "issue:44297", + "right": "issue:44462", "accept": false, - "reason": "Different areas: missing files from `processor.save_pretrained(...)` vs a Gemma-4 ZeRO3 `from_pretrained` loading failure." + "reason": "Tokenizer save_pretrained metadata mismatch is different from AutoTokenizer ignoring tokenizer.json on load." }, { - "left": "issue:44623", - "right": "issue:44749", + "left": "issue:33290", + "right": "issue:45656", "accept": false, - "reason": "Saving processor files is unrelated to a reported slowdown during filtering after upgrading Transformers." + "reason": "Both mention deepspeed/optimizer behavior, but OOM with Adafactor and double optimizer.step are distinct failure modes." }, { - "left": "issue:43653", - "right": "issue:45593", + "left": "issue:44016", + "right": "issue:44291", "accept": false, - "reason": "BigBirdTokenizer special-token registration is unrelated to D-FINE auxiliary-loss behavior." + "reason": "Notebook syntax error is unrelated to init_empty_weights TypeError during model loading." }, { - "left": "issue:43723", - "right": "issue:44162", + "left": "issue:45600", + "right": "issue:45712", "accept": false, - "reason": "Both concern loading/model usage, but one is a generic tokenizer-loading regression and the other is an ESM2-specific model breakage; too different to merge." + "reason": "Both are CI/repo-maintenance flavored, but one is stale auto_mappings references and the other is leftover dummy classes. Different fixes." }, { - "left": "issue:43262", - "right": "issue:44521", + "left": "issue:43441", + "right": "issue:45834", "accept": false, - "reason": "Audio processor sampling-rate defaults and multimodal assistant mask generation are distinct `apply_chat_template` problems." + "reason": "Different models and failures: FlashAttention regression vs long OCR index error." }, { - "left": "issue:43784", - "right": "issue:45542", + "left": "issue:43450", + "right": "issue:44279", "accept": false, - "reason": "Different missing-backend/import failures: `nn` missing in sentence-transformers import vs undefined `tf` backend when only tensorboard is installed." + "reason": "Video batch-shape bug and a dependency issue are unrelated." }, { - "left": "issue:44671", - "right": "issue:44779", + "left": "issue:42994", + "right": "issue:43317", "accept": false, - "reason": "Separate regressions affecting different model/tokenizer paths (CamemBERT MLM vs DeepSeek tokenizer)." + "reason": "Both touch quantization/dequantization, but saving quantized models and device_map offload loading are different code paths." }, { - "left": "issue:43673", - "right": "issue:43761", + "left": "issue:43065", + "right": "issue:44898", "accept": false, - "reason": "Generation cache handling during chunked prefill is unrelated to CLIPVisionModel not returning hidden states." + "reason": "Both are vision-model issues, but a dummy Conv2d placeholder and Perceiver resolution handling are not the same bug." }, { - "left": "issue:44016", - "right": "issue:45823", + "left": "issue:44261", + "right": "issue:44263", "accept": false, - "reason": "Notebook syntax error vs Gemma4 device-map mismatch; no shared underlying bug." + "reason": "Different models and code paths: MLA layernorm epsilon mismatch vs torch.split return-value handling." }, { - "left": "issue:44361", - "right": "issue:45593", + "left": "issue:44466", + "right": "issue:45276", "accept": false, - "reason": "MLukeTokenizer task AttributeError is unrelated to D-FINE auxiliary-loss gating." + "reason": "Both involve Gemma4 serialization/embedding behavior, but one is tied lm_head.weight serialization and the other is resize_token_embeddings propagation." }, { - "left": "issue:42175", - "right": "issue:43976", + "left": "issue:43441", + "right": "issue:44683", "accept": false, - "reason": "Package/backend installation issue vs Python version compatibility issue; not the same defect." + "reason": "FlashAttention failure for a specific model is not the same as compiled flex_attention breaking on torch>=2.9." }, { - "left": "issue:43901", - "right": "issue:43994", + "left": "issue:43650", + "right": "issue:45290", "accept": false, - "reason": "Docs drift for TextClassificationPipeline vs incorrect SigLIP2 inference outputs; different problem types." + "reason": "Unrelated: vague data request vs apply_chat_template crash on tool-call assistant messages." }, { - "left": "issue:44987", - "right": "issue:45542", + "left": "issue:44623", + "right": "issue:45397", "accept": false, - "reason": "Model-loading failure for a specific repo is not the same as the TensorFlow/tensorboard backend packaging bug." + "reason": "processor.save_pretrained missing files and gemma-4 zero3 from_pretrained are distinct issues." }, { - "left": "issue:43122", - "right": "issue:43650", + "left": "issue:44623", + "right": "issue:44749", "accept": false, - "reason": "Tokenizer behavior regression vs an unrelated low-information issue." + "reason": "Saving processor files and training slowdown after upgrade are not the same underlying bug." }, { - "left": "issue:43824", - "right": "issue:43976", + "left": "issue:43653", + "right": "issue:45593", "accept": false, - "reason": "Import error for a specific VL class is unrelated to a Python-version support problem." + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." }, { - "left": "issue:43525", - "right": "issue:43881", + "left": "issue:43723", + "right": "issue:44162", "accept": false, - "reason": "Both are model-loading failures, but they involve different models and different failure modes; too weak to treat as duplicates." + "reason": "AutoTokenizer loading regression and ESM2 model breakage are different failures." }, { - "left": "issue:44297", - "right": "issue:45397", + "left": "issue:43784", + "right": "issue:45542", "accept": false, - "reason": "Tokenizer save metadata mismatch is unrelated to Gemma-4 ZeRO3 loading." - }, - { - "left": "issue:43525", - "right": "issue:43643", - "accept": true, - "reason": "Strong match: both point to config fields missing after remote/custom config loading; #43525 looks like a concrete symptom of the generic field-loss bug in #43643." + "reason": "Both are import/backend-related, but one is a missing nn import and the other is a TensorFlow backend packaging issue." }, { - "left": "issue:44188", - "right": "issue:44336", + "left": "issue:43262", + "right": "issue:44521", "accept": false, - "reason": "Attention-kernel divergence under `torch.compile` is unrelated to ANSI-code output from loading reports." + "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant-mask generation." }, { - "left": "issue:43295", - "right": "issue:44617", + "left": "issue:44671", + "right": "issue:44779", "accept": false, - "reason": "Processor/tokenizer regression and CUDA OOM are different issues." + "reason": "Two separate v5 regressions on different models/tokenizers; no evidence they share the same code defect." }, { - "left": "issue:42491", - "right": "issue:43299", + "left": "issue:43673", + "right": "issue:43761", "accept": false, - "reason": "Both involve Qwen3/MoE and v5 breakage, but one is LoRA compatibility on hf4.x\u2192main and the other is Qwen3VL MoE loading; similar area, not clearly the same concrete bug." + "reason": "Generation cache chunked-prefill bug and CLIPVision hidden_states regression are unrelated." }, { - "left": "issue:44589", - "right": "issue:45362", + "left": "issue:44361", + "right": "issue:45593", "accept": false, - "reason": "Float8 storage import/type error is unrelated to Qwen3.5 chat loading crashes." + "reason": "MLukeTokenizer task error and D-FINE auxiliary-loss issue share nothing substantive." }, { - "left": "issue:44242", - "right": "issue:45593", + "left": "issue:44016", + "right": "issue:45823", "accept": false, - "reason": "MoE load-balancing loss gating and D-FINE auxiliary losses are different model-specific training behaviors." + "reason": "Notebook syntax error is unrelated to Gemma4 device-mapping mismatch." }, { - "left": "issue:45561", - "right": "issue:45563", + "left": "issue:42175", + "right": "issue:43976", "accept": false, - "reason": "pytest-xdist file race and a stale generate warning are unrelated." + "reason": "Different packaging/runtime problems: missing TensorFlow in a torch install vs Python version compatibility." }, { - "left": "issue:41628", - "right": "issue:43976", + "left": "issue:43901", + "right": "issue:43994", "accept": false, - "reason": "Importing `AutoImageProcessor` and Python version support are unrelated." + "reason": "Docs mismatch for return_all_scores is unrelated to SigLIP2 bad outputs." }, { - "left": "issue:44242", - "right": "issue:45593", + "left": "issue:44987", + "right": "issue:45542", "accept": false, - "reason": "MoE router-loss gating and D-FINE denoising/aux-loss behavior are different bugs." + "reason": "Model-loading failure for a specific repo and a TensorFlow backend install issue are unrelated." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary stays grounded in the packet and the soft-edge verdicts are conservative. The single accepted pair, `issue:43525` / `issue:43643`, is a reasonable config-deserialization duplicate anchor, while the rest are mostly symptom-level or model-specific mismatches and are safely rejected." - }, - "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 }, @@ -10540,57 +10489,71 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36246", + "issue:41628", "issue:41950", + "issue:42491", "issue:42757", - "issue:42886", - "issue:43065", - "issue:43232", - "issue:43257", - "issue:43262", + "issue:43122", + "issue:43299", "issue:43352", - "issue:43408", + "issue:43450", + "issue:43525", "issue:43526", "issue:43531", "issue:43596", + "issue:43643", + "issue:43650", "issue:43673", + "issue:43824", + "issue:43881", "issue:43901", + "issue:43976", "issue:44162", + "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:44877", - "issue:44987", - "issue:44995", "issue:45003", - "issue:45137", "issue:45200", - "issue:45229", "issue:45250", "issue:45292", "issue:45362", - "issue:45375", "issue:45397", - "issue:45459", "issue:45561", - "issue:45584", - "issue:45701", - "issue:45759" + "issue:45563", + "issue:45593" ], "soft_pairs": [ + "issue:43122|issue:43650", + "issue:43824|issue:43976", + "issue:43525|issue:43881", + "issue:44297|issue:45397", + "issue:43525|issue:43643", + "issue:44188|issue:44336", + "issue:43450|issue:44617", + "issue:42491|issue:43299", + "issue:44589|issue:45362", + "issue:43901|issue:44246", + "issue:41628|issue:43976", + "issue:45561|issue:45563", + "issue:44242|issue:45593", "issue:44336|issue:44373", "issue:43352|issue:45250", "issue:44295|issue:45397", @@ -10608,235 +10571,222 @@ "issue:44162|issue:45200", "issue:36246|issue:43596", "issue:44295|issue:44749", - "issue:44779|issue:45292", - "issue:44877|issue:45375", - "issue:45292|issue:45584", - "issue:45292|issue:45701", - "issue:43901|issue:45003", - "issue:44987|issue:45459", - "issue:42886|issue:45229", - "issue:44496|issue:45003", - "issue:43065|issue:43408", - "issue:43232|issue:44336", - "issue:45375|issue:45759", - "issue:43257|issue:45137", - "issue:43262|issue:44246", - "issue:44995|issue:45200" + "issue:44779|issue:45292" ], - "prepared_review_unit_hash": "c8ac76f557dee294c1fa761d08651e52493795aa17356523e8e33598d85c76bc", + "prepared_review_unit_hash": "93642bd330585083ab3115e0dbc6b862b8294319cb6db69ddb561a24d83d40d5", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36150, - "estimated_input_tokens": 9038, - "estimated_eval_tokens": 18332 + "serialized_chars": 36598, + "estimated_input_tokens": 9150, + "estimated_eval_tokens": 18556 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is very heterogeneous: most items are distinct import/config/model-specific regressions, not duplicates. I wouldn\u2019t merge any soft pair as the same underlying bug/change.", - "confidence": 0.32, - "canonical_issue_reason": "issue:45003 is the most concrete and actionable representative of the cluster\u2019s import/loading surface; it describes a specific code-path bug (`sys.modules` access) rather than a symptom, model-specific variant, or doc issue.", + "summary": "These issues are broadly heterogeneous: unrelated import errors, model-loading regressions, tokenizer behavior changes, loss-computation bugs, and docs/test/reporting problems. No duplicate cluster is strong enough to merge into a single canonical item.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45003 is the strongest single representative here because it points to a specific runtime/loading implementation defect and is more central than the broader symptom-only tickets.", + "best_issue_reason": "No single issue is a reliable canonical representative; even the closest matches point to different model families or different failure modes.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44336", - "right": "issue:44373", + "left": "issue:43122", + "right": "issue:43650", "accept": false, - "reason": "ANSI escape handling in loading_report is unrelated to a wrong-docstring bug about position_ids." + "reason": "Tokenizer behavior regression vs an unrelated low-quality placeholder issue; no shared bug." }, { - "left": "issue:43352", - "right": "issue:45250", + "left": "issue:43824", + "right": "issue:43976", "accept": false, - "reason": "One is a model-specific Flash Attention 2 unsupported error; the other is a generic FA2 topic, not the same code-path bug." + "reason": "Specific Qwen2.5-VL import failure vs a Python version compatibility complaint; different root causes." }, { - "left": "issue:44295", + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config vs GLM-4V loading failure; different models and failure points." + }, + { + "left": "issue:44297", "right": "issue:45397", "accept": false, - "reason": "These are different failures: a position_ids buffer read error vs a Gemma-4 ZeRO3 from_pretrained issue." + "reason": "Tokenizer save_pretrained metadata mismatch vs gemma-4 Zero3 loading; unrelated." }, { - "left": "issue:41950", - "right": "issue:44220", + "left": "issue:43525", + "right": "issue:43643", "accept": false, - "reason": "Video-classification/image-processor lookup and audio fbank extraction are different subsystems and bugs." + "reason": "Config attribute missing vs trust_remote_code returning incomplete config; not the same bug." }, { - "left": "issue:44246", - "right": "issue:44496", + "left": "issue:44188", + "right": "issue:44336", "accept": false, - "reason": "Import slowness and unrecognized model config are unrelated symptoms with different root causes." + "reason": "torch.compile attention-kernel divergence vs ANSI escape output in loading_report; unrelated subsystems." }, { - "left": "issue:43531", - "right": "issue:45362", - "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and Qwen3.5-35B chat crashes are not the same concrete issue." - }, - { - "left": "issue:36246", - "right": "issue:42757", + "left": "issue:43450", + "right": "issue:44617", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different dependency breakages." + "reason": "Incorrect batched video processor shape vs CUDA OOM in Sam3Video; different classes of problem." }, { - "left": "issue:36246", - "right": "issue:44351", + "left": "issue:42491", + "right": "issue:43299", "accept": false, - "reason": "Qwen2.5 VLImageProcessor missing and HybridCache missing are separate import failures." + "reason": "Qwen3 MoE version incompatibility for LoRA loading vs Qwen3VL MoE model loading breakage; similar family, different code paths and symptoms." }, { - "left": "issue:43526", - "right": "issue:45003", + "left": "issue:44589", + "right": "issue:45362", "accept": false, - "reason": "A BeitImageProcessorFast label-reduction bug is unrelated to unsafe `sys.modules` access." + "reason": "Float8 storage type error vs Qwen3.5 chat crash; no concrete overlap." }, { - "left": "issue:44336", - "right": "issue:44485", + "left": "issue:43901", + "right": "issue:44246", "accept": false, - "reason": "Terminal ANSI output in loading_report is not the same as a GLM-5 RoPE implementation issue." + "reason": "Docs/behavior mismatch vs intermittent import slowness; unrelated." }, { - "left": "issue:45003", - "right": "issue:45561", + "left": "issue:41628", + "right": "issue:43976", "accept": false, - "reason": "Unsafe `sys.modules` access and an xdist race on captured_info.txt are different bugs in different paths." + "reason": "Missing AutoImageProcessor export vs Python 3.9/3.10 compatibility; different issues." }, { - "left": "issue:43673", - "right": "issue:44561", + "left": "issue:45561", + "right": "issue:45563", "accept": false, - "reason": "A generation cache regression during chunked_prefill is unrelated to removal of `is_torch_fx_available`." + "reason": "xdist file race vs stale warning in generate(); unrelated." }, { - "left": "issue:44246", - "right": "issue:44871", + "left": "issue:44242", + "right": "issue:45593", "accept": false, - "reason": "Import performance and Gemma-3 eos_token_id config mismatch are different problems." + "reason": "Missing load-balancing loss in MoE routing vs missing auxiliary losses for D-FINE denoising; different models and conditions." }, { - "left": "issue:44242", - "right": "issue:44857", + "left": "issue:44336", + "right": "issue:44373", "accept": false, - "reason": "MoE router loss handling and an AMP/CUDA crash in LwDetrImageLoss are unrelated." + "reason": "Terminal ANSI formatting bug vs wrong docstring for position_ids; not duplicates." }, { - "left": "issue:44162", - "right": "issue:45200", + "left": "issue:43352", + "right": "issue:45250", "accept": false, - "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids defaults do not share the same underlying bug." + "reason": "Specific model not supporting Flash Attention 2.0 vs a generic Flash Attention topic; too broad and not same bug." }, { - "left": "issue:36246", - "right": "issue:43596", + "left": "issue:44295", + "right": "issue:45397", "accept": false, - "reason": "A missing processor import and a DeepSpeed ZeRO3 BertModel index error are unrelated." + "reason": "position_ids buffer access error vs gemma-4 Zero3 loading; different failure modes." }, { - "left": "issue:44295", - "right": "issue:44749", + "left": "issue:41950", + "right": "issue:44220", "accept": false, - "reason": "Position_ids buffer access and tokenization slowdown after upgrade are different issues." + "reason": "Video-classification pipeline image-processor lookup vs fbank feature extraction issue; unrelated." }, { - "left": "issue:44779", - "right": "issue:45292", + "left": "issue:44246", + "right": "issue:44496", "accept": false, - "reason": "Tokenizer output changes and resize_token_embeddings not updating output embeddings are distinct bugs." + "reason": "Slow imports vs unrecognized model/config missing model_type; no shared root cause." }, { - "left": "issue:44877", - "right": "issue:45375", + "left": "issue:43531", + "right": "issue:45362", "accept": false, - "reason": "Strict config rejection for granite_speech and a missing field in Qwen3_5MoeVisionConfig are different config-loading issues." + "reason": "Sliding-window bug in Qwen3-MoE vs Qwen3.5 chat crash; similar model family but not the same concrete problem." }, { - "left": "issue:45292", - "right": "issue:45584", + "left": "issue:36246", + "right": "issue:42757", "accept": false, - "reason": "Embedding resize behavior and Whisper empty-transcription handling after align_special_tokens are not the same bug." + "reason": "Missing Qwen2_5_VL symbol vs missing is_offline_mode from huggingface_hub; unrelated import errors." }, { - "left": "issue:45292", - "right": "issue:45701", + "left": "issue:36246", + "right": "issue:44351", "accept": false, - "reason": "A model embedding resize bug is unrelated to version-dependent tokenization changes." + "reason": "Different missing exports from different modules; same symptom class, different underlying issues." }, { - "left": "issue:43901", + "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "A documentation mismatch about return_all_scores is not the same as unsafe `sys.modules` access." + "reason": "BEiT image-processor label reduction bug vs unsafe sys.modules access in modeling_utils; unrelated." }, { - "left": "issue:44987", - "right": "issue:45459", + "left": "issue:44336", + "right": "issue:44485", "accept": false, - "reason": "Loading a specific model failing on transformers>=5.1 and tokenizer error masking without protobuf are different root causes." + "reason": "ANSI escape output bug vs GLM-5 RoPE implementation discussion; not duplicates." }, { - "left": "issue:42886", - "right": "issue:45229", + "left": "issue:45003", + "right": "issue:45561", "accept": false, - "reason": "Offline cache loading failure and multi-GPU OOM are clearly different problems." + "reason": "Internal module access bug vs pytest-xdist race; different areas entirely." }, { - "left": "issue:44496", - "right": "issue:45003", + "left": "issue:43673", + "right": "issue:44561", "accept": false, - "reason": "Unrecognized model config and unsafe `sys.modules` access are different classes of failure." + "reason": "Missing cache in chunked_prefill vs removal of is_torch_fx_available breaking trust_remote_code; different APIs and failures." }, { - "left": "issue:43065", - "right": "issue:43408", + "left": "issue:44246", + "right": "issue:44871", "accept": false, - "reason": "A dummy Conv2d implementation and a sam3_video/sam3_tracker model-type warning are related only by family, not by the same bug." + "reason": "Import slowness vs Gemma eos_token_id config inconsistency; unrelated." }, { - "left": "issue:43232", - "right": "issue:44336", + "left": "issue:44242", + "right": "issue:44857", "accept": false, - "reason": "Generation kwargs after sync_gpus and ANSI codes in loading_report are unrelated." + "reason": "Missing router load-balancing loss vs AMP/CUDA crash in LwDetrImageLoss; not the same bug." }, { - "left": "issue:45375", - "right": "issue:45759", + "left": "issue:44162", + "right": "issue:45200", "accept": false, - "reason": "Missing `deepstack_visual_indexes` and failing to unwrap `text_config` are different multimodal config issues." + "reason": "ESM2 broken loading vs Gemma 4 mm_token_type_ids defaulting; different models and code paths." }, { - "left": "issue:43257", - "right": "issue:45137", + "left": "issue:36246", + "right": "issue:43596", "accept": false, - "reason": "Qwen3 MoE weight conversion with accelerate+deepspeed and an empty-deque ZeRO3 crash are different failure modes." + "reason": "Qwen2_5_VL import failure vs deepspeed Zero3/BertModel index error; unrelated." }, { - "left": "issue:43262", - "right": "issue:44246", + "left": "issue:44295", + "right": "issue:44749", "accept": false, - "reason": "Audio chat-template sampling-rate defaults and import slowness are unrelated." + "reason": "position_ids buffer error vs tokenizer/filtering slowdown after upgrade; different symptoms and layers." }, { - "left": "issue:44995", - "right": "issue:45200", + "left": "issue:44779", + "right": "issue:45292", "accept": false, - "reason": "A stale indexer cache crash and Gemma 4 token-type-id defaults are different bugs." + "reason": "Deepseek tokenizer regression vs resize_token_embeddings not updating output embeddings; different subsystems." } ] }, @@ -10858,62 +10808,76 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:28282", - "issue:30990", - "issue:41628", - "issue:42371", - "issue:42994", + "issue:42886", + "issue:43065", "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", "issue:43475", - "issue:43482", - "issue:43525", "issue:43540", - "issue:43643", "issue:43646", "issue:43653", "issue:43673", + "issue:43901", "issue:43931", - "issue:44038", "issue:44060", "issue:44077", "issue:44162", + "issue:44246", "issue:44297", - "issue:44361", + "issue:44336", "issue:44368", "issue:44466", + "issue:44496", "issue:44623", - "issue:44661", "issue:44734", - "issue:44749", "issue:44869", + "issue:44877", "issue:44933", "issue:44977", + "issue:44987", "issue:44995", - "issue:45081", - "issue:45092", - "issue:45103", + "issue:45003", "issue:45137", - "issue:45230", + "issue:45200", + "issue:45229", "issue:45278", - "issue:45310", + "issue:45292", "issue:45335", "issue:45356", - "issue:45381", + "issue:45375", "issue:45397", "issue:45459", "issue:45563", + "issue:45584", "issue:45588", "issue:45600", - "issue:45656" + "issue:45656", + "issue:45701", + "issue:45759" ], "soft_pairs": [ + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:45292|issue:45701", + "issue:43901|issue:45003", + "issue:42886|issue:45229", + "issue:44496|issue:45003", + "issue:44987|issue:45459", + "issue:43232|issue:44336", + "issue:43065|issue:43408", + "issue:45375|issue:45759", + "issue:43257|issue:45137", + "issue:43262|issue:44246", "issue:44060|issue:44077", + "issue:44995|issue:45200", "issue:43475|issue:43540", "issue:44466|issue:45335", - "issue:44995|issue:45588", "issue:43653|issue:44162", + "issue:44995|issue:45588", "issue:44368|issue:45563", "issue:44368|issue:44977", "issue:45397|issue:45656", @@ -10925,243 +10889,216 @@ "issue:43232|issue:43673", "issue:44297|issue:44623", "issue:43673|issue:45278", - "issue:43646|issue:44162", - "issue:44361|issue:44749", - "issue:44623|issue:45656", - "issue:42994|issue:43482", - "issue:28282|issue:30990", - "issue:44749|issue:45656", - "issue:44749|issue:45310", - "issue:43475|issue:43643", - "issue:42371|issue:45092", - "issue:43475|issue:45381", - "issue:45230|issue:45397", - "issue:44038|issue:44623", - "issue:41628|issue:44933", - "issue:45081|issue:45103", - "issue:42994|issue:43525", - "issue:43475|issue:44661" + "issue:43646|issue:44162" ], - "prepared_review_unit_hash": "a03580f52b946152d94f46c7fe1b726a467c7bf673578cf54fbd1e104db2f60c", + "prepared_review_unit_hash": "c50f5c71a19dddfc16b08677609cdde094380f44662c0482d8aefc36b7e7077a", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 32, - "serialized_chars": 36720, - "estimated_input_tokens": 9180, - "estimated_eval_tokens": 18616 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36664, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 }, "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 that only share broad themes like imports, generation, tokenizers, or model-loading. None of the soft edges looks like a true duplicate pair under a strict same-bug standard. The broadest representative issue is the open import-regression umbrella #45278.", - "confidence": 0.41, - "canonical_issue_reason": "#45278 is the broadest umbrella in the set: it describes multiple import errors after upgrading to 5.5.0, which makes it the most plausible canonical issue for a cluster containing several import-related reports.", + "summary": "This cluster is mostly a mix of unrelated Transformers issues that only share broad themes like model loading, tokenization, generation, or config handling. None of the soft pairs look like true duplicates or mergeable PR-equivalents, so I rejected them all.", + "confidence": 0.28, + "canonical_issue_reason": "issue:45278 is the broadest umbrella symptom in the set: a general upgrade regression causing multiple import/load failures. It is the closest representative of the cluster, though the rest are mostly narrower model-specific bugs rather than duplicates.", "canonical_pr_reason": null, - "best_issue_reason": "#45278 is the best cluster representative because it is broad enough to cover the recurring import-failure theme, while the other issues are mostly narrow, model-specific, or unrelated regressions.", + "best_issue_reason": "issue:45278 is the best single representative because it is broad, user-facing, and captures the general upgrade-breakage theme better than the more specialized model-specific reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both are strict-config style bugs, but they affect different models and different missing fields; not the same underlying defect." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "resize_token_embeddings mismatch and Whisper empty-transcription failure are unrelated code paths." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "One is an embedding-resize bug; the other is a version-dependent tokenization change complaint." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mentioning return_all_scores and unsafe sys.modules access are unrelated." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline cache loading failure and Gemma4 multi-GPU CUDA OOM are different problems." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model/config loading and sys.modules access are distinct failure modes." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Both involve tokenizer loading, but one is a model-load regression and the other is an exception-suppression bug in decode handling." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs sync issue and ANSI terminal output issue are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Same SAM3 family, but a dummy Conv2d in the pixel decoder is not the same bug as the tracker-type warning." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both are Qwen multimodal config issues, but one is a missing field and the other is an unwrap-text_config initialization bug." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Accelerate+DeepSpeed weight conversion and ZeRO3 deque underflow are different loading failures." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate default and slow import are unrelated." + }, { "left": "issue:44060", "right": "issue:44077", "accept": false, - "reason": "Both are warnings/regression reports, but they concern different models and different code paths; no evidence of the same bug." + "reason": "Tied-weights warning behavior and patchtsmixer post_init policy are not the same defect." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "A stale indexer cache crash and a missing mm_token_type_ids default are different bugs." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "Both are video-input issues, but one is a SAM 3 attribute error and the other is a Qwen3OmniMoe value error; not the same underlying defect." + "reason": "Both touch video models, but the SAM3 attribute error and Qwen3OmniMoe video ValueError are separate code paths." }, { "left": "issue:44466", "right": "issue:45335", "accept": false, - "reason": "Both touch embedding/tied-weight behavior, but one is about inconsistent serialization and the other about resize_token_embeddings not updating decoder embeddings." + "reason": "Both concern tied/resized embeddings, but serialization inconsistency and decoder.embed_tokens resize behavior are not the same issue." }, { - "left": "issue:44995", - "right": "issue:45588", + "left": "issue:43653", + "right": "issue:44162", "accept": false, - "reason": "These are unrelated crashes in different subsystems: GlmMoeDsa caching versus flash_attention handling of s_aux=None." + "reason": "BigBirdTokenizer special-token registration and ESM2 breakage are unrelated." }, { - "left": "issue:43653", - "right": "issue:44162", + "left": "issue:44995", + "right": "issue:45588", "accept": false, - "reason": "BigBirdTokenizer special-token registration and ESM2 breakage are different bugs with no clear shared code path." + "reason": "A stale cache crash and a flash-attention s_aux=None AttributeError are different problems." }, { "left": "issue:44368", "right": "issue:45563", "accept": false, - "reason": "One is a tied-weights warning in Qwen3.5 fine-tuning; the other is a stale warning for num_return_sequences in paged generate()." + "reason": "One is a tied-embeddings warning, the other a stale num_return_sequences warning." }, { "left": "issue:44368", "right": "issue:44977", "accept": false, - "reason": "A tied-embeddings warning is not the same as a flash-attention generation failure." + "reason": "A warning about tie_word_embeddings is not the same as a flash-attention generation failure." }, { "left": "issue:45397", "right": "issue:45656", "accept": false, - "reason": "DeepSpeed ZeRO3 from_pretrained and a doubled optimizer step are distinct training/runtime problems." + "reason": "Gemma4 ZeRO3 from_pretrained failure and optimizer step being called twice under DeepSpeed are unrelated." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Both mention generation/cache, but one is a missing GenerationMixin cache in chunked_prefill and the other is wrong tensor indexing in serve KV-cache continuation." + "reason": "Both involve generation/cache, but chunked_prefill cache absence and serve KV-cache continuation indexing are different bugs." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "DeepSpeed ZeRO3 deque underflow and stale auto_mappings references are unrelated failures." + "reason": "DeepSpeed deque underflow and stale Sam3LiteText config references are unrelated." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "A Qwen3-VL weight-shape mismatch is not the same as a tied-embeddings warning in Qwen3.5 fine-tuning." + "reason": "Qwen3-VL weight-shape mismatch and tie_word_embeddings warning are different issues." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "Both involve imports or decoding paths, but one is a missing image_utils import and the other is protobuf decode-error masking." + "reason": "A missing import from image_utils and tokenizer error masking are unrelated." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Whisper timestamp decoding and Kimi-K2.5 tokenizer codec handling are different tokenizer bugs." + "reason": "Both are tokenizer/decoding regressions, but they affect different models and different root causes." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "Both are generation internals, but they are different regressions in different functions and scenarios." + "reason": "Both are generation-related, but sync_gpus kwargs handling and chunked_prefill cache behavior are not the same bug." }, { "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "Saving tokenizer metadata and saving processor files are related only at a high level; the concrete failures differ." + "reason": "save_pretrained tokenizer-class mismatch and processor.save_pretrained missing files are different serialization bugs." }, { "left": "issue:43673", "right": "issue:45278", "accept": false, - "reason": "Generation cache handling is not the same bug as a broad report about multiple import errors after upgrade." + "reason": "Generation cache behavior and broad import errors after upgrade are not the same issue." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Custom model initialization under Transformers v5 and ESM2 breakage are not the same underlying issue." - }, - { - "left": "issue:44361", - "right": "issue:44749", - "accept": false, - "reason": "An MLukeTokenizer AttributeError and a data-filtering slowdown after upgrade are unrelated." - }, - { - "left": "issue:44623", - "right": "issue:45656", - "accept": false, - "reason": "Processor save_pretrained file loss and a duplicated optimizer step are different problems in different layers." - }, - { - "left": "issue:42994", - "right": "issue:43482", - "accept": false, - "reason": "Quantized model saving and Qwen2.5-GGUF loading are opposite directions and different failure modes." - }, - { - "left": "issue:28282", - "right": "issue:30990", - "accept": false, - "reason": "A missing PyTorch import error and Sentence Transformers hanging on load are not the same bug." - }, - { - "left": "issue:44749", - "right": "issue:45656", - "accept": false, - "reason": "A data-processing slowdown after upgrade has nothing to do with double optimizer stepping in DeepSpeed." - }, - { - "left": "issue:44749", - "right": "issue:45310", - "accept": false, - "reason": "Performance regression in data filtering and Qwen3.5-Moe from_pretrained failure are unrelated." - }, - { - "left": "issue:43475", - "right": "issue:43643", - "accept": false, - "reason": "Both involve model/config loading, but one is a SAM 3 vision encoder attribute error and the other is missing fields from AutoConfig with trust_remote_code." - }, - { - "left": "issue:42371", - "right": "issue:45092", - "accept": false, - "reason": "TF32 API-setting guidance and InternVL2 meta-initialization incompatibility are unrelated." - }, - { - "left": "issue:43475", - "right": "issue:45381", - "accept": false, - "reason": "Both concern video models, but they affect different model families and different failure modes." - }, - { - "left": "issue:45230", - "right": "issue:45397", - "accept": false, - "reason": "A generic bug report and a DeepSpeed/Gemma-4 from_pretrained issue do not indicate the same defect." - }, - { - "left": "issue:44038", - "right": "issue:44623", - "accept": false, - "reason": "Qwen3-VL-Moe import/compatibility problems are not the same as processor.save_pretrained missing files." - }, - { - "left": "issue:41628", - "right": "issue:44933", - "accept": false, - "reason": "These are both import errors, but they refer to different missing symbols in different modules." - }, - { - "left": "issue:45081", - "right": "issue:45103", - "accept": false, - "reason": "The Mistral regex crash and the future-annotations auto-docstring crash are separate AttributeError issues." - }, - { - "left": "issue:42994", - "right": "issue:43525", - "accept": false, - "reason": "Quantized model saving failure and missing pad_token_id on Llama4Config are unrelated." - }, - { - "left": "issue:43475", - "right": "issue:44661", - "accept": false, - "reason": "A SAM 3 vision-encoder attribute error is not the same as add-new-model-like failing for tokenizer mapping names." + "reason": "Both are broad regressions, but they concern different models and different failure surfaces." } ] }, @@ -11183,68 +11120,83 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ + "issue:28282", "issue:30990", - "issue:35141", "issue:36010", "issue:41628", "issue:42175", "issue:42222", + "issue:42371", "issue:42673", "issue:42831", - "issue:42898", "issue:42994", "issue:43232", - "issue:43278", "issue:43377", - "issue:43479", - "issue:43504", + "issue:43475", + "issue:43482", + "issue:43525", "issue:43526", + "issue:43643", "issue:43673", "issue:43704", - "issue:43784", "issue:43824", "issue:43873", - "issue:43976", "issue:44038", - "issue:44079", "issue:44188", "issue:44222", "issue:44242", "issue:44351", - "issue:44373", + "issue:44361", "issue:44496", - "issue:44568", "issue:44623", - "issue:44734", + "issue:44661", + "issue:44749", "issue:44792", - "issue:44869", "issue:44933", "issue:44945", - "issue:44964", + "issue:45081", + "issue:45092", "issue:45103", - "issue:45137", "issue:45200", + "issue:45230", "issue:45310", "issue:45375", + "issue:45381", + "issue:45397", "issue:45478", "issue:45561", + "issue:45656", "issue:45712", - "issue:45753", - "issue:45812" + "issue:45753" ], "soft_pairs": [ + "issue:44361|issue:44749", + "issue:44623|issue:45656", + "issue:42994|issue:43482", + "issue:28282|issue:30990", + "issue:44749|issue:45656", + "issue:44749|issue:45310", + "issue:43475|issue:43643", + "issue:42371|issue:45092", + "issue:43475|issue:45381", + "issue:45230|issue:45397", + "issue:44038|issue:44623", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:42994|issue:43525", + "issue:43475|issue:44661", "issue:45375|issue:45478", "issue:42673|issue:43704", "issue:43232|issue:44188", - "issue:43873|issue:44945", "issue:45310|issue:45375", + "issue:43873|issue:44945", "issue:41628|issue:44351", "issue:42831|issue:44222", "issue:44945|issue:45753", - "issue:42222|issue:45200", "issue:44222|issue:45310", + "issue:42222|issue:45200", "issue:42994|issue:43824", "issue:43232|issue:44792", "issue:36010|issue:41628", @@ -11253,254 +11205,246 @@ "issue:44038|issue:45310", "issue:43377|issue:44242", "issue:43526|issue:45561", - "issue:44496|issue:45561", - "issue:43504|issue:45561", - "issue:44964|issue:45137", - "issue:42898|issue:44568", - "issue:42175|issue:44933", - "issue:43479|issue:44869", - "issue:30990|issue:35141", - "issue:43976|issue:44933", - "issue:43479|issue:44079", - "issue:42898|issue:45812", - "issue:43784|issue:43824", - "issue:44188|issue:44373", - "issue:44623|issue:45310", - "issue:43278|issue:45137", - "issue:44734|issue:45103" + "issue:44496|issue:45561" ], - "prepared_review_unit_hash": "fa0fa99ad59093464e80402746c7d40d762b26a80960673e24073b7e52497f95", + "prepared_review_unit_hash": "889681603087fe1a5943d53c9619b2edf887dc15a9a9d7d5894d28451746e191", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37396, - "estimated_input_tokens": 9349, - "estimated_eval_tokens": 18954 + "soft_pair_count": 34, + "serialized_chars": 37628, + "estimated_input_tokens": 9407, + "estimated_eval_tokens": 19070 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous, but it does contain two clear exact-duplicate pairs: 42673/43704 for the Qwen3ForCausalLM VRAM leak, and 45310/45478 for the Qwen3.5 Moe from_pretrained error. The remaining Qwen/vision/config/import items are thematically related in places, but not confidently the same underlying bug.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 42673 is a strong canonical issue because it has an exact duplicate in 43704 and the pair describes the same concrete VRAM-leak failure in multi-dataloader-thread use. It is also the earliest clearly matched duplicate pair in the packet.", + "summary": "The set is mostly heterogeneous, but it contains more than one duplicate-looking pocket: the Qwen3ForCausalLM VRAM leak pair (42673/43704) is a clear duplicate relationship, and 45310/45478 also look like the same Qwen3.5-MoE from_pretrained bug by title. I\u2019d keep 42673 as the canonical issue for the leak pair, while being conservative about broader cluster sameness.", + "confidence": 0.66, + "canonical_issue_reason": "42673 is the earlier, more detailed report of the Qwen3ForCausalLM VRAM leak and has stronger discussion context than 43704.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 42673 is the best overall issue anchor for this packet because it is a clean exact-duplicate case with a concrete reproduction, while the other near-matches are weaker. The separate 45310/45478 exact-title pair is also a duplicate, but it represents a different bug family.", + "best_issue_reason": "42673 is the strongest issue to anchor the cluster because it cleanly subsumes 43704 and is the most developed report of a clearly duplicated bug; the rest of the cluster appears to split into separate issue pockets.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:45375", - "right": "issue:45478", + "left": "issue:44361", + "right": "issue:44749", "accept": false, - "reason": "Same model family, but one is a specific missing config-field symptom and the other is a broader from_pretrained error; not the same concrete bug." + "reason": "Different failures: tokenizer/task AttributeError vs performance slowdown after upgrade." }, { - "left": "issue:42673", - "right": "issue:43704", - "accept": true, - "reason": "Exact duplicate title and same VRAM-leak behavior for Qwen3ForCausalLM in multi-dataloader threads." + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Unrelated code paths: processor.save_pretrained file omissions vs deepspeed optimizer stepping twice." }, { - "left": "issue:43232", - "right": "issue:44188", + "left": "issue:42994", + "right": "issue:43482", "accept": false, - "reason": "Both touch generation internals, but the concrete failures differ: sync_gpus kwarg handling vs attention-kernel branching under torch.compile." + "reason": "Both involve quantization/loading, but one is a save failure and the other is a GGUF load failure; not the same bug." }, { - "left": "issue:43873", - "right": "issue:44945", + "left": "issue:28282", + "right": "issue:30990", "accept": false, - "reason": "Quantization/offloading behavior and pipeline-parallel output corruption are different failure modes and likely different fixes." + "reason": "PyTorch missing ImportError is unrelated to Sentence Transformers getting stuck while loading." }, { - "left": "issue:45310", - "right": "issue:45375", + "left": "issue:44749", + "right": "issue:45656", "accept": false, - "reason": "Related Qwen3.5 MoE area, but a generic from_pretrained error and a specific missing config field are not clearly the same bug." + "reason": "Performance regression after upgrade is not the same as duplicate optimizer-step behavior under deepspeed." }, { - "left": "issue:41628", - "right": "issue:44351", + "left": "issue:44749", + "right": "issue:45310", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different fixes." + "reason": "Different issues: slowdown regression vs Qwen3.5-MoE from_pretrained error." }, { - "left": "issue:42831", - "right": "issue:44222", + "left": "issue:43475", + "right": "issue:43643", "accept": false, - "reason": "Both mention FP8, but one is an accuracy regression and the other is a save_pretrained/moe serialization problem." + "reason": "Both are field/attribute-related, but they affect different model/config paths and have different causes." }, { - "left": "issue:44945", - "right": "issue:45753", + "left": "issue:42371", + "right": "issue:45092", "accept": false, - "reason": "Pipeline-parallel wrong output and infinite-loop generation for a specific image are distinct symptoms and code paths." + "reason": "TF32 behavior settings are unrelated to meta-init incompatibility for old InternVL2 remote-code checkpoints." }, { - "left": "issue:42222", - "right": "issue:45200", + "left": "issue:43475", + "right": "issue:45381", "accept": false, - "reason": "Both are multimodal/model config bugs, but they concern different fields and different models." + "reason": "Different model-specific bugs: missing attribute on SAM 3 Video vs wrong vision_position_ids on Qwen2.5-VL." }, { - "left": "issue:44222", - "right": "issue:45310", + "left": "issue:45230", + "right": "issue:45397", "accept": false, - "reason": "FP8 save_pretrained/moe and Qwen3.5 MoE from_pretrained error are unrelated beyond broad model-family overlap." + "reason": "Generic bug report is not the same concrete issue as Gemma-4 ZeRO3 from_pretrained failure." }, { - "left": "issue:42994", - "right": "issue:43824", + "left": "issue:44038", + "right": "issue:44623", "accept": false, - "reason": "Quantized model saving failure and an import error for a specific class are unrelated." + "reason": "Qwen3-VL-Moe/transformers v5 incompatibility is unrelated to processor.save_pretrained missing files." }, { - "left": "issue:43232", - "right": "issue:44792", + "left": "issue:41628", + "right": "issue:44933", "accept": false, - "reason": "Generation kwarg syncing and janus image-generation test failure are different issues." + "reason": "Both are import errors, but they concern different symbols and likely different export paths." }, { - "left": "issue:36010", - "right": "issue:41628", + "left": "issue:45081", + "right": "issue:45103", "accept": false, - "reason": "Both are import-related, but they concern different APIs and likely different regressions." + "reason": "Tokenizer regex crash and auto_docstring crash are unrelated code-path failures." }, { - "left": "issue:42175", - "right": "issue:45712", + "left": "issue:42994", + "right": "issue:43525", "accept": false, - "reason": "Backend dependency packaging and leftover dummy classes in repo checks are unrelated." + "reason": "Quantized model saving failure is unrelated to Llama4Config missing pad_token_id." }, { - "left": "issue:43673", - "right": "issue:44188", + "left": "issue:43475", + "right": "issue:44661", "accept": false, - "reason": "Cache-missing generation bug and divergent attention kernels under torch.compile are different problems." + "reason": "Different model/processor plumbing bugs; no shared concrete failure." }, { - "left": "issue:44038", - "right": "issue:45310", + "left": "issue:45375", + "right": "issue:45478", "accept": false, - "reason": "Different model families and failure modes; not the same bug." + "reason": "Same model family, but one is a missing config field and the other is a from_pretrained error; not enough to merge as duplicates." }, { - "left": "issue:43377", - "right": "issue:44242", - "accept": false, - "reason": "Missing padding-mask support in MIMI encoder vs router-logit loss gating in MoE are unrelated." + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same exact bug report: Qwen3ForCausalLM VRAM leak when used in multiple dataloader threads." }, { - "left": "issue:43526", - "right": "issue:45561", + "left": "issue:43232", + "right": "issue:44188", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and xdist race on captured_info.txt are unrelated." + "reason": "Generation kwargs update after sync_gpus is unrelated to attention-kernel divergence under torch.compile." }, { - "left": "issue:44496", - "right": "issue:45561", + "left": "issue:45310", + "right": "issue:45375", "accept": false, - "reason": "Unrecognized model loading and xdist race in testing utils are unrelated." + "reason": "Different Qwen3.5-MoE symptoms: from_pretrained error vs missing deepstack_visual_indexes field." }, { - "left": "issue:43504", - "right": "issue:45561", + "left": "issue:43873", + "right": "issue:44945", "accept": false, - "reason": "Legacy field during pretrained load vs xdist race in testing utils are unrelated." + "reason": "Quantization offloading issue is not the same as incorrect pipeline-parallel LLM output." }, { - "left": "issue:44964", - "right": "issue:45137", + "left": "issue:41628", + "right": "issue:44351", "accept": false, - "reason": "Phi-4 multimodal load failure and DeepSpeed ZeRO3 deque error are different code paths." + "reason": "Different missing imports: AutoImageProcessor vs HybridCache." }, { - "left": "issue:42898", - "right": "issue:44568", + "left": "issue:42831", + "right": "issue:44222", "accept": false, - "reason": "Tokenization cleanup behavior change and missing BOS/EOS addition are different tokenizer regressions." + "reason": "FP8 accuracy regression and FP8 save_pretrained failure are different bugs." }, { - "left": "issue:42175", - "right": "issue:44933", + "left": "issue:44945", + "right": "issue:45753", "accept": false, - "reason": "Backend dependency packaging and missing import from image_utils are unrelated." + "reason": "Pipeline-parallel output corruption is unrelated to an infinite loop on a specific image." }, { - "left": "issue:43479", - "right": "issue:44869", + "left": "issue:44222", + "right": "issue:45310", "accept": false, - "reason": "Default multimodal config initialization and Whisper word-timestamp decode crash are unrelated." + "reason": "FP8 save_pretrained moe and Qwen3.5-MoE from_pretrained error are different issues." }, { - "left": "issue:30990", - "right": "issue:35141", + "left": "issue:42222", + "right": "issue:45200", "accept": false, - "reason": "Sentence Transformers loading hang and embedding resize reinitialization are unrelated." + "reason": "Broken vitpose models and Gemma 4 mm_token_type_ids defaults are unrelated." }, { - "left": "issue:43976", - "right": "issue:44933", + "left": "issue:42994", + "right": "issue:43824", "accept": false, - "reason": "Python version support issue and missing image_utils import are unrelated." + "reason": "Saving quantized models and missing Qwen2_5_VL import are unrelated." }, { - "left": "issue:43479", - "right": "issue:44079", + "left": "issue:43232", + "right": "issue:44792", "accept": false, - "reason": "Default multimodal config initialization and ModelOutput None-key assignment are unrelated." + "reason": "Generation kwargs update bug is unrelated to the janus image-generation test failure." }, { - "left": "issue:42898", - "right": "issue:45812", + "left": "issue:36010", + "right": "issue:41628", "accept": false, - "reason": "Tokenization cleanup change and Granite token-id regression are different bugs." + "reason": "Both are import errors, but they involve different APIs and likely different regressions." }, { - "left": "issue:43784", - "right": "issue:43824", + "left": "issue:42175", + "right": "issue:45712", "accept": false, - "reason": "Both are import errors after a transformers update, but for different symbols and different fixes." + "reason": "Packaging/backend dependency issue is distinct from dummy_pt_objects cleanup and dir(transformers) leakage." }, { - "left": "issue:44188", - "right": "issue:44373", + "left": "issue:43673", + "right": "issue:44188", "accept": false, - "reason": "Attention-kernel branching bug and docstring issue are not the same underlying problem." + "reason": "Chunked_prefill cache regression is unrelated to attention-kernel divergence under compile." }, { - "left": "issue:44623", + "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Processor save_pretrained file omission and Qwen3.5 MoE from_pretrained error are unrelated." + "reason": "Different Qwen model variants and different failure modes; not the same concrete bug." }, { - "left": "issue:43278", - "right": "issue:45137", + "left": "issue:43377", + "right": "issue:44242", "accept": false, - "reason": "Embedding dtype drift in eval and ZeRO3 deque pop error are unrelated." + "reason": "Missing padding-mask batching bug is unrelated to load-balancing loss omission." }, { - "left": "issue:44734", - "right": "issue:45103", + "left": "issue:43526", + "right": "issue:45561", "accept": false, - "reason": "KV-cache indexing crash in serve and auto_docstring annotation crash are unrelated." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to xdist captured_info.txt race." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized model/config issue is unrelated to the xdist race condition." } ] }, "evaluator_result": { "accept": false, - "feedback": "The writeup is a bit too strong for the packet: besides 42673/43704, the packet also contains 45310 and 45478 with the exact same title ('Qwen3.5 Moe from_pretrained error'), so the claim that only the VRAM leak reports are a clear duplicate pair is not fully grounded. The soft-edge rejections are mostly conservative, but the summary understates another obvious duplicate-like pair." + "feedback": "The Qwen3ForCausalLM leak pairing (42673/43704) is plausible, but the summary overstates the cluster\u2019s heterogeneity by saying it is the only clear duplicate pair. The packet also contains two issues with the same title, 45310 and 45478, which looks like another duplicate pair. Please keep the summary more conservative and acknowledge that there may be more than one duplicate relationship in the set." }, "evaluator_used": true, "retried": true, @@ -11519,64 +11463,78 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:22355", "issue:28282", "issue:30333", + "issue:30990", "issue:33290", - "issue:34689", "issue:35141", "issue:36331", "issue:41628", + "issue:42175", "issue:42757", "issue:42831", "issue:42898", - "issue:43232", + "issue:43278", "issue:43479", + "issue:43504", "issue:43644", "issue:43723", + "issue:43784", + "issue:43824", "issue:43874", + "issue:43976", "issue:44060", + "issue:44079", + "issue:44188", "issue:44206", "issue:44222", - "issue:44261", - "issue:44263", "issue:44295", "issue:44297", - "issue:44360", "issue:44373", "issue:44448", - "issue:44483", - "issue:44484", - "issue:44485", - "issue:44514", "issue:44568", "issue:44623", + "issue:44734", "issue:44779", - "issue:44871", + "issue:44869", "issue:44933", - "issue:44977", - "issue:44991", + "issue:44964", "issue:45092", "issue:45103", "issue:45125", + "issue:45137", "issue:45310", "issue:45356", - "issue:45357", "issue:45405", - "issue:45406", + "issue:45561", "issue:45656", "issue:45712", - "issue:45834" + "issue:45812" ], "soft_pairs": [ + "issue:43504|issue:45561", + "issue:44964|issue:45137", + "issue:42898|issue:44568", + "issue:42175|issue:44933", + "issue:30990|issue:35141", + "issue:43479|issue:44869", + "issue:43976|issue:44933", + "issue:43479|issue:44079", + "issue:42898|issue:45812", + "issue:43784|issue:43824", + "issue:44188|issue:44373", + "issue:44623|issue:45310", + "issue:43278|issue:45137", + "issue:44734|issue:45103", "issue:30333|issue:33290", "issue:43723|issue:44568", "issue:42898|issue:45356", "issue:44060|issue:45125", - "issue:42898|issue:44779", "issue:43874|issue:45092", + "issue:42898|issue:44779", "issue:45405|issue:45712", "issue:42898|issue:44448", "issue:44295|issue:45656", @@ -11587,271 +11545,236 @@ "issue:44206|issue:45103", "issue:44222|issue:44623", "issue:42831|issue:44623", - "issue:30333|issue:36331", "issue:41628|issue:42757", "issue:22355|issue:28282", - "issue:43232|issue:45834", - "issue:30333|issue:34689", - "issue:43723|issue:44977", - "issue:44222|issue:44484", - "issue:44297|issue:45310", - "issue:28282|issue:30333", - "issue:30333|issue:35141", - "issue:44263|issue:45092", - "issue:44483|issue:45406", - "issue:44263|issue:44360", - "issue:44514|issue:45103", - "issue:44373|issue:44485", - "issue:44295|issue:44623", - "issue:43723|issue:44871", - "issue:45092|issue:45357", - "issue:44261|issue:45092", - "issue:43723|issue:44991" + "issue:30333|issue:36331" ], - "prepared_review_unit_hash": "8064fa8b371931c5d1d7cdde7abdc8da72c63380a0413f8a250887ce36e60387", + "prepared_review_unit_hash": "9f8ca32d8cbb559640ebb7995e13caf5054e393b68a6e67036f9d20f23404284", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 36, - "serialized_chars": 38419, - "estimated_input_tokens": 9605, - "estimated_eval_tokens": 19466 + "soft_pair_count": 33, + "serialized_chars": 37643, + "estimated_input_tokens": 9411, + "estimated_eval_tokens": 19078 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are mostly unrelated issue reports. The soft-similarity links are driven by broad overlap in areas like tokenizers, save/load, and v5 regressions, but the concrete failures are different, so I would not collapse any of the candidate pairs.", - "confidence": 0.66, - "canonical_issue_reason": "issue:42898 is the broadest and most representative issue here, centered on a v5 tokenizer-behavior regression; it is the closest thing to a topical anchor among the tokenizer-related items.", + "summary": "These soft pairs are overwhelmingly unrelated. They span different subsystems (tokenizers, model loading, training loops, deepspeed, multimodal processors, imports, docs, and packaging), so none should be merged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical issue: the candidate pairs are heterogeneous and do not appear to describe the same underlying bug.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42898 is the best issue to anchor the cluster because it is generic enough to represent the recurring tokenizer/regression theme, even though the overall set is heterogeneous and not duplicate-safe.", + "best_issue_reason": "No single best issue for duplicate anchoring; even the broadest regression reports are still model- or subsystem-specific and do not cover the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:30333", - "right": "issue:33290", + "left": "issue:43504", + "right": "issue:45561", "accept": false, - "reason": "Different subsystems and failure modes: MLflow reporting after training failure vs a deepspeed/Adafactor OOM." + "reason": "Legacy field loading failure and pytest-xdist file-race are unrelated bugs in different code paths." }, { - "left": "issue:43723", - "right": "issue:44568", + "left": "issue:44964", + "right": "issue:45137", "accept": false, - "reason": "Both are tokenizer regressions, but one is a v5 AutoTokenizer loading issue and the other is missing BOS/EOS insertion for a specific tokenizer." + "reason": "Phi-4 multimodal model loading and DeepSpeed ZeRO3 deque underflow are different failures with no shared root cause." }, { "left": "issue:42898", - "right": "issue:45356", + "right": "issue:44568", "accept": false, - "reason": "Both mention tokenizer regressions, but one is clean_up_tokenization_spaces behavior and the other is Kimi-K2.5 codec/ warning handling." + "reason": "Both are tokenizer regressions, but one is a v5 cleanup behavior change and the other is missing BOS/EOS insertion for a specific tokenizer." }, { - "left": "issue:44060", - "right": "issue:45125", + "left": "issue:42175", + "right": "issue:44933", "accept": false, - "reason": "Different Qwen model bugs: a tied-weights warning in Qwen3-Next vs a missing tensor-parallel plan in Qwen3_5Moe." + "reason": "Packaging/backend dependency mismatch and a missing image_utils import are unrelated." }, { - "left": "issue:42898", - "right": "issue:44779", + "left": "issue:30990", + "right": "issue:35141", "accept": false, - "reason": "Both are v5 tokenizer regressions, but they affect different models and different code paths." + "reason": "Sentence-transformers loading hang and embedding reinitialization after resize are different model lifecycle problems." }, { - "left": "issue:43874", - "right": "issue:45092", + "left": "issue:43479", + "right": "issue:44869", "accept": false, - "reason": "Different problems: a missing image-processor method vs meta-init incompatibility for old InternVL2 remote-code checkpoints." + "reason": "Phi4MultimodalConfig defaults and Whisper timestamp decoding are unrelated multimodal issues." }, { - "left": "issue:45405", - "right": "issue:45712", + "left": "issue:43976", + "right": "issue:44933", "accept": false, - "reason": "Unrelated: dependency version bump policy vs leftover dummy classes leaking into the package namespace." + "reason": "Python version compatibility and a missing image_utils symbol are different classes of failure." }, { - "left": "issue:42898", - "right": "issue:44448", + "left": "issue:43479", + "right": "issue:44079", "accept": false, - "reason": "Different regression types: tokenizer cleanup behavior vs a model output difference between v4 and v5." + "reason": "Config default initialization and ModelOutput key assignment are unrelated internals." }, { - "left": "issue:44295", - "right": "issue:45656", + "left": "issue:42898", + "right": "issue:45812", "accept": false, - "reason": "Unrelated bugs: reading a registered buffer vs optimizer stepping twice under deepspeed." + "reason": "Both involve tokenizers, but they affect different models and different regression mechanisms." }, { - "left": "issue:44933", - "right": "issue:45712", + "left": "issue:43784", + "right": "issue:43824", "accept": false, - "reason": "Different issues: a missing image_utils import/export vs dummy PT class cleanup." + "reason": "Sentence-transformers import NameError and missing Qwen2_5_VL export are unrelated import failures." }, { - "left": "issue:44222", - "right": "issue:44297", + "left": "issue:44188", + "right": "issue:44373", "accept": false, - "reason": "Both involve save_pretrained, but one is FP8/MoE serialization and the other is tokenizer metadata mismatch." + "reason": "A torch.compile attention-kernel bug and a docstring issue do not share a concrete code-path problem." }, { - "left": "issue:44297", - "right": "issue:45656", + "left": "issue:44623", + "right": "issue:45310", "accept": false, - "reason": "Tokenizer save metadata bug vs deepspeed optimizer double-step; no shared underlying failure." + "reason": "Missing processor save artifacts and Qwen3.5 MoE from_pretrained errors are different bugs." }, { - "left": "issue:43479", - "right": "issue:43644", + "left": "issue:43278", + "right": "issue:45137", "accept": false, - "reason": "Different initialization bugs: bad default multimodal configs vs non-persistent buffers being filled with junk." + "reason": "Embedding dtype drift in eval and DeepSpeed deque popping are unrelated." }, { - "left": "issue:44206", + "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "Different code paths: feature extractor argument compatibility vs auto-docstring parsing under future annotations." - }, - { - "left": "issue:44222", - "right": "issue:44623", - "accept": false, - "reason": "Both mention save_pretrained, but one is FP8 MoE model saving and the other is processor file omission." - }, - { - "left": "issue:42831", - "right": "issue:44623", - "accept": false, - "reason": "Accuracy issue in FineGrainedFP8 is unrelated to processor save_pretrained missing files." + "reason": "KV-cache continuation crash and auto-docstring annotation handling are separate areas with no common fix." }, { "left": "issue:30333", - "right": "issue:36331", + "right": "issue:33290", "accept": false, - "reason": "Training-related, but not the same bug: MLflow status reporting vs CustomTrainer API breakage." + "reason": "MLFlow status reporting on failed jobs and Adafactor OOM are different training issues." }, { - "left": "issue:41628", - "right": "issue:42757", + "left": "issue:43723", + "right": "issue:44568", "accept": false, - "reason": "Separate import failures from different packages and causes: transformers AutoImageProcessor vs huggingface_hub offline mode." + "reason": "Generic tokenizer loading regression and add_special_tokens behavior for one tokenizer are not the same bug." }, { - "left": "issue:22355", - "right": "issue:28282", + "left": "issue:42898", + "right": "issue:45356", "accept": false, - "reason": "Both are import errors, but one is a missing transformers.onnx module and the other is missing PyTorch for AutoModel." + "reason": "Different tokenizer regressions affecting different models and different failure modes." }, { - "left": "issue:43232", - "right": "issue:45834", + "left": "issue:44060", + "right": "issue:45125", "accept": false, - "reason": "Different generation/input failures with no shared code-path." + "reason": "Incorrect tied-weights warning and missing tensor-parallel plan are distinct Qwen3-family issues." }, { - "left": "issue:30333", - "right": "issue:34689", + "left": "issue:43874", + "right": "issue:45092", "accept": false, - "reason": "Unrelated issues: MLflow reporting after training failure vs a model-loading regression for Llama 3.2 Vision." + "reason": "Missing image patch count method and remote-code meta-init incompatibility are separate multimodal-loading problems." }, { - "left": "issue:43723", - "right": "issue:44977", + "left": "issue:42898", + "right": "issue:44779", "accept": false, - "reason": "Tokenizer loading regression vs generation failure with flash-attention; different layers of the stack." + "reason": "Both are tokenizer regressions, but they concern different model families and outputs." }, { - "left": "issue:44222", - "right": "issue:44484", + "left": "issue:45405", + "right": "issue:45712", "accept": false, - "reason": "Save_pretrained serialization bug vs a question about default shard size; not the same defect." + "reason": "A version pin not yet released and leftover dummy classes failing repo checks are unrelated maintenance issues." }, { - "left": "issue:44297", - "right": "issue:45310", + "left": "issue:42898", + "right": "issue:44448", "accept": false, - "reason": "Tokenizer config mismatch on save vs Qwen3.5 MoE from_pretrained error; different symptom and model area." + "reason": "Tokenization cleanup behavior and Pegasus output differences are not the same underlying bug." }, { - "left": "issue:28282", - "right": "issue:30333", + "left": "issue:44295", + "right": "issue:45656", "accept": false, - "reason": "ImportError for missing PyTorch is unrelated to MLflow not reporting failed training jobs." + "reason": "position_ids buffer access and double optimizer stepping with deepspeed are unrelated training/runtime issues." }, { - "left": "issue:30333", - "right": "issue:35141", + "left": "issue:44933", + "right": "issue:45712", "accept": false, - "reason": "Different issues: MLflow reporting vs embeddings being reinitialized in post_init." + "reason": "Missing import from image_utils and dummy class leakage in dir(transformers) are different export/cleanup problems." }, { - "left": "issue:44263", - "right": "issue:45092", + "left": "issue:44222", + "right": "issue:44297", "accept": false, - "reason": "Different GLM/DSA indexing bug vs InternVL2 meta-init incompatibility." + "reason": "FP8 save_pretrained behavior and tokenizer_class metadata mismatch are different save paths and should not be merged." }, { - "left": "issue:44483", - "right": "issue:45406", + "left": "issue:44297", + "right": "issue:45656", "accept": false, - "reason": "Different serving failures: chat completions request handling vs Gemma4Processor missing _tokenizer." + "reason": "Tokenizer save metadata and duplicated optimizer steps are unrelated." }, { - "left": "issue:44263", - "right": "issue:44360", + "left": "issue:43479", + "right": "issue:43644", "accept": false, - "reason": "Same broad DSA indexer area, but different concrete bugs: torch.split outputs vs missing ReLU." + "reason": "Default multimodal config initialization and non-persistent buffer junk are different initialization bugs." }, { - "left": "issue:44514", + "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Different failures: batched chat template padding behavior vs docstring tooling crashing on future annotations." + "reason": "Feature extractor argument handling and auto-docstring annotation parsing are unrelated." }, { - "left": "issue:44373", - "right": "issue:44485", - "accept": false, - "reason": "A docstring typo about position_ids is unrelated to a GLM-5 RoPE implementation discussion." - }, - { - "left": "issue:44295", + "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "Reading a registered buffer error is unrelated to processor save_pretrained file omission." + "reason": "Model FP8 save_pretrained and processor save_pretrained missing files are not the same failure." }, { - "left": "issue:43723", - "right": "issue:44871", + "left": "issue:42831", + "right": "issue:44623", "accept": false, - "reason": "Both are tokenizer/config issues, but one is loading v5 tokenizers and the other is eos_token_id mismatch between tokenizer and model config." + "reason": "FP8 accuracy regression and missing processor files are unrelated." }, { - "left": "issue:45092", - "right": "issue:45357", + "left": "issue:41628", + "right": "issue:42757", "accept": false, - "reason": "Different Qwen/VL issues: old InternVL2 meta-init compatibility vs Qwen3.5 visual encoder keys saved incorrectly." + "reason": "Both are import errors, but they involve different symbols and different packages." }, { - "left": "issue:44261", - "right": "issue:45092", + "left": "issue:22355", + "right": "issue:28282", "accept": false, - "reason": "Precision/config mismatch in MLA q_a_layernorm is not the same as remote-code checkpoint meta-init incompatibility." + "reason": "Missing transformers.onnx module and missing PyTorch dependency are separate import-time problems." }, { - "left": "issue:43723", - "right": "issue:44991", + "left": "issue:30333", + "right": "issue:36331", "accept": false, - "reason": "Both are tokenizer loading regressions in v5, but they affect different models and likely different tokenizer implementations." + "reason": "MLFlow reporting on failed jobs and Trainer compute_loss signature change are different training-stack issues." } ] }, @@ -11873,58 +11796,75 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:22355", - "issue:28218", + "issue:28282", + "issue:30333", "issue:30990", - "issue:33357", + "issue:34689", + "issue:35141", "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:43408", - "issue:43475", "issue:43479", "issue:43576", "issue:43723", "issue:43756", "issue:43784", "issue:43824", - "issue:43937", - "issue:43976", "issue:44038", "issue:44060", - "issue:44117", + "issue:44222", + "issue:44261", "issue:44263", "issue:44295", "issue:44297", + "issue:44360", "issue:44373", "issue:44442", - "issue:44488", + "issue:44483", + "issue:44484", + "issue:44485", "issue:44514", - "issue:44521", "issue:44568", - "issue:44704", - "issue:44743", + "issue:44623", + "issue:44871", "issue:44913", - "issue:44945", + "issue:44977", + "issue:44991", + "issue:45092", + "issue:45103", "issue:45278", - "issue:45290", "issue:45310", + "issue:45357", + "issue:45406", "issue:45593", - "issue:45600", - "issue:45753" + "issue:45753", + "issue:45834" ], "soft_pairs": [ + "issue:30333|issue:34689", + "issue:43232|issue:45834", + "issue:44222|issue:44484", + "issue:28282|issue:30333", + "issue:44297|issue:45310", + "issue:43723|issue:44977", + "issue:30333|issue:35141", + "issue:44263|issue:45092", + "issue:44483|issue:45406", + "issue:44263|issue:44360", + "issue:44514|issue:45103", + "issue:44373|issue:44485", + "issue:44295|issue:44623", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:44261|issue:45092", + "issue:43723|issue:44991", "issue:30990|issue:38175", "issue:43723|issue:44442", "issue:41628|issue:43824", @@ -11932,245 +11872,228 @@ "issue:39401|issue:44568", "issue:42831|issue:45310", "issue:42886|issue:42994", - "issue:42757|issue:45278", - "issue:43756|issue:44060", "issue:44263|issue:44373", + "issue:42757|issue:45278", "issue:42831|issue:44038", + "issue:43756|issue:44060", "issue:43232|issue:45593", "issue:43576|issue:43784", - "issue:42831|issue:45753", - "issue:42886|issue:43066", - "issue:22355|issue:28218", - "issue:43122|issue:44521", - "issue:42371|issue:44263", - "issue:44117|issue:44704", - "issue:30990|issue:33357", - "issue:43232|issue:44743", - "issue:42907|issue:44945", - "issue:44704|issue:45290", - "issue:43976|issue:44945", - "issue:41628|issue:45278", - "issue:44295|issue:44297", - "issue:43122|issue:44514", - "issue:39401|issue:44488", - "issue:43784|issue:45600", - "issue:42907|issue:43937", - "issue:43408|issue:43475" + "issue:42831|issue:45753" ], - "prepared_review_unit_hash": "05e25974bd00fa569a1b278cc5095df6ca9c12c8057a74430f722bb242403aec", + "prepared_review_unit_hash": "9e6f88b24e4a375b00b23c3da707746c3ea35b71fb8aae4cdaea180c24c63098", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36479, - "estimated_input_tokens": 9120, - "estimated_eval_tokens": 18496 + "serialized_chars": 36700, + "estimated_input_tokens": 9175, + "estimated_eval_tokens": 18606 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is highly heterogeneous: most items are unrelated transformer bugs spanning tokenization, loading/imports, generation, config, and quantization. I did not find any soft pair that looks like the same underlying defect, so all soft edges are rejected.", - "confidence": 0.41, - "canonical_issue_reason": "If one issue must serve as the cluster representative, issue:45278 is the broadest umbrella for the import-regression theme after upgrading to v5. That said, this cluster does not appear to contain true duplicates overall.", + "summary": "This cluster is mostly noisy and heterogeneous. Several items are vaguely about Transformers v5 import/loading regressions, but none of the soft pairs look like the same concrete bug or fix.", + "confidence": 0.81, + "canonical_issue_reason": "issue #45278 is the broadest umbrella in the set: it summarizes multiple import failures after upgrading to v5, which best matches the cluster\u2019s loose theme better than the narrower tokenizer/model-specific reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best single issue to anchor triage because it is broad, recent, and open; it captures the most general regression signal in the set, even though many other items are distinct bugs.", + "best_issue_reason": "issue #45278 is the best single issue to anchor the cluster because it is broad, current, and captures the repeated import-regression pattern without overfitting to one model or API.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:30990", - "right": "issue:38175", + "left": "issue:30333", + "right": "issue:34689", "accept": false, - "reason": "Different problems: loading hang vs zero-probability output on a specific model." + "reason": "Different problems: MLflow job-status reporting vs a specific model-loading regression." }, { - "left": "issue:43723", - "right": "issue:44442", + "left": "issue:43232", + "right": "issue:45834", "accept": false, - "reason": "Both involve tokenizer loading, but the affected tokenizers and failure modes are different." + "reason": "Generation bookkeeping after sync_gpus is unrelated to Kosmos2.5 OCR position indexing." }, { - "left": "issue:41628", - "right": "issue:43824", + "left": "issue:44222", + "right": "issue:44484", "accept": false, - "reason": "Different missing imports for different symbols; not the same code-path bug." + "reason": "FP8 save_pretrained failure is a concrete serialization bug; max_shard_size question is a separate API/behavior issue." }, { - "left": "issue:43479", - "right": "issue:44913", + "left": "issue:28282", + "right": "issue:30333", "accept": false, - "reason": "Both are config defaults/reload issues, but they concern different model families and fields." + "reason": "ImportError for missing PyTorch and MLflow reporting on training failure are unrelated." }, { - "left": "issue:39401", - "right": "issue:44568", + "left": "issue:44297", + "right": "issue:45310", "accept": false, - "reason": "Both are tokenizer behavior bugs, but one is offset mapping and the other is special-token insertion." + "reason": "Tokenizer_class metadata mismatch in save_pretrained is not the same as Qwen3.5 MoE from_pretrained loading failure." }, { - "left": "issue:42831", - "right": "issue:45310", + "left": "issue:43723", + "right": "issue:44977", "accept": false, - "reason": "Unrelated: FineGrainedFP8 accuracy vs Qwen3.5-MoE from_pretrained failure." + "reason": "Both involve loading, but one is tokenizer loading in v5 and the other is Qwen3.5 flash-attention generation behavior." }, { - "left": "issue:42886", - "right": "issue:42994", + "left": "issue:30333", + "right": "issue:35141", "accept": false, - "reason": "Offline tokenizer cache loading is unrelated to quantized model saving." + "reason": "Training-job reporting and embedding reinitialization in post_init are unrelated bugs." }, { - "left": "issue:42757", - "right": "issue:45278", + "left": "issue:44263", + "right": "issue:45092", "accept": false, - "reason": "The latter is a broad import-regression report, but the former is a specific missing hub symbol; not the same defect." + "reason": "torch.split/indexer logic and remote-code meta-initialization compatibility are different code paths." }, { - "left": "issue:43756", - "right": "issue:44060", + "left": "issue:44483", + "right": "issue:45406", "accept": false, - "reason": "Different model-specific architecture issues with no shared failing code path." + "reason": "Chat-completions request handling and Gemma4Processor missing _tokenizer are separate serving failures." }, { "left": "issue:44263", - "right": "issue:44373", + "right": "issue:44360", "accept": false, - "reason": "A runtime tensor split issue is not the same as a docstring correction." + "reason": "Both mention DSA/indexer internals, but one is a torch.split issue and the other is a missing ReLU; not the same bug." }, { - "left": "issue:42831", - "right": "issue:44038", + "left": "issue:44514", + "right": "issue:45103", "accept": false, - "reason": "Different model/runtime bugs; no concrete overlap." + "reason": "Qwen2_5_VL batched chat-template crash is unrelated to the auto_docstring annotations crash." }, { - "left": "issue:43232", - "right": "issue:45593", + "left": "issue:44373", + "right": "issue:44485", "accept": false, - "reason": "Generation-state bug vs D-FINE training-loss behavior; unrelated." + "reason": "Wrong docstring for position_ids is documentation-only; GLM-5 RoPE is an implementation issue." }, { - "left": "issue:43576", - "right": "issue:43784", + "left": "issue:44295", + "right": "issue:44623", "accept": false, - "reason": "CLI/env-command breakage is unrelated to a missing nn import in sentence-transformers integration." + "reason": "Buffer registration/readback error is unrelated to processor.save_pretrained missing files." }, { - "left": "issue:42831", - "right": "issue:45753", + "left": "issue:43723", + "right": "issue:44871", "accept": false, - "reason": "Different model issues with no shared concrete code path." + "reason": "Tokenizer loading regression and eos_token_id config inconsistency are different failures." }, { - "left": "issue:42886", - "right": "issue:43066", + "left": "issue:45092", + "right": "issue:45357", "accept": false, - "reason": "Offline cache loading failure is not the same as a wrong decoder type mapping." + "reason": "Meta-initialization incompatibility for old checkpoints is not the same as incorrect visual encoder keys on save." }, { - "left": "issue:22355", - "right": "issue:28218", + "left": "issue:44261", + "right": "issue:45092", "accept": false, - "reason": "ONNX import error and tokenizer spacing bug are unrelated." + "reason": "MLA rms_norm_eps precision issue is unrelated to InternVL2 meta-init incompatibility." }, { - "left": "issue:43122", - "right": "issue:44521", + "left": "issue:43723", + "right": "issue:44991", "accept": false, - "reason": "Tokenization drift and multimodal assistant-mask failure are different behaviors." + "reason": "Both are tokenizer-load complaints, but they concern different models and likely different failure modes." }, { - "left": "issue:42371", - "right": "issue:44263", + "left": "issue:30990", + "right": "issue:38175", "accept": false, - "reason": "TF32 settings warning has nothing to do with torch.split indexing." + "reason": "Sentence-Transformers loading hangs and SigLIP2 zero probabilities are unrelated." }, { - "left": "issue:44117", - "right": "issue:44704", + "left": "issue:43723", + "right": "issue:44442", "accept": false, - "reason": "Tokenizer-mapping None handling and AutoProcessor cached_file kwargs are different loading bugs." + "reason": "Generic AutoTokenizer load failure and FastSpeech2ConformerTokenizer load failure are not clearly the same underlying bug." }, { - "left": "issue:30990", - "right": "issue:33357", + "left": "issue:41628", + "right": "issue:43824", "accept": false, - "reason": "Different symptoms and model/runtime contexts; not duplicates." + "reason": "Missing AutoImageProcessor and missing Qwen2_5_VLForConditionalGeneration are different import symbols, not one duplicate." }, { - "left": "issue:43232", - "right": "issue:44743", + "left": "issue:43479", + "right": "issue:44913", "accept": false, - "reason": "Both are generation-related, but they affect different mechanisms and code paths." + "reason": "Phi4Multimodal config initialization and GPTNeoX rotary_pct reload behavior are unrelated config bugs." }, { - "left": "issue:42907", - "right": "issue:44945", + "left": "issue:39401", + "right": "issue:44568", "accept": false, - "reason": "Quantized model save failure is unrelated to pipeline-parallel generation correctness." + "reason": "Offset_mapping is a tokenizer alignment bug; missing BOS/EOS on add_special_tokens is a different tokenizer behavior." }, { - "left": "issue:44704", - "right": "issue:45290", + "left": "issue:42831", + "right": "issue:45310", "accept": false, - "reason": "Both mention chat/template-style APIs, but one is cached-file argument forwarding and the other is assistant-message crash handling." + "reason": "FineGrainedFP8 accuracy drift and Qwen3.5 MoE from_pretrained failure are unrelated." }, { - "left": "issue:43976", - "right": "issue:44945", + "left": "issue:42886", + "right": "issue:42994", "accept": false, - "reason": "Python-version compatibility issue vs incorrect LLM output under pipeline parallelism." + "reason": "Offline cache tokenizer loading and quantized model saving are separate subsystems." }, { - "left": "issue:41628", - "right": "issue:45278", + "left": "issue:44263", + "right": "issue:44373", "accept": false, - "reason": "The broad import-regression theme is different from the specific AutoImageProcessor import failure." + "reason": "DSA indexer torch.split behavior and a wrong docstring are not the same issue." }, { - "left": "issue:44295", - "right": "issue:44297", + "left": "issue:42757", + "right": "issue:45278", "accept": false, - "reason": "Buffer access for position_ids and tokenizer class metadata are unrelated." + "reason": "A missing huggingface_hub symbol and broad v5 import errors overlap only at a very high level, not the same concrete bug." }, { - "left": "issue:43122", - "right": "issue:44514", + "left": "issue:42831", + "right": "issue:44038", "accept": false, - "reason": "Different tokenizer/chat-template failures with different triggers." + "reason": "FineGrainedFP8 accuracy and Qwen3-VL-Moe bug reports are unrelated." }, { - "left": "issue:39401", - "right": "issue:44488", + "left": "issue:43756", + "right": "issue:44060", "accept": false, - "reason": "Offset mapping regression and loading a specific model are not the same bug." + "reason": "Smollm3 RoPE-layer loss and Qwen3-Next tied-weight warning concern different model implementations." }, { - "left": "issue:43784", - "right": "issue:45600", + "left": "issue:43232", + "right": "issue:45593", "accept": false, - "reason": "Missing nn import in integration code is unrelated to stale auto_mappings references." + "reason": "Generation kwarg update logic is unrelated to D-FINE auxiliary-loss handling." }, { - "left": "issue:42907", - "right": "issue:43937", + "left": "issue:43576", + "right": "issue:43784", "accept": false, - "reason": "Quantized save failure is unrelated to invalid GenerationConfig." + "reason": "Broken transformers env command and sentence-transformers import NameError are separate regressions." }, { - "left": "issue:43408", - "right": "issue:43475", + "left": "issue:42831", + "right": "issue:45753", "accept": false, - "reason": "Warning about mismatched model type is not the same as a missing output attribute in SAM 3 Video." + "reason": "FineGrainedFP8 accuracy and Qwen3_5 infinite-loop behavior are different bugs." } ] }, @@ -12192,289 +12115,323 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:22355", + "issue:28218", "issue:29127", "issue:30990", + "issue:33357", "issue:36296", - "issue:38617", "issue:39401", - "issue:42222", + "issue:41628", "issue:42371", - "issue:42673", "issue:42757", + "issue:42886", "issue:42907", "issue:43066", "issue:43116", "issue:43122", - "issue:43278", - "issue:43441", + "issue:43232", + "issue:43408", "issue:43452", - "issue:43493", + "issue:43475", "issue:43784", "issue:43824", - "issue:43874", "issue:43937", - "issue:43992", + "issue:43976", "issue:44038", + "issue:44117", "issue:44222", "issue:44261", + "issue:44263", "issue:44295", "issue:44297", "issue:44351", "issue:44360", "issue:44373", "issue:44485", + "issue:44488", + "issue:44514", "issue:44521", "issue:44625", "issue:44704", + "issue:44743", "issue:44779", "issue:44829", "issue:44945", "issue:44964", - "issue:44977", - "issue:45072", "issue:45200", - "issue:45216", "issue:45278", - "issue:45446", - "issue:45478", - "issue:45753" + "issue:45290", + "issue:45600" ], "soft_pairs": [ + "issue:42886|issue:43066", + "issue:22355|issue:28218", + "issue:43122|issue:44521", + "issue:42371|issue:44263", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:43232|issue:44743", + "issue:42907|issue:44945", + "issue:44704|issue:45290", + "issue:41628|issue:45278", + "issue:44295|issue:44297", + "issue:43976|issue:44945", + "issue:43122|issue:44514", + "issue:39401|issue:44488", + "issue:43784|issue:45600", + "issue:42907|issue:43937", + "issue:43408|issue:43475", "issue:44360|issue:44485", "issue:44261|issue:44373", - "issue:39401|issue:44521", "issue:44625|issue:44829", + "issue:39401|issue:44521", "issue:43116|issue:45200", "issue:29127|issue:30990", - "issue:43122|issue:44779", "issue:42907|issue:44964", + "issue:43122|issue:44779", "issue:44038|issue:44297", "issue:44038|issue:44295", "issue:42907|issue:43452", "issue:36296|issue:43116", "issue:43824|issue:44351", "issue:44038|issue:44222", - "issue:42757|issue:44351", - "issue:45216|issue:45478", - "issue:43278|issue:44945", - "issue:43066|issue:44779", - "issue:43493|issue:45753", - "issue:43122|issue:44977", - "issue:42907|issue:44222", - "issue:43992|issue:44704", - "issue:43784|issue:45446", - "issue:38617|issue:45278", - "issue:42673|issue:45072", - "issue:43937|issue:44485", - "issue:22355|issue:29127", - "issue:42222|issue:43441", - "issue:42371|issue:43874" + "issue:42757|issue:44351" ], - "prepared_review_unit_hash": "608c50a01c793d3cbc27c31c59ab3c60a797b75a69f775d48606e0f1bfe69472", + "prepared_review_unit_hash": "2513658dccefc7cb679dc3fed5776ce5caae9301bb0a344e9d94f3e2ea0abc3b", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, - "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35378, - "estimated_input_tokens": 8845, - "estimated_eval_tokens": 17946 + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36833, + "estimated_input_tokens": 9209, + "estimated_eval_tokens": 18674 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous set of Transformers bug reports, mostly around import regressions, tokenizer/model behavior, and model-family-specific failures. The soft-similar pairs share broad themes but do not look like the same underlying bug or change, so I would not merge any of them as duplicates.", - "confidence": 0.81, - "canonical_issue_reason": "issue:45278 is the broadest umbrella in the set because it captures the general post-upgrade import-regression theme and can reasonably subsume several import-related reports. That said, the cluster is still very mixed, so it is only a partial canonical fit.", + "summary": "This set is a loose collection of mostly unrelated Transformers issues; none of the soft pairs look like the same underlying bug/change, so I reject all soft edges. The best representative issue is the broad import-regression report (#45278), but only as a loose umbrella example rather than a true duplicate canonical.", + "confidence": 0.18, + "canonical_issue_reason": "#45278 is the broadest, most umbrella-like report in the set: it describes many import errors after an upgrade and can loosely represent several import-breakage themes present here.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best representative because it is the most general, high-level issue here and aligns with the most recurring subtheme (import errors after upgrading to v5.5.0).", + "best_issue_reason": "#45278 is the strongest single issue representative because it is a general regression report, open, and closer to the recurring import-related failures than the more one-off model/tokenizer bugs.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44360", - "right": "issue:44485", + "left": "issue:42886", + "right": "issue:43066", "accept": false, - "reason": "Both are model/math bugs, but they affect different components and symptoms; not the same concrete defect." + "reason": "Offline-cache tokenizer loading and a tokenizer decoder-type mismatch are different failure modes in different code paths." }, { - "left": "issue:44261", - "right": "issue:44373", + "left": "issue:22355", + "right": "issue:28218", "accept": false, - "reason": "One is a precision/config bug in MLA q_a_layernorm, the other is a docstring issue for position_ids." + "reason": "ONNX import failure and extra-space tokenization behavior are unrelated bugs." }, { - "left": "issue:39401", + "left": "issue:43122", "right": "issue:44521", "accept": false, - "reason": "Both involve tokenization-related outputs, but one is offset_mapping and the other is multimodal assistant masks; different code paths." + "reason": "Version-to-version tokenization drift is not the same as multimodal assistant_mask generation failing." }, { - "left": "issue:44625", - "right": "issue:44829", + "left": "issue:42371", + "right": "issue:44263", "accept": false, - "reason": "Qwen3.5 num_labels propagation and flash_attention_3 degenerate training are unrelated failures." + "reason": "TF32 configuration guidance and a torch.split return-value issue are unrelated." }, { - "left": "issue:43116", - "right": "issue:45200", + "left": "issue:44117", + "right": "issue:44704", "accept": false, - "reason": "Different example/model contexts and different failure modes; not the same underlying bug." + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor kwargs forwarding are different from_pretrained plumbing bugs." }, { - "left": "issue:29127", - "right": "issue:30990", + "left": "issue:30990", + "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 error messaging and Sentence Transformers loading hang are unrelated." + "reason": "A load hang in sentence-transformers and a MacOS bus error on CLIP are not the same bug." }, { - "left": "issue:43122", - "right": "issue:44779", + "left": "issue:43232", + "right": "issue:44743", "accept": false, - "reason": "Both are tokenization regressions, but for different model families and symptoms; too broad to be one bug." + "reason": "Generation kwargs updating and recurrent-state reset in Qwen3.5 are different code paths." }, { "left": "issue:42907", - "right": "issue:44964", + "right": "issue:44945", "accept": false, - "reason": "Saving a dequantized model and failing to load Phi-4 multimodal are separate code paths." + "reason": "Saving dequantized models and wrong outputs under pipeline parallelism are unrelated." }, { - "left": "issue:44038", + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor cached_file kwargs and chat_template crashes on tool-call assistant messages are distinct issues." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "A single missing import and a broad collection of import errors after upgrade are related only at a very high level, not the same concrete bug." + }, + { + "left": "issue:44295", "right": "issue:44297", "accept": false, - "reason": "Qwen3-VL-Moe compatibility and tokenizer save_pretrained class metadata are different issues." + "reason": "Reading a position_ids buffer and tokenizer_class metadata mismatching on save_pretrained are different serialization/state problems." }, { - "left": "issue:44038", - "right": "issue:44295", + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version incompatibility and pipeline-parallel output corruption are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer behavior differences across versions and batched chat_template crashes are different bugs." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping errors and a model load failure for cjvt/sleng-bert are unrelated." + }, + { + "left": "issue:43784", + "right": "issue:45600", "accept": false, - "reason": "One is a Qwen3-VL-Moe bug, the other is a position_ids buffer access problem." + "reason": "A NameError importing sentence-transformers and stale auto_mappings references are different import breakages." }, { "left": "issue:42907", - "right": "issue:43452", + "right": "issue:43937", "accept": false, - "reason": "Dequantized model saving and gguf_file loading are not the same defect." + "reason": "Model save failures and invalid GenerationConfig reports do not describe the same problem." }, { - "left": "issue:36296", - "right": "issue:43116", + "left": "issue:43408", + "right": "issue:43475", "accept": false, - "reason": "Tensor-parallel training and example-script multi-label classification are unrelated." + "reason": "A model-type warning and a missing fpn_position_embeddings attribute are different SAM3 issues." }, { - "left": "issue:43824", - "right": "issue:44351", + "left": "issue:44360", + "right": "issue:44485", "accept": false, - "reason": "Both are import errors, but for different missing symbols and different dependency layers." + "reason": "Missing ReLU in the DSA indexer and GLM-5 RoPE implementation are unrelated model-specific bugs." }, { - "left": "issue:44038", - "right": "issue:44222", + "left": "issue:44261", + "right": "issue:44373", "accept": false, - "reason": "Qwen3-VL-Moe and FP8 save_pretrained moe problems are model-specific but not the same bug." + "reason": "A precision bug in MLA q_a_layernorm and a wrong docstring for position_ids are not the same change." }, { - "left": "issue:42757", - "right": "issue:44351", + "left": "issue:44625", + "right": "issue:44829", "accept": false, - "reason": "These are import failures from different packages/symbols; no shared underlying defect is evident." + "reason": "num_labels propagation and flash_attention_3 training degeneration are different failures." }, { - "left": "issue:45216", - "right": "issue:45478", + "left": "issue:39401", + "right": "issue:44521", "accept": false, - "reason": "Both involve Qwen3.5 regressions, but one is save_pretrained checkpoint output and the other is from_pretrained loading behavior." + "reason": "Qwen3 offset_mapping and multimodal assistant_masks are different tokenizer/processor bugs." }, { - "left": "issue:43278", - "right": "issue:44945", + "left": "issue:43116", + "right": "issue:45200", "accept": false, - "reason": "A dtype regression in evaluate is unrelated to incorrect outputs under pipeline parallelism." + "reason": "Empty multi-label classification outputs and mm_token_type_ids defaulting are unrelated example/model issues." }, { - "left": "issue:43066", - "right": "issue:44779", + "left": "issue:29127", + "right": "issue:30990", "accept": false, - "reason": "Both mention tokenizer behavior across v5, but they concern different tokenizer implementations and outputs." + "reason": "Error-message clarity in LayoutLMv3 and a loading hang in Sentence Transformers are unrelated." }, { - "left": "issue:43493", - "right": "issue:45753", + "left": "issue:42907", + "right": "issue:44964", "accept": false, - "reason": "SigLIP2 implementation discrepancy and Qwen3_5 infinite-loop generation are unrelated model bugs." + "reason": "Dequantized-save failures and inability to load a multimodal Phi-4 model are different bugs." }, { "left": "issue:43122", - "right": "issue:44977", + "right": "issue:44779", "accept": false, - "reason": "Both are Qwen/tokenizer-related regressions, but one is general tokenization drift and the other is flash-attention generation failure." + "reason": "General tokenization drift across versions and DeepSeek tokenizer regressions are not the same underlying issue." }, { - "left": "issue:42907", - "right": "issue:44222", + "left": "issue:44038", + "right": "issue:44297", "accept": false, - "reason": "Model saving after dequantization and FP8 save_pretrained are different serialization problems." + "reason": "A Qwen3-VL-Moe bug and tokenizer_class metadata mismatch on save_pretrained are unrelated." }, { - "left": "issue:43992", - "right": "issue:44704", + "left": "issue:44038", + "right": "issue:44222", "accept": false, - "reason": "Missing embed_tokens.weight in a specific encoder and AutoProcessor kwarg forwarding are separate loading issues." + "reason": "These both mention moe, but one is a model behavior bug and the other is FP8 save_pretrained handling; not the same concrete code path." }, { - "left": "issue:43784", - "right": "issue:45446", + "left": "issue:42757", + "right": "issue:44351", "accept": false, - "reason": "Sentence-transformers import NameError and flex_attention version-check bug are unrelated." + "reason": "Missing is_offline_mode and missing HybridCache are separate import errors with different fixes." }, { - "left": "issue:38617", - "right": "issue:45278", + "left": "issue:42907", + "right": "issue:43452", "accept": false, - "reason": "Both are import-related, but they refer to different missing names and different release contexts; not the same bug." + "reason": "Saving dequantized models and gguf_file handling in from_pretrained are unrelated." }, { - "left": "issue:42673", - "right": "issue:45072", + "left": "issue:36296", + "right": "issue:43116", "accept": false, - "reason": "VRAM leak in Qwen3ForCausalLM and dtype mismatch CI failure are distinct problems." + "reason": "A tensor-parallel training bug and a multi-label example script bug are different layers of the stack." }, { - "left": "issue:43937", - "right": "issue:44485", + "left": "issue:43824", + "right": "issue:44351", "accept": false, - "reason": "GenerationConfig validation for GLM-5 and GLM-5 RoPE implementation are different code-path issues." + "reason": "Missing Qwen2_5_VLForConditionalGeneration and missing HybridCache imports are different symbols and different regressions." }, { - "left": "issue:22355", - "right": "issue:29127", + "left": "issue:44038", + "right": "issue:44222", "accept": false, - "reason": "A missing transformers.onnx module and a LayoutLMv3 error-message concern are unrelated." + "reason": "Qwen3-VL-Moe loading/behavior and FP8 save_pretrained in moe are related only by subsystem, not by the same bug." }, { - "left": "issue:42222", - "right": "issue:43441", + "left": "issue:44038", + "right": "issue:44295", "accept": false, - "reason": "VitPose breakage and Ministral-3 FlashAttention failure are different model-specific bugs." + "reason": "Qwen3-VL-Moe behavior and position_ids buffer access are unrelated." }, { - "left": "issue:42371", - "right": "issue:43874", + "left": "issue:42757", + "right": "issue:44351", "accept": false, - "reason": "TF32 API guidance and a missing image-patch method are unrelated." + "reason": "These are separate missing-import reports for different names and should not be merged." } ] }, @@ -12496,57 +12453,71 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ + "issue:22355", + "issue:29127", "issue:33453", "issue:38617", "issue:39401", - "issue:41628", "issue:42222", "issue:42371", "issue:42673", + "issue:42907", "issue:43064", + "issue:43066", "issue:43116", - "issue:43408", - "issue:43421", - "issue:43450", + "issue:43122", + "issue:43278", + "issue:43441", "issue:43493", - "issue:43582", "issue:43673", - "issue:43742", + "issue:43784", "issue:43825", "issue:43827", + "issue:43874", "issue:43906", "issue:43937", "issue:43976", - "issue:43986", + "issue:43992", "issue:44038", "issue:44075", "issue:44117", "issue:44222", - "issue:44261", "issue:44291", - "issue:44410", - "issue:44484", + "issue:44485", + "issue:44704", "issue:44779", - "issue:44829", "issue:44936", + "issue:44945", "issue:44977", "issue:45071", - "issue:45081", + "issue:45072", "issue:45083", "issue:45216", - "issue:45310", - "issue:45341", + "issue:45278", "issue:45405", "issue:45446", "issue:45478", - "issue:45542", - "issue:45561", "issue:45563", - "issue:45588" + "issue:45588", + "issue:45753" ], "soft_pairs": [ + "issue:45216|issue:45478", + "issue:43278|issue:44945", + "issue:43066|issue:44779", + "issue:43493|issue:45753", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43992|issue:44704", + "issue:43784|issue:45446", + "issue:38617|issue:45278", + "issue:42673|issue:45072", + "issue:43937|issue:44485", + "issue:22355|issue:29127", + "issue:42371|issue:43874", + "issue:42222|issue:43441", "issue:43064|issue:43673", "issue:43976|issue:45446", "issue:44075|issue:44936", @@ -12554,231 +12525,231 @@ "issue:43116|issue:43825", "issue:44038|issue:45478", "issue:44222|issue:45478", - "issue:43937|issue:45563", "issue:45083|issue:45446", + "issue:43937|issue:45563", "issue:33453|issue:39401", - "issue:39401|issue:44779", "issue:44117|issue:45588", + "issue:39401|issue:44779", "issue:43827|issue:45446", "issue:43937|issue:44977", "issue:42673|issue:43906", "issue:44291|issue:45071", - "issue:43450|issue:43986", - "issue:45405|issue:45446", - "issue:45341|issue:45561", - "issue:44117|issue:45081", - "issue:38617|issue:41628", - "issue:39401|issue:43421", - "issue:44410|issue:45310", - "issue:44829|issue:45216", - "issue:44484|issue:45310", - "issue:42673|issue:43582", - "issue:42371|issue:44261", - "issue:42222|issue:45542", - "issue:43408|issue:43742" + "issue:45405|issue:45446" ], - "prepared_review_unit_hash": "f58488340764759d5bdc7e995a7af879af81cc62ae7e38dd212df215342addf4", + "prepared_review_unit_hash": "87ab9625cd4691659aaefe0302892544a74aebeb5df6865b4e7f12baadf7dbbe", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 35686, - "estimated_input_tokens": 8922, - "estimated_eval_tokens": 18100 + "soft_pair_count": 31, + "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 proposed soft edges are mostly false positives: they share broad subsystems like tokenizers, Qwen, training, or testing utils, but they describe different failure modes and code paths. No PRs are present. The closest actual duplicate in the set is the pair of Qwen3.5 Moe from_pretrained reports (45310/45478), but that pair is not among the soft edges.", - "confidence": 0.82, - "canonical_issue_reason": "Issue 45310 is the best canonical issue because it is an earlier, clearer report of the Qwen3.5 Moe from_pretrained failure and is effectively duplicated by the later 45478 report with the same title.", + "summary": "This cluster is mostly a loose collection of Transformers v5-era regressions across tokenization, model loading, generation, and import-time breakages. The titles overlap on version upgrades and model families, but the concrete failure modes are different enough that I don\u2019t see true duplicate pairs here.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the broadest and most current umbrella-style report in the set: multiple import errors after upgrading to 5.5.0. It is the best anchor for related upgrade/import regressions, even though the rest of the cluster is not actually one duplicate bug.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45310 is the strongest global representative among these items due to its direct duplicate signal with 45478 and its concrete, user-facing reproduction of the model-loading bug.", + "best_issue_reason": "issue:45278 is the best representative issue because it is open-ended, upgrade-focused, and broad enough to serve as the cluster anchor for nearby version-regression reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen3.5/MoE save/load regressions around 5.4.0, but one is about save_pretrained producing a bad checkpoint and the other is a from_pretrained loading error. Related family, not the same concrete bug." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "BF16/FP32 dtype drift in evaluate is unrelated to incorrect outputs under pipeline parallelism." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both involve tokenizer behavior in v5, but one is a decoder-type mismatch and the other is incorrect DeepSeek tokenization results. Different failure modes." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 implementation mismatch and a Qwen3.5 image-specific infinite loop are distinct model bugs." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both touch saving quantized models, but one is dequantized Ministral/Devstral save failure and the other is FP8 MoE save_pretrained. Not the same code-path problem." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer-version output changes and a flash-attention generation failure for Qwen3.5 are unrelated." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "UMT5 weight-loading and AutoProcessor forwarding kwargs to cached_file are different APIs and bugs." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import NameError and a flex_attention version-check issue are unrelated import-time breakages." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Both are import errors after upgrading, but one is a specific missing symbol and the other is a broad report of many import errors. Not the same underlying bug." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "A VRAM leak in multi-dataloader-thread Qwen3ForCausalLM use is unrelated to dtype mismatches in inference." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "Invalid GenerationConfig for GLM-5 and a GLM-5 RoPE implementation discussion are separate issues." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Missing transformers.onnx module and a LayoutLMv3 error-message clarity issue are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API guidance and a missing get_number_of_image_patches method in GLM46V are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Broken VitPose models and a Ministral-3 flash-attention failure are different model-specific regressions." + }, { "left": "issue:43064", "right": "issue:43673", "accept": false, - "reason": "Different failures: optimizer state corruption during FSDP2+PEFT training vs missing GenerationMixin cache during chunked prefill." + "reason": "Wrong optimizer state handling with FSDP2/PEFT and a missing cache during chunked_prefill are different training vs generation bugs." }, { "left": "issue:43976", "right": "issue:45446", "accept": false, - "reason": "Unrelated compatibility checks: Python version support for Transformers 5.1.0 vs a PyTorch version guard in flex_attention." + "reason": "Python version compatibility and a PyTorch version check for AuxRequest import are not the same defect." }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "SGD arguments not being applied is a different bug from trainer.evaluate() failing after training." + "reason": "Unused SGD arguments and trainer.evaluate failing after train do not share the same code path." }, { "left": "issue:43116", "right": "issue:43493", "accept": false, - "reason": "Example-script multi-label output bug vs SigLIP2 implementation mismatch; different models and code paths." + "reason": "Example-script multi-label classification output and SigLIP2 implementation mismatch are unrelated." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Example classification output bug vs pipeline() error-message/docs mismatch; not the same underlying defect." + "reason": "A classification example returning empty results is unrelated to pipeline() suggesting unsupported translation tasks." }, { "left": "issue:44038", "right": "issue:45478", "accept": false, - "reason": "Both concern Qwen/Moe models, but one is a v5 Qwen3-VL-Moe bug and the other is a Qwen3.5 Moe from_pretrained error." + "reason": "Both mention Qwen3-family MoE models, but one is a broader Qwen3-VL-Moe issue and the other is a Qwen3.5 from_pretrained error. Not the same concrete bug." }, { "left": "issue:44222", "right": "issue:45478", "accept": false, - "reason": "FP8 save_pretrained behavior is a different code path from from_pretrained loading failures." + "reason": "FP8 save_pretrained for MoE and a Qwen3.5 from_pretrained failure are different save vs load problems." }, { - "left": "issue:43937", - "right": "issue:45563", + "left": "issue:45083", + "right": "issue:45446", "accept": false, - "reason": "GenerationConfig validation error vs a stale warning for num_return_sequences; unrelated symptoms." + "reason": "A helper-function bug in qwen3_omni_moe and a version-check import issue are unrelated." }, { - "left": "issue:45083", - "right": "issue:45446", + "left": "issue:43937", + "right": "issue:45563", "accept": false, - "reason": "Audio feature-length helper behavior in qwen3_omni_moe vs a flex_attention import/version check." + "reason": "GLM-5 generation config validation and a stale warning in paged generate() are different generation-layer bugs." }, { "left": "issue:33453", "right": "issue:39401", "accept": false, - "reason": "Both are tokenizer-related, but one is a tokenizer-loading regression and the other is a wrong offset_mapping bug." + "reason": "Tokenizer loading regression and Qwen3 offset_mapping errors are both tokenizer-related but not the same failure." }, { - "left": "issue:39401", - "right": "issue:44779", + "left": "issue:44117", + "right": "issue:45588", "accept": false, - "reason": "Different tokenizer models and failures: offset_mapping correctness vs general incorrect results in Deepseek tokenizer." + "reason": "TOKENIZER_MAPPING_NAMES returning None and a flash_attention AttributeError on s_aux=None are unrelated." }, { - "left": "issue:44117", - "right": "issue:45588", + "left": "issue:39401", + "right": "issue:44779", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES fallback issue vs flash_attention crashing on s_aux=None; different subsystems." + "reason": "Both are tokenizer regressions, but they affect different models and symptoms (offset_mapping vs incorrect outputs)." }, { "left": "issue:43827", "right": "issue:45446", "accept": false, - "reason": "Docs still referencing pipeline() after removals is unrelated to a PyTorch version check bug." + "reason": "Docs still referencing pipeline() and a PyTorch version-check import bug are unrelated." }, { "left": "issue:43937", "right": "issue:44977", "accept": false, - "reason": "GenerationConfig invalidity in GLM-5 is a different failure from Qwen3.5 flash-attention generation problems." + "reason": "GLM-5 invalid generation config and Qwen3.5 flash-attention generation failures are different model-specific problems." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "VRAM leak in multi-dataloader-thread usage does not match an isolated reproduction of another issue." + "reason": "A VRAM leak in dataloader-threaded generation and an isolated reproduction of another issue are not the same bug." }, { "left": "issue:44291", "right": "issue:45071", "accept": false, - "reason": "init_empty_weights unexpected argument error and PretrainedConfig type-checking breakage are separate API compatibility issues." - }, - { - "left": "issue:43450", - "right": "issue:43986", - "accept": false, - "reason": "Incorrect batched video processor shapes are different from AutoProcessor crashing without torchvision installed." + "reason": "init_empty_weights argument handling and PretrainedConfig type-checking are separate v5 compatibility issues." }, { "left": "issue:45405", "right": "issue:45446", "accept": false, - "reason": "Released-version dependency bump problem vs flex_attention import/version guard; not the same bug." - }, - { - "left": "issue:45341", - "right": "issue:45561", - "accept": false, - "reason": "A minor testing_utils bug is not the same as the xdist race on captured_info.txt." - }, - { - "left": "issue:44117", - "right": "issue:45081", - "accept": false, - "reason": "Tokenizer mapping returning None is unrelated to a Mistral regex patch crash." - }, - { - "left": "issue:38617", - "right": "issue:41628", - "accept": false, - "reason": "Two different missing symbol import errors in different modules; not the same underlying export regression." - }, - { - "left": "issue:39401", - "right": "issue:43421", - "accept": false, - "reason": "Wrong offset mappings and stale post-processor updates are distinct tokenizer-runtime issues." - }, - { - "left": "issue:44410", - "right": "issue:45310", - "accept": false, - "reason": "Missing projections in qwen3next is a model-architecture bug, not a from_pretrained loading error for Qwen3.5 Moe." - }, - { - "left": "issue:44829", - "right": "issue:45216", - "accept": false, - "reason": "Degenerate training under flash_attention_3 is unrelated to an incorrect checkpoint saved by save_pretrained." - }, - { - "left": "issue:44484", - "right": "issue:45310", - "accept": false, - "reason": "Sharding-size question is unrelated to the Qwen3.5 Moe loading failure." - }, - { - "left": "issue:42673", - "right": "issue:43582", - "accept": false, - "reason": "VRAM leakage and Apple Silicon TypeError in caching_allocator_warmup are unrelated failures." - }, - { - "left": "issue:42371", - "right": "issue:44261", - "accept": false, - "reason": "TF32 settings guidance and MLA q_a_layernorm precision/config handling are different issues." - }, - { - "left": "issue:42222", - "right": "issue:45542", - "accept": false, - "reason": "VitPose model breakage and a TensorBoard-without-TensorFlow backend error are unrelated." - }, - { - "left": "issue:43408", - "right": "issue:43742", - "accept": false, - "reason": "sam3_video/sam3_tracker warning mismatch is not the same as a MobileLLM-125M key-loading error." + "reason": "An unreleased PEFT minimum version bump and a flex_attention import version check are unrelated release/compatibility issues." } ] }, @@ -12800,9 +12771,10 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:38617", + "issue:39401", "issue:41628", "issue:42175", "issue:42222", @@ -12814,24 +12786,21 @@ "issue:43066", "issue:43097", "issue:43122", - "issue:43335", "issue:43408", - "issue:43441", - "issue:43452", + "issue:43421", + "issue:43450", "issue:43577", + "issue:43582", "issue:43673", + "issue:43742", "issue:43874", - "issue:43931", "issue:43937", - "issue:43976", "issue:43986", - "issue:44038", "issue:44075", "issue:44117", "issue:44220", "issue:44261", "issue:44263", - "issue:44368", "issue:44410", "issue:44483", "issue:44484", @@ -12840,26 +12809,40 @@ "issue:44496", "issue:44829", "issue:44933", - "issue:44987", - "issue:45003", "issue:45071", + "issue:45081", + "issue:45216", "issue:45278", + "issue:45310", "issue:45341", "issue:45459", "issue:45464", "issue:45478", "issue:45542", + "issue:45561", "issue:45656" ], "soft_pairs": [ - "issue:44933|issue:45278", + "issue:43450|issue:43986", + "issue:45341|issue:45561", + "issue:44117|issue:45081", + "issue:38617|issue:41628", + "issue:39401|issue:43421", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:42673|issue:43582", + "issue:44484|issue:45310", + "issue:42371|issue:44261", + "issue:43408|issue:43742", "issue:42617|issue:45341", - "issue:42175|issue:42222", - "issue:43937|issue:44496", + "issue:44933|issue:45278", + "issue:42222|issue:45542", "issue:42673|issue:43577", + "issue:43937|issue:44496", + "issue:42175|issue:42222", "issue:38617|issue:44220", - "issue:44483|issue:45464", "issue:44075|issue:45656", + "issue:44483|issue:45464", "issue:42371|issue:42831", "issue:43066|issue:43122", "issue:43012|issue:43577", @@ -12869,249 +12852,230 @@ "issue:43874|issue:44261", "issue:43097|issue:44493", "issue:44263|issue:44485", - "issue:42222|issue:45459", "issue:43012|issue:43408", - "issue:41628|issue:45071", - "issue:43441|issue:44829", - "issue:45071|issue:45542", - "issue:43931|issue:44410", - "issue:45003|issue:45341", - "issue:43931|issue:44038", - "issue:44117|issue:44987", - "issue:43097|issue:43452", - "issue:43335|issue:45071", - "issue:43986|issue:45341", - "issue:43986|issue:44484", - "issue:43408|issue:44368", - "issue:43874|issue:44263", - "issue:43976|issue:45071" + "issue:42222|issue:45459", + "issue:41628|issue:45071" ], - "prepared_review_unit_hash": "49c48daa1665f645cea2639d0730456ffff424634faf0fbbe359f5c7f3c2240a", + "prepared_review_unit_hash": "8056a92d962830c99ba69fa53c8d9262014d3ce1f9c4ae5eec76b32c3262c919", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37285, - "estimated_input_tokens": 9322, - "estimated_eval_tokens": 18900 + "soft_pair_count": 32, + "serialized_chars": 36975, + "estimated_input_tokens": 9244, + "estimated_eval_tokens": 18744 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated issue reports; I did not find any soft pair that clearly describes the same concrete bug/change strongly enough to merge. The closest is the broad import-regression report, but it is still too generic to treat as a duplicate of a specific import error. No PRs were present.", - "confidence": 0.82, - "canonical_issue_reason": "issue:45278 is the broadest umbrella report in the set: it describes multiple import failures after a version bump, making it the best anchor for an import-regression cluster if one is formed.", + "summary": "The set is mostly heterogeneous: import/API regressions, tokenizer issues, model-loading bugs, optimizer problems, and backend/config complaints. I did not find any soft-edge pair that is clearly the same underlying bug/change. The only obvious duplicate-looking item in the list is the repeated Qwen3.5 MoE from_pretrained report (issue:45310 and issue:45478), but that pair was not part of the supplied soft edges.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45310 is the cleanest concrete bug report to anchor the only near-exact duplicate-looking thread in this set; issue:45478 repeats the same Qwen3.5 MoE from_pretrained error title and reads like a later duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 has the widest impact and clearest regression framing among the issues shown, so it is the best single issue to keep as the representative report.", + "best_issue_reason": "issue:45310 is the best issue anchor because it is specific, reproducible, and has a later same-title twin (issue:45478), making it the most plausible canonical issue among the listed items.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44933", - "right": "issue:45278", + "left": "issue:43450", + "right": "issue:43986", "accept": false, - "reason": "Both are import-related, but 44933 is one specific missing import while 45278 is a broad post-upgrade import-regression report; not the same concrete bug." + "reason": "Different failures: incorrect batched video processor shape vs AutoProcessor crashing without torchvision." }, { - "left": "issue:42617", - "right": "issue:45341", + "left": "issue:45341", + "right": "issue:45561", "accept": false, - "reason": "Unrelated: failing to run a script vs a small testing_utils bug." + "reason": "A general testing_utils bug is not the same as a pytest-xdist race on captured_info.txt." }, { - "left": "issue:42175", - "right": "issue:42222", + "left": "issue:44117", + "right": "issue:45081", "accept": false, - "reason": "Packaging/backend installation issue vs a broken VitPose model path; different symptoms and fixes." + "reason": "Tokenizer mapping None handling and Mistral regex patching are separate tokenizer code paths." }, { - "left": "issue:43937", - "right": "issue:44496", + "left": "issue:38617", + "right": "issue:41628", "accept": false, - "reason": "Different failures: invalid GenerationConfig vs unrecognized model/config missing model_type." + "reason": "Two unrelated import errors: missing layer_type_validation vs missing AutoImageProcessor." }, { - "left": "issue:42673", - "right": "issue:43577", + "left": "issue:39401", + "right": "issue:43421", "accept": false, - "reason": "VRAM leak in threaded dataloader use is unrelated to dtype staying float32 when loading Blip2." + "reason": "Offset-mapping corruption and runtime special-token/post-processor sync are different tokenizer bugs." }, { - "left": "issue:38617", - "right": "issue:44220", + "left": "issue:44410", + "right": "issue:45310", "accept": false, - "reason": "Separate import error vs audio feature extraction bug." + "reason": "qwen3next missing projections is a model-architecture bug, not the Qwen3.5 MoE from_pretrained error." }, { - "left": "issue:44483", - "right": "issue:45464", + "left": "issue:44829", + "right": "issue:45216", "accept": false, - "reason": "Both touch chat/completions, but one is a general request rejection and the other is a streaming-specific inference failure." + "reason": "FlashAttention-3 training degeneration is unrelated to Qwen3.5 save_pretrained checkpoint regression." }, { - "left": "issue:44075", - "right": "issue:45656", + "left": "issue:42673", + "right": "issue:43582", "accept": false, - "reason": "Optimizer argument handling and double step calls under deepspeed are different code paths and likely different bugs." + "reason": "VRAM leak in Qwen3ForCausalLM threads and an Apple Silicon TypeError are different issues." }, { - "left": "issue:42371", - "right": "issue:42831", + "left": "issue:44484", + "right": "issue:45310", "accept": false, - "reason": "TF32 behavior guidance is unrelated to FineGrainedFP8 accuracy regression." + "reason": "max_shard_size behavior in save_pretrained is unrelated to the Qwen3.5 MoE from_pretrained error." }, { - "left": "issue:43066", - "right": "issue:43122", + "left": "issue:42371", + "right": "issue:44261", "accept": false, - "reason": "Tokenizer decoder-type issue and changed tokenization output are related to tokenization, but not the same concrete bug." + "reason": "TF32 API guidance and MLA rms_norm_eps precision mismatch are not the same bug." }, { - "left": "issue:43012", - "right": "issue:43577", + "left": "issue:43408", + "right": "issue:43742", "accept": false, - "reason": "A precision warning during bf16 compilation is not the same as Blip2 parameters remaining float32 after loading." + "reason": "sam3_tracker model-type warning and MobileLLM key error are separate loading problems." }, { - "left": "issue:43673", + "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "Generation cache/chunked_prefill regression is unrelated to the testing_utils bug." + "reason": "3d_parallel.py runtime failure is unrelated to the testing_utils bug." }, { - "left": "issue:44484", - "right": "issue:45478", + "left": "issue:44933", + "right": "issue:45278", "accept": false, - "reason": "A question about save_pretrained shard size is unrelated to a Qwen3.5-Moe from_pretrained load failure." + "reason": "A specific missing import from image_utils is not the same as a broad import-error regression report." }, { - "left": "issue:44410", - "right": "issue:45478", + "left": "issue:42222", + "right": "issue:45542", "accept": false, - "reason": "Missing layer projections in qwen3next is a different model bug than the Qwen3.5-Moe loading error." + "reason": "Broken vitpose models and tf-backend detection without TensorFlow are unrelated backend/model issues." }, { - "left": "issue:43874", - "right": "issue:44261", + "left": "issue:42673", + "right": "issue:43577", "accept": false, - "reason": "Missing image patch helper and missing rms_norm_eps are separate multimodal bugs." + "reason": "A dataloader-thread VRAM leak is not the same as dtype propagation staying float32 in Blip2." }, { - "left": "issue:43097", - "right": "issue:44493", + "left": "issue:43937", + "right": "issue:44496", "accept": false, - "reason": "Removed config field warning and unexpected position-id keys are not the same underlying change." + "reason": "GenerationConfig validation failure and missing model_type in config.json are distinct loading/config problems." }, { - "left": "issue:44263", - "right": "issue:44485", + "left": "issue:42175", + "right": "issue:42222", "accept": false, - "reason": "torch.split return handling in GlmMoeDsaIndexer is distinct from the GLM-5 RoPE implementation issue." + "reason": "TensorFlow not included in the torch extra and broken vitpose models are not the same underlying bug." }, { - "left": "issue:42222", - "right": "issue:45459", + "left": "issue:38617", + "right": "issue:44220", "accept": false, - "reason": "A broken model family and a tokenizer error-mask bug are unrelated." + "reason": "ImportError for a missing symbol and an fbank feature-extraction bug do not share the same code-path." }, { - "left": "issue:43012", - "right": "issue:43408", + "left": "issue:44075", + "right": "issue:45656", "accept": false, - "reason": "Both mention warnings, but they concern different models and different warning causes." + "reason": "SGD args being ignored and optimizer.step() being called twice with deepspeed are separate optimizer bugs." }, { - "left": "issue:41628", - "right": "issue:45071", + "left": "issue:44483", + "right": "issue:45464", "accept": false, - "reason": "Missing AutoImageProcessor import and PreTrainedConfig type-checking regression are separate API breakages." + "reason": "Generic /v1/chat/completions request rejection is not the same as streaming inference failing on Qwen3.5-0.8B." }, { - "left": "issue:43441", - "right": "issue:44829", + "left": "issue:42371", + "right": "issue:42831", "accept": false, - "reason": "FlashAttention load failure for one model is unrelated to degenerate training under flash_attention_3." + "reason": "TF32 behavior guidance and FineGrainedFP8 accuracy loss are different GPU/numerics issues." }, { - "left": "issue:45071", - "right": "issue:45542", + "left": "issue:43066", + "right": "issue:43122", "accept": false, - "reason": "Config type-checking regression and undefined TF backend due to tensorboard-only install are different problems." + "reason": "Wrong tokenizer decoder type and tokenization drift across 4.57.3 to 5.0 are related only at a very broad level, not the same bug." }, { - "left": "issue:43931", - "right": "issue:44410", + "left": "issue:43012", + "right": "issue:43577", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and qwen3next missing projections are different model-loading bugs." + "reason": "A compile-time float32 warning on bfloat16 models is not the same as Blip2 dtype fields staying float32 on load." }, { - "left": "issue:45003", + "left": "issue:43673", "right": "issue:45341", "accept": false, - "reason": "Unsafe sys.modules access is unrelated to the testing_utils bug." + "reason": "Missing GenerationMixin cache during chunked_prefill is unrelated to a testing_utils bug." }, { - "left": "issue:43931", - "right": "issue:44038", - "accept": false, - "reason": "Different Qwen3-VL-related failures with different symptoms and likely different fixes." - }, - { - "left": "issue:44117", - "right": "issue:44987", + "left": "issue:44484", + "right": "issue:45478", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES returning None is a different failure mode than loading a specific model repo on v5.1.0." + "reason": "save_pretrained shard-size behavior is unrelated to the Qwen3.5 MoE from_pretrained regression." }, { - "left": "issue:43097", - "right": "issue:43452", + "left": "issue:44410", + "right": "issue:45478", "accept": false, - "reason": "Removed tie_embeddings-related config behavior is unrelated to gguf_file breaking from_pretrained calls." + "reason": "qwen3next missing projections and Qwen3.5 MoE from_pretrained are different model-loading/architecture problems." }, { - "left": "issue:43335", - "right": "issue:45071", + "left": "issue:43874", + "right": "issue:44261", "accept": false, - "reason": "SwitchTransformers config construction bug and PreTrainedConfig type checking regression are unrelated." + "reason": "Missing get_number_of_image_patches in an image processor and an MLA layernorm epsilon issue are unrelated." }, { - "left": "issue:43986", - "right": "issue:45341", + "left": "issue:43097", + "right": "issue:44493", "accept": false, - "reason": "Video-model AutoProcessor crash without torchvision is unrelated to the testing_utils bug." + "reason": "Removed tie_embeddings_and_encoder_decoder and unexpected position-id keys are different compatibility regressions." }, { - "left": "issue:43986", - "right": "issue:44484", + "left": "issue:44263", + "right": "issue:44485", "accept": false, - "reason": "Video-model import crash and a save_pretrained shard-size question do not share a concrete bug." + "reason": "torch.split indexing values in GlmMoeDsaIndexer is not the same as the GLM-5 RoPE implementation discussion." }, { - "left": "issue:43408", - "right": "issue:44368", + "left": "issue:43012", + "right": "issue:43408", "accept": false, - "reason": "These are both warning-related but involve different configs/models and different warning conditions." + "reason": "bfloat16 compile warning and sam3 model-type mismatch are unrelated." }, { - "left": "issue:43874", - "right": "issue:44263", + "left": "issue:42222", + "right": "issue:45459", "accept": false, - "reason": "Missing image patch counting and torch.split return handling are unrelated implementation bugs." + "reason": "Vitpose breakage and protobuf-related tokenizer error masking are different subsystems." }, { - "left": "issue:43976", + "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Python-version compatibility and type-checking regression are separate issues." + "reason": "Missing AutoImageProcessor import and PreTrainedConfig type-checking breakage are unrelated regressions." } ] }, @@ -13133,30 +13097,27 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ - "issue:36683", "issue:38617", "issue:42757", - "issue:42886", - "issue:42907", - "issue:43012", "issue:43064", "issue:43066", "issue:43097", - "issue:43208", + "issue:43335", "issue:43352", - "issue:43381", + "issue:43408", + "issue:43441", + "issue:43452", "issue:43502", - "issue:43526", "issue:43531", - "issue:43550", - "issue:43582", "issue:43824", "issue:43825", "issue:43873", + "issue:43874", "issue:43901", "issue:43906", + "issue:43931", "issue:43976", "issue:43986", "issue:43992", @@ -13164,6 +13125,7 @@ "issue:44062", "issue:44117", "issue:44261", + "issue:44263", "issue:44315", "issue:44351", "issue:44368", @@ -13174,269 +13136,267 @@ "issue:44655", "issue:44704", "issue:44829", + "issue:44987", + "issue:45003", + "issue:45071", "issue:45103", "issue:45245", "issue:45341", "issue:45372", "issue:45375", - "issue:45479", - "issue:45588", - "issue:45753" + "issue:45542", + "issue:45588" ], "soft_pairs": [ - "issue:43531|issue:45341", + "issue:43441|issue:44829", + "issue:45071|issue:45542", + "issue:43931|issue:44410", + "issue:45003|issue:45341", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43097|issue:43452", + "issue:43986|issue:45341", + "issue:44117|issue:44987", + "issue:43986|issue:44484", + "issue:43408|issue:44368", + "issue:43976|issue:45071", + "issue:43874|issue:44263", "issue:44829|issue:45245", + "issue:43531|issue:45341", "issue:43986|issue:45372", "issue:38617|issue:42757", "issue:44261|issue:44485", "issue:43064|issue:44315", "issue:44410|issue:45375", "issue:38617|issue:44351", - "issue:44062|issue:44117", "issue:43097|issue:45588", + "issue:44062|issue:44117", "issue:44038|issue:44410", "issue:44704|issue:45103", "issue:43502|issue:43992", - "issue:43986|issue:44117", "issue:43097|issue:43873", + "issue:43986|issue:44117", "issue:43824|issue:43986", "issue:43066|issue:43906", "issue:43097|issue:43901", "issue:43825|issue:44655", "issue:43992|issue:44484", - "issue:43352|issue:44380", - "issue:43208|issue:43550", - "issue:43012|issue:43550", - "issue:43012|issue:44368", - "issue:42886|issue:43381", - "issue:42907|issue:45753", - "issue:42907|issue:44655", - "issue:44380|issue:45479", - "issue:43352|issue:43976", - "issue:43064|issue:44380", - "issue:43208|issue:43526", - "issue:36683|issue:43582" + "issue:43352|issue:44380" ], - "prepared_review_unit_hash": "2802e91ac11d376d76adf9647714f5ae122577600d8ac0156803afac886aa3fd", + "prepared_review_unit_hash": "5d53d1c406b599f366300c1babf83e7b4de98b5f5f7aeb433308afe89ea083f2", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 32, - "serialized_chars": 36691, - "estimated_input_tokens": 9173, - "estimated_eval_tokens": 18602 + "soft_pair_count": 34, + "serialized_chars": 37372, + "estimated_input_tokens": 9343, + "estimated_eval_tokens": 18942 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous: the soft-similarity pairs mostly connect unrelated regressions across different models, loaders, tokenizer behavior, and training paths. I do not see a true duplicate group here.", - "confidence": 0.93, - "canonical_issue_reason": "No single canonical issue stands out; the items are largely unrelated bugs rather than the same underlying defect.", + "summary": "A heterogeneous set of mostly unrelated Transformers issues: import/load failures, model-specific regressions, config bugs, and docs/API mismatches. None of the soft-edge pairs look like the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43097 is the broadest, most representative v5 regression in the set: a clear API/config removal with widespread user impact, closer to the cluster\u2019s general breakage theme than the narrower model-specific reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43097 is the closest representative by visibility and references, but it is still only a broad v5 compatibility complaint, not a duplicate anchor for the rest.", + "best_issue_reason": "issue:43097 is the best single issue to anchor this cluster because it is high-signal, broadly relevant, and clearly describes a concrete Transformers v5 compatibility break.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43531", - "right": "issue:45341", - "accept": false, - "reason": "Sliding-window Qwen3-MoE bug vs a small testing_utils bug; unrelated code paths." - }, - { - "left": "issue:44829", - "right": "issue:45245", + "left": "issue:43441", + "right": "issue:44829", "accept": false, - "reason": "FlashAttention 3 training degeneration vs category-count limit error; no shared underlying defect." + "reason": "Unsupported Flash Attention 2 error vs. degenerate training with Flash Attention 3; different symptoms and code paths." }, { - "left": "issue:43986", - "right": "issue:45372", + "left": "issue:45071", + "right": "issue:45542", "accept": false, - "reason": "AutoProcessor/torchvision loading crash vs Gemma 4 processor import failure from mistral_common; different failure sources." + "reason": "PretrainedConfig type-checking regression vs. tensorboard/TF backend import problem; unrelated subsystems." }, { - "left": "issue:38617", - "right": "issue:42757", + "left": "issue:43931", + "right": "issue:44410", "accept": false, - "reason": "Both are import errors, but for different symbols and dependencies; not the same bug." + "reason": "Qwen3-VL weight-shape mismatch vs. qwen3next missing projections; different models and failures." }, { - "left": "issue:44261", - "right": "issue:44485", + "left": "issue:45003", + "right": "issue:45341", "accept": false, - "reason": "Missing rms_norm_eps in MLA q_a_layernorm vs GLM-5 RoPE discussion; distinct model implementations." + "reason": "Unsafe sys.modules access vs. a testing_utils bug; unrelated areas of the codebase." }, { - "left": "issue:43064", - "right": "issue:44315", + "left": "issue:43931", + "right": "issue:44038", "accept": false, - "reason": "Different training bugs: FSDP2/PEFT optimizer state corruption vs Liger Kernel not applied with model_init." + "reason": "Both are Qwen3-VL family issues, but one is a load-time shape mismatch and the other is a Qwen3-VL-MoE support problem; not the same bug." }, { - "left": "issue:44410", - "right": "issue:45375", + "left": "issue:43335", + "right": "issue:45071", "accept": false, - "reason": "Different Qwen3 family config/model issues; missing projections is not the same as a dropped vision config field." + "reason": "SwitchTransformers sparse-layer config bug vs. PretrainedConfig type-checking regression; distinct code paths." }, { - "left": "issue:38617", - "right": "issue:44351", + "left": "issue:43097", + "right": "issue:43452", "accept": false, - "reason": "Different missing imports ('layer_type_validation' vs 'HybridCache'); separate compatibility problems." + "reason": "Removed tie_embeddings behavior vs. gguf_file handling in AutoTokenizer/AutoModel loading; different failures." }, { - "left": "issue:44062", - "right": "issue:44117", + "left": "issue:43986", + "right": "issue:45341", "accept": false, - "reason": "Tokenizer AddedToken constructor error vs TOKENIZER_MAPPING_NAMES returning None; different tokenizer bugs." + "reason": "AutoProcessor/video-model crash without torchvision vs. testing_utils bug; unrelated issues." }, { - "left": "issue:43097", - "right": "issue:45588", + "left": "issue:44117", + "right": "issue:44987", "accept": false, - "reason": "Embedding-tie API removal vs flash_attention sink handling crash; unrelated changes." + "reason": "TOKENIZER_MAPPING_NAMES None handling vs. loading physical-intelligence/fast; both loader-related but different root causes." }, { - "left": "issue:44038", - "right": "issue:44410", + "left": "issue:43986", + "right": "issue:44484", "accept": false, - "reason": "Different Qwen model variants and different symptoms; not the same code-path bug." + "reason": "Processor/torchvision crash vs. a save_pretrained shard-size question; unrelated." }, { - "left": "issue:44704", - "right": "issue:45103", + "left": "issue:43408", + "right": "issue:44368", "accept": false, - "reason": "AutoProcessor kwargs forwarding vs auto_docstring annotation handling; unrelated failures." + "reason": "sam3_video/sam3_tracker type warning vs. tie_word_embeddings warning; not the same underlying problem." }, { - "left": "issue:43502", - "right": "issue:43992", + "left": "issue:43976", + "right": "issue:45071", "accept": false, - "reason": "Offline/local file access bug vs missing embed_tokens.weight in UMT5Encoder; separate loading issues." + "reason": "Python version compatibility issue vs. type-checking regression; separate bugs." }, { - "left": "issue:43986", - "right": "issue:44117", + "left": "issue:43874", + "right": "issue:44263", "accept": false, - "reason": "Video model loading without torchvision vs tokenizer mapping None; different subsystems." + "reason": "Missing image-patch method vs. torch.split return-value issue in a different model component." }, { - "left": "issue:43097", - "right": "issue:43873", + "left": "issue:44829", + "right": "issue:45245", "accept": false, - "reason": "Embedding tie API removal vs quantization offloading behavior; not the same defect." + "reason": "FlashAttention 3 training degeneration vs. category-count runtime limit; unrelated." }, { - "left": "issue:43824", - "right": "issue:43986", + "left": "issue:43531", + "right": "issue:45341", "accept": false, - "reason": "Missing Qwen2.5-VL export vs AutoProcessor crash without torchvision; different import/load paths." + "reason": "Qwen3-MoE sliding-window bug vs. testing_utils bug; no shared code path." }, { - "left": "issue:43066", - "right": "issue:43906", + "left": "issue:43986", + "right": "issue:45372", "accept": false, - "reason": "Wrong tokenizer decoder type vs an isolated reproduction of another issue; no concrete overlap shown." + "reason": "Processor loading without torchvision vs. ReasoningEffort import failure; both load-time errors but different dependencies and fixes." }, { - "left": "issue:43097", - "right": "issue:43901", + "left": "issue:38617", + "right": "issue:42757", "accept": false, - "reason": "API removal warning vs TextClassificationPipeline docs mismatch; one is behavior, the other documentation." + "reason": "Different missing imports from different modules/packages; only superficial similarity." }, { - "left": "issue:43825", - "right": "issue:44655", + "left": "issue:44261", + "right": "issue:44485", "accept": false, - "reason": "Pipeline task message bug vs inability to save Pipeline objects; different pipeline operations." + "reason": "MLA layernorm epsilon config bug vs. GLM-5 RoPE implementation issue; distinct model logic." }, { - "left": "issue:43992", - "right": "issue:44484", + "left": "issue:43064", + "right": "issue:44315", "accept": false, - "reason": "Missing encoder weights on load vs save_pretrained shard-size question; unrelated save/load concerns." + "reason": "Optimizer-state corruption with FSDP2+PEFT vs. Liger Kernel application with model_init; different training integrations." }, { - "left": "issue:43352", - "right": "issue:44380", + "left": "issue:44410", + "right": "issue:45375", "accept": false, - "reason": "FlashAttention 2 support error vs attention-scaling ignored under SDPA/FlashAttention; different attention backend issues." + "reason": "qwen3next missing projections vs. missing deepstack_visual_indexes field; different config/model fields." }, { - "left": "issue:43208", - "right": "issue:43550", + "left": "issue:38617", + "right": "issue:44351", "accept": false, - "reason": "xLSTM training blockers vs Bamba torch.compile+SDPA failure; unrelated models and symptoms." + "reason": "layer_type_validation import error vs. HybridCache import error; unrelated missing exports." }, { - "left": "issue:43012", - "right": "issue:43550", + "left": "issue:43097", + "right": "issue:45588", "accept": false, - "reason": "PyTorch warning during bf16 compilation vs compile-time failure with SDPA; not the same bug." + "reason": "Config/API removal issue vs. flash_attention.py s_aux=None crash; different subsystems and fixes." }, { - "left": "issue:43012", - "right": "issue:44368", + "left": "issue:44062", + "right": "issue:44117", "accept": false, - "reason": "Compilation precision warning vs tie_word_embeddings warning; unrelated warnings." + "reason": "AddedToken keyword collision vs. TOKENIZER_MAPPING_NAMES None assumption; unrelated tokenizer bugs." }, { - "left": "issue:42886", - "right": "issue:43381", + "left": "issue:44038", + "right": "issue:44410", "accept": false, - "reason": "Offline cache loading bug vs gradient checkpointing in eval mode; separate behaviors." + "reason": "Qwen3-VL-MoE loading bug vs. qwen3next projection omission; different model variants and code paths." }, { - "left": "issue:42907", - "right": "issue:45753", + "left": "issue:44704", + "right": "issue:45103", "accept": false, - "reason": "Saving dequantized models vs Qwen3_5 infinite loop on a specific image; unrelated." + "reason": "AutoProcessor kwargs propagation vs. docstring annotation crash under future annotations; unrelated." }, { - "left": "issue:42907", - "right": "issue:44655", + "left": "issue:43502", + "right": "issue:43992", "accept": false, - "reason": "Both involve saving, but one is dequantized model save failure and the other is pipeline save_pretrained; different code paths." + "reason": "local_files_only still triggers network access vs. missing embed_tokens.weight in UMT5Encoder; unrelated." }, { - "left": "issue:44380", - "right": "issue:45479", + "left": "issue:43097", + "right": "issue:43873", "accept": false, - "reason": "Attention backend scaling bug vs degenerate zero-loss classification with num_labels=1; unrelated training behavior." + "reason": "API removal/regression report vs. offloading-with-quantization behavior issue; not the same bug." }, { - "left": "issue:43352", - "right": "issue:43976", + "left": "issue:43986", + "right": "issue:44117", "accept": false, - "reason": "Model-specific FlashAttention support issue vs Python version compatibility problem; not the same bug." + "reason": "Video-model loading without torchvision vs. tokenizer mapping None issue; different failure modes." }, { - "left": "issue:43064", - "right": "issue:44380", + "left": "issue:43824", + "right": "issue:43986", "accept": false, - "reason": "Optimizer-state corruption in distributed training vs attention scaling ignored under backend swap; different subsystems." + "reason": "Missing Qwen2_5_VLForConditionalGeneration export vs. video-model/torchvision crash; distinct missing symbols." }, { - "left": "issue:43208", - "right": "issue:43526", + "left": "issue:43066", + "right": "issue:43906", "accept": false, - "reason": "xLSTM training blockers vs BeitImageProcessorFast label reduction bug; unrelated." + "reason": "Wrong tokenizer decoder type vs. an isolated reproduction of a different issue; insufficient evidence of sameness." }, { - "left": "issue:36683", - "right": "issue:43582", + "left": "issue:43825", + "right": "issue:44655", "accept": false, - "reason": "Gemma3Config missing vocab_size vs Apple Silicon caching_allocator_warmup TypeError; no shared defect." + "reason": "Pipeline translation-task messaging bug vs. saving Pipeline objects; different pipeline behaviors." } ] }, @@ -13458,23 +13418,29 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:36010", "issue:36683", "issue:38617", "issue:42757", + "issue:42886", "issue:42898", + "issue:42907", "issue:42994", - "issue:43010", "issue:43012", "issue:43064", "issue:43066", + "issue:43208", "issue:43299", "issue:43352", + "issue:43381", "issue:43475", "issue:43502", "issue:43525", + "issue:43526", + "issue:43550", + "issue:43582", "issue:43611", "issue:43618", "issue:43756", @@ -13482,51 +13448,56 @@ "issue:43824", "issue:43867", "issue:43901", - "issue:43931", "issue:43937", "issue:43976", - "issue:43992", "issue:44038", "issue:44077", - "issue:44188", "issue:44230", - "issue:44242", "issue:44263", + "issue:44368", "issue:44380", "issue:44483", "issue:44485", - "issue:44492", "issue:44514", "issue:44655", "issue:44683", "issue:44938", "issue:45216", - "issue:45278", "issue:45290", - "issue:45310", "issue:45381", "issue:45440", - "issue:45593", + "issue:45479", "issue:45753" ], "soft_pairs": [ + "issue:43208|issue:43550", + "issue:43012|issue:43550", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:42907|issue:45753", + "issue:42907|issue:44655", + "issue:44380|issue:45479", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:43208|issue:43526", + "issue:36683|issue:43582", "issue:44483|issue:44514", - "issue:43618|issue:43761", "issue:43012|issue:44683", + "issue:43618|issue:43761", "issue:43618|issue:44380", "issue:42757|issue:43824", "issue:38617|issue:43502", "issue:44038|issue:44230", "issue:44483|issue:45290", "issue:43299|issue:43867", - "issue:43756|issue:44485", "issue:44483|issue:45381", + "issue:43756|issue:44485", "issue:43299|issue:45753", "issue:43901|issue:44655", "issue:36683|issue:43475", "issue:42994|issue:44655", - "issue:43867|issue:45216", "issue:43352|issue:43937", + "issue:43867|issue:45216", "issue:44077|issue:44380", "issue:36010|issue:42757", "issue:42898|issue:43066", @@ -13534,212 +13505,252 @@ "issue:43611|issue:44655", "issue:43976|issue:44938", "issue:44263|issue:45440", - "issue:36683|issue:43525", - "issue:43352|issue:45593", - "issue:43618|issue:45216", - "issue:44188|issue:44380", - "issue:36683|issue:44242", - "issue:43064|issue:44492", - "issue:43352|issue:43931", - "issue:43010|issue:45278", - "issue:43992|issue:45310" + "issue:36683|issue:43525" ], - "prepared_review_unit_hash": "890014d64f0bdae68357c2d0596270dfc7e0078b599d1b71ddab98c3730ea37e", + "prepared_review_unit_hash": "933d243d8e51ebe703a7eb203f9ffd54da3314c3cdc9ad024ba4791132b25bfc", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37130, - "estimated_input_tokens": 9283, - "estimated_eval_tokens": 18822 + "soft_pair_count": 36, + "serialized_chars": 38206, + "estimated_input_tokens": 9552, + "estimated_eval_tokens": 19360 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of Transformers v5 regressions: import errors, model-loading/saving bugs, tokenizer/chat-template behavior changes, and a few unrelated model-specific issues. The strongest umbrella issue is the open report about many import errors after upgrading to 5.5.0.", - "confidence": 0.69, - "canonical_issue_reason": "issue:45278 is the broadest umbrella: it is open, user-facing, and explicitly groups multiple import failures after upgrading to 5.5.0, which matches the repeated import-regression theme in this cluster best.", + "summary": "This cluster is not a duplicate set; it mixes unrelated Transformers issues across imports, config attributes, tokenizer behavior, model loading/saving, generation, and backend-specific regressions. The soft pairs mostly share only broad keywords like \"v5\", \"load\", \"save\", or a model family name, not the same concrete bug.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best representative issue because it is the most general and consolidating report; the others are narrower model- or API-specific regressions.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44483", - "right": "issue:44514", + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training bugs for sub-7B models and a Bamba torch.compile/SDPA failure are different models and different failure modes." + }, + { + "left": "issue:43012", + "right": "issue:43550", "accept": false, - "reason": "Both involve chat-related APIs, but one is an OpenAI-style /v1/chat/completions acceptance issue and the other is a batched apply_chat_template crash. Different code paths." + "reason": "One is a bfloat16 warning during compile; the other is a specific Bamba compile/runtime failure. Same broad area, not the same bug." }, { - "left": "issue:43618", - "right": "issue:43761", + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both mention warnings, but one is a PyTorch precision warning and the other is a tie_word_embeddings config warning in a different workflow." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading and gradient checkpointing in eval mode are unrelated code paths." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized models and an infinite-loop image generation bug are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Both involve saving, but one is dequantized model serialization and the other is saving Pipeline objects." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "GPT2 attention scaling with SDPA/FlashAttention and zero-loss sequence classification are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Flash Attention 2 support for Nemotron and Python version compatibility are different issues." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption and GPT2 attention scaling are different training/inference bugs." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs and a BeitImageProcessorFast label reduction bug do not overlap." + }, + { + "left": "issue:36683", + "right": "issue:43582", "accept": false, - "reason": "Both mention CLIP and v5 regressions, but one is about attentions in CLIPOutput and the other is about hidden_states in CLIPVisionModel.forward. Not the same bug." + "reason": "Gemma3Config missing vocab_size and an Apple Silicon TypeError in caching_allocator_warmup are unrelated." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Chat/completions request rejection and a batched apply_chat_template crash are different layers and different symptoms." }, { "left": "issue:43012", "right": "issue:44683", "accept": false, - "reason": "A PyTorch precision warning from torch.compile is unrelated to a compiled flex_attention failure on torch>=2.9." + "reason": "A bfloat16 precision warning is not the same as compiled flex_attention breaking on torch>=2.9." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP regressions, but one drops attentions and the other drops hidden_states; different outputs and code paths." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "Different models and failures: CLIPOutput attentions vs GPT2 attention scaling being ignored under SDPA/FlashAttention." + "reason": "CLIP attentions regression and GPT2 attention scaling are unrelated." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but they are for different symbols and packages; no sign of the same missing export or code path." + "reason": "Missing is_offline_mode in huggingface_hub and missing Qwen2_5_VLForConditionalGeneration in transformers are separate import errors." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "Importing layer_type_validation and ignoring local_files_only are unrelated problems." + "reason": "Importing layer_type_validation and making API requests despite local_files_only=True are unrelated." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Both reference Qwen3-VL MoE, but one is a loading regression and the other is fp8 support for inference; not the same underlying bug." + "reason": "Qwen3-VL-Moe loading breakage and fp8 inference support for Qwen3.5 MoE are not the same bug." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Different chat surfaces: request validation at /v1/chat/completions versus apply_chat_template crashing on assistant tool-call messages." + "reason": "A /v1/chat/completions acceptance problem and a tool-call chat-template crash are different request paths." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Both are model loading failures, but one is Qwen3-VL MoE import/loading breakage and the other is a state_dict sorting error. Different root causes." + "reason": "Qwen3VL-Moe loading failures and a state_dict-sorting load error are distinct load-time issues." }, { - "left": "issue:43756", - "right": "issue:44485", + "left": "issue:44483", + "right": "issue:45381", "accept": false, - "reason": "RoPE-layer count in Smollm3 is unrelated to GLM-5 RoPE implementation discussion." + "reason": "API request validation and incorrect vision_position_ids in Qwen2.5-VL video input are unrelated." }, { - "left": "issue:44483", - "right": "issue:45381", + "left": "issue:43756", + "right": "issue:44485", "accept": false, - "reason": "One is an API request acceptance problem; the other is Qwen2.5-VL video position IDs being wrong." + "reason": "Smollm3 RoPE-layer dropping and GLM-5 RoPE implementation discussion are different models and different defects." }, { "left": "issue:43299", "right": "issue:45753", "accept": false, - "reason": "Qwen3-VL MoE loading breakage and a specific-image infinite loop are different bugs." + "reason": "Qwen3VL-Moe loading breakage and a Qwen3.5 infinite-loop image bug are unrelated." }, { "left": "issue:43901", "right": "issue:44655", "accept": false, - "reason": "Documentation mismatch for return_all_scores is unrelated to Pipeline save_pretrained failing." + "reason": "A docs mismatch about return_all_scores and a pipeline save_pretrained failure are unrelated." }, { "left": "issue:36683", "right": "issue:43475", "accept": false, - "reason": "Gemma3Config missing vocab_size and SAM3 output missing fpn_position_embeddings are different model-specific attribute errors." + "reason": "Gemma3Config missing vocab_size and Sam3VisionEncoderOutput missing fpn_position_embeddings are different attribute regressions." }, { "left": "issue:42994", "right": "issue:44655", "accept": false, - "reason": "Quantized model saving failure and pipeline serialization failure are both about saving, but they are not the same issue." + "reason": "Quantized model saving failure and Pipeline.save_pretrained failure are both save-related but affect different object types and code paths." }, { - "left": "issue:43867", - "right": "issue:45216", + "left": "issue:43352", + "right": "issue:43937", "accept": false, - "reason": "Both concern saving/loading checkpoints, but one is a state_dict ordering error and the other is a Qwen3.5 save_pretrained regression." + "reason": "Nemotron FlashAttention support and GLM-5 GenerationConfig validation are unrelated." }, { - "left": "issue:43352", - "right": "issue:43937", + "left": "issue:43867", + "right": "issue:45216", "accept": false, - "reason": "FlashAttention2 support for Nemotron and invalid GenerationConfig for GLM-5 are unrelated." + "reason": "A load error when state_dict is sorted and a Qwen3.5 save_pretrained regression are different checkpoint issues." }, { "left": "issue:44077", "right": "issue:44380", "accept": false, - "reason": "patchtsmixer post_init validation and GPT2 attention scaling under backend kernels are different code paths." + "reason": "PatchTSMixer post_init restrictions and GPT2 attention scaling with SDPA/FlashAttention are unrelated." }, { "left": "issue:36010", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they are for different missing symbols from different modules." + "reason": "GenerationMixin missing from transformers.generation and is_offline_mode missing from huggingface_hub are separate import regressions." }, { "left": "issue:42898", "right": "issue:43066", "accept": false, - "reason": "A v5 tokenization_spaces behavior change and an incorrect tokenizer decoder type are distinct tokenizer issues." + "reason": "A clean_up_tokenization_spaces behavior change and a wrong tokenizer decoder type are both tokenizer regressions but not the same bug." }, { "left": "issue:36683", "right": "issue:44077", "accept": false, - "reason": "Unrelated issues: Gemma3Config attribute error versus patchtsmixer post_init policy change." + "reason": "Gemma3Config missing vocab_size and patchtsmixer post_init policy are unrelated." }, { "left": "issue:43611", "right": "issue:44655", "accept": false, - "reason": "base_model_prefix loading breakage is not the same bug as inability to save Pipeline objects." + "reason": "base_model_prefix loading breakage and Pipeline.save_pretrained failure are different serialization/loading paths." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Both are version/platform compatibility reports, but one is Python 3.9/3.10 package compatibility and the other is Python 3.14 loading failure. Different causes." + "reason": "Python-version support problems in 5.1.0 and Python 3.14 load failure are both compatibility issues but not the same one." }, { "left": "issue:44263", "right": "issue:45440", "accept": false, - "reason": "GlmMoeDsaIndexer torch.split behavior and DeepseekV3MoE divergence are different model internals, not one bug." + "reason": "A torch.split return-value bug in GlmMoeDsaIndexer and DeepseekV3MoE divergence are different model internals." }, { "left": "issue:36683", "right": "issue:43525", "accept": false, - "reason": "Different missing-config-attribute bugs: vocab_size on Gemma3Config versus pad_token_id on Llama4Config." - }, - { - "left": "issue:43352", - "right": "issue:45593", - "accept": false, - "reason": "FlashAttention2 support for Nemotron is unrelated to D-FINE auxiliary losses when denoising is off." - }, - { - "left": "issue:43618", - "right": "issue:45216", - "accept": false, - "reason": "A CLIP attentions regression and a Qwen3.5 save_pretrained regression are unrelated." - }, - { - "left": "issue:44188", - "right": "issue:44380", - "accept": false, - "reason": "Both mention attention kernels, but one is a torch.compile branching divergence and the other is backend-specific attention scaling being ignored." + "reason": "Missing vocab_size on Gemma3Config and missing pad_token_id on Llama4Config are similar only in that both are config attributes, but they affect different models and code paths." } ] }, @@ -13761,57 +13772,66 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:28282", "issue:33453", "issue:36296", "issue:36683", "issue:41669", - "issue:42548", "issue:42890", "issue:43010", "issue:43064", - "issue:43065", + "issue:43352", "issue:43502", "issue:43575", "issue:43618", "issue:43723", "issue:43867", + "issue:43931", "issue:43976", "issue:43992", "issue:44062", "issue:44075", "issue:44077", "issue:44112", - "issue:44222", + "issue:44188", + "issue:44242", "issue:44246", - "issue:44351", "issue:44355", "issue:44360", - "issue:44387", + "issue:44380", "issue:44484", - "issue:44485", + "issue:44492", "issue:44556", - "issue:44749", "issue:44855", + "issue:44857", "issue:44938", "issue:44964", "issue:44977", "issue:45071", - "issue:45125", - "issue:45341", + "issue:45216", + "issue:45278", + "issue:45310", "issue:45357", "issue:45375", "issue:45381", "issue:45440", "issue:45478", "issue:45561", - "issue:45588", + "issue:45593", "issue:45600", "issue:45850" ], "soft_pairs": [ + "issue:43352|issue:45593", + "issue:43618|issue:45216", + "issue:44188|issue:44380", + "issue:36683|issue:44242", + "issue:43064|issue:44492", + "issue:43352|issue:43931", + "issue:43010|issue:45278", + "issue:43992|issue:45310", "issue:43867|issue:45375", "issue:41669|issue:44246", "issue:44355|issue:44855", @@ -13828,246 +13848,230 @@ "issue:36296|issue:43575", "issue:28282|issue:33453", "issue:43867|issue:44484", + "issue:43618|issue:44857", "issue:43618|issue:44977", - "issue:43618|issue:45588", "issue:42890|issue:44964", "issue:42890|issue:44112", "issue:42890|issue:45600", "issue:43502|issue:44062", "issue:43010|issue:44075", - "issue:43723|issue:44556", - "issue:42548|issue:44351", - "issue:42890|issue:45341", - "issue:44222|issue:45125", - "issue:44387|issue:44556", - "issue:43010|issue:43065", - "issue:43502|issue:44485", - "issue:44355|issue:44749" + "issue:43723|issue:44556" ], - "prepared_review_unit_hash": "8ad98356e6c7c3bb67b608d5a0e48592f04166d6d40389a0c3ab5099965e0de2", + "prepared_review_unit_hash": "218bdf440d4df1bb5149181c96859c71df6dbf6327c4abf6096fec450dace22f", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 35961, - "estimated_input_tokens": 8991, - "estimated_eval_tokens": 18238 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36853, + "estimated_input_tokens": 9214, + "estimated_eval_tokens": 18684 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous v5-era regression reports. The only strong duplicate-like pair is the import-time slowdown issue around `import *` in model modules; the rest are related only at a broad subsystem level and should stay separate.", - "confidence": 0.91, - "canonical_issue_reason": "issue:41669 is the most concrete and actionable report: it identifies a specific root cause (`import *` in models) and a measurable impact (slow import / many files).", + "summary": "This cluster is a loose collection of Transformers bug reports, mostly version-regression and model-specific loading/training issues. The soft pairs share broad themes at best, but none look like the same concrete bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.76, + "canonical_issue_reason": "Issue 45278 is the closest umbrella report in this set because it captures the broad post-v5 import/regression theme, but it is still only a thematic representative, not a true duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": "issue:41669 is the best representative because it clearly states the underlying bug and can anchor the small import-performance subset of this cluster.", + "best_issue_reason": "45278 is the best single issue to stand in for the cluster because it is the broadest and most general description among the reports, though the cluster is too heterogeneous for a strong canonical fit.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "Different models and failure modes: FlashAttention 2 support error vs auxiliary-loss behavior in D-FINE." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "Unrelated regressions: missing CLIP attentions field vs Qwen3.5 save_pretrained key corruption." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "Both touch attention backends, but one is torch.compile divergence and the other is GPT2 scaling ignored under SDPA/FlashAttention; different bugs." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3 config attribute missing vs MoE load-balancing loss gating; no shared underlying defect." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Training/optimizer state bug vs a cache strategy typo; clearly unrelated." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Different model-loading problems with different roots: unsupported FlashAttention 2 vs Qwen3-VL tensor shape mismatch." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Cache no_grad decoration issue is unrelated to broad import errors after upgrading to v5.5.0." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different load/save regressions affecting different Qwen models and different failure points." + }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "Both concern model/config loading, but one is a state-dict loading error and the other is a missing config field; different bugs." + "reason": "State-dict sorting/load error vs missing config field dropped by strict handling; not the same bug." }, { "left": "issue:41669", "right": "issue:44246", - "accept": true, - "reason": "`44246` describes the same symptom as `41669`: importing transformers is intermittently slow, and `41669` identifies the likely cause in model `import *` usage." + "accept": false, + "reason": "Both concern import performance, but one identifies a concrete import-* cause while the other is only a vague slowdown report." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "Both are import-related, but one is a generic compiled-file/import failure and the other is a Python 3.13 `torch.jit.script` parsing issue; not the same bug." + "reason": "Compiled Python file errors vs a Python 3.13 IndentationError from torch.jit parsing; different code paths." }, { "left": "issue:36683", "right": "issue:43064", "accept": false, - "reason": "These are unrelated: a missing config attribute in Gemma3 versus a distributed training optimizer-state bug." + "reason": "Config attribute regression vs FSDP2/PEFT optimizer-state corruption; unrelated." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Both are test flakiness, but they involve different failure modes and code paths (`set_seed` omissions vs xdist race on captured_info.txt)." + "reason": "Both are flaky test/CI issues, but the failing mechanisms differ: missing set_seed vs xdist race on captured_info.txt." }, { "left": "issue:44938", "right": "issue:45071", "accept": false, - "reason": "One is a Python 3.14 load failure and the other is a `PretrainedConfig` type-checking regression; they do not point to the same underlying defect." + "reason": "Python-version import failure vs PretrainedConfig typing regression; not the same concrete issue." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Different Qwen-related load/save issues: one is sorted-state-dict loading, the other is incorrect visual encoder keys during save." + "reason": "Load-time state_dict issue vs save_pretrained writing wrong visual encoder keys; opposite sides of the serialization flow and different models." }, { "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "`43010` is a specific no-grad decoration request for cache updates; `45850` is a broad complaint about many broken models after v5." + "reason": "A specific cache-update no_grad bug does not match a generic complaint that v5 breaks many models." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "Both are model-loading failures, but one is a missing encoder weight and the other is a Qwen3.5 MoE `from_pretrained` error; different root causes." + "reason": "Different Qwen/UMT5 loading regressions with different missing keys and error paths." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "Unrelated problems: cache update decoration versus Python-version compatibility for Transformers 5.1.0." + "reason": "Cache update autograd issue is unrelated to Python 3.9/3.10 compatibility." }, { "left": "issue:44938", "right": "issue:45381", "accept": false, - "reason": "Both mention version regressions, but one is a Python 3.14 load failure and the other is a Qwen2.5-VL video-position-id bug." + "reason": "Python 3.14 load failure vs Qwen2.5-VL video position-id bug; unrelated." }, { "left": "issue:43618", "right": "issue:44077", "accept": false, - "reason": "Different functionality and failures: missing CLIP attentions output versus an API change around `patchtsmixer` `post_init`." + "reason": "Different model API regressions: CLIP attentions field vs patchtsmixer post_init policy." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "Completely different bugs in different model families: DSA indexer activation versus DeepSeekV3MoE divergence." + "reason": "DSA indexer activation bug vs DeepseekV3MoE implementation drift; unrelated." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Both involve tensor parallelism, but one is a training bug and the other is OOM when loading a large model; too different to merge." + "reason": "Both mention tensor parallelism, but one is a training bug and the other is an OOM on loading a huge model; not the same defect." }, { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "An environment import error for PyTorch is unrelated to a tokenizer-loading regression." + "reason": "ImportError about missing PyTorch is unrelated to tokenizer-loading regression." }, { "left": "issue:43867", "right": "issue:44484", "accept": false, - "reason": "Model load failure versus a question about the default `max_shard_size`; not the same issue." + "reason": "Model load error vs a question about default shard size; no duplicate evidence." }, { "left": "issue:43618", - "right": "issue:44977", + "right": "issue:44857", "accept": false, - "reason": "CLIP attentions assignment and Qwen3.5 flash-attention generation are unrelated." + "reason": "CLIP output attentions regression and an AMP float16 crash in LwDetrImageLoss are unrelated." }, { "left": "issue:43618", - "right": "issue:45588", + "right": "issue:44977", "accept": false, - "reason": "Both mention attention code, but one is CLIP output fields and the other is a flash-attention crash on `s_aux=None`; different code paths." + "reason": "Different models and symptoms: CLIP attentions assignment vs Qwen3.5 flash-attention generation failure." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "Test seeding flakiness is unrelated to a model-loading failure for Phi-4-multimodal." - }, - { - "left": "issue:42890", - "right": "issue:44112", - "accept": false, - "reason": "Different CI/test issues: missing `set_seed` in a model test versus a stale device-override test in GraniteSpeech." - }, - { - "left": "issue:42890", - "right": "issue:45600", - "accept": false, - "reason": "Different CI failures: a flaky SamHQ test versus stale auto-mapping references to removed configs." + "reason": "Test flakiness from missing set_seed is unrelated to Phi-4 multimodal load failure." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "One is an offline-loading network bug, the other is an `AddedToken` argument conflict in tokenizer construction." + "reason": "Local-files-only network leakage vs AddedToken constructor argument duplication; different subsystems." }, { "left": "issue:43010", "right": "issue:44075", "accept": false, - "reason": "A no-grad decoration request for cache updates is unrelated to SGD arguments being ignored." + "reason": "Cache update autograd bug is unrelated to SGD arguments being ignored." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Tokenizer loading in v5 and checkpoint reload compatibility after upgrading versions are related only broadly; they are not the same concrete bug." - }, - { - "left": "issue:42548", - "right": "issue:44351", - "accept": false, - "reason": "Both are missing-import issues, but they affect different exported symbols (`PreTrainedModel` vs `HybridCache`) and likely different fixes." - }, - { - "left": "issue:42890", - "right": "issue:45341", - "accept": false, - "reason": "A flaky integration test due to seeding is unrelated to a generic bug in `testing_utils.py`." - }, - { - "left": "issue:44222", - "right": "issue:45125", - "accept": false, - "reason": "FP8 save/pretrained behavior for MoE is different from a missing tensor-parallel plan on a Qwen3_5 model." - }, - { - "left": "issue:44387", - "right": "issue:44556", - "accept": false, - "reason": "Int4 quantization memory growth and checkpoint reload incompatibility are distinct problems." - }, - { - "left": "issue:43010", - "right": "issue:43065", - "accept": false, - "reason": "Cache update no-grad behavior is unrelated to a dummy `nn.Conv2d` in Sam3PixelDecoder." - }, - { - "left": "issue:43502", - "right": "issue:44485", - "accept": false, - "reason": "Offline loading/network behavior is unrelated to the GLM-5 RoPE implementation discussion." - }, - { - "left": "issue:44355", - "right": "issue:44749", - "accept": false, - "reason": "Compiled-file/import failures and a Chinese-language report about slowdown after upgrading to 5.3.0 are not the same bug." + "reason": "Tokenizer-loading regression vs checkpoint reload incompatibility after version upgrades; similar domain but different concrete failures." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative overall. The accepted soft pair (41669/44246) is a plausible duplicate around import-time slowdown, and the rejected pairs are mostly separated by clear differences in failure mode or code path. No PR-pair mergeability issue applies here." - }, - "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 }, @@ -14082,7 +14086,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:30333", "issue:30990", @@ -14095,7 +14099,9 @@ "issue:42548", "issue:42757", "issue:42831", + "issue:42890", "issue:43010", + "issue:43065", "issue:43232", "issue:43299", "issue:43502", @@ -14109,32 +14115,38 @@ "issue:44222", "issue:44230", "issue:44261", - "issue:44273", "issue:44315", + "issue:44351", "issue:44355", "issue:44360", + "issue:44387", "issue:44485", "issue:44492", "issue:44556", - "issue:44623", "issue:44655", + "issue:44749", "issue:44908", "issue:44938", "issue:44961", - "issue:45003", "issue:45071", "issue:45125", - "issue:45230", + "issue:45341", "issue:45362", "issue:45375", "issue:45468", "issue:45478", - "issue:45542", "issue:45850" ], "soft_pairs": [ - "issue:30990|issue:31795", + "issue:42548|issue:44351", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:44387|issue:44556", + "issue:43010|issue:43065", + "issue:43502|issue:44485", + "issue:44355|issue:44749", "issue:43010|issue:43232", + "issue:30990|issue:31795", "issue:45125|issue:45478", "issue:45125|issue:45375", "issue:30333|issue:33453", @@ -14165,265 +14177,283 @@ "issue:41628|issue:44355", "issue:36296|issue:43526", "issue:45362|issue:45850", - "issue:44261|issue:44360", - "issue:44623|issue:45230", - "issue:44273|issue:45542", - "issue:44273|issue:45003" + "issue:44261|issue:44360" ], - "prepared_review_unit_hash": "4f6c672451d8dbc02844d6f4a0b6c237eb57eaa26491446992fd887ad3f3661a", + "prepared_review_unit_hash": "c8adefc2b256768e1ed7ac312899f2914d137ea48128e9a440d29ef2b9d1667d", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 - }, - "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 36, - "serialized_chars": 37082, - "estimated_input_tokens": 9271, - "estimated_eval_tokens": 18798 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 40, + "serialized_chars": 39017, + "estimated_input_tokens": 9755, + "estimated_eval_tokens": 19766 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Most pairs are clearly different bugs. The only plausible duplicate is the Qwen3.5 MoE loading pair (45125/45478), where one issue describes the underlying missing tensor-parallel plan and the other describes the resulting from_pretrained failure.", - "confidence": 0.79, - "canonical_issue_reason": "issue:45125 is the cleaner, root-cause-oriented report: it names the specific missing _tp_plan problem for Qwen3_5MoeForConditionalGeneration, which can explain the broader loading failure reported elsewhere.", + "summary": "The cluster is mostly a loose collection of unrelated Transformers regressions, import/load failures, cache bugs, docs issues, and a few model-specific problems. I found no soft-edge pair that clearly shares the same underlying bug or change.", + "confidence": 0.78, + "canonical_issue_reason": "issue:44556 is the clearest concrete version-compatibility regression in the set: a user-facing reload failure after upgrading from v4.57 to v5.2/v5.3. It is more representative than the narrower model-specific or docs-only items.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45125 is the best representative issue in this set because it is specific, actionable, and tied to a concrete code path rather than a broad symptom or unrelated regression.", + "best_issue_reason": "issue:44556 is the best single issue to keep as the cluster anchor because it is specific, actionable, and sits near the main theme of v5 breakage/loading regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:30990", - "right": "issue:31795", + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols (`PreTrainedModel` vs `HybridCache`) and likely different breakpoints." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "One is test flakiness from missing `set_seed()`, the other is a different testing_utils bug; not the same failure." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained on MoE vs missing `_tp_plan` for tensor parallelism are distinct code paths and symptoms." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization OOM and checkpoint reload compatibility after upgrade are different bugs." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "`no_grad` decoration for cache update and a dummy Conv2d in Sam3PixelDecoder are unrelated fixes." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Offline-mode network calls and GLM-5 RoPE implementation are different issues." + }, + { + "left": "issue:44355", + "right": "issue:44749", "accept": false, - "reason": "Different problems: a runtime loading hang vs documentation confusion about forward arguments." + "reason": "Compiled Python-file errors and a slowdown after upgrade are different failure modes." }, { "left": "issue:43010", "right": "issue:43232", "accept": false, - "reason": "Different generation/cache issues: one is about no_grad decoration, the other about sync_gpus and _update_model_kwargs_for_generation." + "reason": "Cache update decoration and generation kwargs after `sync_gpus` are separate generation bugs." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Loading stall for Sentence Transformers vs documentation confusion in `model.forward` are unrelated." }, { "left": "issue:45125", "right": "issue:45478", - "accept": true, - "reason": "Likely the same Qwen3.5 MoE loading bug: one reports the missing _tp_plan/root cause, the other the resulting from_pretrained failure on newer transformers." + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but one is missing tensor-parallel metadata while the other is a `from_pretrained` failure; root causes differ." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Related Qwen3.5 MoE area, but this is about a missing vision config field, not the tensor-parallel loading path." + "reason": "Missing `_tp_plan` and missing `deepstack_visual_indexes` are different config omissions." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "Different failure modes: MLFlow reporting on training failure vs tokenizer loading regression." + "reason": "MLflow failure reporting and tokenizer loading regression are unrelated." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "Different bugs: offline/local_files_only network leakage vs FP8 moe save_pretrained behavior." + "reason": "Local-files-only network requests and FP8 save_pretrained on MoE are different bugs." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Both are loading regressions, but they affect different scenarios and model families; too broad to treat as the same bug." + "reason": "Both are loading regressions, but they affect different models and have different concrete failure points." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Unrelated: Liger Kernel application during model_init vs a DSA indexer activation/detail issue." + "reason": "Liger Kernel not applied via `model_init` and a missing ReLU in DSA indexer are unrelated." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "Different model-specific numerical/attribute issues in different components." + "reason": "FP8 accuracy issue and missing processor method causing multimodal token counting failure are distinct." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "Unrelated: network requests despite local_files_only vs a placeholder/non-descriptive issue." + "reason": "Offline API-call bug and an unrelated issue titled `racoon` are not the same." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "Different subsystems and symptoms: MLFlow job status reporting vs tensor parallel training." + "reason": "MLflow reporting and tensor-parallel training bug are unrelated." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Different code paths: compiled Python file handling vs PretrainedConfig type checking." + "reason": "Compiled-file loading errors and `PretrainedConfig` type checking are different problems." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "Both mention FP8/moe, but one is about saving pretrained models and the other about inference support." + "reason": "Save-pretrained FP8 MoE support and inference support for Qwen3-VL/Qwen3.5 FP8 are not the same concrete bug." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Different save/load mechanics: compiled Python file errors vs saving Pipeline objects." + "reason": "Compiled Python-file errors and pipeline save_pretrained are unrelated." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Documentation referencing pipeline() vs an unrelated non-specific issue." + "reason": "Docs referencing removed `pipeline()` and an unrelated `racoon` issue do not match." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Both are loading regressions, but the titles point to different concrete failures: tokenizer loading vs Llama 3.2 vision model loading." + "reason": "Tokenizer loading regression and Llama 3.2 Vision model loading breakage are different model/load paths." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "Unrelated: missing huggingface_hub import vs a broken transformers env command." + "reason": "`is_offline_mode` import error and broken `transformers env` command are unrelated." }, { "left": "issue:33453", "right": "issue:36296", "accept": false, - "reason": "Different components and symptoms: tokenizer loading regression vs tensor parallel training bug." + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." }, { "left": "issue:43576", "right": "issue:43824", "accept": false, - "reason": "Different issues: env command breakage vs missing Qwen2_5_VL export." + "reason": "Broken env command and Qwen2_5_VL import error are different issues." }, { "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "Different code paths: env command broken vs PretrainedConfig type-checking regression." + "reason": "Broken env command and config type-checking regression are unrelated." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation issue vs import error for layer_type_validation." + "reason": "Docs confusion and an import error are different categories of issue." }, { "left": "issue:41628", "right": "issue:42548", "accept": false, - "reason": "Both are import errors, but they concern different exported symbols and are not clearly the same root cause." + "reason": "Both are import errors, but for different missing symbols; no clear shared root cause." }, { "left": "issue:44961", "right": "issue:45468", "accept": false, - "reason": "Unrelated: placeholder issue vs Gemma-4 audio positional encoding bug." + "reason": "`racoon` and Gemma-4 audio positional encoding are unrelated." }, { "left": "issue:38617", "right": "issue:43576", "accept": false, - "reason": "Different failures: missing configuration_utils symbol vs broken env command." + "reason": "Different failures: missing import vs broken CLI command." }, { "left": "issue:43673", "right": "issue:44492", "accept": false, - "reason": "Different cache-related problems: missing GenerationMixin cache in chunked_prefill vs a typo in cache strategies." + "reason": "Missing generation cache in chunked prefill and a cache-strategy typo are not the same bug." }, { "left": "issue:43576", "right": "issue:44938", "accept": false, - "reason": "Different problems: env command breakage vs Python 3.14 import/load failure." + "reason": "Broken env command and Python 3.14 load failure are unrelated." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Unrelated: scheduler kwargs handling vs placeholder issue." + "reason": "Scheduler kwargs bug and unrelated `racoon` issue do not match." }, { "left": "issue:44485", "right": "issue:44961", "accept": false, - "reason": "Unrelated: GLM-5 RoPE implementation vs placeholder issue." + "reason": "GLM-5 RoPE implementation and unrelated `racoon` issue are not the same." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor parallel training bug vs documentation mismatch for TextClassificationPipeline." + "reason": "Tensor-parallel training bug and a docs mismatch about `return_all_scores` are unrelated." }, { "left": "issue:41628", "right": "issue:44355", "accept": false, - "reason": "Different issues: missing AutoImageProcessor export vs compiled Python file errors." + "reason": "Importing `AutoImageProcessor` and errors running compiled Python files are different failures." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Different problems: tensor parallel training vs BeitImageProcessorFast reduce_labels bug." + "reason": "Tensor-parallel training bug and BeitImageProcessorFast label reduction bug are unrelated." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "General model crashes under chat vs a broad complaint about v5 breaking too many models; not the same concrete bug." + "reason": "A Qwen3.5 chat crash and a broad meta complaint that v5 breaks many models are not the same concrete bug." }, { "left": "issue:44261", "right": "issue:44360", "accept": false, - "reason": "Different bugs: missing rms_norm_eps precision discussion vs DSA indexer missing ReLU." - }, - { - "left": "issue:44623", - "right": "issue:45230", - "accept": false, - "reason": "Processor.save_pretrained missing files vs an unspecified bug report." - }, - { - "left": "issue:44273", - "right": "issue:45542", - "accept": false, - "reason": "Lazy loading malfunction vs a TensorFlow/tensorboard backend initialization issue." - }, - { - "left": "issue:44273", - "right": "issue:45003", - "accept": false, - "reason": "Different bugs: lazy loading vs unsafe sys.modules access in modeling_utils." + "reason": "MLA precision issue and missing ReLU in the DSA indexer are unrelated." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet, and the soft-edge verdicts are appropriately conservative. The only accepted duplicate, issue:45125 vs issue:45478, is stated as likely rather than certain, which fits the evidence available from 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 }, @@ -14438,12 +14468,10 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:31795", "issue:33453", - "issue:34689", - "issue:37428", "issue:41669", "issue:42371", "issue:42890", @@ -14454,7 +14482,6 @@ "issue:43572", "issue:43576", "issue:43673", - "issue:43704", "issue:43827", "issue:43874", "issue:43976", @@ -14471,12 +14498,14 @@ "issue:44485", "issue:44492", "issue:44556", + "issue:44623", "issue:44655", "issue:44704", "issue:44829", "issue:44861", "issue:44908", "issue:44945", + "issue:45003", "issue:45071", "issue:45092", "issue:45125", @@ -14486,22 +14515,26 @@ "issue:45341", "issue:45468", "issue:45478", + "issue:45542", "issue:45753", "issue:45850" ], "soft_pairs": [ + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:44273|issue:45003", "issue:44393|issue:45753", "issue:43576|issue:44556", - "issue:44393|issue:45071", "issue:44038|issue:45125", + "issue:44393|issue:45071", "issue:43525|issue:45850", "issue:41669|issue:43673", "issue:44556|issue:45092", "issue:44492|issue:45850", "issue:43572|issue:45850", "issue:42371|issue:44492", - "issue:42890|issue:44908", "issue:44704|issue:44908", + "issue:42890|issue:44908", "issue:45278|issue:45850", "issue:43408|issue:44315", "issue:44246|issue:44273", @@ -14517,8 +14550,8 @@ "issue:43874|issue:45850", "issue:44393|issue:45478", "issue:44077|issue:44861", - "issue:44315|issue:44829", "issue:43827|issue:44908", + "issue:44315|issue:44829", "issue:31795|issue:33453", "issue:41669|issue:44908", "issue:43576|issue:44273", @@ -14527,283 +14560,282 @@ "issue:45230|issue:45310", "issue:44273|issue:44908", "issue:43519|issue:44485", - "issue:43519|issue:44908", - "issue:31795|issue:34689", - "issue:41669|issue:43704", - "issue:31795|issue:37428", - "issue:44315|issue:45092", - "issue:44485|issue:45468", - "issue:43704|issue:44485", - "issue:42371|issue:43704" + "issue:43519|issue:44908" ], - "prepared_review_unit_hash": "4dee5a1f01b1ab8aa54eff347dd3d84a1bc5da98f12b51c7526e1a4e713ff977", + "prepared_review_unit_hash": "1490750601a2ce5345f60a94f8978aa2397bdfb6de30fa98db27286718d26c20", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 45, - "serialized_chars": 40581, - "estimated_input_tokens": 10146, - "estimated_eval_tokens": 20548 + "soft_pair_count": 41, + "serialized_chars": 39314, + "estimated_input_tokens": 9829, + "estimated_eval_tokens": 19914 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is dominated by broad v5-era regression reports, but the soft-edge pairs mostly point to different model-specific or subsystem-specific bugs rather than true duplicates. No soft-edge pair is a safe merge candidate.", - "confidence": 0.62, - "canonical_issue_reason": "issue:45278 is the most representative anchor: it describes a concrete upgrade regression (\u201cmany import errors after update from 4.57.0 to 5.5.0\u201d) and fits the cluster\u2019s broad v5 breakage theme better than the more generic complaint issues.", + "summary": "This cluster is mostly a grab bag of Transformers v5 regression reports across import/loading, config, cache, and model-specific issues. The shared theme is broad upgrade breakage, but the soft pairs usually describe different concrete failure paths, so I would not merge them as duplicates.", + "confidence": 0.83, + "canonical_issue_reason": "issue:45278 is the best umbrella issue here: it captures the broad v5 upgrade/import-breakage pattern that recurs across several reports, even though the set is not a true duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best single issue to keep as the cluster representative because it is specific enough to be actionable while still covering the common version-regression theme seen across the set.", + "best_issue_reason": "issue:45278 is the most representative user-facing report of the shared v5 regression theme and is broad enough to anchor triage without overfitting to one model or code path.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "One is a specific processor.save_pretrained bug; the other is an unspecific placeholder issue. No clear same code path." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading failures and undefined tf backend errors are different problems." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading behavior does not match modeling_utils sys.modules access." + }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Same model family, but different failures: 2D bbox hallucination/error vs an infinite loop on a specific image." + "reason": "Both are Qwen3-VL/Qwen3.5-related, but one is 2D box output hallucination and the other is an infinite loop on a specific image." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Both are v5-related breakages, but one is the `transformers env` CLI and the other is checkpoint reload compatibility; different code paths." + "reason": "Generic transformers env command breakage is not the same as checkpoint reload incompatibility after upgrading." }, { - "left": "issue:44393", - "right": "issue:45071", + "left": "issue:44038", + "right": "issue:45125", "accept": false, - "reason": "Qwen3-VL output bug and PretrainedConfig type-checking regression are unrelated issues." + "reason": "Qwen3-VL-Moe bug and missing tensor-parallel plan are different model-level failures." }, { - "left": "issue:44038", - "right": "issue:45125", + "left": "issue:44393", + "right": "issue:45071", "accept": false, - "reason": "Both involve Qwen3-VL/MoE naming, but one is a from_pretrained failure and the other is a missing tensor-parallel plan; not the same bug." + "reason": "A model output quality bug is unrelated to PretrainedConfig type checking breakage." }, { "left": "issue:43525", "right": "issue:45850", "accept": false, - "reason": "A missing `pad_token_id` attribute in Llama4Config is a specific config bug, not the generic \u201cmany models break\u201d complaint." + "reason": "Specific Llama4Config pad_token_id error is not the same as a broad complaint that many models break." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-star cleanup/performance and missing GenerationMixin cache during chunked prefill are different underlying problems." + "reason": "Import-star slowdown and missing GenerationMixin cache in chunked prefill are different issues." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both are checkpoint-loading regressions after v5, but one is general reload failure and the other is InternVL2 remote-code/meta-init incompatibility; not clearly the same defect." + "reason": "Checkpoint reload after upgrade and old remote-code checkpoint/meta-init incompatibility are related only at a very broad version-upgrade level." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "A cache-strategy typo is not the same as a broad v5 breakage report." + "reason": "Cache-strategy typo is not the same as a generic v5 breakage report." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "StableLmConfig missing `pad_token_idx` is a specific attribute regression, not the generic v5 complaint." + "reason": "Missing pad_token_idx in StableLmConfig is a specific config regression, not a general 'many models break' report." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "TF32 API guidance and a cache-strategy typo do not describe the same issue." + "reason": "TF32 settings and cache-strategy typo are unrelated." }, { - "left": "issue:42890", + "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "A flaky integration test due to missing seeds is unrelated to an inverse_sqrt scheduler kwargs bug." + "reason": "AutoProcessor kwargs forwarding and inverse_sqrt scheduler kwargs are different APIs and failures." }, { - "left": "issue:44704", + "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "AutoProcessor kwargs forwarding and scheduler kwargs handling are separate code paths." + "reason": "Test flakiness from missing set_seed is unrelated to scheduler kwargs handling." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "Both are broad v5 regression reports, but one is about import errors after upgrade and the other is a vague general complaint; too imprecise to treat as duplicates." + "reason": "Both are broad v5 complaint titles, but they do not identify the same concrete bug or code path." }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "A model-type mismatch warning and Liger Kernel application with `model_init` are unrelated." + "reason": "sam3_tracker type warning and Liger Kernel not applied with model_init are unrelated." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Import slowness and lazy-loading malfunction are related in theme, but not clearly the same concrete bug." + "reason": "Import taking long sometimes is not the same as lazy loading not working properly." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python-version compatibility and Qwen3-VL bounding-box output errors are unrelated." + "reason": "Python version compatibility and Qwen3-VL box output issues are unrelated." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Flash Attention 2 support for NemotronH and Qwen3-VL hallucination are different model bugs." + "reason": "Flash Attention 2 support missing and Qwen3-VL 2D box hallucination are different model concerns." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "CLI env behavior and scheduler-kwargs forwarding do not share an underlying bug." + "reason": "Broken env command and scheduler kwargs ignore are different subsystems." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer save metadata mismatch is a specific serialization bug, while the other item is too vague to establish sameness." + "reason": "Tokenizer save_pretrained metadata mismatch is not the same as a vague placeholder bug report." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs being ignored is unrelated to PretrainedConfig type checking." + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are unrelated." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "position_ids buffer handling and an unspecific bug report are not the same issue." + "reason": "position_ids buffer access error does not match a generic bug placeholder." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Import-star cleanup/perf and a missing `HybridCache` import are different import-related problems." + "reason": "Import-star slowdown and missing HybridCache import are distinct import-time issues." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Import-time performance cleanup and a testing_utils typo/bug are unrelated." + "reason": "Package import slowdown and a testing_utils typo are not the same bug." }, { "left": "issue:44492", "right": "issue:44945", "accept": false, - "reason": "Cache-strategy typo and incorrect pipeline-parallel LLM output are different bugs." + "reason": "Cache-strategy typo and incorrect output under pipeline parallelism are unrelated." }, { "left": "issue:43874", "right": "issue:45850", "accept": false, - "reason": "A missing image-patch helper in GLM46V is a specific multimodal bug, not a general v5 breakage report." + "reason": "Missing multimodal token helper in GLM46V is a specific AttributeError, not a broad version-wide breakage report." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Same model family and same broad area, but one is bbox output behavior and the other is a from_pretrained error; not the same defect." + "reason": "Two Qwen3.5/Qwen3-VL reports, but one is box-output hallucination and the other is from_pretrained failure; different code paths." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Optional post_init enforcement and `_get_tied_weight_keys` crashing on a list are distinct code issues." + "reason": "post_init policy enforcement and tied-weight-key AttributeError are different model-internal validation bugs." }, { - "left": "issue:44315", - "right": "issue:44829", + "left": "issue:43827", + "right": "issue:44908", "accept": false, - "reason": "Liger Kernel application and flash_attention_3 training degeneration are unrelated." + "reason": "Docs still referencing pipeline() and scheduler kwargs are unrelated." }, { - "left": "issue:43827", - "right": "issue:44908", + "left": "issue:44315", + "right": "issue:44829", "accept": false, - "reason": "Docs still referencing pipeline() and a scheduler kwargs bug are not duplicates." + "reason": "Liger Kernel application with model_init and flash_attention_3 training degeneration are different problems." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Documentation confusion about forward args and tokenizer-loading regression are unrelated." + "reason": "Documentation confusion in model.forward and tokenizer loading regression are not the same underlying issue." }, { "left": "issue:41669", "right": "issue:44908", "accept": false, - "reason": "Import-star cleanup/performance and inverse_sqrt scheduler kwargs are different issues." - }, - { - "left": "issue:43519", - "right": "issue:44485", - "accept": false, - "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are separate model-specific bugs." + "reason": "Import slowdown and inverse_sqrt scheduler kwargs are unrelated." }, { - "left": "issue:43519", - "right": "issue:44908", + "left": "issue:43576", + "right": "issue:44273", "accept": false, - "reason": "Timestamp calculation and scheduler kwargs handling are unrelated." + "reason": "Broken env command and lazy loading failure are different areas." }, { - "left": "issue:45230", - "right": "issue:45310", + "left": "issue:44655", + "right": "issue:44861", "accept": false, - "reason": "A generic bug report cannot be safely merged with a specific Qwen3.5-Moe from_pretrained error report." + "reason": "Pipeline save_pretrained failure and tied-weight key handling are separate save/load bugs." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "DSA ReLU discussion and Gemma-4 audio positional encoding are unrelated." + "reason": "DSA indexer discussion and Gemma-4 audio positional encoding are unrelated." }, { "left": "issue:45230", - "right": "issue:45341", + "right": "issue:45310", "accept": false, - "reason": "The generic placeholder report does not establish the same bug as the testing_utils issue." + "reason": "Two generic Qwen3.5/Qwen3 Moe reports, but the former is unspecific while the latter is a concrete from_pretrained error." }, { "left": "issue:44273", "right": "issue:44908", "accept": false, - "reason": "Lazy loading malfunction and inverse_sqrt scheduler kwargs are different subsystems." + "reason": "Lazy loading and scheduler kwargs are different code paths." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Different model families and different failure modes; not duplicates." - }, - { - "left": "issue:43704", - "right": "issue:44485", - "accept": false, - "reason": "VRAM leak in dataloader threads and GLM-5 RoPE implementation are unrelated." + "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are distinct model-specific bugs." }, { - "left": "issue:42371", - "right": "issue:43704", + "left": "issue:43519", + "right": "issue:44908", "accept": false, - "reason": "TF32 API behavior and a Qwen3ForCausalLM VRAM leak are unrelated." + "reason": "Timestamp calculation in a processor and scheduler kwargs handling are unrelated." } ] }, @@ -14825,14 +14857,18 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-15354-395", + "cluster_id": "cluster-15354-396", "nodes": [ "issue:30333", "issue:31515", "issue:31795", "issue:33453", + "issue:34689", "issue:36296", + "issue:37428", "issue:38617", + "issue:41669", + "issue:42371", "issue:42913", "issue:43066", "issue:43298", @@ -14846,11 +14882,14 @@ "issue:44230", "issue:44261", "issue:44263", + "issue:44315", + "issue:44485", "issue:44492", "issue:44623", "issue:44861", "issue:44908", "issue:44998", + "issue:45092", "issue:45290", "issue:45310", "issue:45341", @@ -14858,6 +14897,13 @@ "issue:45850" ], "soft_pairs": [ + "issue:31795|issue:34689", + "issue:41669|issue:43704", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:42371|issue:43704", "issue:43502|issue:43519", "issue:43519|issue:44623", "issue:43519|issue:43704", @@ -14883,178 +14929,220 @@ "issue:31515|issue:33453", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "632739abd6585a0ccaac3950f0f02e9286b3097ae735c00587335086f05cd8fe", + "prepared_review_unit_hash": "fccaac278417efc62b8c94622e76222ee5da07b4e60813450adaebce4c4ee012", "component_budget": { - "node_count": 395, - "item_count": 395, - "soft_pair_count": 1484, - "serialized_chars": 764571, - "estimated_input_tokens": 191143, - "estimated_eval_tokens": 382542 + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 }, "budget": { - "node_count": 29, - "item_count": 29, - "soft_pair_count": 24, - "serialized_chars": 23391, - "estimated_input_tokens": 5848, - "estimated_eval_tokens": 11952 + "node_count": 36, + "item_count": 36, + "soft_pair_count": 31, + "serialized_chars": 29500, + "estimated_input_tokens": 7375, + "estimated_eval_tokens": 15006 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly noisy and spans unrelated bugs across loading, tokenizers, configs, processors, and assorted regressions. The only somewhat coherent theme is a small tokenizer/v5 regression subgroup, but none of the proposed soft pairs are safe duplicate merges.", - "confidence": 0.37, - "canonical_issue_reason": "issue:42913 is the clearest broad regression report in the tokenizer/v5 subgroup and is more representative than the more specific follow-up-style reports.", + "summary": "The cluster is heterogeneous: a few issues are about Transformers v5/model-loading regressions, but most are unrelated runtime, tokenizer, training, or documentation bugs. None of the soft pairs look like the same concrete bug/change closely enough to merge as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "42913 is the best single representative issue for the only coherent mini-theme in this noisy cluster; the rest are too heterogeneous to anchor the cluster.", + "best_issue_reason": "issue:45850 is the broadest umbrella report about widespread breakage since v5, so it best represents the cluster theme, though it is too general to be a true duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Docs confusion about input_ids/past_key_values is not the same as a tokenizer/model loading regression." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import * performance cleanup and a VRAM leak in multithreaded causal LM use are different problems." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Documentation ambiguity is unrelated to the flash-attention import error." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger-kernel application with model_init and v5 meta-init incompatibility for old InternVL2 checkpoints are different code paths." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in multi-threaded inference and RoPE implementation concerns are not the same bug." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 API guidance is unrelated to the VRAM leak issue." + }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "Different bugs: unwanted remote API calls with local_files_only versus a Qwen3VL timestamp calculation error." + "reason": "Unexpected network/API requests with local_files_only=True is different from a Qwen3VL timestamp calculation bug." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Different code paths: timestamp computation in a processor versus missing files from processor.save_pretrained()." + "reason": "Timestamp computation in a processor and missing saved files are separate processor bugs." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Unrelated symptoms: processor timestamp math versus VRAM leak in Qwen3ForCausalLM multithreaded use." + "reason": "Qwen3VL timestamp math is unrelated to the multi-thread VRAM leak." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "Different models and failures: torch.split return handling in GlmMoeDsaIndexer versus Gemma-4 audio positional encoding." + "reason": "torch.split return handling in an indexer is unrelated to Gemma-4 audio positional encoding." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "Different bug classes: CPU offload device mismatch in bark-small CI versus Gemma-4 audio positional encoding." + "reason": "CPU offload device mismatch and audio positional encoding are different failure modes." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "Related only at a very high level; these are distinct model-specific precision/config issues." + "reason": "Missing rms_norm_eps causing precision error is unrelated to Gemma-4 audio positional encoding." }, { "left": "issue:43704", "right": "issue:45341", "accept": false, - "reason": "Different bugs and subsystems: VRAM leak under multithreaded dataloaders versus a testing_utils issue." + "reason": "A runtime VRAM leak and a testing_utils bug are not the same underlying issue." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both are tokenizer/v5 regressions, but the descriptions point to different concrete failures and there's not enough evidence they are the same bug." + "reason": "Both concern tokenizer changes in v5, but one is a broad behavior difference while the other is a specific wrong decoder type bug." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "No duplicate relationship: inverse_sqrt scheduler kwargs bug versus an unrelated issue titled 'Unemployment'." + "reason": "Scheduler kwargs being ignored is unrelated to the unrelated 'Unemployment' issue." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Different failures: tied-weights key handling versus apply_chat_template crashing on tool-call assistant messages." + "reason": "Tied-weight-key lookup crash and apply_chat_template tool-call crash affect different subsystems and code paths." }, { "left": "issue:44492", "right": "issue:44998", "accept": false, - "reason": "A typo in cache strategy naming is unrelated to the unrelated 'Unemployment' issue." + "reason": "Cache-strategy typo is unrelated to the unrelated 'Unemployment' issue." }, { "left": "issue:44998", "right": "issue:45850", "accept": false, - "reason": "'Unemployment' is not the same underlying bug as a broad '5.0 breaks too many models' report." + "reason": "'Unemployment' is unrelated to the broad v5 model-breakage report." }, { "left": "issue:43618", "right": "issue:44998", "accept": false, - "reason": "CLIPOutput attentions assignment regression is unrelated to the generic 'Unemployment' issue." + "reason": "CLIPOutput attentions regression is unrelated to the unrelated 'Unemployment' issue." }, { "left": "issue:44998", "right": "issue:45341", "accept": false, - "reason": "No shared bug: 'Unemployment' versus a small testing_utils bug." + "reason": "'Unemployment' is unrelated to the testing_utils bug." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Different root causes: missing pad_token_id on Llama4Config versus AttributeError from _tied_weights_keys being a list." + "reason": "Missing pad_token_id in Llama4Config and tied-weight-key crashes are different config/code-path bugs." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "Different config issues: StableLm pad_token_idx regression versus tied-weights key handling." + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to the tied-weight-key AttributeError." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Checkpoint loading speed is unrelated to the layer_type_validation import error." + "reason": "Slow from_pretrained checkpoint loading and an ImportError for layer_type_validation are unrelated." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 inference support for qwen3-vl/qwen3.5 moe is unrelated to missing save_pretrained files." + "reason": "FP8 inference support and missing processor save files are different feature/bug reports." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow training-job reporting failure and slow from_pretrained checkpoint loading are different issues." + "reason": "MLFlow job-status reporting after failed training and slow checkpoint loading are unrelated." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Slow checkpoint loading is not the same bug as tensor-parallel training failure." + "reason": "Slow checkpoint loading and a tensor-parallel training bug are different issues." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Checkpoint loading performance and confusing forward docs are unrelated." + "reason": "Checkpoint loading performance and model.forward documentation confusion are not duplicates." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "Both mention Qwen3.5/MoE-style regressions, but one is FP8 inference support and the other is a from_pretrained error; not the same concrete bug." + "reason": "FP8 inference support and a Qwen3.5 MoE from_pretrained error are different concrete bugs." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Slow checkpoint loading and tokenizer loading regression are different failure modes." + "reason": "Slow checkpoint loading is not the same as a tokenizer-loading regression." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching support for audio models is a different feature gap than FP8 qwen3-vl/qwen3.5 inference support." + "reason": "Continuous batching not supporting audio models and FP8 inference support are unrelated." } ] }, @@ -15084,7 +15172,7 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "cbe7c5ce88ed257c8cd416fe06597acfed64b53c3af7112b126b31f8fb6d4521", + "prepared_review_unit_hash": "a489d63ab653c2cac4a69a33ed564d7aa619e8268d41478cba7fe1bc400c1192", "component_budget": { "node_count": 2, "item_count": 2, @@ -15106,18 +15194,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are not duplicates: one requests Flash Attention 2 support for more architectures, while the other requests GGUF support for more architectures. They concern different features and different code paths, so the soft match should be rejected.", + "summary": "These are not duplicates: one requests Flash Attention 2 support for more architectures, the other requests GGUF support for more architectures. They are related only at the broad level of model-format/attention support, but they describe different changes and code paths.", "confidence": 0.98, - "canonical_issue_reason": "If a single representative is needed, issue 26350 is the better canonical issue because it is older and has substantially more discussion activity; however, it is not the same request as 33260.", + "canonical_issue_reason": "No canonical issue: the two issues target different features and underlying implementation work.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 26350 is the stronger overall cluster representative due to higher engagement and earlier creation, but it should not be treated as a duplicate of issue 33260.", + "best_issue_reason": "Neither issue is a clear representative of the other; if one must be chosen as the cluster anchor, issue #26350 is slightly older and has more discussion, but it is not a duplicate of #33260.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Different feature requests: Flash Attention 2 architecture support vs GGUF architecture support. They do not describe the same underlying bug or change." + "reason": "Different feature requests (Flash Attention 2 vs GGUF support) with no evidence of the same bug or change; not the same underlying work." } ] }, @@ -15154,7 +15242,7 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "921fa6141fa1fc1bee104dc3719f77fe2fafd3847e490b6a8140cdb637ec39f9", + "prepared_review_unit_hash": "f97fca90c2f02dd169dd2df3e67154172cac3fff0ebe8095a61c01d959695273", "component_budget": { "node_count": 4, "item_count": 4, @@ -15176,48 +15264,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All four items are the same issue template family for translating docs, but they do not appear to be the same underlying translation request. One is concrete (Turkish); the others are placeholder/template variants that likely correspond to different language tasks. No PRs are present.", - "confidence": 0.89, - "canonical_issue_reason": "issue:27088 is the only concrete request with an actual language code/title ([i18n-TR] Translating docs to Turkish); the others are generic placeholder titles and are less informative as a representative issue.", + "summary": "These are near-identical i18n translation request issues, but only one is specific to Turkish; the others are generic placeholder translation tickets and should not be merged as duplicates without matching language context.", + "confidence": 0.57, + "canonical_issue_reason": "issue:27088 is the only concrete, language-specific ticket (Turkish) and is the most actionable representative of the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:27088 is the best representative because it identifies a specific target language and looks like a real actionable translation request rather than a template stub.", + "best_issue_reason": "issue:27088 best captures the actual user-facing request; the other issues look like templated placeholders rather than a distinct, identifiable translation task.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Same translation-template family, but no evidence they target the same language or change; likely separate doc-translation requests." + "reason": "Same broad translation template, but the language context is different/unspecified; not enough to treat as the same underlying issue." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "The concrete Turkish request is not the same underlying issue as a generic placeholder translation request." + "reason": "Both are translation requests, but one is specifically Turkish and the other is a generic placeholder; likely separate tickets." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "These look like different language-specific translation issues, not duplicates of one concrete bug/change." + "reason": "The titles are similar, but the generic placeholder issue does not clearly refer to the same language or exact task as Turkish docs translation." }, { "left": "issue:43834", "right": "issue:44370", "accept": false, - "reason": "Both are placeholder translation issues, but there is no sign they refer to the same language or work item." + "reason": "These look like repeated template issues, but there is no evidence they target the same language or identical change." }, { "left": "issue:43834", "right": "issue:44365", "accept": false, - "reason": "Highly similar template text alone is insufficient; they likely represent separate localization tasks." + "reason": "Highly similar wording alone is not enough; the placeholder titles suggest separate translation requests rather than duplicates." }, { "left": "issue:44365", "right": "issue:44370", "accept": false, - "reason": "Same generic i18n template, but not enough evidence of the same underlying request." + "reason": "No concrete evidence that these two placeholder issues are the same language/docs translation request." } ] }, @@ -15294,256 +15382,244 @@ "issue:37015|issue:45027", "issue:43837|issue:45177" ], - "prepared_review_unit_hash": "5d2932690eeecec36024c072820e4442488e6d417b33c4e8a000b2cd16f7f0a7", + "prepared_review_unit_hash": "0e67f930024631b32b23df643746a0f333d39d0e599dd1b616030c40cd58f7e0", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20710, - "estimated_input_tokens": 5178, - "estimated_eval_tokens": 10612 + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 }, "budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20710, - "estimated_input_tokens": 5178, - "estimated_eval_tokens": 10612 + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are thematically similar model-request issues, but they describe distinct models, modalities, and code paths. No pair looks like a true duplicate; the cluster is better treated as related requests rather than one underlying issue.", - "confidence": 0.96, - "canonical_issue_reason": "No single canonical duplicate stands out because each issue targets a different model or architecture request. If forced to pick the broadest umbrella, issue:42738 is the most general, but it does not actually subsume the others.", + "summary": "These are not duplicates; they are separate model-request issues across different models, architectures, and modalities. The similarity is mostly generic 'add support' wording.", + "confidence": 0.98, + "canonical_issue_reason": "No clear canonical duplicate exists because the cluster spans many distinct model requests rather than one underlying bug/change.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42738 is the broadest and most umbrella-like topic in the set ('BERT-like models with RoPE'), so it is the closest thing to a representative issue, though still not a true duplicate target for the rest.", + "best_issue_reason": "issue:43671 is the closest hub among the Qwen3 speech-related requests, but it is still not a good duplicate canonical for the heterogeneous cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "EuroBert and DEIMv2 are different model requests with different architectures and scopes." + "reason": "EuroBert config vs DEIMv2; only the generic 'add model' intent matches." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert model config request and Qwen3-TTS support are unrelated model families and tasks." + "reason": "EuroBert config vs Qwen3-TTS support; different model and modality." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "EuroBert and RF-DETR are different models; no shared underlying bug/change." + "reason": "EuroBert vs RF-DETR are unrelated model additions." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are separate model additions, not the same request." + "reason": "RF-DETR and DEIMv2 are different vision models, not the same change." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "RF-DETR is a detection model, while LFM2.5 Audio 1.5B is an audio model; different code paths." + "reason": "RF-DETR is a detection model; LFM2.5 Audio is an audio model." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "RF-DETR and the weight-sparse transformer request concern different architectures." + "reason": "RF-DETR vs weight-sparse transformer: different code paths and model families." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR and Qwen3-ASR are distinct model support requests." + "reason": "RF-DETR vs Qwen3-ASR; unrelated model requests." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR and Qwen3-TTS are different modalities and implementations." + "reason": "RF-DETR vs Qwen3-TTS; unrelated model and modality." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT and Qwen3-ASR are unrelated models and not the same underlying change." + "reason": "NeoBERT vs Qwen3-ASR are different model integrations." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT support and the OpenAI weight-sparse transformer request target different architectures." + "reason": "NeoBERT and the sparse transformer request are distinct model changes." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT is a text model request; LFM2.5 Audio 1.5B is an audio model request." + "reason": "NeoBERT vs LFM2.5 Audio; unrelated requests." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are separate model requests with no concrete overlap." + "reason": "RF-DETR and NeoBERT are different model requests." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are different model additions, not duplicates." + "reason": "NeoBERT vs ModernVBERT; separate model additions." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture support and Qwen3-ASR support are different model/task requests." + "reason": "MiniCPM3 architecture vs Qwen3-ASR; different model and modality." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 and the weight-sparse transformer request are distinct architecture additions." + "reason": "MiniCPM3 vs sparse transformer; not the same underlying change." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 and ModernVBERT are different models; similarity is only thematic." + "reason": "MiniCPM3 vs ModernVBERT; distinct model requests." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral TTS are separate model requests for different modalities." + "reason": "MiniCPM3 vs Voxtral TTS; different model family and task." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 and Qwen3-TTS are unrelated model support requests." + "reason": "DEIMv2 vs Qwen3-TTS; unrelated model additions." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT models and Qwen3-ASR are different models/tasks, not the same bug/change." + "reason": "ModernVBERT models vs Qwen3-ASR; different families." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT and Qwen3-TTS are separate requests with different code paths." + "reason": "ModernVBERT vs Qwen3-TTS; not the same change." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT and BERT-like models with RoPE overlap only loosely; they are not the same concrete request." + "reason": "ModernVBERT request vs general BERT-like RoPE proposal; too broad to be duplicates." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "BERT-like models with RoPE and Voxtral TTS support are unrelated model families and tasks." + "reason": "General BERT-like RoPE proposal vs Voxtral TTS support; different scope and model." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are related by prefix but are different tasks and implementations." + "reason": "Both are Qwen3 requests, but TTS and ASR are different concrete capabilities/code paths." }, { "left": "issue:43671", - "right": "issue:43909", + "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS support and LFM2.5 Audio 1.5B support are different audio-model requests." + "reason": "Qwen3-TTS vs Voxtral TTS; different model integrations." }, { "left": "issue:43671", - "right": "issue:44121", + "right": "issue:45177", "accept": false, - "reason": "Qwen3-TTS and the weight-sparse transformer request are unrelated changes." + "reason": "Qwen3-TTS vs DeepSeek-OCR2; unrelated." }, { "left": "issue:43671", - "right": "issue:45027", + "right": "issue:44121", "accept": false, - "reason": "Qwen3-TTS and Voxtral TTS are both audio/text models, but they are different model-specific additions." + "reason": "Qwen3-TTS vs sparse transformer; different model and implementation." }, { "left": "issue:43671", - "right": "issue:45177", - "accept": false, - "reason": "Qwen3-TTS and DeepSeek-OCR2 are different model requests with different code paths." - }, - { - "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are distinct audio-model support requests." - }, - { - "left": "issue:43837", - "right": "issue:44121", - "accept": false, - "reason": "Qwen3-ASR and the weight-sparse transformer request are not the same underlying change." + "reason": "Qwen3-TTS vs LFM2.5 Audio; different audio model requests." }, { "left": "issue:43837", - "right": "issue:45027", + "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different speech-model tasks." + "reason": "Qwen3-ASR vs LFM2.5 Audio; distinct speech/audio models." }, { "left": "issue:43837", - "right": "issue:45177", + "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are separate model additions." + "reason": "Qwen3-ASR vs EUPE; unrelated model requests." }, { "left": "issue:43837", - "right": "issue:45322", + "right": "issue:44121", "accept": false, - "reason": "Qwen3-ASR and EUPE are unrelated model requests." + "reason": "Qwen3-ASR vs sparse transformer; different change." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "LFM2.5 Audio 1.5B and SAM3-LiteText are different model families and modalities." + "reason": "LFM2.5 Audio vs SAM3-LiteText; different families and modalities." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "OpenAI weight-sparse transformer and EUPE are distinct architecture requests, not one fix." + "reason": "Sparse transformer vs EUPE; unrelated." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different model support tasks." + "reason": "Qwen3-ASR vs Voxtral TTS; different model integrations." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated requests." + "reason": "NeoBERT vs Voxtral TTS; unrelated model requests." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model additions." + "reason": "Qwen3-ASR vs DeepSeek-OCR2; different modalities and code paths." } ] }, @@ -15584,82 +15660,82 @@ "issue:43668|issue:44031", "issue:43668|issue:43813" ], - "prepared_review_unit_hash": "a7f91a21d26aa513f6025d4bdd36f8b8dc0a18ffd65192495c666dd321fca80a", + "prepared_review_unit_hash": "94c8ad2dfe9f4ad52670dd2ae5ed717236f23c9a71b0f044f50929b36b47fff0", "component_budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6287, - "estimated_input_tokens": 1572, - "estimated_eval_tokens": 3400 + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 }, "budget": { "node_count": 6, "item_count": 6, "soft_pair_count": 8, - "serialized_chars": 6287, - "estimated_input_tokens": 1572, - "estimated_eval_tokens": 3400 + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues are not duplicates; they span unrelated models, config typing, tokenizer warnings, and a loss-argument bug. The soft-similarity links are superficial.", + "summary": "These are unrelated issue reports clustered only by weak textual similarity; they do not appear to describe the same underlying bug or change.", "confidence": 0.98, - "canonical_issue_reason": "No true canonical duplicate exists here. If one issue must represent the cluster, issue 43240 is the most concrete code-path bug report; the others are unrelated and should not be merged into it.", + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43240 is the strongest standalone issue: it describes a specific runtime bug with clear behavior and likely actionable fix. The rest are narrower API/typo/reporting issues or unrelated model problems.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Different components and bug types: Llama4 normalization behavior vs ModernBERT config type hint. No shared code-path problem." + "reason": "Different components and failure modes: Llama4 norm implementation vs ModernBERT config type hint. No shared code path or concrete bug." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Mask2Former ignore_value handling and loss kwargs propagation are distinct bugs in different call sites." + "reason": "Mask2Former ignore_value handling is unrelated to loss kwargs propagation; different models and different defects." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2Former target handling bug vs tokenizer regex warning regression; unrelated subsystems and symptoms." + "reason": "Mask2Former loss-parameter issue is unrelated to tokenizer regex warnings; no same underlying bug." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "Model loss/ignore_value issue is unrelated to a typo in a quantization attribute name." + "reason": "Mask2Former ignore_value bug and a typo in a quantization attribute name are unrelated." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "Unrelated: training target usage in Mask2Former versus a ModernBERT config annotation mistake." + "reason": "Model-specific ignore_value behavior and a ModernBERT config annotation typo are not the same issue." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Loss-function kwargs forwarding bug is not the same as an incorrect type hint in config." + "reason": "Loss kwargs forwarding bug and config type-hint typo affect different subsystems and code paths." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "Config type-hint problem and tokenizer regex warning regression are different issues with no common fix." + "reason": "ModernBERT norm_eps type hint problem is unrelated to tokenizer regex warnings after 4.57.3." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "These are separate small correctness issues in different modules: config typing vs typo in quantization attribute." + "reason": "A config annotation typo does not match a quantization-operation typo; different targets and fixes." } ] }, @@ -15689,7 +15765,7 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "8a36da8cebcc0bf116ddb625130b95e98b4c052502b87012b2e5fdc2e07d8794", + "prepared_review_unit_hash": "e11bf4f0a21561d451af3409dc9fb46a65a6b3995c3e8a323ccfca80089af33e", "component_budget": { "node_count": 2, "item_count": 2, @@ -15711,18 +15787,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are about different topics: one requests block decoding, the other asks for DeepSeek v3.2 support. They are not duplicates or the same underlying bug/change.", - "confidence": 0.97, - "canonical_issue_reason": "No canonical issue: the issues describe unrelated requests, so there is no single shared problem to canonicalize.", + "summary": "The two issues do not appear to describe the same underlying change. One is a vague request around block decoding, while the other is a specific request for DeepSeek v3.2 support.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 43037 is the more concrete and identifiable request; 41084 is too vague to serve as a clear representative.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43037 is the more specific and actionable request; issue 41084 is too terse to serve as a representative cluster issue.", + "best_issue_reason": "43037 is the best issue anchor because it has a specific product/version target, whereas 41084 is underspecified and broader.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different feature requests with no shared underlying bug or implementation change." + "reason": "These look like different feature requests with no explicit linkage: block decoding vs DeepSeek v3.2 support." } ] }, @@ -15752,7 +15828,7 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "22d8a8696d915764b5bdac159d95ff6699880673bc066a0ebe2ad72a9311d10d", + "prepared_review_unit_hash": "114ba5b76567f4f00d390d9ab55b7f4daf53eb6979a8d4f739b058f8c5f3acd9", "component_budget": { "node_count": 2, "item_count": 2, @@ -15774,18 +15850,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These issues are related to Trainer extensibility/custom trainer behavior, but they describe different problems: one is about `remove_unused_column` behavior, the other about FLOPS estimation for custom trainers.", - "confidence": 0.88, - "canonical_issue_reason": "No strong canonical issue: the titles point to separate Trainer edge cases rather than the same bug or feature request.", + "summary": "These two closed issues are both about Trainer custom behavior, but they target different concerns: one is about `remove_unused_column` customizability, the other about FLOPS estimation for custom trainers. They do not look like the same underlying bug.", + "confidence": 0.96, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "If forced to pick one representative issue, #43598 is the broader Trainer customizability request and is slightly more central to the cluster theme.", + "best_issue_reason": "If one issue must be retained as the cleaner representative, #43598 is the more concrete Trainer API/customization concern; #43600 is a separate performance-accounting topic.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "They share the general area of custom trainers, but the underlying concerns differ: column-removal customizability vs FLOPS estimation logic. They do not look like the same bug/change." + "reason": "Different trainer behaviors are being discussed: column pruning vs FLOPS estimation. They share a subsystem but not the same bug or change, so they should not be merged as duplicates." } ] }, @@ -15815,7 +15891,7 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "e8c5eff11a70e1a75a7b86da489d2cd6fdf6db00a13050791bd9e90b074e3b0f", + "prepared_review_unit_hash": "1b4bb1502904aadeaef581fccc2a20753843af5a15dd389226c612a093f5f974", "component_budget": { "node_count": 2, "item_count": 2, @@ -15837,18 +15913,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are related to Qwen/Qwen3.x support, but they request different changes: one is broad model registration for Qwen3-Omni, the other is a specific AutoModelForSequenceClassification mapping for Qwen3.5. They should not be merged as duplicates.", - "confidence": 0.89, - "canonical_issue_reason": "Issue 43684 is the broader, more foundational request about registering Qwen3-Omni in AutoModel/AutoModelForConditionalGeneration, so it is the better canonical issue among the two.", + "summary": "The two issues are both about adding support for Qwen models, but they target different model families and different AutoModel heads, so they are not duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43684 is the best representative issue because it targets core model registration rather than a narrower task-head support request.", + "best_issue_reason": "issue:43684 is the broader, more general request about registering Qwen3-Omni with AutoModel and AutoModelForConditionalGeneration; issue:44405 is a separate, narrower request for AutoModelForSequenceClassification support on Qwen3.5.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different underlying change requests: model registration for Qwen3-Omni vs adding sequence-classification support for Qwen3.5. They touch related model families but not the same code-path or fix." + "reason": "Different underlying feature requests: Qwen3-Omni model registration vs Qwen3.5 sequence-classification support. They share a broad ecosystem theme but not the same code-path change." } ] }, @@ -15885,77 +15961,80 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "c25569be07e74ba8b6bb021c7237314e3b285e0bcd1828193b7280890080084e", + "prepared_review_unit_hash": "ad031eca7391db36422f1274cf316f2dc0fe1606c764a3294bcc691563386432", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4265, - "estimated_input_tokens": 1067, - "estimated_eval_tokens": 2390 + "serialized_chars": 4261, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4265, - "estimated_input_tokens": 1067, - "estimated_eval_tokens": 2390 + "serialized_chars": 4261, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are ultra-low-information issue reports. Three issues share the exact title \"huggingface \" and were opened close together, but there is no body detail or target to confirm they describe the same underlying problem; the \"Fett\" issue looks unrelated from the title alone.", - "confidence": 0.82, - "canonical_issue_reason": "Issue 43845 is the earliest of the three identical-title \"huggingface \" reports, so it is the best placeholder representative if this cluster is treated as duplicate-like.", + "summary": "The three issues titled \"huggingface\" look like near-identical duplicates and likely describe the same report; the \"Fett\" issue appears unrelated. With no substantive body text or linked targets, triage has to rely mostly on the repeated title and close similarity.", + "confidence": 0.74, + "canonical_issue_reason": "Issue #43845 is the earliest of the near-identical \"huggingface\" reports and is as good a representative as any of that duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "43845 is the strongest cluster anchor because it is earliest and shares the exact title with 43846 and 43859; 43835 is title-distinct.", + "best_issue_reason": "#43845 is the best issue candidate because it is the earliest in the cluster and matches the other two \"huggingface\" issues most closely.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Titles are unrelated and there is no body evidence of the same bug." + "reason": "Different titles and no supporting body/target evidence; likely unrelated." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "Titles are unrelated and there is no body evidence of the same bug." + "reason": "Different titles and no supporting body/target evidence; likely unrelated." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "Titles are unrelated and there is no body evidence of the same bug." + "reason": "Different titles and no supporting body/target evidence; likely unrelated." }, { "left": "issue:43845", "right": "issue:43846", - "accept": false, - "reason": "Exact title match is not enough here; the bodies provide no concrete shared bug description." + "accept": true, + "reason": "Same title, close creation time, and no evidence of distinct underlying reports." }, { "left": "issue:43845", "right": "issue:43859", - "accept": false, - "reason": "Exact title match is not enough here; the bodies provide no concrete shared bug description." + "accept": true, + "reason": "Same title and highly similar placeholder-style reports; likely duplicates." }, { "left": "issue:43846", "right": "issue:43859", - "accept": false, - "reason": "Exact title match is not enough here; the bodies provide no concrete shared bug description." + "accept": true, + "reason": "Same title and highly similar placeholder-style reports; likely duplicates." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The conclusions are grounded in the packet: the three \"huggingface\" issues share the same title, have close timestamps, and show strong soft-similarity, while #43835 has a clearly different title and only weak similarity. The verdicts are conservative overall, and the representative choice of the earliest huggingface issue is reasonable." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -15989,88 +16068,88 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "72422d0dfcd5a7bd0a6fb871df5a1eebee266a336dff48d0f45435a112932c16", + "prepared_review_unit_hash": "dc161b0e75081b0c43c6f114de3523cc27a5b030635a82f6461264839369e2ab", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5791, - "estimated_input_tokens": 1448, - "estimated_eval_tokens": 3152 + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5791, - "estimated_input_tokens": 1448, - "estimated_eval_tokens": 3152 + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster looks like unrelated low-signal spam/placeholder issues rather than duplicates of one concrete bug. There is no substantive shared problem statement to consolidate.", - "confidence": 0.93, - "canonical_issue_reason": "No strong canonical issue exists here; the tickets are mostly spam/placeholder titles with no usable body or explicit linkage.", + "summary": "All five issues are low-information or spam-like and do not describe the same concrete bug or change. There is no credible duplicate cluster here; at most they are similarly malformed submissions.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 44371 is a reasonable placeholder canonical because it is the earliest of the near-empty spam-like issues, but it is not meaningfully better than the others.", "canonical_pr_reason": null, - "best_issue_reason": "None of the issues provides enough concrete detail to serve as a reliable representative for a duplicate cluster.", + "best_issue_reason": "44371 is the least-bad representative only by chronology; none of the issues contains enough substance to serve as a true canonical bug report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are placeholder spam titles, but there is no concrete bug report or shared underlying problem to confirm duplication." + "reason": "Same generic spam-like title, but no underlying bug/change is described and there is no evidence they refer to the same report." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Identical spam-style titles are not enough to establish the same underlying issue without any real description." + "reason": "Both are empty spam submissions, but that is not enough to treat them as the same concrete issue." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "One is spam and the other is a generic documentation suggestion; these do not describe the same issue." + "reason": "One is spam-like, the other is a generic documentation suggestion; they are not the same underlying issue." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "The titles are unrelated and there is no evidence they refer to the same bug or change." + "reason": "Completely different titles and no shared technical context; unrelated." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "A documentation enhancement request is not the same as a spam placeholder ticket." + "reason": "Documentation enhancement request versus spam-like post; no shared defect or change." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "Generic documentation feedback and spam placeholder content are different underlying reports." + "reason": "Different intent and no evidence of the same underlying problem." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Although the titles match, the items contain no substantive details to verify they are the same real issue." + "reason": "Identical spam-like titles, but with no substantive content or explicit linkage, they should not be merged as a confirmed duplicate bug/change." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Spam placeholder and quoted-name title are unrelated; no shared bug or change is visible." + "reason": "Unrelated titles and no technical overlap." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "No evidence indicates these refer to the same underlying problem; the titles are unrelated." + "reason": "Unrelated titles and no technical overlap." } ] }, @@ -16100,7 +16179,7 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "732ca3ee77261dedce8b543dfbcbb8419e71792c55d92cbb9fba873b027ecddd", + "prepared_review_unit_hash": "90421f4e2ae5d52e16df810089c106d3f26c372e26cc58b542a5e5236257bdb2", "component_budget": { "node_count": 2, "item_count": 2, @@ -16122,24 +16201,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues have identical titles and very similar body lengths, with no explicit links or targets, so they look like likely duplicates even though the packet does not show the full report bodies. issue:45145 is the better canonical issue because it was created first and has the only inbound reference.", - "confidence": 0.86, - "canonical_issue_reason": "issue:45145 is the earliest of the likely duplicate pair and has the only inbound reference, so it is the best canonical issue.", + "summary": "The two closed issues look very likely to be duplicates: they share the exact same title and a strong soft-similarity signal. However, the packet does not prove their bodies are identical, so the duplication claim should stay cautious. #45145 is the better canonical representative because it already has one inbound reference.", + "confidence": 0.84, + "canonical_issue_reason": "#45145 is the safer canonical issue because it has the same title as #45151 and is the only one with an inbound reference. The evidence supports a likely duplicate pair, but not a claim that the bodies are the same.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45145 is the best overall issue candidate because it appears to be the earlier instance of the likely duplicate report and has slightly stronger inbound evidence.", + "best_issue_reason": "#45145 is the best issue to keep as the representative since it matches #45151 on title, has the only inbound linkage, and there is no stronger evidence favoring #45151.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", "accept": true, - "reason": "Identical titles plus closely similar body lengths make these look like the same underlying issue, but the evidence is limited because the packet does not expose the bodies or any explicit links/targets." + "reason": "Identical titles plus a soft-similarity signal make this look like the same underlying issue, even though the packet does not establish body identity." } ] }, "evaluator_result": { "accept": false, - "feedback": "The duplicate call is a bit too strong for the packet: we only know the titles are identical, body lengths are close, and there are no explicit links/targets. The packet does not show the report bodies, so saying they are the \"exact same report\" or that the content is \"essentially the same\" overstates the evidence. The canonical choice of the earlier issue is grounded, but the soft-edge verdict and summary should be phrased more conservatively." + "feedback": "Reject: the conclusion is too strong for the packet. The issues do have identical titles and a soft-similarity signal, but the packet does not show that their bodies are the same\u2014only similar lengths and a soft_similarity edge. Saying they are duplicates with \u2018same title/body\u2019 and \u2018nearly identical bodies\u2019 overstates the evidence. The inbound reference on #45145 is a reasonable conservative point, but the duplicate/canonical claim should be phrased more cautiously." }, "evaluator_used": true, "retried": true, @@ -16220,7 +16299,7 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "8a94fa9346501088f3aebf95adb27b196dac52057554c27f7307135f4f8da59e", + "prepared_review_unit_hash": "31d19a648781f5bdc2681092bf7eb9473586f8382fd7a83537ed83686fb03105", "component_budget": { "node_count": 2, "item_count": 2, @@ -16242,18 +16321,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are both 4-bit inference bugs, but they describe different failure modes and likely different root causes: one is a Gemma4/audio-module torch.finfo TypeError on uint8 weights, the other is a BitsAndBytesConfig regression where llm_int8_skip_modules removes the default lm_head exclusion and triggers an AssertionError. They should not be deduplicated.", - "confidence": 0.96, - "canonical_issue_reason": "If one issue must represent the cluster, 45674 is the cleaner canonical issue because it isolates a specific BitsAndBytesConfig regression with a concrete trigger and assertion failure. 45672 appears to be a separate Gemma4 audio-module bug.", + "summary": "These are two separate 4-bit inference bugs: one is a Gemma4/audio-module torch.finfo(uint8) TypeError, the other is a BitsAndBytesConfig lm_int8_skip_modules regression that removes the default lm_head exclusion and triggers an AssertionError. They should not be treated as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "45674 is the better global issue candidate: it names the exact configuration path, states the observable failure, and is easier to action. 45672 is also valid, but it is a different bug rather than the same report.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Different bug reports: one concerns torch.finfo on uint8 weights in Gemma4 audio modules, the other concerns llm_int8_skip_modules clearing lm_head exclusion and causing an AssertionError. Same broad 4-bit area, but not the same underlying issue." + "reason": "Different failure modes and code paths: Gemma4 audio-module uint8 handling vs BitsAndBytesConfig skip-module exclusion logic. They share a broad 4-bit inference context but not the same underlying bug or fix." } ] }, @@ -16283,7 +16362,7 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "92e52ef0a4ec2976b03d79bec2c27aeea501b848ec1e75b5009f57c732d65d1d", + "prepared_review_unit_hash": "fe18c5feab7c741564e440293cc674d13e8cf84c0e93c8bce74f0df139811311", "component_budget": { "node_count": 2, "item_count": 2, @@ -16305,18 +16384,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues are just empty titles with different personal names and birth dates; there is no evidence they describe the same bug or request.", - "confidence": 0.99, - "canonical_issue_reason": "Issue 45762 is only the earliest item, but neither issue has enough content to justify a true canonical duplicate choice.", + "summary": "The two issues are just different personal-name/date strings with no shared bug report, code context, or discussion. They do not look like duplicates; this looks more like unrelated/spam entries.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: the titles point to different people and different dates, with no evidence they describe the same underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "45762 is the earliest and therefore the least arbitrary representative, though this does not look like a real duplicate cluster.", + "best_issue_reason": "If one must be selected, issue 45762 is only marginally preferable because it was created first, but it is not a true canonical duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "Titles refer to different people and different dates, with no body or shared context suggesting the same underlying issue." + "reason": "The titles reference different names and birth dates, and there is no shared bug, feature, or code context. They do not appear to describe the same underlying issue." } ] }, @@ -16346,7 +16425,7 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "88a238557d0374e32cd79eca39b5d02676ce8f706767a5e389e3bb4ca7069f2f", + "prepared_review_unit_hash": "88db9dcd1f4a9b091dec6d2a7205f9785010188b05dc0c91d5669cf526304492", "component_budget": { "node_count": 2, "item_count": 2, @@ -16368,18 +16447,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two issues are not duplicates; they are unrelated by title and contain no substantive discussion or shared target.", - "confidence": 0.98, - "canonical_issue_reason": "No canonical issue: the issues reference different names and dates, with no shared bug report or problem statement.", + "summary": "Two closed issues with no body, links, or technical context; they only share a loose naming/date pattern and do not look like the same underlying bug report.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 45764 is not meaningfully distinguishable from 45765 as a duplicate candidate, but if one must be chosen, 45764 is simply the first and no evidence favors either as the canonical report.", "canonical_pr_reason": null, - "best_issue_reason": "Neither issue is a good representative for a cluster because they do not appear to describe the same underlying problem.", + "best_issue_reason": "Neither issue is a strong canonical ticket because neither contains any actionable bug description; 45764 is marginally preferable only by ordering, not by content.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "Different named subjects and dates; no evidence they refer to the same underlying issue." + "reason": "No substantive issue content, explicit linkage, or shared technical subject; the titles are just different personal-name/date strings and do not indicate the same underlying bug." } ] }, @@ -16419,91 +16498,91 @@ "issue:45871|issue:45873", "issue:45872|issue:45873" ], - "prepared_review_unit_hash": "263a4e2826871b8027743cf0c4326eb7e93f887fee3b62da7e5d3cf10499586c", + "prepared_review_unit_hash": "c41efad3a06d73b826b264e21627476395e30915279369a895d36a18adf13bb3", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5728, - "estimated_input_tokens": 1432, - "estimated_eval_tokens": 3120 + "serialized_chars": 5722, + "estimated_input_tokens": 1431, + "estimated_eval_tokens": 3118 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5728, - "estimated_input_tokens": 1432, - "estimated_eval_tokens": 3120 + "serialized_chars": 5722, + "estimated_input_tokens": 1431, + "estimated_eval_tokens": 3118 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster contains two separate duplicate pairs: 45870/45871 and 45872/45873. Issue 45869 is related by theme but is not the same underlying request/bug as either pair.", - "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue for the full set: there are two distinct duplicate groups, and 45869 is unrelated to both. If triaged separately, 45870 and 45872 are the earliest representatives of their respective pairs.", + "summary": "The cluster appears to split into two likely duplicate issue pairs\u201445870/45871 and 45872/45873\u2014plus one unrelated dataset promo issue (45869). The duplicate calls should be treated as likely duplicates based on identical titles and matching body lengths, but not as proven exact body matches since the bodies are not shown.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 45870 is the earliest representative of the strongest likely-duplicate pair ('Example: Financial time series prediction with DataForge'); it is the cleanest canonical choice in that pair, though the exact body text is not visible here.", "canonical_pr_reason": null, - "best_issue_reason": "No single global best issue across this cluster because it splits into two independent duplicate topics rather than one shared bug/change.", + "best_issue_reason": "Issue 45870 is the best global representative because it anchors one of the likely duplicate pairs, is earliest among its duplicate mate, and the remaining items are either a separate similar pair or a different dataset promo topic.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45869", "right": "issue:45870", "accept": false, - "reason": "Same general finance/DataForge theme, but one is a dataset promo and the other is an example request; not the same underlying issue." + "reason": "Different topics: a dataset bundle promo versus a DataForge example issue." }, { "left": "issue:45869", "right": "issue:45871", "accept": false, - "reason": "Dataset listing vs. example writeup; related topic but not the same concrete request." + "reason": "Different topics: a dataset bundle promo versus a DataForge example issue." }, { "left": "issue:45870", "right": "issue:45871", "accept": true, - "reason": "Identical title and highly similar body; clear duplicate of the same example request." + "reason": "Identical title and matching body length strongly suggest the same issue; likely duplicates, though the body text itself is not visible." }, { "left": "issue:45870", "right": "issue:45872", "accept": false, - "reason": "Both mention finance/DataForge, but one is a prediction example and the other adds a scraping service; different underlying request." + "reason": "Different titles and only soft-similarity signal; this looks like a separate DataForge topic, not the same underlying issue." }, { "left": "issue:45870", "right": "issue:45873", "accept": false, - "reason": "Same as 45870/45872: similar broad theme, but not the same concrete change/request." + "reason": "Different titles and only soft-similarity signal; this looks like a separate DataForge topic, not the same underlying issue." }, { "left": "issue:45871", "right": "issue:45872", "accept": false, - "reason": "Different feature ideas: example prediction workflow versus prediction plus scraping service." + "reason": "Different titles and only broad topical overlap; not enough evidence that they are the same issue." }, { "left": "issue:45871", "right": "issue:45873", "accept": false, - "reason": "Different concrete request; only the broad finance/DataForge context overlaps." + "reason": "Different titles and only broad topical overlap; not enough evidence that they are the same issue." }, { "left": "issue:45872", "right": "issue:45873", "accept": true, - "reason": "Identical title and body characteristics; clear duplicate of the same DataForge scraping-service request." + "reason": "Identical title and matching body length strongly suggest the same issue; likely duplicates, though the body text itself is not visible." } ] }, "evaluator_result": { - "accept": true, - "feedback": "Grounded in the packet. The summary cleanly separates the two exact-duplicate pairs (45870/45871 and 45872/45873) and treats 45869 as only theme-related, not the same request. The soft-edge rejections are conservative, and the accepted edges are supported by identical titles plus matching body lengths." + "accept": false, + "feedback": "Reject: the analyst overstates the evidence by calling 45870/45871 and 45872/45873 \u201cexact duplicate title/body\u201d pairs. The packet only shows identical titles and matching body lengths, plus soft-similarity signals; it does not provide the bodies to confirm exact duplication. A conservative reading is that these are likely duplicates, not proven exact matches. The rest of the verdicts are broadly conservative, but the summary and canonical reasoning need to be downgraded accordingly." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -16511,7 +16590,7 @@ { "label": "pull_request", "component_index": 1, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16564,160 +16643,160 @@ "pull_request:43823|pull_request:45899", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "9e2400ce1b300f526cf5adfeb7a6b370b9683111f20a6408b7856450b91608a5", + "prepared_review_unit_hash": "5e14f3cde3d6565f00479a9ce3250515c28e0b2b1fbb9f4e40d37044e8b655e3", "component_budget": { "node_count": 14, "item_count": 14, "soft_pair_count": 26, - "serialized_chars": 39789, - "estimated_input_tokens": 9948, - "estimated_eval_tokens": 20152 + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 }, "budget": { "node_count": 14, "item_count": 14, "soft_pair_count": 26, - "serialized_chars": 39789, - "estimated_input_tokens": 9948, - "estimated_eval_tokens": 20152 + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is almost entirely a set of unrelated PRs across different models, docs, and utilities. The only true duplicate/competing change is the pair of PRs updating `fixed_cross_entropy` to accept extra `cross_entropy` kwargs.", - "confidence": 0.99, + "summary": "This cluster is mostly heterogeneous: model additions, docs updates, tokenizer utility changes, and unrelated bug fixes. The only clear duplicate pair is the two fixed_cross_entropy PRs against issue 43240; the rest should not be merged as duplicates.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the clearest representative: it is explicitly tied to issue 43240 and directly implements the `fixed_cross_entropy` kwargs fix in `loss_utils.py`. PR 43254 is an overlapping alternative patch for the same code path.", + "canonical_pr_reason": "PR 43251 is the strongest canonical PR: it directly targets issue 43240, has the fuller implementation, and 43254 is the near-identical alternative in the same file/function.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the best cluster representative because it is the only issue-linked, concrete fix for the shared `fixed_cross_entropy` change; the rest of the items are unrelated or only loosely similar.", + "best_pr_reason": "PR 43251 is the best representative of the only true duplicate pair in this set; the remaining PRs are unrelated changes and not suitable for consolidation.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Unrelated PRs: VideoPrism model addition vs ExecuTorch dynamic-shape test." + "reason": "Unrelated PRs: VideoPrism model/docs implementation vs an ExecuTorch dynamic-shapes test." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Different targets: Mistral tokenizer methods vs adding MobileLLM model files." + "reason": "Unrelated changes: Mistral tokenizer helper methods vs adding the MobileLLM model." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer API fix and ExecuTorch export test are unrelated changes." + "reason": "Tokenizer API addition and ExecuTorch export test are different code paths and problems." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor robustness changes for audio models do not match a new MobileLLM model addition." + "reason": "Processor auto-loading robustness vs adding a new model; different underlying changes." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Cross-entropy loss kwargs fix is unrelated to MobileLLM model scaffolding." + "reason": "Cross-entropy kwarg handling is unrelated to a new MobileLLM model implementation." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Loss utility kwargs fix and Mistral4 test/model updates are different code paths." + "reason": "Different fixes: loss utility kwargs vs Mistral4 test/model adjustments." }, { "left": "pull_request:43424", "right": "pull_request:45899", "accept": false, - "reason": "ExecuTorch export testing is unrelated to continuous batching docs." + "reason": "ExecuTorch export tests vs continuous batching docs; not the same bug/change." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Dynamic-shape export tests do not overlap with Mistral4 test/model fixes." + "reason": "ExecuTorch exportability test and Mistral4 test/model fixes are unrelated." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "ExecuTorch exportability testing is unrelated to adding MobileLLM." + "reason": "Dynamic-shape export testing has no overlap with adding MobileLLM." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New MobileLLM model code is unrelated to the `cls.config` resolution fix." + "reason": "Adding MobileLLM is unrelated to a core config-resolution order fix." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM model addition and Falcon output-collection refactor are not the same change." + "reason": "New model addition vs Falcon output-collection refactor; different code paths." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon refactoring and Mistral4 test fixes touch different models and problems." + "reason": "Falcon output-interface refactor is unrelated to Mistral4 test fixes." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon model refactor is unrelated to the model-creation skill PR." + "reason": "Falcon model refactor and model-creation skill addition are not the same change." }, { "left": "pull_request:43995", "right": "pull_request:45899", "accept": false, - "reason": "Falcon refactor and continuous batching docs are unrelated." + "reason": "Falcon model refactor vs docs for continuous batching decode fast path; unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45899", "accept": false, - "reason": "Mistral4 test/model changes and decode fast-path docs are unrelated despite both mentioning performance/testing." + "reason": "Mistral4 test/model fixes do not match the continuous batching decode fast-path docs change." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test fixes are unrelated to the `layrnorm` -> `layernorm` rename across CLIP-like models." + "reason": "Mistral4 test fixes and CLIP-like layrnorm renaming are different subsystems and fixes." }, { "left": "pull_request:44827", "right": "pull_request:45795", "accept": false, - "reason": "Mistral4 fixes are unrelated to docs for adding audio/video processors." + "reason": "Mistral4 test/model changes are unrelated to docs for adding audio/video processors." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 test fixes and `cls.config` resolution ordering are different issues." + "reason": "Mistral4 test fixes vs class config resolution order fix; different concrete problems." }, { "left": "pull_request:45170", "right": "pull_request:45899", "accept": false, - "reason": "Weight-renaming/model cleanup and continuous batching docs do not describe the same bug or change." + "reason": "Weight-renaming for CLIP-like models is unrelated to docs about decode fast path." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 test fixes are unrelated to the model-creation skill PR." + "reason": "Mistral4 bugfix/test PR is unrelated to the model-creation skill draft PR." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "Adding MobileLLM and adding the model-creation skill are unrelated." + "reason": "A new MobileLLM model and a model-creation skill are different artifacts, not the same bug/change." }, { "left": "pull_request:45213", @@ -16729,31 +16808,31 @@ "left": "pull_request:45795", "right": "pull_request:45899", "accept": false, - "reason": "Docs for audio/video processors and decode fast-path docs are different documentation changes." + "reason": "Docs for audio/video processors and docs for decode fast path address different documentation topics." }, { "left": "pull_request:43823", "right": "pull_request:45795", "accept": false, - "reason": "MobileLLM model addition and processor docs are unrelated." + "reason": "New MobileLLM model implementation vs docs for audio/video processors; unrelated." }, { "left": "pull_request:43823", "right": "pull_request:45899", "accept": false, - "reason": "MobileLLM model code and decode fast-path docs are unrelated." + "reason": "MobileLLM addition is unrelated to continuous batching decode-path docs." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Both PRs fix the same `fixed_cross_entropy` code path in `loss_utils.py` by plumbing supported `nn.functional.cross_entropy` kwargs (`weight`, `label_smoothing`) for issue 43240; they are competing implementations of the same change." + "reason": "Same concrete code-path and same target issue 43240: both modify fixed_cross_entropy in loss_utils.py to forward cross_entropy kwargs; they are plausible alternatives to one merged fix." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: it correctly isolates the single explicit duplicate/competing fix in `loss_utils.py` and treats the rest as unrelated. The soft-edge verdicts are conservative overall, with only the `43251`/`43254` pair accepted on the same issue-linked code path and file. No evidence of overstatement or unsafe pairing beyond what the packet supports." + "feedback": "The summary is grounded in the packet and stays conservative. The only clearly mergeable duplicate pair is 43251/43254: both target issue 43240 and modify the same fixed_cross_entropy path. The other rejected pairs are sufficiently different in file, subsystem, or change intent to not look like a single bugfix PR." }, "evaluator_used": true, "retried": false, @@ -16764,7 +16843,7 @@ { "label": "pull_request", "component_index": 2, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16780,7 +16859,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "d660bd06c083cce9f582b585b4ae6bcccf3927d10ea0c363c9755068af4e3f11", + "prepared_review_unit_hash": "d30d8b0ddbd9e8781b153144714ad2812140dd84262509fb17cb8613858e4ff3", "component_budget": { "node_count": 2, "item_count": 2, @@ -16802,18 +16881,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related VibeVoice PRs, but they are not duplicates: one implements the base VibeVoice integration, while the other adds a separate Realtime variant plus an acoustic tokenizer. The overlap is mostly shared model scaffolding, not the same concrete change.", - "confidence": 0.84, + "summary": "Both PRs work on VibeVoice, but they target different scopes: PR 40546 is the base implementation, while PR 42781 is a later VibeVoice Realtime expansion with additional acoustic tokenizer and generation changes. They are related, but not the same concrete change, so they should not be deduplicated.", + "confidence": 0.83, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the better canonical PR because it is the broader, more mature base implementation of VibeVoice, with more review activity and a complete initial integration path.", + "canonical_pr_reason": "PR 42781 is the broader, newer VibeVoice effort and includes the realtime/acoustic-tokenizer path, so it is the better cluster representative than the initial base implementation in PR 40546.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the best overall PR candidate because it covers the core VibeVoice feature set; PR #42781 is a draft, narrower extension focused on Realtime/tokenizer support and should remain separate.", + "best_pr_reason": "PR 42781 is the strongest representative of the VibeVoice work because it covers the more complete realtime feature set and related model components rather than only the initial implementation.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Shared VibeVoice files reflect common scaffolding, but the scopes differ: #40546 implements the base model integration, while #42781 adds VibeVoice Realtime and an acoustic tokenizer. They are not the same concrete fix/change and would not cleanly merge into one PR." + "reason": "They share the same model family and several files, but 40546 is the initial VibeVoice implementation while 42781 adds VibeVoice Realtime plus acoustic-tokenizer/generation changes. Different feature scopes, so not the same underlying change." } ] }, @@ -16827,7 +16906,7 @@ { "label": "pull_request", "component_index": 3, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16843,7 +16922,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "4aa530911a4fc4e97d637d44aa1217ebc5f0dfd86c5eb134b82748987bb9bfe7", + "prepared_review_unit_hash": "481515828b615765673249d55baa3ee2dc272908e55bb32d0e1fe3dacae8da48", "component_budget": { "node_count": 2, "item_count": 2, @@ -16865,7 +16944,7 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are unrelated: one adds TimesFM covariate forecasting support, the other adds DINOv3 image classification support. There is no duplicate or same-change relationship here.", + "summary": "The two pull requests are unrelated: one adds covariate forecasting support to TimesFM, while the other adds image classification support for DINOv3ViT. They do not describe the same underlying bug or change.", "confidence": 0.99, "canonical_issue_reason": null, "canonical_pr_reason": null, @@ -16873,10 +16952,10 @@ "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "[TimesFM] Add support for forecasting with covariates", - "right": "Add DINOv3ViTForImageClassification support", + "left": "pull_request:40755", + "right": "pull_request:41224", "accept": false, - "reason": "Different model families, different code paths, and different user-facing features. The TimesFM PR adds covariate-based forecasting utilities and docs; the DINOv3 PR adds image classification support and related examples/tests. They cannot plausibly be merged as one change." + "reason": "Different models and different feature areas (TimesFM time-series covariates vs. DINOv3 image classification); no shared code-path problem or mergeable duplicate change." } ] }, @@ -16890,7 +16969,7 @@ { "label": "pull_request", "component_index": 4, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16953,7 +17032,7 @@ { "label": "pull_request", "component_index": 5, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16971,46 +17050,46 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "72aa9a63325e00a114a795635d7ce0157a4a30f8f48a56956cc36361f8f38b7e", + "prepared_review_unit_hash": "573d5579612f3407391159f5bd0fa545c67c76040b7ac5930ee1a9ec0d1cbb53", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10406, - "estimated_input_tokens": 2602, - "estimated_eval_tokens": 5460 + "serialized_chars": 10404, + "estimated_input_tokens": 2601, + "estimated_eval_tokens": 5458 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10406, - "estimated_input_tokens": 2602, - "estimated_eval_tokens": 5460 + "serialized_chars": 10404, + "estimated_input_tokens": 2601, + "estimated_eval_tokens": 5458 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The three PRs are separate model-introduction changes (DeepSeek OCR, Isaac, Kimi2-6). They share routine transformers scaffolding, but they do not fix the same underlying bug or implement the same concrete change, so this cluster is not a duplicate set.", - "confidence": 0.97, + "summary": "These are three unrelated model-addition pull requests. They share the usual Transformers boilerplate for registering new models, but each introduces a different model family and codepath, so none are duplicates or mergeable as one change.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: each pull request adds a different model and associated integration files; the overlap is generic new-model boilerplate, not the same change.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "No single best PR for deduplication: none of these PRs is a duplicate of the others, and each is only the representative for its own model addition.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different model additions (DeepSeek OCR vs Isaac). Shared auto/config/docs wiring is standard boilerplate, not the same code-path change." + "reason": "Different model families and implementations: DeepSeek OCR vs Isaac. Shared auto-registry/docs scaffolding is generic new-model plumbing, not the same underlying bug or feature." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different model additions (Isaac vs Kimi2-6). The overlap is broad model-registration scaffolding, not one concrete fix or feature." + "reason": "Different additions: Isaac vs Kimi2-6. They touch similar registration files, but they introduce separate model codepaths and cannot plausibly be merged into one PR." } ] }, @@ -17024,7 +17103,7 @@ { "label": "pull_request", "component_index": 6, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17040,7 +17119,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "ce00d4b9c71f1bcb239566b72a301278b559488ffc64d7e6e5d4672d470f9fe8", + "prepared_review_unit_hash": "12e149d25faaae870ac02e44d6882e9bde52e5c6891252ec1ffa847923f26998", "component_budget": { "node_count": 2, "item_count": 2, @@ -17062,18 +17141,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are broad GitHub Actions dependency bumps, but they target different upgrade tracks: #42975 is specifically about Node 24 compatibility for several core actions, while #42976 updates Docker-related actions to newer versions. They overlap in workflows but not in the concrete change they\u2019re making.", - "confidence": 0.93, + "summary": "Two open PRs both upgrade GitHub Actions in workflow files, but they target different actions and different change themes: one is for Node 24 compatibility of core GitHub actions, the other is a docker/build-push-action version bump. They are related in broad area only, not the same underlying change.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "#42975 is the more canonical PR because it has the clearest, cohesive goal: upgrading workflow actions for Node 24 compatibility across multiple CI workflows.", + "canonical_pr_reason": "42975 is the broader and more representative workflow-actions upgrade, centered on Node 24 compatibility across many workflows; 42976 is a separate docker/build-push-action bump.", "best_issue_reason": null, - "best_pr_reason": "#42975 is the best standalone PR representative here because its scope and intent are explicit and cohesive, whereas #42976 is a separate version bump focused on Docker actions.", + "best_pr_reason": "42975 is the best single representative of the cluster because it captures the broader GitHub Actions compatibility work, while 42976 is a distinct docker-action upgrade.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Do not merge: they change different action families and solve different upgrade concerns. Shared workflow filenames alone are not enough to treat them as the same underlying change." + "reason": "Different concrete changes: 42975 updates checkout/cache/upload-artifact for Node 24 compatibility, while 42976 bumps docker/build-push-action to v6 in docker image workflows. They share the broad CI subsystem but not the same underlying bug or mergeable PR." } ] }, @@ -17087,7 +17166,7 @@ { "label": "pull_request", "component_index": 7, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17116,88 +17195,88 @@ "pull_request:44601|pull_request:45838", "pull_request:45490|pull_request:45838" ], - "prepared_review_unit_hash": "a6a665adbc8958362070639754f9908464079affec07b8d5eb88af5e63e98834", + "prepared_review_unit_hash": "bd699948f2538e4252e276ee7c51399977268ab5b6b410f92e3c0f81ae45731c", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23512, - "estimated_input_tokens": 5878, - "estimated_eval_tokens": 12012 + "serialized_chars": 23513, + "estimated_input_tokens": 5879, + "estimated_eval_tokens": 12014 }, "budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 23512, - "estimated_input_tokens": 5878, - "estimated_eval_tokens": 12012 + "serialized_chars": 23513, + "estimated_input_tokens": 5879, + "estimated_eval_tokens": 12014 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are not duplicates: they span different model additions and one distributed-loading infrastructure change. The shared files are mostly generic registration/docs plumbing, not evidence of a single underlying bug or change.", + "summary": "These PRs only look similar at a broad level because they add models or touch shared auto/docs plumbing, but they are different model families or an unrelated distributed-loading feature. None of the soft edges represent the same underlying change.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No true canonical PR: the set mixes unrelated model additions (ViT NEPA, Molmo, Molmo2, Lfm2Audio, CTSM, PP-OCRv6) plus an unrelated pipeline-parallel runtime change, so there is no single duplicate target.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "If forced to pick one representative, pull_request:45838 is the strongest standalone PR because it has a coherent feature scope around PP-OCRv6 text recognition variants and a substantial, self-contained implementation.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different model families: ViT NEPA vs Molmo. They only overlap on generic docs/auto-registration files, not the same code-path change." + "reason": "Different model additions: ViT NEPA vs Molmo. Shared auto/docs files are just common registration plumbing, not the same change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "Different model families: ViT NEPA vs Molmo2. Shared auto/docs edits are boilerplate for adding a new model, not a duplicate bugfix." + "reason": "Different model additions: ViT NEPA vs Molmo2. They are separate model families despite both touching Transformers registration files." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "Different model families: ViT NEPA vs CTSM. These are separate model additions with no common underlying change." + "reason": "Different model additions: ViT NEPA vs CTSM. Same broad subsystem, but not the same bug or feature." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related names but distinct model integrations with different files, configs, and tests; not the same PR mergeable into one." + "reason": "Molmo and Molmo2 are related by naming, but the PRs add distinct model implementations and docs, not one concrete change." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo vs CTSM are unrelated model additions. Similar registration changes are expected and do not indicate duplication." + "reason": "Molmo and CTSM are unrelated model families; overlap is limited to generic auto/docs updates." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are separate model implementations; overlap is only in standard framework wiring." + "reason": "Molmo2 and CTSM are separate model additions with different codepaths and model docs." }, { "left": "pull_request:43973", "right": "pull_request:45838", "accept": false, - "reason": "Lfm2 Audio vs PP-OCRv6 text recognition are unrelated domains and code paths; both are new model support, not duplicates." + "reason": "Lfm2 audio support vs PP-OCRv6 text recognition support are unrelated model additions; only the surrounding registration/docs files overlap." }, { "left": "pull_request:44601", "right": "pull_request:45838", "accept": false, - "reason": "Distributed pipeline-parallel loading support is infrastructure, while PP-OCRv6 is a model family addition. They address different problems." + "reason": "Distributed pipeline-parallel loading support is unrelated to PP-OCRv6 model support; they do not fix the same code-path problem." }, { "left": "pull_request:45490", "right": "pull_request:45838", "accept": false, - "reason": "CTSM time-series model support and PP-OCRv6 OCR support are different model additions with no shared underlying bug or feature." + "reason": "CTSM model support and PP-OCRv6 text recognition support are different features, with only generic registry/docs overlap." } ] }, @@ -17211,7 +17290,7 @@ { "label": "pull_request", "component_index": 8, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17234,70 +17313,70 @@ "pull_request:43665|pull_request:45892", "pull_request:44815|pull_request:45892" ], - "prepared_review_unit_hash": "f2334b63bcd0c2e6fa4214a6ea010020b725637a6126ca87410a4c7ce0f22eff", + "prepared_review_unit_hash": "0019a58ca6bf35b117f8153601fd391b1f234580e641c1ae440f699efe956acb", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10135, - "estimated_input_tokens": 2534, - "estimated_eval_tokens": 5324 + "serialized_chars": 10707, + "estimated_input_tokens": 2677, + "estimated_eval_tokens": 5610 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 10135, - "estimated_input_tokens": 2534, - "estimated_eval_tokens": 5324 + "serialized_chars": 10707, + "estimated_input_tokens": 2677, + "estimated_eval_tokens": 5610 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are not duplicates: they target different models and code paths, and the apparent similarity is mostly from generic fix/test titles. One is Whisper tokenization/tests, one is test-only CLIP/ViT noise, one is FP8 dequant/loading, and one is DeepSeek v4 attention logic.", + "summary": "These PRs are not duplicates: they target unrelated subsystems and fixes (Whisper tokenization/tests, CLIP/ViT test edits, FP8 dequantization/loading, and DeepSeek v4 implementation/docs).", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44815 is the strongest representative of the cluster because it is a concrete code fix with a clear implementation path across loading, quantization, and tests; the others are unrelated fixes or test-only edits.", + "canonical_pr_reason": "No single canonical PR fits this cluster because the PRs do not share the same underlying bug or change; they are separate, unrelated changes. If one must be named as the most substantive standalone fix, 44815 is the most coherent, but it is not a duplicate of the others.", "best_issue_reason": null, - "best_pr_reason": "PR 44815 is the best standalone PR in this set because it has the clearest bug-fix scope and the most substantive patch, while the others are either test-only or concern different model-specific behaviors.", + "best_pr_reason": "44815 is the best standalone PR in terms of completeness and technical coherence: it addresses a specific FP8 dequantization/loading path across code and tests. The others are either test-only/placeholder-like or concern different models and features.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Whisper tokenizer/test cleanup is unrelated to CLIP/ViT test edits; same generic 'fix' wording only." + "reason": "Whisper tokenizer decode/test fix vs. CLIP/ViT test edits; different models and different problems." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Different subsystems and bugs: Whisper decoding vs FP8 dequant/loading." + "reason": "Whisper batch/timestamp decode logic is unrelated to FP8 dequantization and model loading." }, { "left": "pull_request:43291", "right": "pull_request:45892", "accept": false, - "reason": "Whisper tokenization/tests and DeepSeek v4 causal attention are unrelated changes." + "reason": "Whisper tokenizer/tests and DeepSeek v4 model/docs are separate code paths with no shared concrete bug." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "Test-only CLIP/ViT edits do not share the same concrete code-path problem as FP8 dequant logic." + "reason": "Test-only changes for CLIP/ViT do not match an FP8 dequantization/loading fix." }, { "left": "pull_request:43665", "right": "pull_request:45892", "accept": false, - "reason": "These touch different model families and fix different issues; only superficial title similarity." + "reason": "CLIP/ViT test edits are unrelated to DeepSeek v4 model implementation and docs." }, { "left": "pull_request:44815", "right": "pull_request:45892", "accept": false, - "reason": "Both are model internals, but they fix different bugs in different paths: FP8 dequant vs DeepSeek v4 top-k attention selection." + "reason": "FP8 quantization/dequantization changes are unrelated to DeepSeek v4 architecture and test/doc updates." } ] }, @@ -17311,7 +17390,7 @@ { "label": "pull_request", "component_index": 9, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17327,12 +17406,12 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "dd2ecb21684aabf6080e47fd4577ba4662ea67e51750c38c937c047b21a41967", + "prepared_review_unit_hash": "75cfd2b35a876a9ef79fbb8e838326a0bb4bbe8959700ce00a4212eb9a27d6b9", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4563, + "serialized_chars": 4562, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17340,7 +17419,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4563, + "serialized_chars": 4562, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17349,18 +17428,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are not duplicates: one is a packaging/version/test-dependency change, while the other rewires CI/workflow and test utility behavior. Their overlap is only a shared Vit test file, which is too broad to imply the same underlying change.", + "summary": "The two PRs are not duplicates: one is a small packaging/setup change, while the other rewrites CI/workflow and testing utility behavior. They only overlap on a Vit test file, which is incidental.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No clear canonical PR for a duplicate cluster: the PRs address different code paths and subsystems, with only a superficial shared test filename.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 43532 is the better representative only because it contains the larger, more coherent change set; however, it is still not a duplicate of PR 43488.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "They change different areas and solve different problems: 43488 updates packaging/dependencies and a version string, while 43532 modifies CI/workflow and testing utilities. Shared Vit test file alone is not enough to merge them as the same PR." + "reason": "Different underlying changes and code paths: PR 43488 is about setup/version/dependency metadata, while PR 43532 changes CI workflows and testing/notification utilities. Shared Vit test filenames do not make them the same fix." } ] }, @@ -17374,7 +17453,7 @@ { "label": "pull_request", "component_index": 10, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17390,12 +17469,12 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "b5ccf2d9e85e2121529873e65c547eeaa70a5b8e01e68b6ab9aeda327fd7e958", + "prepared_review_unit_hash": "d348b222343b51bf6a4e36bd81e6bdd308c46ea5a4e2885d493a3d67cbdf4713", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6083, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17403,7 +17482,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6083, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -17412,18 +17491,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate pipeline-addition PRs: one for Promptable Concept Segmentation and one for Promptable Visual Segmentation. They share docs/registry boilerplate, but they target different tasks, different pipeline classes, and different model integrations, so they are not duplicates.", - "confidence": 0.98, + "summary": "These are two related but distinct PRs adding different segmentation pipelines: one for promptable concept segmentation and one for promptable visual segmentation. They share scaffolding and docs wiring, but the underlying task/model support differs, so they should not be treated as duplicates.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical duplicate PR: 43612 and 43613 implement different segmentation pipelines, so they should not be merged into one change.", + "canonical_pr_reason": "PR 43613 is the broader, more fully integrated pipeline addition, with support across SAM/EdgeTam-related models and dedicated tests/docs. It is the better representative of this cluster than the narrower concept-segmentation PR.", "best_issue_reason": null, - "best_pr_reason": "43613 is the broader PR with more model/test coverage, so it is the better representative of the pair, but it is still a distinct feature from 43612.", + "best_pr_reason": "PR 43613 is the best representative because it covers the more general promptable visual segmentation feature and includes more complete implementation and validation work.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Reject: despite similar docs/registry edits, one adds Promptable Concept Segmentation and the other adds Promptable Visual Segmentation. They touch different pipeline classes and model paths, so they are not the same underlying change." + "reason": "Do not merge: they add different pipelines for different tasks/code paths (concept segmentation vs visual segmentation). Shared docs/registry updates are not enough to make them the same underlying change." } ] }, @@ -17437,7 +17516,7 @@ { "label": "pull_request", "component_index": 11, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17453,7 +17532,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "a17d4fd46b5cde7a0dff5366edbf13f01fdc3fa7a83f1f62a59bd95b873dd192", + "prepared_review_unit_hash": "f742b799f08897de5b079c7e840ca2a912367f734e4500eb1ecd65ebc5d36125", "component_budget": { "node_count": 2, "item_count": 2, @@ -17475,18 +17554,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs in the same file, but they address different trainer extension points: gradient-accumulation loss scaling vs. column/signature filtering for custom trainers.", - "confidence": 0.96, + "summary": "These two PRs are related to `trainer.py` extensibility, but they address different behaviors: gradient-accumulation loss scaling vs. dataset column filtering/signature inspection. They are not duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 43651 is the more direct bug-fix style change and a cleaner representative of the cluster, but it is not a duplicate of 43663.", + "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "PR 43651: Add _loss_is_scaled_for_ga to allow custom trainers to control gradient accumulation loss scaling", - "right": "PR 43663: Add _get_signature_columns method to allow custom trainers to override column filtering", + "left": "pull_request:43651", + "right": "pull_request:43663", "accept": false, - "reason": "Same file, but different code paths and behaviors: one changes loss scaling in training_step, the other refactors input-signature column selection. They could not plausibly be merged as one duplicate PR." + "reason": "Reject: PR 43651 changes training-step loss scaling for gradient accumulation, while PR 43663 adds a helper for model signature-based column filtering. Different code paths and different underlying changes." } ] }, @@ -17500,7 +17579,7 @@ { "label": "pull_request", "component_index": 12, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17518,63 +17597,63 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "479d767abf4674dd2107dce59f48da91d70560364ad5fc7302487609abf8aef8", + "prepared_review_unit_hash": "8e5aebd9e28b93dbaaa57714a0b143d8e3d3b30bca7a6cd8cc55a229bf96b7b8", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, - "estimated_input_tokens": 1498, - "estimated_eval_tokens": 3252 + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5992, - "estimated_input_tokens": 1498, - "estimated_eval_tokens": 3252 + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "PR 43842 is the best standalone fix for the TypeAdapter NameError in `src/transformers/cli/serve.py`. PR 43836 is a broader but still plausibly related annotation fix in the same file and under the same issue target (43824). PR 43656 should not be clustered with 43842: it targets a different issue (43576) and appears to fix a different annotation/runtime problem around `TimedModel` rather than the specific `TypeAdapter` import/annotation issue.", - "confidence": 0.86, + "summary": "PR 43842 is the clearest targeted fix for the `TypeAdapter` NameError in `src/transformers/cli/serve.py`. The other two PRs touch the same file and related tracking issue, but the shown diffs are too broad/indirect to treat them as the same concrete bugfix or safely mergeable duplicates.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43842 is the most direct, narrow fix for the concrete `TypeAdapter` NameError: it moves the import under `TYPE_CHECKING` and quotes the annotation, which cleanly avoids runtime evaluation.", + "canonical_pr_reason": "PR 43842 is the most precise fix: it directly imports `TypeAdapter` under `TYPE_CHECKING` and stringifies the annotation to avoid the NameError, with the smallest and most focused change set.", "best_issue_reason": null, - "best_pr_reason": "PR 43842 is the best standalone PR because it solves the specific `TypeAdapter` NameError with the least extra refactoring.", + "best_pr_reason": "PR 43842 is the best global representative because it addresses the exact runtime name-resolution problem with minimal scope, unlike the other PRs whose previews show broader annotation cleanup.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Do not cluster these: 43656 targets a different issue (43576) and its diff centers on broader `TimedModel` annotation changes, not the same concrete `TypeAdapter` NameError fix." + "reason": "The shared file alone is not enough here: the visible changes in 43656 are mostly `__future__` annotations and broader type-annotation cleanup, not a clear fix for the same `TypeAdapter` NameError. The evidence does not support treating them as the same bugfix." }, { "left": "pull_request:43836", "right": "pull_request:43842", - "accept": true, - "reason": "These look like variants of the same annotation/runtime-evaluation problem in `serve.py` under issue 43824; 43836 is broader, but it could plausibly have been merged as one PR with 43842." + "accept": false, + "reason": "Both PRs target `serve.py` and share issue linkage, but 43836 looks like a broader annotation refactor while 43842 is a narrow `TypeAdapter` import/string-annotation fix. That is related, but not enough to conclude the same underlying change or a safe duplicate merge." } ] }, "evaluator_result": { "accept": false, - "feedback": "The summary overstates the evidence for PR 43656. In the packet, 43656 targets a different issue (43576) and its preview shows a broader annotation fix around `TimedModel`, not the specific `TypeAdapter` import/annotation problem shown in 43842. Soft similarity in the same file is not enough to conclude they are the same underlying bug or safely mergeable as one PR. The 43836 \u2194 43842 pair is more defensible because they share issue target 43824 and the diffs are in the same area, but the claim that all three are the same TypeAdapter NameError is too strong." + "feedback": "The summary overstates the evidence. PR 43656 does touch `serve.py`, but the shown changes are about adding `__future__` annotations and adjusting other type annotations; the packet does not support calling it the same `TypeAdapter` NameError fix as 43842. For 43836 vs 43842, the shared file and issue target show relatedness, but the diffs are not enough to conclude they are the same bugfix or safely mergeable into one PR; 43836 looks like a broader annotation cleanup, while 43842 is a narrow `TypeAdapter` import/annotation change. The conservative conclusion is that 43842 is the clearest targeted fix, but the other pairings should not be accepted on this evidence." }, "evaluator_used": true, "retried": true, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, { "label": "pull_request", "component_index": 13, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17640,7 +17719,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 2, "status": "reviewed", @@ -17752,385 +17831,349 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "f1fa8567be63558447dd2962cc8c55b27421817abc84a2a8ea19db4669bbf09d", + "prepared_review_unit_hash": "df5ef87b77dd602b21836eba54907360aaafe300ae8553a0c763be43b534db1e", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, - "estimated_input_tokens": 21224, - "estimated_eval_tokens": 42704 + "serialized_chars": 84885, + "estimated_input_tokens": 21222, + "estimated_eval_tokens": 42700 }, "budget": { "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75091, - "estimated_input_tokens": 18773, - "estimated_eval_tokens": 37802 + "serialized_chars": 75083, + "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 batch of model-specific PRs migrating output tracing to the new standardized decorator pattern. The only clearly duplicate-like pair is GPT-Neo (44018/44068); GPT-J PRs are also close enough to be overlapping iterations of the same code-path refactor. Most other pairs are just the same umbrella migration across different models, which is not enough to merge.", - "confidence": 0.84, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44066 is the best canonical representative: it has an explicit tracking issue, touches the core GPT-J path plus its copied CodeGen block, and shows the concrete standardized output-tracing refactor most clearly.", - "best_issue_reason": null, - "best_pr_reason": "PR 44066 is the strongest single PR to anchor the cluster because it is broad, explicit about the tracked issue, and contains a concrete code-path change rather than just a model-specific wrapper cleanup.", + "summary": "This cluster is mostly a collection of model-specific standardized output-tracing refactors rather than one broad duplicate. The only convincing duplicate subclusters are GPT-J/CodeGen and GPT-Neo. #43979 is a shared umbrella tracker for part of the cluster, but many PRs do not explicitly target it.", + "confidence": 0.87, + "canonical_issue_reason": "#43979 is the best issue anchor because it is the shared umbrella tracker explicitly referenced by several PRs in the cluster and best captures the recurring standardized output-tracing refactor theme, though many PRs do not link it.", + "canonical_pr_reason": "PR #44722 is the best PR anchor because it most clearly represents the GPT-J/CodeGen duplicate subcluster, with concrete overlap in modeling_gptj.py and modeling_codegen.py and an explicit #43979 link.", + "best_issue_reason": "#43979 is the strongest issue anchor for the cluster as a whole because it is the recurring tracker for the standardized output-tracing work, but it should be described conservatively as shared by several PRs rather than most.", + "best_pr_reason": "PR #44722 is the cleanest single PR representative of the shared GPT-J/CodeGen refactor, and it best captures the concrete duplicate change among the cluster's PRs.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model families and files; same umbrella output-tracing effort is too broad to treat as a duplicate." + "reason": "Different model families and different code paths; same umbrella refactor theme only." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "FNet/CVT vs DeBERTa are separate model refactors, not the same underlying bug or change." + "reason": "Cvt/FNet and DeBERTa v2 are unrelated model implementations." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both are GPT-J output-tracing refactors in the same code path; one is a narrower/broader iteration of the same change." + "reason": "Both are GPT-J output-tracing refactors in modeling_gptj.py and look like duplicate iterations of the same concrete change." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet and EfficientNet are distinct model implementations; shared migration pattern alone is insufficient." + "reason": "RegNet/ResNet and EfficientNet are different vision-model code paths; only the refactor style matches." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet vs GPT-J/CodeGen are unrelated concrete code paths despite the same general tracing theme." + "reason": "EfficientNet and GPT-J/CodeGen are unrelated model implementations." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen and EfficientNet are separate refactors in different models." + "reason": "GPT-J/CodeGen and EfficientNet do not share the same concrete bug or code path." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are unrelated implementations; no shared concrete fix." + "reason": "MobileNetV2 and DeBERTa v2 are unrelated model-specific refactors." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen and MGP-STR are different model code paths, so this is not a duplicate." + "reason": "GPT-J/CodeGen and MGP-STR are different model code paths." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen vs MPT are distinct model refactors, not one bug fix." + "reason": "GPT-J/CodeGen and MPT are separate model implementations; shared theme is too broad." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Both target GPT-Neo output tracing in the same file and appear to implement the same decorator-based refactor." + "reason": "Both are GPT-Neo output-tracing refactors on the same model file and appear to be duplicate versions of the same change." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen and GPT-Neo are separate model paths; same issue family is not enough." + "reason": "GPT-J/CodeGen and GPT-Neo are different model-specific refactors." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated model implementations." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "GPT-Neo and GPT-J/CodeGen are different model families with different code paths." + "reason": "GPT-Neo and GPT-J/CodeGen are distinct model refactors, not one duplicate fix." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet and GPT-J/CodeGen are unrelated implementations." + "reason": "ResNet and GPT-J/CodeGen are unrelated concrete changes." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are different concrete fixes." + "reason": "MGP-STR and GPT-J/CodeGen are different model code paths." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPT-J are separate code paths; no same underlying change." + "reason": "ResNet and GPT-J are separate model refactors with no shared concrete fix." }, { "left": "pull_request:44018", - "right": "pull_request:44019", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and ResNet are separate model refactors." + "reason": "GPT-Neo and MPT are different model-specific refactors." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are unrelated model implementations." + "reason": "ResNet and MPT do not share the same underlying bug or change." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert are different models; shared tracing theme is too broad." + "reason": "GPT-Neo and Flaubert/XLM are different model families and separate changes." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo vs GPT-J/CodeGen are different model code paths." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44086", - "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated concrete changes." + "reason": "GPT-Neo and GPT-J/CodeGen are distinct model refactors, even if both are output-tracing related." }, { "left": "pull_request:44018", - "right": "pull_request:44085", + "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and GPT-J are different files and model paths." + "reason": "GPT-Neo vs Flaubert/XLM are unrelated concrete changes." }, { "left": "pull_request:44071", - "right": "pull_request:44085", + "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J are separate model implementations." + "reason": "MPT and GPT-J/CodeGen are different implementations; shared theme is too broad." }, { - "left": "pull_request:44068", + "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are not the same underlying fix." + "reason": "GPT-2 and MGP-STR are unrelated model-specific changes." }, { - "left": "pull_request:44059", - "right": "pull_request:44086", + "left": "pull_request:44018", + "right": "pull_request:44059", "accept": false, - "reason": "GPT2 and MGP-STR are different model refactors." + "reason": "GPT-Neo and GPT-2 are separate model refactors, not one duplicate bug fix." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J and MGP-STR are unrelated code paths." + "reason": "GPT-J and MGP-STR are different model code paths." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert/XLM are separate model changes." + "reason": "ViLT and Flaubert/XLM are unrelated model changes." }, { - "left": "pull_request:44017", - "right": "pull_request:44161", + "left": "pull_request:44059", + "right": "pull_request:44722", "accept": false, - "reason": "Segformer and LongT5 are distinct implementations; same tracing modernization is not enough." + "reason": "GPT-2 and GPT-J/CodeGen are different model-specific refactors." }, { - "left": "pull_request:44017", - "right": "pull_request:44073", + "left": "pull_request:44073", + "right": "pull_request:44101", "accept": false, - "reason": "Segformer and VisualBert are different model paths." + "reason": "ViLT and Flaubert/XLM are unrelated concrete changes." }, { "left": "pull_request:44074", "right": "pull_request:44101", "accept": false, - "reason": "TextNet and Flaubert/XLM are unrelated fixes." + "reason": "TextNet and Flaubert/XLM are unrelated model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44074", + "accept": false, + "reason": "GPT-Neo and TextNet do not share the same concrete code-path change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "ViLT and LongT5 are unrelated model-specific refactors." }, { "left": "pull_request:44056", "right": "pull_request:44101", "accept": false, - "reason": "MPNet and Flaubert/XLM are separate model refactors." + "reason": "MPNet and Flaubert/XLM are distinct model refactors." }, { "left": "pull_request:43997", "right": "pull_request:44017", "accept": false, - "reason": "RegNet and Segformer are different model families." + "reason": "RegNet and SegFormer are different models and different code paths." }, { "left": "pull_request:43997", "right": "pull_request:44056", "accept": false, - "reason": "RegNet and MPNet are distinct code paths." + "reason": "RegNet and MPNet are unrelated changes." }, { "left": "pull_request:44071", - "right": "pull_request:44129", + "right": "pull_request:44076", "accept": false, - "reason": "MPT and SpeechT5 are unrelated model implementations." + "reason": "MPT and ImageGPT are separate model implementations; only the refactor style matches." }, { - "left": "pull_request:43996", + "left": "pull_request:44074", "right": "pull_request:44161", "accept": false, - "reason": "FNet/CVT and LongT5 are different model refactors." - }, - { - "left": "pull_request:43996", - "right": "pull_request:44017", - "accept": false, - "reason": "FNet/CVT and Segformer are not the same concrete change." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44071", - "accept": false, - "reason": "SqueezeBert and MPT are unrelated code paths." + "reason": "TextNet and LongT5 are unrelated model-specific refactors." }, { "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "MPNet and LongT5 are different models; same issue family alone is insufficient." + "reason": "MPNet and LongT5 are different concrete changes." }, { "left": "pull_request:43997", "right": "pull_request:44018", "accept": false, - "reason": "RegNet and GPT-Neo are unrelated refactors." + "reason": "RegNet and GPT-Neo are unrelated model refactors." }, { "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "RegNet and LongT5 are separate model changes." - }, - { - "left": "pull_request:44074", - "right": "pull_request:44161", - "accept": false, - "reason": "TextNet and LongT5 are different model code paths." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44019", - "accept": false, - "reason": "GPT-Neo and ResNet are different models and fixes." - }, - { - "left": "pull_request:44059", - "right": "pull_request:44086", - "accept": false, - "reason": "GPT2 and MGP-STR are unrelated concrete changes." + "reason": "RegNet and LongT5 do not share the same underlying bug or change." }, { - "left": "pull_request:44018", - "right": "pull_request:44059", - "accept": false, - "reason": "GPT-Neo and GPT2 are separate refactors in different files." - }, - { - "left": "pull_request:44059", - "right": "pull_request:44068", + "left": "pull_request:44071", + "right": "pull_request:44129", "accept": false, - "reason": "GPT2 and GPT-Neo are different code paths." + "reason": "MPT and SpeechT5 are different model code paths." }, { - "left": "pull_request:44018", + "left": "pull_request:44010", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo and MPT are separate model refactors." - }, - { - "left": "pull_request:44073", - "right": "pull_request:44101", - "accept": false, - "reason": "VisualBert and Flaubert/XLM are distinct changes." + "reason": "SqueezeBert and MPT are unrelated concrete changes." }, { - "left": "pull_request:44017", - "right": "pull_request:44071", + "left": "pull_request:44018", + "right": "pull_request:44129", "accept": false, - "reason": "Segformer and MPT are unrelated model implementations." + "reason": "GPT-Neo and SpeechT5 are different model-specific refactors." }, { "left": "pull_request:44010", - "right": "pull_request:44073", + "right": "pull_request:44044", "accept": false, - "reason": "SqueezeBert and VisualBert are different concrete fixes." + "reason": "SqueezeBert and DeBERTa v2 are unrelated code paths." }, { - "left": "pull_request:43997", + "left": "pull_request:44044", "right": "pull_request:44074", "accept": false, - "reason": "RegNet and TextNet are different model code paths." + "reason": "DeBERTa v2 and TextNet are different model changes." }, { - "left": "pull_request:44071", - "right": "pull_request:44076", - "accept": false, - "reason": "MPT and ImageGPT are separate model changes." + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J/CodeGen standardized output-tracing refactor; 44722 consolidates the same underlying change." }, { - "left": "pull_request:44074", - "right": "pull_request:44098", - "accept": false, - "reason": "TextNet and ViLT are unrelated refactors." + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both touch GPT-J output tracing in the same file and appear to be the same underlying refactor, with 44722 as the consolidated version." }, { - "left": "pull_request:44017", - "right": "pull_request:44074", + "left": "pull_request:44085", + "right": "pull_request:44129", "accept": false, - "reason": "Segformer and TextNet are different models." + "reason": "GPT-J and SpeechT5 are unrelated model implementations." }, { - "left": "pull_request:44044", - "right": "pull_request:44074", + "left": "pull_request:43996", + "right": "pull_request:44007", "accept": false, - "reason": "DeBERTa and TextNet are separate code paths." + "reason": "Cvt/FNet and RegNet/ResNet are different model families." }, { - "left": "pull_request:44066", - "right": "pull_request:44722", - "accept": true, - "reason": "Both are GPT-J/CodeGen output-tracing refactors over the same concrete code path and could be merged into one PR." - }, - { - "left": "pull_request:44085", - "right": "pull_request:44722", - "accept": true, - "reason": "Both target GPT-J output tracing in the same file; 44722 is just a broader variant that also includes CodeGen." + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "Cvt/FNet and SpeechT5 are unrelated concrete changes." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa and SpeechT5 are unrelated model fixes." + "reason": "DeBERTa v2 and SpeechT5 are distinct model-specific refactors." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa and Vits are separate refactors." + "reason": "DeBERTa v2 and Vits are unrelated model implementations." } ] }, "evaluator_result": { - "accept": true, - "feedback": "Grounded overall. The accepted soft pairs are mergeable as same-model output-tracing iterations (GPT-Neo and GPT-J/CodeGen), and the rejections stay conservative by not collapsing different model families just because they share the same standardized-tracing theme. The summary matches the packet reasonably well." + "accept": false, + "feedback": "The cluster-level summary is mostly grounded, but one anchor claim is overstated: `#43979` is clearly a shared umbrella issue, yet the packet does not show it as the target for *most* PRs in the cluster. Several PRs have no explicit issue link. Please keep that wording conservative. The duplicate judgments that are accepted look plausible, especially the GPT-J/CodeGen pair and the GPT-Neo pair, but the issue-anchor rationale needs to be tightened before accepting." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -18138,7 +18181,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 27, + "component_count": 28, "review_unit_index": 2, "review_unit_count": 2, "status": "reviewed", @@ -18165,70 +18208,70 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "2f715bb9a8c3f8af57d7f3bb38a04942ac06af7282068f9e90f238dda8c2e1c0", + "prepared_review_unit_hash": "b201d2d159faa142de47b4beaa44e6f59c1600100ca6b7b532a6566c340cd4b2", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, - "estimated_input_tokens": 21224, - "estimated_eval_tokens": 42704 + "serialized_chars": 84885, + "estimated_input_tokens": 21222, + "estimated_eval_tokens": 42700 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17126, - "estimated_input_tokens": 4282, - "estimated_eval_tokens": 8820 + "serialized_chars": 17123, + "estimated_input_tokens": 4281, + "estimated_eval_tokens": 8818 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are mostly separate model-specific refactors to adopt standardized output tracing/capture_outputs. They share a common theme, but each PR touches a different architecture and code path, so they should not be collapsed as duplicates.", - "confidence": 0.87, + "summary": "These are model-specific refactors to standardized output tracing/capture across different architectures, not the same underlying bug or change. The cluster is thematically related, but the PRs should remain separate.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44129 is the strongest representative: it has an explicit issue target, a substantial output-tracing refactor, and its changes are concrete rather than just naming/cleanup. It best captures the cluster\u2019s theme without being the most generic.", + "canonical_pr_reason": "PR 44129 is the best representative: it is a clear output-tracing refactor, has an explicit issue target, and the diff is self-contained and easy to understand.", "best_issue_reason": null, - "best_pr_reason": "PR 44129 is the best standalone PR in this set because it appears more complete and anchored to a tracked issue, while still exemplifying the standardized output-capture migration pattern.", + "best_pr_reason": "PR 44129 is the strongest standalone example of the cluster because it directly implements the standardized output capture pattern with an explicit tracked issue, making it the clearest anchor for this theme.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are output-tracing migrations, but they affect different model implementations (FocalNet vs ImageGPT). This is a shared refactor pattern, not the same underlying bug or change set." + "reason": "Both are output-tracing refactors, but they touch different model code paths (FocalNet vs ImageGPT). They are not the same fix and would not be merged as one PR." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "VisualBert and TextNet are unrelated code paths. The similarity is only that both adopt the same output-capture approach, so they should stay separate." + "reason": "These are separate model migrations to the same tracing pattern, but VisualBert and TextNet are unrelated code paths. Similar subsystem is not enough for duplicate PR merging." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "MPNet and VisualBert are different models with different forward/output semantics. They are not the same fix and would not plausibly be merged into one PR." + "reason": "MPNet and VisualBert each refactor their own output-capture logic; this is a shared pattern, not the same concrete bug or change." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "These are independent model refactors in different files and architectures. Same theme, but not the same concrete change." + "reason": "Different models and different forward/output machinery. The overlap is only the standardized tracing approach, so this is not a duplicate change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert each migrate output handling in their own model code. The overlap is generic standardization, not a duplicate bug or patch." + "reason": "RegNet and SqueezeBert are unrelated implementations. These PRs share the migration theme but not the same underlying code-path problem." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 touch unrelated model internals. The shared output-tracing motif is too broad to treat as one change." + "reason": "SqueezeBert and SpeechT5 are separate model-specific refactors. The shared issue label/theme is insufficient to treat them as the same PR." } ] }, @@ -18242,7 +18285,7 @@ { "label": "pull_request", "component_index": 15, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18308,268 +18351,262 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "e6b6781e8bb2d108158f59acd5d06beee14a0fd3ea259144ba905d6343dbf036", + "prepared_review_unit_hash": "58295d7bcd5a48d5222e354f40d27830f845787b19c29eb593df82a7a9808286", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40177, - "estimated_input_tokens": 10045, - "estimated_eval_tokens": 20346 + "serialized_chars": 40173, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 40, - "serialized_chars": 40177, - "estimated_input_tokens": 10045, - "estimated_eval_tokens": 20346 + "serialized_chars": 40173, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are all model-specific output-tracing refactors with similar naming, but they target different code paths and model families. I would not treat them as duplicates; the cluster is more a thematic grouping than a single underlying change.", - "confidence": 0.91, + "summary": "All items are refactor-style pull requests for output tracing in different model families. They are thematically similar but not duplicate code-path changes, so I reject every soft edge. I treat PR #44003 as the best canonical representative because it is the most substantial multi-file tracing refactor among the set.", + "confidence": 0.82, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44025 is the best representative: it makes a coherent decorator-based output-tracing change across two closely related Depth Anything files, with a clear, self-contained scope.", + "canonical_pr_reason": "PR #44003 is the strongest representative of the cluster: it is a broader multi-file output-tracing refactor spanning related Mamba/FalconMamba code, whereas the others are narrower model-specific variants.", "best_issue_reason": null, - "best_pr_reason": "PR #44025 is the strongest cluster representative because it is centralized, model-family-consistent, and more complete than the narrower single-model refactors.", + "best_pr_reason": "PR #44003 best captures the shared pattern while still being the most substantial implementation in the group; it is the most suitable single representative for triage.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model implementations (`timm_backbone` vs `upernet`); same refactor theme, but not the same concrete bug/change." + "reason": "Same refactor theme, but timm_backbone and upernet are different model code paths; not one mergeable bug/change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different model families (`timm_backbone` vs `vision_text_dual_encoder`); no shared code path or overlapping fix." + "reason": "Both are output-tracing refactors, but for different models (timm_backbone vs vision_text_dual_encoder); not duplicates." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different models (`timm_backbone` vs `univnet`); analogous output-tracing cleanup, not a duplicate change." + "reason": "Different model families and implementations; similar tracing cleanup, not the same underlying change." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Different code paths (`timm_backbone` vs `mamba/falcon_mamba`); same subsystem theme is too broad to merge as duplicates." + "reason": "timm_backbone and mamba/falcon_mamba are unrelated code paths; only the refactor style matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "CodeGen and timm_backbone fix different components; cannot be merged as one concrete fix." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different model families (`timm_backbone` vs `rwkv`) and different output plumbing." + "reason": "Different models and execution paths; same tracing refactor pattern only." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "Separate model implementations (`mobilenet_v1` vs `univnet`); same refactor pattern, not the same underlying fix." + "reason": "MobileNetV1 and UnivNet are unrelated model implementations; not the same bug/change." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "`mobilenet_v1` and `upernet` are unrelated model paths; not a duplicate PR." + "reason": "MobileNetV1 vs UperNet: same refactor motif, different model code paths." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Different model families (`mobilenet_v1` vs `depth_anything/prompt_depth_anything`); only the naming is similar." + "reason": "Different model families (MobileNetV1 vs Depth Anything); not a duplicate fix." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model wrappers (`mobilenet_v1` vs `vision_encoder_decoder`); same generic refactor theme is not enough." + "reason": "MobileNetV1 and VisionEncoderDecoder touch unrelated forward paths; only broadly similar." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "Different model wrappers (`mobilenet_v1` vs `speech_encoder_decoder`); not the same code path." + "reason": "MobileNetV1 and SpeechEncoderDecoder are different subsystems; not one mergeable change." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "`vision_text_dual_encoder` and `univnet` are unrelated implementations; no overlapping bug or change." + "reason": "Vision-text dual encoder and UnivNet are different model code paths; similarity is only mechanical." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different models (`vision_text_dual_encoder` vs `upernet`); only the output-tracing refactor pattern matches." + "reason": "Different models (vision-text dual encoder vs UperNet); not the same underlying issue." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Different architectures and files; not the same underlying issue." + "reason": "Vision-text dual encoder and Mamba/FalconMamba are unrelated implementations; not duplicates." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "CodeGen and vision-text dual encoder address different forward/tracing code paths." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "`vision_text_dual_encoder` vs `depth_anything` are separate code paths; same refactor language, not a duplicate." + "reason": "Different model families and target code paths; only the refactor pattern matches." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "`univnet` and `upernet` are different model implementations; no shared concrete fix." + "reason": "UnivNet and UperNet are unrelated model implementations; not one concrete fix." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different model families (`univnet` vs `mamba/falcon_mamba`); not mergeable as the same PR." + "reason": "Different architectures and files; similar output-tracing cleanup only." }, { "left": "pull_request:44001", - "right": "pull_request:44025", + "right": "pull_request:44004", "accept": false, - "reason": "Different models (`univnet` vs `depth_anything/prompt_depth_anything`); same broad refactor theme only." + "reason": "UnivNet and CodeGen fix different model-specific forward methods." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "Different model families (`upernet` vs `rwkv`); no shared code-path bug." + "reason": "UperNet and RWKV are different subsystems; same theme, different change." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "`upernet` and `mamba/falcon_mamba` are unrelated implementations; same subsystem wording is too broad." + "reason": "UperNet and Mamba/FalconMamba are unrelated model code paths; not duplicates." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Different model code paths (`mamba/falcon_mamba` vs `superpoint`); no evidence of the same fix." + "reason": "Mamba/FalconMamba and SuperPoint are different models; only broadly similar tracing refactor." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "`mamba/falcon_mamba` and `codegen` are distinct implementations; same output-tracing theme is not enough." - }, - { - "left": "pull_request:43998", - "right": "pull_request:44004", - "accept": false, - "reason": "Different model families (`timm_backbone` vs `codegen`); not the same concrete change." - }, - { - "left": "pull_request:44001", - "right": "pull_request:44004", - "accept": false, - "reason": "`univnet` and `codegen` are unrelated code paths; same refactor pattern only." - }, - { - "left": "pull_request:44002", - "right": "pull_request:44004", - "accept": false, - "reason": "`upernet` and `codegen` are different implementations; no duplicate evidence." + "reason": "Different concrete implementations (Mamba vs CodeGen); not the same fix." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "`depth_anything` vs `vision_encoder_decoder` are different model families; they are parallel refactors, not the same change." + "reason": "Depth Anything and VisionEncoderDecoder are different model wrappers; not one underlying bug." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "`depth_anything` and `speech_encoder_decoder` do not share a concrete code path or bug." + "reason": "Depth Anything and SpeechEncoderDecoder are separate code paths; similarity is superficial." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "`depth_anything` vs `superpoint`; different model implementations and output handling." + "reason": "Depth Anything and SuperPoint target different models and forward logic." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "`depth_anything` and `rwkv` are separate code paths; same naming pattern is not a duplicate signal." + "reason": "Depth Anything and RWKV are unrelated model families; not duplicates." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "`depth_anything` vs `dpr`; unrelated model code paths." + "reason": "Depth Anything and DPR touch different model-specific tracing paths." }, { "left": "pull_request:44026", - "right": "pull_request:44029", + "right": "pull_request:44027", "accept": false, - "reason": "`vision_encoder_decoder` and `rwkv` are unrelated implementations; no common concrete bug/change." + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are distinct wrappers; same style, different change." }, { "left": "pull_request:44026", - "right": "pull_request:44027", + "right": "pull_request:44028", "accept": false, - "reason": "Vision and speech encoder-decoder wrappers are analogous but separate code paths; not a duplicate PR." + "reason": "Different model families and forward paths; not the same concrete fix." }, { "left": "pull_request:44026", - "right": "pull_request:44028", + "right": "pull_request:44029", "accept": false, - "reason": "`vision_encoder_decoder` vs `superpoint`; different models and different output behavior." + "reason": "VisionEncoderDecoder and RWKV are unrelated implementations; not a duplicate." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "`vision_encoder_decoder` and `dpr` are distinct implementations; same refactor style only." + "reason": "Different model code paths (vision encoder-decoder vs DPR); only the refactor pattern is shared." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "`speech_encoder_decoder` and `superpoint` are unrelated code paths; not mergeable as one fix." + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated models; not one mergeable change." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "`speech_encoder_decoder` vs `rwkv`; separate model families and separate output plumbing." + "reason": "SpeechEncoderDecoder and RWKV are different subsystems; similar tracing cleanup only." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "`speech_encoder_decoder` and `dpr` are different implementations; no duplicate evidence." + "reason": "SpeechEncoderDecoder and DPR fix different model-specific forward code." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "`superpoint` and `rwkv` are unrelated model code paths; same refactor theme is too broad." + "reason": "SuperPoint and RWKV are different model families; not the same underlying issue." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "`superpoint` and `dpr` are different models with different output handling." + "reason": "SuperPoint and DPR target different code paths; not duplicates." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "`rwkv` and `dpr` are distinct implementations; not the same underlying bug or change." + "reason": "RWKV and DPR are unrelated models; only broad output-tracing similarity." } ] }, @@ -18583,7 +18620,7 @@ { "label": "pull_request", "component_index": 16, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18602,52 +18639,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "d26f93017d1948c51ff7fc42720dcd314654560ffa06a3cdcb5acac4132e272f", + "prepared_review_unit_hash": "93b3cc655fc6b6a6ab072af555e2a9ecab39179a0b07f42edbf295a4977c19b9", "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": "These are three separate model-addition PRs (PenguinVL, DeepSeek-OCR-2, Voxtral-TTS). They share boilerplate integration files, but they do not fix the same underlying code or implement the same change, so none should be clustered as duplicates.", - "confidence": 0.95, + "summary": "These are three separate model-addition PRs for PenguinVL, DeepSeek-OCR-2, and Voxtral TTS. They overlap on standard Transformers boilerplate, but each targets a different model and codepath, so none should be treated as duplicates.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR for duplication: the PRs target different models and different implementation paths, despite overlapping Transformers integration scaffolding.", + "canonical_pr_reason": "No single PR is a true duplicate of the others; if one must be picked as the representative, PR 45075 is the strongest candidate because it is the most complete, has the highest review activity, and includes an explicit issue target.", "best_issue_reason": null, - "best_pr_reason": "PR 45075 is the strongest standalone representative only because it is the most developed non-draft model-addition PR with broad implementation and review activity; it is not a duplicate of the others.", + "best_pr_reason": "PR 45075 is the best overall representative of the cluster because it is the most developed integration and most clearly tied to a tracking issue, even though the other PRs are distinct model additions.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different models and different feature domains: PenguinVL is a vision-language model implementation, while Voxtral-TTS is a text-to-speech model. Shared auto/docs plumbing is generic scaffolding, not the same underlying change." + "reason": "Different model additions: PenguinVL vs Voxtral TTS. Shared framework/doc boilerplate is expected, but they implement different architectures and targets." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Both add unrelated model implementations. PenguinVL and DeepSeek-OCR-2 have different architectures, files, and conversion/processing logic; the overlap is only common Transformers registration and docs." + "reason": "Different model additions: PenguinVL vs DeepSeek-OCR-2. Similar Transformers wiring does not make them the same underlying change." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral-TTS are distinct model families with different code paths and asset types. Similar repo integration files do not make them the same bug or change." + "reason": "Different model additions: DeepSeek-OCR-2 vs Voxtral TTS. They touch overlapping auto/docs files, but the concrete model codepaths are unrelated." } ] }, @@ -18661,7 +18698,7 @@ { "label": "pull_request", "component_index": 17, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18677,7 +18714,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "a9c0d405a529015eaf893c8a845cf9d498d51eb16401e4b07768d985804e7f37", + "prepared_review_unit_hash": "05976633c21674e22b5b69e8bb51a34dd9b02792d19bd022d04302baa2f1b882", "component_budget": { "node_count": 2, "item_count": 2, @@ -18699,18 +18736,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related by the general theme of fusion, but they are not the same change: one introduces a generic Module Fusion API, while the other implements KernelConfig-driven n-to-1 kernel fusion and example wiring. They should not be deduplicated.", - "confidence": 0.93, + "summary": "Both PRs are about module/kernel fusion in Transformers, but they implement different layers of the feature: one introduces a generic Module Fusion API, while the other wires up n-to-1 kernel fusion through KernelConfig and integration hooks.", + "confidence": 0.86, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR for a duplicate set here: PR #44979 is core module-fusion infrastructure, while PR #45363 is a separate KernelConfig-based fusion integration built around different files and behavior.", + "canonical_pr_reason": "PR #44979 is the better canonical PR because it introduces the foundational Module Fusion API and core abstraction; PR #45363 is a more specific follow-on feature built on top of that mechanism.", "best_issue_reason": null, - "best_pr_reason": "PR #45363 is the better representative of the cluster\u2019s practical fusion work because it touches the main integration path (modeling_utils, integrations, kernel_config) and shows an end-to-end use case.", + "best_pr_reason": "PR #44979 is the best representative of the cluster since it is the more general and central change, whereas #45363 is a narrower application of fusion for a particular kernel-config path.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Different levels of abstraction: #44979 adds a new generic Module Fusion API and tests, while #45363 adds KernelConfig-based n-to-1 kernel fusion plus example/integration changes. They are related, but not the same underlying bug or mergeable change." + "reason": "Do not treat these as duplicates: they target related fusion work, but #44979 adds a general module fusion API and #45363 adds a specific n-to-1 kernel fusion integration. They could coexist in one codebase and are not the same concrete change or bug fix." } ] }, @@ -18724,7 +18761,7 @@ { "label": "pull_request", "component_index": 18, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18740,7 +18777,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "d396ad27da3d786672935261ec4c166966960fc984065f38e7565889dceffb3b", + "prepared_review_unit_hash": "f8ae818d88b38cc06394fa7288d4b93cf10c7826ed5b3b33ab3b10514b4491ff", "component_budget": { "node_count": 2, "item_count": 2, @@ -18762,18 +18799,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs patch the same Mistral pre-tokenizer AttributeError in the same file and target the same issue; one adds tests, but the underlying fix is identical.", + "summary": "Both PRs fix the same AttributeError in `_patch_mistral_regex` by switching from `tokenizer.backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer`; the later PR also adds test coverage, so they are duplicates with 45317 the stronger candidate.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45317 is the better canonical representative because it contains the same fix plus test coverage, making it the more complete version of the duplicate change.", + "canonical_pr_reason": "PR 45317 is the more complete fix: it addresses the same code path as 45086 and adds tests, so it is the best canonical PR in this cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #45317 is the strongest standalone PR here: it fixes the same concrete bug as #45086 and additionally validates the behavior with tests.", + "best_pr_reason": "45317 is best overall because it implements the same bug fix as 45086 but includes validation/tests and is therefore the most complete representative.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same code-path bug in _patch_mistral_regex, same target issue, same file, and the second PR is a test-backed superset of the first; these could plausibly be merged into one PR." + "reason": "Same concrete bug and same patch site in `src/transformers/tokenization_utils_tokenizers.py`; both fix the `_patch_mistral_regex` AttributeError, and 45317 is just the more complete version with tests." } ] }, @@ -18787,7 +18824,7 @@ { "label": "pull_request", "component_index": 19, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18803,7 +18840,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "46764964d18d0434770ca1f88c5c89b31f6ec7f9070e593b0bd9761ed4b0df50", + "prepared_review_unit_hash": "4e064c3b2e352152ffd0e8e79d784c19270a2c9765a227102ee5470bca276e5d", "component_budget": { "node_count": 2, "item_count": 2, @@ -18825,18 +18862,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related NemotronH PRs, but they address different layers: one is a checkpoint conversion/rename refactor, the other is a broader model-family split into NemotronH dense/sparse variants with docs/tests. Not duplicates.", - "confidence": 0.88, + "summary": "Two related NemotronH pull requests, but they target different changes: one is a narrow checkpoint-conversion/mapping refactor, the other is a broader architecture split introducing nemotron_h_dense and nemotron_h_sparse plus docs/tests. They are not duplicates.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45569 is the more comprehensive, user-facing NemotronH change: it introduces the dense/sparse model split, updates auto mappings, docs, and tests. PR 45115 is narrower and mainly adjusts conversion mapping and inheritance plumbing.", + "canonical_pr_reason": "PR #45569 is the better representative because it captures the broader end-state change: the NemotronH model family split, auto/model registration, docs, and tests. PR #45115 is a narrower preprocessing/conversion-mapping adjustment.", "best_issue_reason": null, - "best_pr_reason": "PR 45569 is the best representative of the cluster because it encompasses the larger architectural refactor and associated documentation/test updates, making it the more canonical standalone change.", + "best_pr_reason": "PR #45569 is the strongest standalone PR in the cluster because it is the more complete feature refactor and includes user-facing documentation and test coverage, whereas #45115 only addresses conversion mapping for checkpoint key renaming.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "They share NemotronH files, but 45115 is about conversion key renaming and modular inheritance plumbing, while 45569 introduces the dense/sparse model split and broader API/docs/test changes. Different concrete changes, not one mergeable fix." + "reason": "Not the same underlying change. #45115 updates conversion mappings for NemotronH weight-key renaming, while #45569 splits NemotronH into dense/sparse variants with model/config/doc/test updates. Different scope and code paths." } ] }, @@ -18850,7 +18887,7 @@ { "label": "pull_request", "component_index": 20, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18866,7 +18903,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "428f74f71df610271d04a29785ada60802bedce4eb22ac7cabfb52898c445fee", + "prepared_review_unit_hash": "5f2d17eb3d5bb4dbbe1ae43a465ab11c85946a0b3e21d2ed5743fee2010ceb35", "component_budget": { "node_count": 2, "item_count": 2, @@ -18888,18 +18925,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related foundation PRs for heterogeneous-layer support, but they target different parts of the stack: one adds per-layer config plumbing, the other adds model/runtime support. They share infra files, yet they are not the same concrete change and should not be merged as duplicates.", - "confidence": 0.92, + "summary": "These are related heterogeneous-config/modeling efforts, but they are not the same fix: one PR adds per-layer config support, while the other adds broader heterogeneous model/runtime support. They share infrastructure files, yet target different layers of the feature and should not be deduplicated.", + "confidence": 0.85, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the better canonical representative because it covers the broader model/runtime side of heterogeneous support, including cache and modeling-path changes, rather than only the config plumbing.", + "canonical_pr_reason": "PR #45332 is the more comprehensive umbrella change: it covers heterogeneous model support and includes the runtime/modeling paths that depend on per-layer config handling.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the strongest single representative of the cluster because it addresses the primary code-path behavior change, not just the config API surface.", + "best_pr_reason": "PR #45332 is the strongest standalone representative because it spans the actual model-side behavior and cache/modeling integration, whereas #45333 is mainly the config-side prerequisite.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Shared heterogeneity infrastructure and config files, but one PR is about per-layer config support while the other adds model/runtime support. They are adjacent work, not the same concrete fix/change, and would not plausibly be merged as one PR." + "reason": "Related feature work, but not the same concrete bug/change. #45333 adds per-layer configuration support; #45332 adds heterogeneous model/runtime support on top of that. They could be part of one roadmap, but not one merged PR for a single underlying fix." } ] }, @@ -18913,7 +18950,7 @@ { "label": "pull_request", "component_index": 21, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18929,7 +18966,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "18d6f5a0517e7c4df2916098ac0aeaa87d92132df856111cc9f3efc359a1ad1a", + "prepared_review_unit_hash": "7625eb0fb113900122d04cbb199607cddab7bc77f8846f90189266e234c1fac6", "component_budget": { "node_count": 2, "item_count": 2, @@ -18951,18 +18988,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both items are typing-related open PRs in transformers, but they are not the same change: #45415 is a broad type-checking sweep across many files plus pyproject type-ignore config, while #45425 adds specific typing helper protocols and targeted annotation fixes. Shared filenames look incidental, not duplicate-level overlap.", + "summary": "Both PRs are typing-related, but they are not the same change: one is a broad repo-wide type-checking enablement pass, while the other adds specific typing protocols and support helpers in modeling/modeling_utils paths.", "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "PR #45415 is the broader, more representative repo-wide typing/type-checking pass and best captures the cluster\u2019s main theme.", "best_issue_reason": null, - "best_pr_reason": "No clear duplicate canonical PR: #45425 is the more focused, self-contained typing change, but #45415 is a much broader type-checking cleanup and they address different work.", + "best_pr_reason": "PR #45415 is the best single representative because it covers the widest surface area of the typing cleanups and is the most general change in the cluster.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Different scope and likely different merge intent: #45415 is a repo-wide typing sweep, while #45425 adds specific protocol/type aliases and targeted fixes. Shared files are not enough to make them the same underlying change." + "reason": "They are related by theme, but not the same concrete code-path problem; #45415 is a broad type-checking sweep across many files, while #45425 adds specific typing protocols and fixes in modeling_utils/PEFT-related code. They would not plausibly be merged into one PR as duplicates." } ] }, @@ -18976,7 +19013,7 @@ { "label": "pull_request", "component_index": 22, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18994,12 +19031,12 @@ "pull_request:45487|pull_request:45843", "pull_request:45817|pull_request:45843" ], - "prepared_review_unit_hash": "7c6154f90b59bd85c4ca9b284df7a86bf80902ef524f772611000f2ac76cf4d7", + "prepared_review_unit_hash": "fe99c2df606b79dd9b67c817566b7cbdbca3a0b1a48f1a1ccdbabf30f3bbcec2", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 7563, + "serialized_chars": 7561, "estimated_input_tokens": 1891, "estimated_eval_tokens": 4038 }, @@ -19007,7 +19044,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 7563, + "serialized_chars": 7561, "estimated_input_tokens": 1891, "estimated_eval_tokens": 4038 }, @@ -19016,24 +19053,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-parallel bugfix PRs across different model families. They share a broad theme, but they do not look like the same underlying change or the same concrete code-path bug.", - "confidence": 0.84, + "summary": "These are all pull requests about model-parallel/device-placement fixes, but they target different model families and different code paths, so they do not look like duplicates. The Gemma4 PR is the strongest single representative of the cluster theme.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45817 is the best representative of the cluster because it contains a clear, self-contained model-parallel fix in Gemma4 and directly addresses the missing device/splitting logic with tests.", + "canonical_pr_reason": "PR #45817 is the best cluster representative because it has the most concrete model-parallel fix set in one model family, with clear code changes and tests, and it is the most self-contained of the three PRs.", "best_issue_reason": null, - "best_pr_reason": "PR 45817 is the strongest standalone candidate: it fixes a concrete model-parallel failure mode and is more substantial/central than the other two, which are narrower model-specific adjustments.", + "best_pr_reason": "PR #45817 is the most suitable standalone PR in this cluster: it fixes a specific device-placement bug in Gemma4, includes the relevant model code and test coverage, and reads as a cohesive change rather than a broad umbrella patch.", "soft_edge_verdicts": [ { "left": "pull_request:45487", "right": "pull_request:45843", "accept": false, - "reason": "Both are model-parallel related, but they fix different problems in different architectures: AltCLIP/Chinese-CLIP device placement for token type ids vs. Deimv2 backbone no_split module propagation. Same broad theme, not the same bug or mergeable change." + "reason": "Both are model-parallel fixes, but they target different architectures (AltCLIP/ChineseCLIP vs Deimv2) and different failure points, so they are not the same underlying change." }, { "left": "pull_request:45817", "right": "pull_request:45843", "accept": false, - "reason": "Gemma4 fixes a missing no_split module and device handling in one model; Deimv2 propagates no_split_modules from an embedded backbone. Different code paths and different failure modes, so they should not be merged." + "reason": "Gemma4 device-placement/no-split-module changes are unrelated to Deimv2 backbone propagation of _no_split_modules; same theme, different bug and code path." } ] }, @@ -19047,7 +19084,7 @@ { "label": "pull_request", "component_index": 23, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19063,7 +19100,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "b6dd1c058da986934ff33039a07763359d56da16a5ff3948f587414bd4e46fc4", + "prepared_review_unit_hash": "8e99e1e66043711887846c3de594f513230f7f917f57a195018dfe8aeeebe3b1", "component_budget": { "node_count": 2, "item_count": 2, @@ -19085,18 +19122,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are about expert parallelism, but they fix different bugs in different loading paths: one preserves distributed_config/has_ep for ZeRO-3 loading, the other prevents expert tensors from being overwritten during FSDP2 loading.", - "confidence": 0.89, + "summary": "These are both EP-related distributed-loading PRs, but they target different failure modes and code paths: one is about serializing/restoring `distributed_config` for Accelerate/ZeRO-3 loading, the other is about preventing expert weights from being overwritten during FSDP2/rank-0 broadcast. They should not be merged as duplicates.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the patches target distinct code paths and different distributed backends, so they are not duplicates.", + "canonical_pr_reason": "PR 45662 is the stronger canonical PR for this cluster because it fixes a specific, concrete runtime corruption bug in the loading path (experts overwritten by rank-0 broadcast) and includes coordinated changes across the relevant distributed-loading modules.", "best_issue_reason": null, - "best_pr_reason": "PR #45662 is the broader and more central expert-loading fix, with changes in the actual shard/broadcast path; PR #45548 is a separate config/serialization fix.", + "best_pr_reason": "PR 45662 is the best representative because it addresses a well-defined user-visible correctness issue in EP/FSDP2 loading rather than a narrower serialization tweak.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "They address different failure modes and backends (ZeRO-3 loading vs FSDP2 rank-0 overwrite). Shared EP/modeling_utils overlap is too broad to merge as one PR." + "reason": "Related subsystem, but not the same underlying bug. 45548 focuses on preserving `distributed_config` / EP state for Accelerate + ZeRO-3 loading; 45662 fixes expert tensors being overwritten during FSDP2/broadcast handling. Different concrete code paths and not plausibly one PR." } ] }, @@ -19110,7 +19147,7 @@ { "label": "pull_request", "component_index": 24, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19126,12 +19163,12 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "552e92ac99919adcd10c581683cd4ed1e794a5211923ff4058140f7f080cc7ba", + "prepared_review_unit_hash": "40b4e7a35bc44b52f7af101093435ee0c5729230590f70bb1b4155887ed9bd22", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19139,7 +19176,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19148,18 +19185,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same xdist/captured_info problem in the Transformers testing utilities. PR 45645 is the broader, more complete change: it includes the xdist-safe log-file fix plus CI workflow handling for multiple captured_info files, so it is the better canonical PR.", - "confidence": 0.86, + "summary": "Both pull requests address the same xdist-related captured_info collision in testing utilities; PR 45645 is the broader, more complete fix and subsumes the narrower file-writing change in 45639.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the more comprehensive fix for the same captured_info/xdist collision issue, adding both the core code-path change and CI log collection updates.", + "canonical_pr_reason": "PR 45645 is the better canonical PR because it contains the core testing_utils xdist-safety fix plus the downstream CI/workflow update needed to consume multiple captured_info files, making it the more complete resolution of the bug.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 best represents the cluster because it covers the underlying bug and the downstream CI artifact handling needed to preserve debug logs under xdist.", + "best_pr_reason": "PR 45645 best represents the cluster because it addresses the same underlying captured_info xdist collision and also fixes the report aggregation path, while 45639 is only the local writer-side change.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Both PRs address the same captured_info xdist collision in testing_utils; 45645 expands the same fix with workflow updates, so they are the same underlying change and could plausibly be merged into one PR." + "reason": "Same underlying bug: xdist workers colliding on captured_info output. 45645 expands the same fix with CI/report handling, so the two PRs are plausibly mergeable into one change set." } ] }, @@ -19173,7 +19210,7 @@ { "label": "pull_request", "component_index": 25, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19236,7 +19273,7 @@ { "label": "pull_request", "component_index": 26, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19302,7 +19339,7 @@ { "label": "pull_request", "component_index": 27, - "component_count": 27, + "component_count": 28, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19318,12 +19355,12 @@ "soft_pairs": [ "pull_request:45858|pull_request:45890" ], - "prepared_review_unit_hash": "fcb1872a8dc85cf7d7395e2097a65bcf0ecc0cc1252740ab62ef3014d27c2f32", + "prepared_review_unit_hash": "3963afa2b995fa941eaa3442f8d91a5b11ab8118ef24c14d9ad00bb70ba72aa9", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4140, + "serialized_chars": 4139, "estimated_input_tokens": 1035, "estimated_eval_tokens": 2326 }, @@ -19331,7 +19368,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4140, + "serialized_chars": 4139, "estimated_input_tokens": 1035, "estimated_eval_tokens": 2326 }, @@ -19340,18 +19377,81 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs both add XPU test expectations, but they target different model test files and different model-specific outputs. They share a theme, not the same underlying change.", - "confidence": 0.97, + "summary": "Two open PRs add XPU-specific test expectations for different model test suites (hy_v3 and exaone4_5). They are both test-only changes, but they target different model families and different failure surfaces, so they do not look like duplicates.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the changes are in different model test suites (hy_v3 vs exaone4_5) and update different expected values/code paths, so they are not duplicates.", + "canonical_pr_reason": "No duplicate PR canonical exists here; if one must be chosen as the cluster representative, PR 45890 is slightly more informative because it also adds an XPU determinism guard in addition to expectations, but it is still model-specific and not the same change as 45858.", "best_issue_reason": null, - "best_pr_reason": "PR 45890 is the slightly stronger standalone representative because it includes an XPU determinism guard and a more complete test update, but it is still not a duplicate of 45858.", + "best_pr_reason": "PR 45890 is the better standalone representative because it makes a fuller test harness adjustment for exaone4_5 on XPU. PR 45858 is similarly scoped but only updates expectations for a different model suite.", "soft_edge_verdicts": [ { "left": "pull_request:45858", "right": "pull_request:45890", "accept": false, - "reason": "Same broad theme of adding XPU expectations, but they modify different model tests with different expected tensors and no shared code path; not mergeable as one PR." + "reason": "Both are XPU expectation updates in tests, but they apply to different model suites (hy_v3 vs exaone4_5) and different concrete outputs. They do not appear to fix the same underlying bug or be mergeable into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 28, + "component_count": 28, + "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-45861-2", + "nodes": [ + "pull_request:45861", + "pull_request:45903" + ], + "soft_pairs": [ + "pull_request:45861|pull_request:45903" + ], + "prepared_review_unit_hash": "cb6f945a9544bf6bd24a6a24280d4d07fde49086ce541613a6c8808e1a39b6b1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5529, + "estimated_input_tokens": 1383, + "estimated_eval_tokens": 3022 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5529, + "estimated_input_tokens": 1383, + "estimated_eval_tokens": 3022 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are closely related, with 45903 appearing to subsume the device-mismatch fix from 45861 and add an additional meta/to_empty re-init fix in the same Qwen3-VL M-RoPE code path.", + "confidence": 0.84, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45903 is the better canonical PR because it covers the same M-RoPE device fix as 45861 and also includes an extra related initialization fix, making it the more complete change set.", + "best_issue_reason": null, + "best_pr_reason": "PR 45903 is the strongest representative: it is newer, broader, and appears to incorporate the core fix from 45861 while addressing an additional failure mode in the same family.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45861", + "right": "pull_request:45903", + "accept": true, + "reason": "Accept: 45903 looks like a superset of 45861 on the same concrete Qwen3-VL M-RoPE device-path bug, with an added but related meta/to_empty re-init fix. These could plausibly be combined into one PR." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index c73e169bbf403accdda1e3a53f53e7f7ad398cc4..fe9f195a70a3a69d5f354687e06e8eeda4042a52 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260512t000156z", + "analysis_id": "hybrid-model-20260512t060024z", "archived_artifacts": { - "hybrid": "snapshots/20260512T000156Z/analysis-runs/hybrid-model-20260512t000156z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260512T000156Z/analysis-runs/hybrid-model-20260512t000156z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-12T00:10:54Z", + "published_at": "2026-05-12T06:09:27Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260512T000156Z", + "snapshot_id": "20260512T060024Z", "variant": "hybrid" } diff --git a/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.json b/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..205448f901935280aa3b05542fcdb454f8039abb --- /dev/null +++ b/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.json @@ -0,0 +1,2355 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260512T060024Z", + "generated_at": "2026-05-12T06:09:26Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.805, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.854, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 713, + 720 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 699, + 705 + ], + [ + 1301, + 1307 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43824-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 43824, + "canonical_pr_number": 43836, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-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": 44025, + "issue_numbers": [], + "pr_numbers": [ + 44001, + 44025 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44001, + "right_pr_number": 44025, + "code_similarity": 0.161, + "size_similarity": 0.44, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.486, + "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, + 44004 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44002, + "right_pr_number": 44004, + "code_similarity": 0.125, + "size_similarity": 0.398, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.304, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-45861-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 45861, + "issue_numbers": [], + "pr_numbers": [ + 45861, + 45903 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45861, + "right_pr_number": 45903, + "code_similarity": 0.617, + "size_similarity": 0.516, + "file_overlap": 1.0, + "area_overlap": 0.377, + "patch_similarity": 0.546, + "shared_filenames": [ + "src/transformers/models/qwen3_5/modeling_qwen3_5.py", + "src/transformers/models/qwen3_5_moe/modeling_qwen3_5_moe.py", + "src/transformers/models/qwen3_omni_moe/modeling_qwen3_omni_moe.py", + "src/transformers/models/qwen3_vl/modeling_qwen3_vl.py", + "src/transformers/models/qwen3_vl/modular_qwen3_vl.py", + "src/transformers/models/qwen3_vl_moe/modeling_qwen3_vl_moe.py", + "tests/models/qwen3_vl/test_modeling_qwen3_vl.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/qwen3_5/modeling_qwen3_5.py", + "left_ranges": [ + [ + 146, + 154 + ] + ], + "right_ranges": [ + [ + 146, + 154 + ], + [ + 161, + 183 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_5_moe/modeling_qwen3_5_moe.py", + "left_ranges": [ + [ + 142, + 150 + ] + ], + "right_ranges": [ + [ + 142, + 150 + ], + [ + 157, + 179 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_omni_moe/modeling_qwen3_omni_moe.py", + "left_ranges": [ + [ + 1315, + 1323 + ] + ], + "right_ranges": [ + [ + 1315, + 1323 + ], + [ + 1330, + 1352 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_vl/modeling_qwen3_vl.py", + "left_ranges": [ + [ + 354, + 362 + ] + ], + "right_ranges": [ + [ + 354, + 362 + ], + [ + 369, + 391 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_vl/modular_qwen3_vl.py", + "left_ranges": [ + [ + 294, + 302 + ] + ], + "right_ranges": [ + [ + 32, + 38 + ], + [ + 270, + 292 + ], + [ + 311, + 319 + ] + ] + }, + { + "filename": "src/transformers/models/qwen3_vl_moe/modeling_qwen3_vl_moe.py", + "left_ranges": [ + [ + 865, + 873 + ] + ], + "right_ranges": [ + [ + 865, + 873 + ], + [ + 880, + 902 + ] + ] + }, + { + "filename": "tests/models/qwen3_vl/test_modeling_qwen3_vl.py", + "left_ranges": [ + [ + 17, + 26 + ], + [ + 29, + 35 + ], + [ + 45, + 78 + ], + [ + 522, + 547 + ] + ], + "right_ranges": [ + [ + 17, + 26 + ], + [ + 29, + 35 + ], + [ + 45, + 79 + ], + [ + 523, + 582 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44018-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44068, + "issue_numbers": [], + "pr_numbers": [ + 44018, + 44068 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44018, + "right_pr_number": 44068, + "code_similarity": 0.766, + "size_similarity": 0.939, + "file_overlap": 1.0, + "area_overlap": 0.425, + "patch_similarity": 0.866, + "shared_filenames": [ + "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "tests/models/gpt_neo/test_modeling_gpt_neo.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "left_ranges": [ + [ + 26, + 46 + ], + [ + 138, + 143 + ], + [ + 182, + 187 + ], + [ + 283, + 295 + ], + [ + 327, + 341 + ], + [ + 348, + 354 + ], + [ + 360, + 369 + ], + [ + 399, + 406 + ], + [ + 411, + 419 + ], + [ + 428, + 433 + ], + [ + 472, + 492 + ], + [ + 507, + 513 + ], + [ + 519, + 528 + ], + [ + 541, + 559 + ], + [ + 562, + 567 + ], + [ + 595, + 601 + ], + [ + 607, + 614 + ], + [ + 627, + 643 + ], + [ + 685, + 690 + ], + [ + 708, + 714 + ], + [ + 720, + 727 + ], + [ + 740, + 757 + ], + [ + 761, + 766 + ], + [ + 780, + 786 + ], + [ + 791, + 798 + ], + [ + 807, + 822 + ], + [ + 840, + 845 + ] + ], + "right_ranges": [ + [ + 26, + 31 + ], + [ + 34, + 44 + ], + [ + 136, + 141 + ], + [ + 180, + 185 + ], + [ + 281, + 293 + ], + [ + 325, + 339 + ], + [ + 346, + 352 + ], + [ + 358, + 367 + ], + [ + 397, + 404 + ], + [ + 409, + 417 + ], + [ + 426, + 434 + ], + [ + 463, + 483 + ], + [ + 498, + 504 + ], + [ + 510, + 519 + ], + [ + 532, + 550 + ], + [ + 553, + 564 + ], + [ + 586, + 592 + ], + [ + 598, + 605 + ], + [ + 618, + 634 + ], + [ + 676, + 688 + ], + [ + 699, + 705 + ], + [ + 711, + 718 + ], + [ + 731, + 748 + ], + [ + 752, + 762 + ], + [ + 771, + 777 + ], + [ + 782, + 789 + ], + [ + 798, + 813 + ], + [ + 831, + 836 + ] + ] + }, + { + "filename": "tests/models/gpt_neo/test_modeling_gpt_neo.py", + "left_ranges": [ + [ + 458, + 464 + ] + ], + "right_ranges": [ + [ + 458, + 464 + ] + ] + } + ] + } + ] + } + ], + "duplicate_issues": [], + "duplicate_prs": [ + { + "cluster_id": "cluster-41115-3", + "canonical_pr_number": 45613, + "duplicate_pr_numbers": [ + 41116 + ], + "target_issue_number": 41115, + "reason": "PRs in cluster-41115-3 are treated as duplicates because they converge on issue #41115 with closing_reference evidence." + }, + { + "cluster_id": "cluster-41211-3", + "canonical_pr_number": 44339, + "duplicate_pr_numbers": [ + 41356 + ], + "target_issue_number": 41211, + "reason": "PRs in cluster-41211-3 are treated as duplicates because they converge on issue #41211 with closing_reference evidence." + }, + { + "cluster_id": "cluster-43240-3", + "canonical_pr_number": 43251, + "duplicate_pr_numbers": [ + 43254 + ], + "target_issue_number": 43240, + "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43824-3", + "canonical_pr_number": 43836, + "duplicate_pr_numbers": [ + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference 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": 44025, + "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": [ + 44004 + ], + "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-45861-2", + "canonical_pr_number": 45861, + "duplicate_pr_numbers": [ + 45903 + ], + "target_issue_number": null, + "reason": "PRs in cluster-45861-2 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 12 discussion comments plus 8 inbound references.", + "score": 162.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..d009789f9fdf2663363a7cb74c1448ea1a8d0eb0 --- /dev/null +++ b/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,19466 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260512T060024Z", + "generated_at": "2026-05-12T06:09:26Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "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": "e153ddec1352b53f10c71e2ea036241e882bc651ff08880d676e3ca583d3a804", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are not true duplicates: one is a Tapas tokenization mismatch, one is an auth/error-message problem for private model downloads, and one is a generic model-loading failure for bert-base-uncased. The closest pair still appears to be only superficially similar.", + "confidence": 0.89, + "canonical_issue_reason": "Issue #16618 is the broadest representative of the cluster because it concerns model loading, but it is still a separate failure mode from the other two.", + "canonical_pr_reason": null, + "best_issue_reason": "#16618 is the most central issue by title and scope, but the cluster does not contain a clear duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tapas tokenization mismatch vs. generic bert-base-uncased loading failure; different code paths and symptoms." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Private-model login/error-message behavior is unrelated to loading a public model like bert-base-uncased." + } + ] + }, + "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": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41093", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45070", + "issue:45081", + "issue:45161", + "issue:45237", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45800", + "issue:45823", + "issue:45874", + "issue:45901" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43039|issue:45161", + "issue:43975|issue:44457", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:45823|issue:45874", + "issue:43828|issue:45161", + "issue:43425|issue:44292", + "issue:34928|issue:41720", + "issue:44918|issue:45161", + "issue:43541|issue:43716", + "issue:43716|issue:45685", + "issue:43828|issue:44292", + "issue:45507|issue:45685", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44918|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:43039|issue:44805", + "issue:41762|issue:43596", + "issue:43901|issue:44512", + "issue:39290|issue:41720", + "issue:45237|issue:45901", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:39290|issue:43531", + "issue:41093|issue:43638", + "issue:43792|issue:45901", + "issue:43425|issue:45070", + "issue:43596|issue:45800" + ], + "prepared_review_unit_hash": "cdee891446d5bf3335a2413eae4d0837f15c581e7021225a975e9a65f1c64018", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 63, + "serialized_chars": 45920, + "estimated_input_tokens": 11480, + "estimated_eval_tokens": 23216 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly soft text-similarity noise across unrelated issues, with one clear duplicate family around DeepSpeed ZeRO-3 load/init IndexError failures. A small docs-only pair also shares a broad cleanup theme but not the same concrete change.", + "confidence": 0.78, + "canonical_issue_reason": "issue:43596 is the cleanest representative of the only clear duplicate family: a ZeRO-3 model-init/load failure causing 'index 0 is out of bounds for dimension 0 with size 0'. It is broad enough to cover the matching Bert/ZeRO-3 variants.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43596 best represents the shared ZeRO-3 index-out-of-bounds bug and is the strongest duplicate anchor among the issues provided.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different failures: Qwen3.5 config attribute lookup vs streaming chat/completions behavior." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated runtime paths: AMD GPU loading issue vs MPS histogram kernel limitation." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different models and different device/dtype problems; no shared concrete bug." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Autocast dtype mismatch for Phi MoE is unrelated to GPT-OSS running on AMD GPUs." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different model families and failure modes; not the same bug." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Qwen NVFP4 load error is unrelated to AMD GPU execution failure." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated code paths." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "ModernBERT ONNX export and Qwen3Moe FP8 config error are different issues." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export failure vs CUDA assert during auto device mapping are not the same bug." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs cleanups for v5 removals, but they reference different removed features and are not the same artifact." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export bug and GenerationMixin import error are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Mask/tensor shape mismatch is unrelated to Gemma4 PLE device placement." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both are IndexError-like titles, but one is ZeRO-3 init and the other is a mask indexing mismatch; different bugs." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different failure types: ZeRO-3 empty-tensor init vs mask/index shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Mask shape mismatch and GPT-OSS tensor-parallel issue are different problems." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different subsystems and error causes; not a duplicate pair." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice preset handling is unrelated to ModernBERT ONNX export." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Collective mismatch during ZeRO-3 and Bert ZeRO-3 index error are distinct failures." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 load/init IndexError ('index 0 out of bounds' with size 0), just surfaced on closely related Bert model variants." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger cross_entropy call and GPT-OSS TP failure do not point to the same code-path bug." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Incorrect detokenization and LoRA merge/save inconsistency are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Qwen NVFP4 runtime error and LoRA weight merge/save mismatch are different issues." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation checkpointing/FSDP recomputation mismatch is unrelated to mask indexing errors." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "DeepSpeed training weight-dimension error and collective mismatch are different bugs." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 Bert load failure and GPT-OSS tensor-parallel failure are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "FSDP checkpointing shape mismatch and CustomTrainer signature mismatch are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Same DeepSpeed ZeRO-3 issue family? no; GPT-OSS TP problem is a different subsystem and symptom." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model-specific failures with no shared code path." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3/vLLM config mismatch and Mistral tokenizer patch crash are unrelated." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Device-map forward mismatch and expensive reverse embedding lookup are different Gemma4 issues." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch for Phi MoE is unrelated to GPT-OSS TP failure." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch-version incompatibility and Qwen NVFP4 runtime error are not the same bug." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "FSDP activation checkpointing mismatch and CUDA assert on Qwen3 auto device mapping are unrelated." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "TRL SFT embedding unpacking failure and GPT-OSS TP failure are different issues." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Dynamo tracing grouped_mm error and image preprocessor dtype mismatch are unrelated." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different model/device issues; no shared underlying bug." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Different Qwen/Phi runtime paths and different error causes." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Qwen NVFP4 runtime failure and TRL embedding unpacking failure are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger kernel cross-entropy routing and SFT embedding unpacking are not the same bug." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Both are ZeRO-3 load/init IndexErrors ('index 0 out of bounds' with size 0), with different models exhibiting the same underlying initialization bug." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both mention docs cleanup around removed v5 features, but they are different references and not the same concrete change." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different multimodal/model issues with no shared failure path." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Autocast dtype mismatch and MPS histogram limitation are unrelated." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "SFT trainer embedding issue and MPS int histogram limitation are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Liger kernel usage issue and Phi MoE autocast dtype mismatch are different bugs." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and trainer compute_loss signature break are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Checkpointing/FSDP shape mismatch and GenerationMixin import error are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Different subsystems and symptoms; not a duplicate." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds load/init failure, just on different model classes." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs issues: one is about return_all_scores wording, the other about removed run command docs." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different model/config bugs and different runtime failures." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "GPT-OSS AMD GPU failure and table-question-answering crash are unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral and Gemma4 device-map mismatch are different bugs." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger kernel issue and Qwen3-vl StopIteration are unrelated." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Checkpoint corruption and NemotronH checkpoint loading issue are different problems." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Model loading test failure and corrupted checkpoint report do not describe the same bug." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Gemma3 sliding_window_pattern regression and Qwen3-MoE sliding_window issue are related only by name, not the same change." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Mask shape mismatch and ZeRO-3 empty-tensor IndexError are different failure modes." + }, + { + "left": "issue:43792", + "right": "issue:45901", + "accept": false, + "reason": "Whisper runtime failure and table QA crash are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch compatibility issue and pydantic PretrainedConfig field regression are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "ZeRO-3 model init bug and torch/transformers version incompatibility are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only clearly duplicated family is the ZeRO-3 index-out-of-bounds load/init issue across 43596, 43638, and 41762; the docs pair is reasonably treated as related in theme but not the same concrete change. I didn\u2019t see any soft-edge verdicts that overstate the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 2, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36010", + "issue:39186", + "issue:39290", + "issue:40990", + "issue:41093", + "issue:41762", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43645", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43866", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44512", + "issue:44530", + "issue:44589", + "issue:44841", + "issue:44918", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45084", + "issue:45161", + "issue:45362", + "issue:45399", + "issue:45464", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45800", + "issue:45823", + "issue:45859", + "issue:45901", + "issue:45902" + ], + "soft_pairs": [ + "issue:45859|issue:45902", + "issue:43975|issue:45901", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:44292|issue:45901", + "issue:43404|issue:43866", + "issue:39290|issue:45823", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:41093|issue:41762", + "issue:45800|issue:45823", + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:45020|issue:45800", + "issue:43366|issue:45464", + "issue:43531|issue:45070", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:45542|issue:45800", + "issue:40990|issue:44960", + "issue:43716|issue:44918", + "issue:39186|issue:44918", + "issue:45632|issue:45698", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:44530|issue:45005", + "issue:44360|issue:44512" + ], + "prepared_review_unit_hash": "e9f50a6f38d9ea79408453dfc5c2ab946ac280fa0d2f76170c7ec18a877b20d4", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37846, + "estimated_input_tokens": 9462, + "estimated_eval_tokens": 19180 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a collection of distinct Transformers regression reports. There is some broad overlap around v5/model-loading/runtime breakages, but the soft pairs do not look like true duplicates of the same underlying bug or change.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 45020 is the best umbrella candidate: it is broad, open, and centered on recent-version regressions breaking custom/remote-code models, which is the closest shared theme across many of the other reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45020 is the most representative issue to keep as the cluster anchor because it describes a broad class of recent Transformers regressions rather than a single model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45859", + "right": "issue:45902", + "accept": false, + "reason": "Same model family, but different bugs: one is CPU-offload incompatibility in forward; the other is uninitialized-memory after meta->to_empty(cuda) materialization." + }, + { + "left": "issue:43975", + "right": "issue:45901", + "accept": false, + "reason": "Unrelated symptoms and code paths: detokenization regression vs table-question-answering crash." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Different problems: Whisper loading/runtime failure vs a PretrainedConfig/pydantic regression." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Both involve Qwen3.5 chat paths, but one is a crash in transformers chat and the other is a streaming inference API failure; not clearly the same bug." + }, + { + "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "No meaningful overlap: Qwen-3-8B NVFP4 runtime error vs table-question-answering crash." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Different models and failure modes: tied lm_head weights vs a corrupted Ovis2 checkpoint." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Different models and bugs: missing Gemma3 config attribute under vLLM vs Gemma4 device mismatch during forward." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated issues: Qwen3.5 streaming inference vs an MPS integer-kernel limitation." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Different code paths and hardware backends: torch dynamo grouped_mm tracing vs MPS histogram support." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Both are runtime numeric issues, but one is grouped_mm tracing in Mixtral and the other is autocast dtype mismatch in Phi-tiny-MoE." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "Import error for GenerationMixin is unrelated to a Gemma3 config attribute missing in vLLM." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Different subsystems: processor loading for Voxtral vs a template compilation TypeError." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are shape/indexing errors, but they affect different workflows and models; not enough evidence of the same bug." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "One is a general torch/Transformers incompatibility report; the other is a Gemma4 device-map mismatch." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "Completely different topics: PaddleOCR-VL loading failure vs GGUF gpt-oss support." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Both are v5 config-related, but one is a missing pad_token_idx regression and the other is a pydantic field issue." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Different problems: int4 quantization memory growth vs tied-weights behavior on translation models." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Both mention MoE/GPT-OSS-adjacent behavior, but the concrete failures are different: dynamo tracing vs tensor-parallel support." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Different failures: dtype mismatch under autocast vs streaming chat API failure." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "Both touch model loading, but one is an init_empty_weights argument regression and the other is a PretrainedConfig/pydantic breakage." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "A broad remote_code regression is not the same underlying bug as a specific torch version incompatibility." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF gpt-oss support is unrelated to Qwen3.5 streaming inference." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to the pydantic PretrainedConfig regression." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Different runtime failures: grouped_mm tracing vs missing Float8 storage type." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are index-out-of-bounds style errors, but they arise in different models and initialization contexts." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Both concern embeddings/representation quality, but the models and failure modes are different enough that they are not duplicates." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard-without-TensorFlow backend issue is unrelated to torch/Transformers incompatibility." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on GPT-OSS and a generic GLM5 issue are not the same bug." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Different model families and symptoms: image/text dtype mismatch vs embedding unpacking with trl SFT trainer." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP weight shape error and Qwen3.5 embedding unpacking failure are different code paths." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom-module loading, but one is a cache-path collision and the other is loading the wrong module after save_pretrained; not the same defect." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Tied lm_head weights in Mistral3 and tied weights in translation models are related conceptually, but these are different model families and likely different fixes." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Custom-model notebook initialization breakage is unrelated to flash-attn fallback logic." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash is unrelated to tied-weights regressions." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "A technical discussion about the DSA indexer is unrelated to stale documentation." + } + ] + }, + "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": 3, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:39692", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43493", + "issue:43643", + "issue:43644", + "issue:43782", + "issue:43828", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:44292", + "issue:44368", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44492", + "issue:44512", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45237", + "issue:45399", + "issue:45507", + "issue:45520", + "issue:45701", + "issue:45800", + "issue:45859" + ], + "soft_pairs": [ + "issue:42915|issue:45399", + "issue:43873|issue:45005", + "issue:44863|issue:45005", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:44292|issue:45507", + "issue:43644|issue:43950", + "issue:39692|issue:43054", + "issue:43828|issue:44928", + "issue:36331|issue:41762", + "issue:43866|issue:44403", + "issue:41628|issue:45800", + "issue:43872|issue:44589", + "issue:43054|issue:45701", + "issue:41553|issue:43883", + "issue:38175|issue:43054", + "issue:44910|issue:45859", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:43054|issue:43493", + "issue:44403|issue:44451", + "issue:43643|issue:45020", + "issue:43975|issue:45520", + "issue:43975|issue:45237", + "issue:42947|issue:43856", + "issue:44403|issue:44488", + "issue:41762|issue:42915", + "issue:43782|issue:44960", + "issue:42491|issue:44368", + "issue:43881|issue:43883" + ], + "prepared_review_unit_hash": "c62746840d5d5711e58dd213e4940021ca79779ed40aa9e135d1595190b4e1f4", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36367, + "estimated_input_tokens": 9092, + "estimated_eval_tokens": 18440 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is about the Transformers v5 non-persistent-buffer corruption regression. Issue 43950 is the clearest anchor, with 43644 and 44534 as true duplicates; 43643 is related to remote-code loading but not the same bug.", + "confidence": 0.94, + "canonical_issue_reason": "43950 most directly names the shared regression (`from_pretrained()` corrupting `register_buffer(persistent=False)` buffers) and is the best representative of the duplicate buffer-corruption cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "43950 is the strongest single issue to represent this cluster because it is the most specific and regression-focused report of the same non-persistent-buffer bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "Both are loading-related, but they describe different failures: Qwen3 MoE LoRA compatibility vs flash-attn2 fallback gating." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is not the same as tied-weights warnings on translation models." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure is a different bug from tied-weights handling." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo is unrelated to outdated docs mentioning a removed command." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Qwen3.5 embedding unpacking with TRL is a different code path from GraniteMoEHybrid calling an invalid method." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "DeepSeek detokenization and Qwen NVFP4 loading are model-specific failures with different causes." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Both report the same Transformers v5 non-persistent-buffer corruption/junk-buffer regression." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Qwen NVFP4 runtime failure is unrelated to GraniteMoEHybrid invalid-method behavior." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Both describe the same non-persistent-buffer corruption regression in Transformers v5." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "SigLIP2 docs-example errors with quantization failure are not the same as a text-embedding quality discrepancy." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Phi autocast dtype mismatch and Qwen3.5 position_ids/SDPA issues are different failures." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "A custom trainer kwarg error is unrelated to Gemma3 ZeRO-3 loading failure." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Corrupted checkpoint and generic loading noise are not the same underlying issue." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "AutoImageProcessor import failure and torch/transformers incompatibility are distinct bugs." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "bitsandbytes kwarg incompatibility is different from missing Float8 storage type errors." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality and tokenizer changes across versions are related only broadly, not the same bug." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Bad AutoTokenizer error messaging and missing `all_tied_weights_keys` are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is not the same as broader text-embedding degradation." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Flash-attn illegal-memory-access on Qwen3.5 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 loading failure are unrelated model-loading problems." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient-checkpointing ineffectiveness and int4 CUDA reserved-memory OOM are different performance bugs." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "Both concern SigLIP2, but one is a quality complaint and the other is an HF-vs-JAX implementation discrepancy." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise is not the same as inability to load a specific checkpoint." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Missing fields with `trust_remote_code=True` is adjacent to, but not the same as, broader remote-code breakage." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization issues and Python 3.13 flash_attn import errors are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Detokenization issues and AMD GPU runtime failures are unrelated." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "Checkpointing/LoRA behavior is unrelated to Qwen3 MoE memory usage." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading-related, but one is generic noise and the other is a specific checkpoint load failure." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading failure and Qwen3 MoE LoRA incompatibility are different model-specific issues." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight-only loading error is not the same as GLM5 loading/reporting issues." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "LoRA compatibility across hf versions and a tie-word-embeddings warning are not the same underlying bug." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "glm-4v loading failure and missing `all_tied_weights_keys` are different failures." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The 43950/44534 match is grounded, but the accepted 43643/43950 soft edge is too strong for the packet: 43643 is only described as missing fields with `trust_remote_code=True`, and the packet does not clearly tie it to the non-persistent-buffer regression. Because that acceptance overstates the evidence, I can\u2019t approve the cluster as written." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 4, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36331", + "issue:41093", + "issue:41553", + "issue:42915", + "issue:43257", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43638", + "issue:43742", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43872", + "issue:43940", + "issue:43950", + "issue:44155", + "issue:44220", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44560", + "issue:44661", + "issue:44805", + "issue:44863", + "issue:44928", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45305", + "issue:45313", + "issue:45356", + "issue:45399", + "issue:45538", + "issue:45584", + "issue:45588", + "issue:45663", + "issue:45685", + "issue:45759", + "issue:45823", + "issue:45902" + ], + "soft_pairs": [ + "issue:45685|issue:45823", + "issue:43824|issue:43872", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:44991|issue:45399", + "issue:43828|issue:45823", + "issue:45081|issue:45399", + "issue:43827|issue:44509", + "issue:43950|issue:45902", + "issue:45020|issue:45356", + "issue:43404|issue:43950", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43257|issue:43866", + "issue:43638|issue:45823", + "issue:43792|issue:44220", + "issue:43872|issue:44291", + "issue:43940|issue:45313", + "issue:42915|issue:43872", + "issue:43854|issue:44863", + "issue:41553|issue:44991", + "issue:43257|issue:45305", + "issue:45759|issue:45902", + "issue:36331|issue:41093", + "issue:44928|issue:45588", + "issue:43872|issue:45538", + "issue:41093|issue:44805", + "issue:44530|issue:44863", + "issue:41553|issue:44488", + "issue:44479|issue:44560", + "issue:24643|issue:30064", + "issue:43366|issue:43828", + "issue:45663|issue:45823", + "issue:44155|issue:45584", + "issue:43366|issue:43531" + ], + "prepared_review_unit_hash": "e4eef7719deb7a488cc9d4a6d00c018a9c8dd8c394233139434d6b812d14469b", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38555, + "estimated_input_tokens": 9639, + "estimated_eval_tokens": 19534 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: most items are unrelated model-, tokenizer-, or docs-specific issues. Only a few clear duplicate pairs stand out, notably the v5 docs/pipeline regression, the `_is_hf_initialized` / `init_empty_weights` loading regression, the identical mask-shape IndexError reports, and the Qwen3-vl video regression.", + "confidence": 0.81, + "canonical_issue_reason": "No single issue cleanly represents the entire cluster, but issue 44291 is the strongest canonical candidate among the clear duplicates because it states the generalized `_is_hf_initialized` / `init_empty_weights` regression rather than only a downstream symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44291 is the best overall issue to anchor deduping here: it is the most generalized and actionable report among the true duplicates, while most other items are separate bugs that should not be collapsed together.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "Different failures: MPS histogram/int support in MoE vs Gemma4 PLE device placement with device_map auto." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Unrelated symptoms: missing Qwen2.5-VL import vs bitsandbytes/_is_hf_initialized incompatibility." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Broad remote_code regression is not the same bug as Gemma4 PLE device mismatch." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Tokenizer mapping edge case vs remote_code breakage; different code paths and fixes." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading regression vs flash-attn fallback gating; different subsystems." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch in Phi-MoE is not the same as Gemma4 device mismatch." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Mistral tokenizer regex crash and flash-attn fallback checks are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Same docs regression: both report stale pipeline-task references removed in v5." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": false, + "reason": "Non-persistent buffer corruption on from_pretrained is a different issue from Qwen3Moe inv_freq materialization." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer/model regressions; no shared concrete bug." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "lm_head weight tying bug is unrelated to non-persistent buffer handling." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM load failure and flash-attn fallback gating are distinct problems." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "FineGrainedFP8Config failure is not the same as remote_code model breakage." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE weight-conversion problem and Ovis2 checkpoint corruption are different bugs." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "Deepspeed ZeRO-3 empty-parameter loading failure is unrelated to Gemma4 device placement." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Both are Whisper/audio-related, but the titles do not establish the same concrete root cause; too weak to merge." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same underlying incompatibility around `_is_hf_initialized` / `init_empty_weights`; 44291 generalizes the bitsandbytes symptom." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both mention DeepSpeed weight-loading issues, but they target different Qwen variants and do not clearly share one code-path bug." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "FP8 config failure and bitsandbytes/_is_hf_initialized incompatibility are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different model-loading failures for different architectures." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Bad error message for Voxtral tokenization is not the same as the est-roberta tokenizer failure." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Qwen3 MoE weight-conversion issue and DeepSpeed GAS gradient averaging regression are separate training bugs." + }, + { + "left": "issue:45759", + "right": "issue:45902", + "accept": false, + "reason": "Composite config unwrapping issue is unrelated to Qwen3Moe rotary embedding materialization." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "CustomTrainer kwarg mismatch and mask-shape IndexError are different training failures." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF NaN/SDPA fallback issue is unrelated to flash_attention.py s_aux=None crash." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes/init_empty_weights incompatibility is unrelated to CLIPTokenizer max length." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same generic mask-shape IndexError pattern; these look like duplicate reports of the same underlying indexing bug." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3.5 paged attention group-type crash is unrelated to NemotronH checkpoint loading." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer-load failures for different models." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": true, + "reason": "Both describe the same Qwen video-input regression around 5.3.0, with 44560 as a specific instance of the broader issue." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "DeepSpeed training weight-shape error and void segmentation map processing are unrelated." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss support and Phi-MoE autocast dtype mismatch are different problems." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states bug and Gemma4 PLE device mismatch are separate forward-path issues." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 token/embedding leakage and Whisper empty-transcription handling are unrelated." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "GGUF gpt-oss support and Qwen3-MoE sliding_window behavior are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet and stays conservative about unrelated issues. The accepted duplicates are well-supported by their titles and descriptions: 43827/44509, 43872/44291, 41093/44805, and 44479/44560. The rejected soft edges also read as appropriately cautious rather than overstated. " + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 5, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42617", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43366", + "issue:43550", + "issue:43596", + "issue:43632", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43720", + "issue:43824", + "issue:43854", + "issue:43931", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44960", + "issue:44977", + "issue:45030", + "issue:45276", + "issue:45313", + "issue:45357", + "issue:45488", + "issue:45685", + "issue:45812", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:44560|issue:45685", + "issue:43824|issue:43957", + "issue:43645|issue:43646", + "issue:43366|issue:44589", + "issue:42915|issue:43957", + "issue:42617|issue:43366", + "issue:44560|issue:44918", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:38175|issue:43994", + "issue:43632|issue:45834", + "issue:44560|issue:44805", + "issue:44877|issue:45030", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:43317|issue:44756", + "issue:43644|issue:44534", + "issue:38175|issue:39692", + "issue:44960|issue:44977", + "issue:42491|issue:43720", + "issue:45313|issue:45357", + "issue:45488|issue:45812", + "issue:44451|issue:44488", + "issue:41720|issue:42915", + "issue:43708|issue:44075", + "issue:43854|issue:43931", + "issue:42491|issue:45276", + "issue:42915|issue:44756", + "issue:43257|issue:43854", + "issue:42491|issue:43931", + "issue:39692|issue:43994" + ], + "prepared_review_unit_hash": "369348f6034820a322d4a9b61b7c71daaf71a21f13d252c9be27aa5ff00c4519", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37802, + "estimated_input_tokens": 9451, + "estimated_eval_tokens": 19158 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly distinct Transformers v5/model-loading regressions; only a few soft pairs are true duplicates, chiefly around non-persistent buffers, custom model init, and SigLIP2 bad outputs.", + "confidence": 0.84, + "canonical_issue_reason": "issue:43950 is the clearest root-cause report of the broad v5 regression in `from_pretrained` buffer handling (`register_buffer(persistent=False)`), which also matches the duplicate buffer-corruption reports.", + "canonical_pr_reason": null, + "best_issue_reason": "It has the most actionable and general bug statement in the cluster, and it describes a reusable loading-path regression rather than a model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Buffer corruption during loading and a Kosmos2.5 OCR index error are unrelated failure modes." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Both involve attention/kernel failures, but they affect different models and code paths with different symptoms." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3-VL video StopIteration and an MPS int-histogram limitation are unrelated bugs." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Importing Qwen2.5-VL and meta-device loading breakage are different model-loading issues." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Both report the same Transformers v5 regression breaking custom model initialization; the notebook detail is just a context variant." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF gpt-oss support and Float8 storage lookup failure are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Qwen3Moe FP8 failure and meta-device loading issues do not share the same underlying bug." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel.py execution failure is unrelated to GGUF architecture support." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Video StopIteration and TRL embedding unpacking are different Qwen3-VL/QLora training failures." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "GenerationMixin import error and Qwen3Moe FP8 failure are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer mapping/model registration bug and Gemma4 device mismatch are separate issues." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": true, + "reason": "Both describe the same SigLIP2 model producing wrong/degenerate outputs; the later issue is a broader symptom report." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "_is_hf_initialized regression and Kosmos2.5 OCR index error are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "These are different runtime errors with no shared concrete code path." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Strict config validation for granite_speech and tiny-random glm4v config loading are different problems." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "DeepSpeed ZeRO-3 Bert indexing failure and add-new-model-like tokenizer mapping failure are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Zero3/BertModel indexing failure is not the same bug as tokenizer mapping registration." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer mapping registration and mask-shape mismatch are different bugs." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "gpu+cpu offload loading failure and mmap OOM on Strix Halo are memory-related but not the same defect." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "These are the same v5 non-persistent-buffer corruption regression, just worded slightly differently." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Both mention SigLIP2, but one is wrong outputs and the other is documentation/example errors with model/processor mismatch." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "GLM5 and Qwen3.5 flash-attention failures are model-specific and different." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Qwen3_moe LoRA compatibility and BitNet packed-weight unpacking are separate accelerate-loading problems." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "ZeRO-3 weight loading for language_model and save_pretrained visual-key regression are unrelated." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer pre-tokenizer override bug and Granite token-ID regression are different tokenizer issues." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "They are similar Scandinavian BERT load failures, but not clearly the same underlying bug from the available evidence." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Qwen3 device-mapping assert and Qwen3Moe FP8 failure are distinct regressions." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Checkpoint max_steps recalculation and SGD args being ignored are unrelated trainer/optimizer bugs." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "GLM-4.7-Flash test loading failure and Qwen3-VL weight-shape mismatch are different model-loading issues." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Qwen3_moe LoRA compatibility and Gemma4 resize_token_embeddings behavior are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3Moe FP8 and Strix Halo mmap OOM are different problems." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed and GLM-4.7-Flash loading are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "LoRA compatibility regression and Qwen3-VL weight mismatch are different bugs." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "SigLIP2 documentation example issues and wrong inference outputs are related only by model family, not clearly the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The clustering is conservative and well grounded in the packet. The three accepted soft pairs are reasonably supported by the titles and descriptions: non-persistent buffer junk (43644/44534), custom model initialization / notebook variant (43645/43646), and SigLIP2 wrong outputs (38175/43994). The rejected pairs are mostly framed cautiously as related but not clearly the same bug, which matches the available evidence. One small note: phrases like \"root-cause report\" for issue 43950 are a bit stronger than the packet alone proves, but not enough to invalidate the overall summary." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 6, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42947", + "issue:43335", + "issue:43381", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43957", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44488", + "issue:44743", + "issue:44756", + "issue:44910", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:44991", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45704", + "issue:45759", + "issue:45823", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:43856|issue:43873", + "issue:44488|issue:44991", + "issue:43644|issue:43645", + "issue:45362|issue:45406", + "issue:43856|issue:44387", + "issue:44910|issue:45588", + "issue:42491|issue:45292", + "issue:36010|issue:39404", + "issue:45276|issue:45335", + "issue:43404|issue:43454", + "issue:44164|issue:44291", + "issue:41720|issue:44155", + "issue:44402|issue:44488", + "issue:43425|issue:43957", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:43873|issue:44387", + "issue:43335|issue:45663", + "issue:45663|issue:45759", + "issue:45663|issue:45859", + "issue:44291|issue:44756", + "issue:44155|issue:45823", + "issue:44387|issue:44756", + "issue:43854|issue:45216", + "issue:44292|issue:44912", + "issue:42947|issue:43381", + "issue:43957|issue:44756", + "issue:44743|issue:44960", + "issue:45276|issue:45292", + "issue:45684|issue:45698", + "issue:43381|issue:44928", + "issue:45663|issue:45902", + "issue:44164|issue:44756", + "issue:43646|issue:43708" + ], + "prepared_review_unit_hash": "bf184a20eebd6e98d2902e7bbadfe4aad681027a72fadfad4ea0782907f8a7d4", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 38089, + "estimated_input_tokens": 9523, + "estimated_eval_tokens": 19302 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a collection of distinct Transformers regressions that only share broad themes like loading, quantization, checkpointing, or embedding resize behavior. I did not find a true duplicate pair with enough evidence to merge.", + "confidence": 0.66, + "canonical_issue_reason": "No item is a clear duplicate hub; issue 45292 is the broadest, least model-specific resize_token_embeddings regression, so it is the best representative.", + "canonical_pr_reason": null, + "best_issue_reason": "45292 is the most generic and reusable bug report in the set, making it the least arbitrary representative for the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory/quantization, but one is Qwen3 MoE training inefficiency and the other is offloading failure; different bugs." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer/model loading regressions, but for different models and different failure modes." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Shared Transformers 5.0 context, but one is non-persistent buffers and the other is Jupyter custom-model init; not the same bug." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different models and different code paths: Qwen chat crash vs Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both are memory-related, but one is training inefficiency and the other is int4 reserved-memory OOM; not the same underlying issue." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both involve flash attention, but one is Qwen3.5 packed-sequence misparse and the other is s_aux=None AttributeError." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "LoRA/qwen3_moe version-compatibility issue vs generic resize_token_embeddings propagation bug; unrelated root causes." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Import error for GenerationMixin vs Whisper pipeline return_language regression; different artifacts and failures." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "Both are resize_token_embeddings bugs, but they affect different model families and different submodules." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both concern untied lm_head weights, but in different models and likely different tie-weight paths." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "save/from_pretrained extra_state handling vs init_empty_weights argument mismatch; different loading mechanisms." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Qwen3 device-mapping crash vs AudioFlamingo3 batch contamination; no shared underlying bug." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Both tokenizer-related, but one is vocab-size inconsistency and the other is model loading failure." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch 2.10 compatibility vs meta-device loading regression; different incompatibilities." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Documentation example errors vs a generic GLM5 issue; no same code-path bug." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing/PEFT issue vs T5 apex RMSNorm leak; unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both mention quantization and memory, but one is offloading behavior and the other is OOM from reserved memory." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug vs Gemma4 FSDP2 shared_kv_states error; different systems." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma4 FSDP2 KeyError vs Qwen multimodal from_config text_config unwrapping; unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Different Qwen/Gemma code paths; one is FSDP2 state rebuild, the other CPU-offload rotary embedding incompatibility." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "init_empty_weights constructor mismatch vs mmap OOM workaround; not the same bug." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 track leakage vs Gemma4 device mismatch under auto device_map; different failures." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Both are memory/OOM reports, but one is quantization-related reserved memory and the other is Strix Halo mmap behavior." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Model load failure in unit tests vs save_pretrained checkpoint regression; different directions of the pipeline." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Different quantized models and different symptoms: load error vs bf16 fallback." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Gradient checkpointing in PEFT vs gradient checkpointing in eval mode; distinct conditions and fixes." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "meta-device loading regression vs mmap/OOM workaround; different code paths." + }, + { + "left": "issue:44743", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3_5 recurrent-state reset bug vs generic GLM5 issue; not the same bug." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": false, + "reason": "Same general resize_token_embeddings theme, but the affected submodules and model scope differ enough that this is not a confirmed duplicate." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load custom models, but one is permissions propagation and the other is wrong module loading." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Checkpointing eval-mode issue vs RLHF NaN from 3D position_ids and SDPA fallback; unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 state bug vs Qwen3_5Moe rotary embedding uninitialized-memory bug; different code paths." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "save/from_pretrained extra_state issue vs Strix Halo mmap OOM; not the same underlying defect." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model init regression vs Trainer resume_from_checkpoint max_steps miscalculation; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 7, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36032", + "issue:39404", + "issue:40990", + "issue:42947", + "issue:43257", + "issue:43299", + "issue:43425", + "issue:43452", + "issue:43596", + "issue:43611", + "issue:43645", + "issue:43716", + "issue:43828", + "issue:43856", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44265", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44671", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44991", + "issue:45005", + "issue:45084", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45701", + "issue:45759", + "issue:45823", + "issue:45902" + ], + "soft_pairs": [ + "issue:44479|issue:44877", + "issue:45588|issue:45663", + "issue:45292|issue:45335", + "issue:43645|issue:44164", + "issue:43257|issue:44863", + "issue:44402|issue:44451", + "issue:43828|issue:43957", + "issue:43425|issue:43828", + "issue:44589|issue:44756", + "issue:39404|issue:45701", + "issue:44683|issue:45823", + "issue:43931|issue:44863", + "issue:43906|issue:44530", + "issue:43611|issue:43645", + "issue:43425|issue:45823", + "issue:44530|issue:45084", + "issue:43425|issue:43716", + "issue:43901|issue:44509", + "issue:39404|issue:44912", + "issue:44265|issue:44898", + "issue:43299|issue:43931", + "issue:44479|issue:44805", + "issue:43994|issue:44079", + "issue:45005|issue:45902", + "issue:39404|issue:44671", + "issue:44589|issue:45084", + "issue:40990|issue:42947", + "issue:43425|issue:44918", + "issue:44671|issue:44991", + "issue:44164|issue:45759", + "issue:43596|issue:44683", + "issue:36032|issue:43452", + "issue:43856|issue:44756" + ], + "prepared_review_unit_hash": "f0f5c5b12c71ece7d9c1c71e3e52b7af2a6b7a8a0d09e3912a79fc1b59575646", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37610, + "estimated_input_tokens": 9403, + "estimated_eval_tokens": 19062 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous. The only clear duplicate-like pair is the resize_token_embeddings bug, where one report is the generic form and the other is a t5gemma-specific instance.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 45292 is the broader, more canonical report; 45335 is a model-specific manifestation of the same resize_token_embeddings not propagating to output/decoder embeddings.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45292 best represents the duplicate pair because it states the underlying bug more generally and is likely the better anchor for triage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Different failures: video-input regression in Qwen VL models vs strict config blocking granite_speech loading." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Unrelated code paths: flash_attention s_aux handling vs Gemma4 FSDP2 shared_kv_states reconstruction." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same underlying bug: resize_token_embeddings not updating downstream embeddings; 45335 is the t5gemma-specific instance." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Custom-model initialization in notebooks is not the same as save/from_pretrained handling extra_state." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Both are loading issues, but for different architectures and different root causes." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Both involve tokenizer/model loading, but the titles point to different models and no shared concrete bug." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Different mismatch scenarios: autocast dtype error vs meta-device loading failure." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version compatibility is too broad to equate with a specific autocast dtype mismatch bug." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure is unrelated to disabling mmap for OOM on Strix Halo." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline return_language regression is not the same as a general tokenization change report." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device_map mismatch are different problems." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3-VL shape mismatch and NemotronH checkpoint-loading failure are distinct model-loading bugs." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "The isolated reproduction of another issue is not the same as the Qwen3.5 PagedAttentionCache crash." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "base_model_prefix loading regression and notebook-defined custom model initialization are separate failures." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch 2.10 incompatibility is too broad and not the same as Gemma4 PLE device mismatch." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash is unrelated to a compiler/template-node TypeError." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Torch version incompatibility is not the same as a Mistral-3 image preprocessor dtype mismatch." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but one is about return_all_scores and the other about removed pipeline tasks." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline language return regression and MXFP4 fallback behavior are different issues." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export failures with torch_compilable_check are unrelated to Perceiver non-default resolution handling." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both concern Qwen3-VL models, but one is a v5 regression and the other is a checkpoint shape mismatch." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression and mask/index shape mismatch are different concrete failures." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "Incorrect SigLIP2 outputs and ModelOutput key assignment are separate bugs." + }, + { + "left": "issue:45005", + "right": "issue:45902", + "accept": false, + "reason": "Tied-weights loading and uninitialized-memory after to_empty are different model/materialization problems." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline behavior and CamemBERT masked LM predictions are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Missing Float8 storage and non-template-node compilation errors do not share the same root cause." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity on gpt-oss-20b is not the same as gradient checkpointing being ineffective with LoRA." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "General Torch incompatibility does not match the Qwen3.5 SFT unpacking failure." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT prediction quality and tokenizer loading for est-roberta are different problems." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "extra_state save/load handling is unrelated to from_config not unwrapping text_config." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Zero3/BertModel index error is unrelated to flex_attention compilation on newer torch." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5Tokenizer special-method conflict and gguf_file loading breaks are different tokenizer/model-loading bugs." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE training memory usage and disabling mmap for Strix Halo OOM are not the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet and stays conservative. The only accepted pair, issue:45292 and issue:45335, is plausibly the same resize_token_embeddings bug affecting different downstream embeddings, and the rest of the pairwise rejections do not overclaim shared root causes." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 8, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42915", + "issue:43262", + "issue:43317", + "issue:43377", + "issue:43404", + "issue:43421", + "issue:43452", + "issue:43482", + "issue:43541", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43716", + "issue:43883", + "issue:43994", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44451", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44534", + "issue:44610", + "issue:44661", + "issue:44683", + "issue:44737", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45507", + "issue:45584", + "issue:45859" + ], + "soft_pairs": [ + "issue:32090|issue:39404", + "issue:44991|issue:45081", + "issue:44737|issue:45859", + "issue:44164|issue:44479", + "issue:43582|issue:43632", + "issue:44488|issue:45081", + "issue:44661|issue:44683", + "issue:40990|issue:43421", + "issue:43611|issue:43644", + "issue:44488|issue:44987", + "issue:43716|issue:45084", + "issue:44206|issue:44220", + "issue:43643|issue:44530", + "issue:43883|issue:44488", + "issue:34567|issue:40444", + "issue:36032|issue:42915", + "issue:44811|issue:45584", + "issue:43644|issue:43646", + "issue:43541|issue:45084", + "issue:44451|issue:44987", + "issue:43452|issue:43482", + "issue:42915|issue:44530", + "issue:44849|issue:45325", + "issue:43317|issue:43482", + "issue:36032|issue:43645", + "issue:44987|issue:44991", + "issue:43404|issue:44466", + "issue:45084|issue:45507", + "issue:43883|issue:44991", + "issue:43262|issue:43377", + "issue:43646|issue:44534", + "issue:43994|issue:44610", + "issue:43645|issue:44534" + ], + "prepared_review_unit_hash": "18f68080e309d48de7e48a3db55d59750bedacef0acd21018dd589c70fea169f", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37700, + "estimated_input_tokens": 9425, + "estimated_eval_tokens": 19106 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "A heterogeneous set of issues with a few topical clusters; the strongest duplicate-like pairings are around custom-model initialization in v5 and GGUF loading regressions. Most other items appear to be distinct bugs in different models or code paths.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 43646 is the best canonical issue because it uses the broadest framing of the v5 custom-model initialization regression, which cleanly covers the paired buffer-junk report.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43646 is the best representative overall because it captures the broad custom-model initialization regression, making it a good umbrella for the closest duplicate-like subcluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Different subsystems and failures: Trainer GPU broadcast NoneType error vs Whisper pipeline return_language behavior." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-loading problems, but they involve different models and different failure modes." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both mention offload/device behavior, but they are different models and distinct code paths." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Unrelated regressions: save/from_pretrained extra_state handling vs video-input processing for Qwen VL models." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Different regressions: Apple Silicon allocator warmup TypeError vs _is_hf_initialized flag breakage." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Shared Mistral/tokenizer theme is too broad; the concrete failure modes differ." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Unrelated areas: tokenizer mapping handling vs compiled flex_attention on torch >= 2.9." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity/LM evaluation problem vs tokenizer post-processor update bug; no shared code path." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but they describe different concrete bugs." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are model-loading failures, but they concern different models and likely different loader regressions." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Different bugs: image preprocessor/model dtype mismatch vs template-node compilation error." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Both touch audio feature extraction, but the titles indicate different failure points." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "Different behaviors: AutoConfig trust_remote_code field loss vs PagedAttentionCache linear_attention crash." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Different problems: missing all_tied_weights_keys on a model class vs a specific tokenizer/model loading failure." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counting vs multi-image IterableDataset finetuning failure are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "Tokenizer special-token conflict vs FineGrainedFP8Config failure on Qwen3Moe; different code paths." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both Whisper-related, but batch_decode skip_special_tokens and empty-transcription after align_special_tokens are distinct symptoms." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": true, + "reason": "These look like the same v5 custom-model initialization regression: 43644 is a specific symptom, while 43646 is the broader failure report." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Different failures in different paths: torch dynamo grouped_mm tracing vs template-node compilation." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Separate model-loading failures for different checkpoints." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": true, + "reason": "Both point to the same GGUF/from_pretrained loader regression; 43482 is a specific instance of the broader 43452 bug." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Qwen3Moe FP8 config failure vs Qwen3.5 paged-attention cache crash; not the same bug." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen-family issues: output_hidden_states bug vs rope index scaling bug in multimodal video handling." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "Different loading contexts: device_map/offload dequantized model load vs GGUF model load failure." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer special-token conflict vs Jupyter/custom model initialization regression; distinct issues." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are version-related loading failures, but they affect different models and likely different tokenizer/model code paths." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both involve lm_head/tied weights, but one is a missing tie in a specific model class and the other is device-dependent serialization." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Different failures: template compilation error vs GraniteMoEHybrid invalid method call." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Unrelated: missing tied-weights metadata vs tokenizer loading regression for a specific model." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio sampling-rate defaulting in apply_chat_template is unrelated to MIMI encoder batch-vs-single behavior." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Different v5 regressions: custom model initialization vs non-persistent buffer junk." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different vision/processor issues for different models with different expected input sizes and failure modes." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook/custom-model initialization bug vs non-persistent buffer junk regression; related theme, but not the same concrete issue." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The pair judgments are conservative and the two accepted pairs are plausible, but the summary is slightly overconfident/inaccurate: the packet includes open issues as well, so describing the set as \u201cclosed transformer issues\u201d is not fully grounded. Please keep the top-level characterization at the level of \u201ca heterogeneous set of issues\u201d rather than asserting state." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 9, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43421", + "issue:43425", + "issue:43531", + "issue:43540", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43742", + "issue:43818", + "issue:43819", + "issue:44062", + "issue:44079", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44462", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44877", + "issue:44987", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45542", + "issue:45663", + "issue:45812" + ], + "soft_pairs": [ + "issue:43322|issue:43540", + "issue:44403|issue:45081", + "issue:43377|issue:43819", + "issue:42915|issue:45084", + "issue:44451|issue:45081", + "issue:44265|issue:44610", + "issue:45216|issue:45357", + "issue:44220|issue:44683", + "issue:44987|issue:45081", + "issue:43404|issue:45127", + "issue:42915|issue:44291", + "issue:43632|issue:44756", + "issue:44062|issue:44987", + "issue:36032|issue:43742", + "issue:43296|issue:43531", + "issue:44479|issue:45325", + "issue:42915|issue:44589", + "issue:43611|issue:44534", + "issue:40444|issue:45325", + "issue:43531|issue:44877", + "issue:40990|issue:44811", + "issue:36032|issue:41720", + "issue:43425|issue:44403", + "issue:44079|issue:45663", + "issue:43632|issue:44534", + "issue:42175|issue:45542", + "issue:41553|issue:43582", + "issue:44462|issue:45812", + "issue:43421|issue:44568", + "issue:43818|issue:45357" + ], + "prepared_review_unit_hash": "761cf492ae8a443344de482b6b650ee59cadb82377cc12b6ab1dfcbec58281ef", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36715, + "estimated_input_tokens": 9179, + "estimated_eval_tokens": 18614 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a mixed cluster of Transformers tokenizer/loading and model-regression reports, with a few genuine duplicate-like pockets. I kept the stronger same-path pairs (Qwen3.5 save_pretrained, Qwen2.5-VL video/position-id, and tokenizer special-token handling) and rejected the weaker AutoTokenizer/Granite link as too speculative.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45812 is still the best single anchor because it is the broadest, active AutoTokenizer regression in the set and has the clearest cluster-wide relevance. That said, not every tokenizer-loading issue here is a duplicate of it, so the linkage should stay conservative.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the strongest representative issue overall: broad impact, open regression, and the most central to the tokenizer-loading subcluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Different multimodal families and failure modes; only the broad video/image-input area overlaps." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "One is generic loading noise, the other is a specific tokenizer patch crash; no same bug path." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Both are audio-related, but batching/padding-mask behavior and DAC latent decoding mismatch are separate bugs." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Different runtime failures with no concrete shared code path." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Both mention loading, but ScandiBERT loading and Mistral regex patching are different paths." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "Unrelated areas: torch.export support vs an image processor size mismatch." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same Qwen3.5 save_pretrained regression; 45357 looks like a narrower manifestation of the same broken checkpoint-writing path." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Different features and failure surfaces: fbank extraction vs compiled flex_attention on newer torch." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Both are loading regressions, but for different models and different tokenizer/config logic." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both mention tied weights, but one is a missing tie in model init and the other is LoRA merge behavior with extended vocab." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Different bugs: FP8 config handling vs init_empty_weights/_is_hf_initialized argument handling." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "Unrelated regressions: a Transformers v5 flag issue versus an Apple Silicon mmap/OOM workaround." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "The AddedToken special-argument error and the physical-intelligence/fast loading failure do not share the same path." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "Both are load-time errors, but the T5 tokenizer method conflict and the MobileLLM key error are unrelated." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "Different model families and different failures; no shared concrete bug." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": true, + "reason": "Both target the same Qwen2.5-VL temporal/video position-id regression; 45325 is a specific manifestation of the broader v5.3.0 video-input breakage." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "The config failure and missing storage-type error are distinct issues despite similar float8 terminology." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Different v5 regressions: base_model_prefix loading breakage vs non-persistent buffer initialization junk." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Both touch Qwen2.5-VL, but one is dataset/multi-image finetuning and the other is still-image temporal position scaling." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Separate model/config problems with no shared code path." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Perplexity on GPT-OSS and Whisper batch_decode skip_special_tokens are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer load conflict versus device-mapping CUDA assert; no substantive overlap." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch version compatibility and loading-noise are not the same bug." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment and Gemma4 FSDP shared_kv_states are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "Different regressions in different parts of model initialization and buffer handling." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both are TensorFlow/backend packaging complaints, but they describe different concrete problems and fixes." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error message and Apple Silicon warmup TypeError are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both involve AutoTokenizer/loading, but the symptoms differ ('ignores tokenizer.json' vs 'wrong token IDs for all Granite models') and the same bug path is not established." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": true, + "reason": "Both concern special-token/post-processor handling in tokenizers, and 44568 plausibly fits the same runtime special-token update gap." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA tower architecture issues are unrelated to Qwen3.5 save_pretrained key serialization." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster summary is broadly grounded, but it is not conservative enough on every soft edge. In particular, the accepted link between issue:44462 and issue:45812 overstates the evidence: both involve AutoTokenizer/loading, but the titles only show different symptoms ('ignores tokenizer.json' vs 'wrong token IDs for all Granite models') and do not clearly establish the same bug path. A few other accepted pairs are plausible, but this one is too speculative for a precision pass." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 10, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:33666", + "issue:35707", + "issue:40444", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43701", + "issue:43749", + "issue:43792", + "issue:43856", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44403", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44589", + "issue:44617", + "issue:44683", + "issue:44829", + "issue:44898", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45381", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45800", + "issue:45823", + "issue:45834" + ], + "soft_pairs": [ + "issue:43317|issue:43856", + "issue:43792|issue:44589", + "issue:44683|issue:45020", + "issue:33666|issue:40444", + "issue:44403|issue:44991", + "issue:44829|issue:45479", + "issue:43482|issue:45538", + "issue:35707|issue:40444", + "issue:44079|issue:44534", + "issue:44291|issue:44589", + "issue:43482|issue:43525", + "issue:43377|issue:45491", + "issue:43749|issue:44079", + "issue:41720|issue:45081", + "issue:43531|issue:44291", + "issue:43644|issue:44079", + "issue:40444|issue:45381", + "issue:44265|issue:45072", + "issue:43632|issue:45072", + "issue:43611|issue:43646", + "issue:42175|issue:43296", + "issue:45325|issue:45381", + "issue:43994|issue:44898", + "issue:43454|issue:44466", + "issue:45325|issue:45834", + "issue:43792|issue:43957", + "issue:42915|issue:43482", + "issue:44387|issue:44617", + "issue:43296|issue:45800", + "issue:43701|issue:45325", + "issue:44479|issue:45823" + ], + "prepared_review_unit_hash": "da6ea750a1277fdc0355e6bd3fe37669a149519d7d29b8ae02294f631885d0c7", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36954, + "estimated_input_tokens": 9239, + "estimated_eval_tokens": 18734 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a loose cluster of recent Transformers v5 regressions across model loading, device mapping, and multimodal position-id handling. Only one soft pair looks like the same underlying custom-model initialization breakage; the rest are adjacent but distinct bugs.", + "confidence": 0.65, + "canonical_issue_reason": "issue:45020 is the broadest umbrella in the set, covering the general class of recent Transformers-version breakages that many of the other issues are specific manifestations of.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the best single representative for this cluster because it captures the widest shared theme of recent Transformers v5 regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Both mention device map/memory, but one is dequantized-model loading and the other is Qwen3 MoE training OOM." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and Float8 storage lookup are different failure modes." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and remote_code loading regressions are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Same model family area, but multi-GPU training and multi-image iterable-dataset finetuning are distinct bugs." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Loading noise vs tokenizer loading failure for a specific model are not the same issue." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Both are training regressions, but FlashAttention-3 degeneration and single-label zero-loss are different code paths." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF/v5 tokenizer loading and CLIPTokenizer max_length behavior are unrelated." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image finetuning." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment and non-persistent buffer junk are separate internals." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized and Float8 storage lookup are different bugs." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Tokenizer loading failure and missing pad_token_id on Llama4Config are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "MIMI padding-mask behavior and Gemma3 sliding-window NaNs are different model paths." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 auto device-map cuda asserts and Mistral regex patch crashes are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights argument handling are separate issues." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer serialization and ModelOutput key assignment are not the same bug." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Multi-image finetuning failure and Qwen2.5-VL video position-id regression are distinct." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export/torch_compilable_check and bfloat16 dtype mismatches are different failures." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized flag breakage and bfloat16 inference dtype mismatch are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": true, + "reason": "Both are Transformers 5.0 model-initialization/custom-model loading regressions and appear to stem from the same breakage." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Missing TensorFlow in a torch extra and PaddleOCR-VL loading failure are unrelated." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen2.5-VL position ids, but one is still-image scaling and the other is video vision ids; too different to merge confidently." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and Perceiver resolution handling are different model bugs." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention lm_head tying, but one is a generation bug and the other is serialization inconsistency; not clearly the same bug." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Qwen2.5-VL position-id regression and Kosmos2.5 OCR index error are unrelated." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper loading/runtime failure and meta-device loading regressions are different issues." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-GGUF tokenizer loading are unrelated." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Int4 quantization memory regression and SAM3Video OOM are different causes." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "PaddleOCR-VL loading failure and torch/transformers incompatibility are not the same bug." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint key mismatch and Qwen2.5-VL position-id scaling are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Qwen2.5-VL video regression and Gemma4 device mismatch are different model-specific bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary stays within the packet: it treats the set as a loose collection of recent Transformers v5 regressions, and the lone accepted soft pair (issue:43611 / issue:43646) is plausibly the same model-initialization breakage. The other soft-edge rejections are conservative given the differing titles, and the representative choice of issue:45020 is a reasonable broad umbrella for the group." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 11, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:44008", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44466", + "issue:44488", + "issue:44534", + "issue:44610", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45357", + "issue:45584", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43881|issue:44488", + "issue:44291|issue:44877", + "issue:43262|issue:43746", + "issue:43606|issue:44265", + "issue:40990|issue:45584", + "issue:34634|issue:35707", + "issue:43873|issue:45701", + "issue:44186|issue:44265", + "issue:43317|issue:43873", + "issue:35707|issue:41720", + "issue:43606|issue:43819", + "issue:43454|issue:43550", + "issue:41720|issue:45823", + "issue:43377|issue:44610", + "issue:43454|issue:45072", + "issue:43572|issue:45759", + "issue:39692|issue:40444", + "issue:43377|issue:44898", + "issue:43526|issue:43883", + "issue:43749|issue:44534", + "issue:44466|issue:45357", + "issue:43454|issue:43720", + "issue:43881|issue:44991", + "issue:43296|issue:44877", + "issue:41720|issue:43322", + "issue:41720|issue:44977", + "issue:40990|issue:45701", + "issue:44008|issue:45823", + "issue:43404|issue:45357", + "issue:45632|issue:45684", + "issue:42617|issue:42915", + "issue:44186|issue:45072", + "issue:43577|issue:43708" + ], + "prepared_review_unit_hash": "3c1e8b7365b2467b938d557c008f5bec6985b12aeedda8952639de2978cebdee", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37820, + "estimated_input_tokens": 9455, + "estimated_eval_tokens": 19166 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose semantic grouping of model-loading, device-map, tokenizer, quantization, and weight-tying issues; none of the soft pairs look like exact duplicates.", + "confidence": 0.8, + "canonical_issue_reason": "No single exact duplicate spans the cluster, but issue 43873 is the broadest representative of the offloading/quantization subgroup and has the strongest activity.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the best standalone anchor because it is the most general loading/offloading report in the set and has the most discussion/inbound attention, though the cluster is not a true duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different models and different loading failures; only the broad \"load fails\" theme overlaps." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "One is an init_empty_weights argument mismatch, the other is strict config parsing for granite_speech." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sample-rate defaults vs PEFT checkpoint loading are unrelated bugs." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU-offload device mismatch for Bark is unrelated to torch.export failures around torch_compilable_check." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "High perplexity during eval and Whisper empty-transcription generation failure are different code paths." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset and progressive generation with inputs_embeds/past_key_values are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Offloading/quantization behavior does not match a tokenization-change regression." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer padding/truncation crash is unrelated to torch.export and torch_compilable_check." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both mention offload, but one is dequantized device_map loading and the other is a broader quantization/offloading report." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation with cached inputs is unrelated to a Qwen3 auto-device-map cuda assert." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Bark CPU offload mismatch and DAC.from_latents missing STE are different model behaviors." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Weight tying in AyaVision is unrelated to Bamba torch.compile/SDPA failure." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Both involve device_map auto, but the failing models and underlying mismatches are different." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "MIMI batching/padding-mask bug is unrelated to OmDet-Turbo processor image-size mismatch." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "A missing lm_head tie is not the same as dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx in config and composite config unwrapping are separate config-handling bugs." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 doc example errors are unrelated to Qwen2.5-VL finetuning on iterable multi-image prompts." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "MIMI padding-mask inconsistency is unrelated to Perceiver resolution/interpolation failure." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and Molmo missing all_tied_weights_keys are unrelated." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer serialization are different mechanisms." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "lm_head serialization inconsistency is not the same as incorrect visual encoder keys in Qwen3.5 save_pretrained." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Weight tying bug in AyaVision is unrelated to BitNet packed-weight unpacking during loading." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Model load failure for glm-4v-9b is unrelated to tokenizer loading for EMBEDDIA/est-roberta." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "PaddleOCR-VL loading in vLLM and strict granite_speech config parsing are distinct failures." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3 auto device-map cuda assert and Llava Next segmentation fault are different bugs." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Auto device mapping crash and flash-attention generation bug are different Qwen3 issues." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Perplexity regression and tokenization changes are not the same defect." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Gemma 3n forward variable collision and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Missing lm_head tying in Mistral3 differs from bad visual encoder key serialization in Qwen3.5." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collisions and read-only permission propagation are different save/load issues." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel launch failure and Qwen3Moe FP8 config failure are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crash and bfloat16 dtype mismatch are different subsystems." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "Blip2 dtype loading bug and Trainer resume max_steps calculation bug are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 12, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:30064", + "issue:33357", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43388", + "issue:43421", + "issue:43450", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43720", + "issue:43782", + "issue:43873", + "issue:43881", + "issue:44186", + "issue:44361", + "issue:44387", + "issue:44423", + "issue:44479", + "issue:44610", + "issue:44671", + "issue:44743", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44991", + "issue:45059", + "issue:45081", + "issue:45161", + "issue:45406", + "issue:45464", + "issue:45701", + "issue:45704", + "issue:45812" + ], + "soft_pairs": [ + "issue:43873|issue:44756", + "issue:44387|issue:45704", + "issue:44423|issue:45406", + "issue:44877|issue:44991", + "issue:36331|issue:42617", + "issue:36331|issue:42915", + "issue:43450|issue:45701", + "issue:43550|issue:43720", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:44479|issue:44918", + "issue:42915|issue:43317", + "issue:41720|issue:42617", + "issue:43550|issue:43606", + "issue:43316|issue:44913", + "issue:43295|issue:45701", + "issue:45081|issue:45812", + "issue:44671|issue:44743", + "issue:43526|issue:43881", + "issue:41720|issue:45161", + "issue:43531|issue:43572", + "issue:43421|issue:45812", + "issue:36010|issue:42617", + "issue:43540|issue:43782", + "issue:44186|issue:44361", + "issue:42915|issue:43322", + "issue:43388|issue:45059", + "issue:45406|issue:45464", + "issue:30064|issue:34634", + "issue:43421|issue:45701", + "issue:33357|issue:35707" + ], + "prepared_review_unit_hash": "bce1ba19d30af66e5b3326d5a6d05d18eb955a46457d88f0b462324d9ed87ca0", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36873, + "estimated_input_tokens": 9219, + "estimated_eval_tokens": 18694 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a collection of unrelated Transformer bugs. The serve-related pair `issue:44423` and `issue:45406` should not be treated as duplicates: they hit different model paths and fail with different concrete exceptions.", + "confidence": 0.93, + "canonical_issue_reason": "`issue:45406` is the clearest standalone issue in the cluster because it names the exact `Gemma4Processor` `_tokenizer` crash; `issue:44423` is a separate Qwen3.5 continuous-batching serve failure and should remain distinct.", + "canonical_pr_reason": null, + "best_issue_reason": "`issue:45406` is the strongest representative issue: specific, reproducible, and tied to an exact exception/path, unlike the broader serve crash reports around it.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Quantization/offloading behavior vs a Strix Halo mmap/OOM workaround; different bugs." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Int4 OOM under Transformers 5.x vs an apex RMSNorm memory leak; not the same failure." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Both are serve-related, but one is a Qwen3.5 continuous-batching `str.to()` crash and the other is a Gemma4Processor `_tokenizer` crash." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer/loading regressions affecting different model paths." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Trainer `compute_loss` API mismatch vs a `3d_parallel.py` runtime failure; unrelated." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Trainer API mismatch vs Qwen3MoE FP8 load failure; different code paths." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video batching shape bug vs a tokenization/version regression; not the same issue." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "Bamba torch.compile/SDPA issue vs BitNet packed-weight unpacking during loading; distinct bugs." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Processor output size mismatch vs a Perceiver non-default-resolution failure; different symptoms and causes." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "LayoutLMv2 tokenizer crash vs an image processor shape bug; not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Video-input regression across Qwen VL models vs an embeddings unpacking/trainer issue." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Qwen3Moe FP8 load failure vs dequantized model offload loading failure; too different." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 auto-device-map CUDA assert vs a generic parallel script failure." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Different models and failure modes: SDPA/torch.compile vs CPU offload device mismatch." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Config API discrepancy vs a rotary_pct reload regression; not the same issue." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Processor/tokenizer regression in custom model code vs a broader tokenization change report." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Mistral regex patch crash vs Granite token ID regression; different tokenizer bugs." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM prediction bug vs Qwen3.5 recurrent-state reset in modular code." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs a glm-4v-9b loading failure; unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both are Qwen/MoE-related, but the concrete errors and affected setups differ." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Sliding-window Qwen3-MoE behavior vs a StableLm config field regression; different issues." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Special-token post-processor update bug vs wrong token IDs in AutoTokenizer; same broad area, but not the same bug." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "GenerationMixin import error vs a parallel script runtime issue; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Video-processing regression vs a `from_pretrained(weight_only=True)` loading error; different code paths." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer/model crashes with different symptoms and models." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "FP8 loading failure vs a Llava Next segmentation fault; not the same bug." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Metric-gathering label truncation vs SAM3 text/bbox behavior; separate issues." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Both mention serve, but one is a Gemma4Processor attribute crash and the other is a Qwen3.5 streaming inference failure." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Void segmentation map processing vs BarkProcessor voice preset handling; unrelated." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Runtime special-token update bug vs a broader version-to-version tokenization change report." + }, + { + "left": "issue:33357", + "right": "issue:35707", + "accept": false, + "reason": "MacOS CLIP bus error vs a progressive-generation `inputs_embeds`/`past_key_values` issue; unrelated." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary overstates the evidence for a duplicate pair. In the packet, `issue:44423` is a continuous-batching crash on Qwen3.5 with `AttributeError: 'str' object has no attribute 'to'`, while `issue:45406` is a Gemma4Processor `_tokenizer` attribute crash. They are both serve-related, but the concrete failures and models differ, so treating them as the same bug is not grounded enough. The rest of the soft-edge rejections are generally conservative, but the single accepted pair should be rejected." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 13, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:34567", + "issue:34634", + "issue:35707", + "issue:39692", + "issue:41720", + "issue:42886", + "issue:43381", + "issue:43421", + "issue:43531", + "issue:43550", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44779", + "issue:44843", + "issue:44898", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45859" + ], + "soft_pairs": [ + "issue:44492|issue:44509", + "issue:41720|issue:43746", + "issue:43606|issue:43720", + "issue:44779|issue:45812", + "issue:43550|issue:43653", + "issue:43873|issue:45704", + "issue:44514|issue:44545", + "issue:44625|issue:45479", + "issue:43606|issue:43653", + "issue:43531|issue:45759", + "issue:34634|issue:41720", + "issue:43421|issue:43927", + "issue:34567|issue:35707", + "issue:44368|issue:45357", + "issue:43782|issue:45381", + "issue:44898|issue:45072", + "issue:44451|issue:44991", + "issue:44077|issue:44625", + "issue:44987|issue:45042", + "issue:43531|issue:44589", + "issue:45759|issue:45859", + "issue:44062|issue:44451", + "issue:43421|issue:43653", + "issue:44918|issue:44936", + "issue:45588|issue:45759", + "issue:39692|issue:44610", + "issue:43381|issue:43844", + "issue:42886|issue:44843", + "issue:43421|issue:44186" + ], + "prepared_review_unit_hash": "521265de539230fa462e3424f8798d2984655bfe92859cfc9a3fb6d0494008ea", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 36032, + "estimated_input_tokens": 9008, + "estimated_eval_tokens": 18272 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a heterogeneous mix of unrelated issue reports; only two soft pairs look like true duplicates. There is no single cluster-wide canonical issue or PR.", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "Both touch docs, but one is a typo and the other is stale pipeline-task documentation; not the same bug." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Different models and failures: Qwen3 device-mapping CUDA assert vs GraniteSpeech local-checkpoint/PEFT loading." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both are loading/offload related, but Bark CPU offload device mismatch and BitNet packed-weight unpacking are different code paths." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but for different model families and symptoms; not the same underlying bug." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Model compile/SDPA failure vs tokenizer special-token registration/empty decode issue." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization/offloading behavior and a T5 Apex RMSNorm memory leak are unrelated bugs." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Same Qwen2_5_VLProcessor.apply_chat_template batched-input crash with padding=False; titles and failure mode match." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "One is Qwen3.5 config propagation for num_labels; the other is a broader sequence-classification loss degeneration issue across models." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Bark CPU offload device mismatch is unrelated to BigBirdTokenizer special-token decode behavior." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Both mention Qwen3.x, but sliding_window behavior and text_config unwrapping are separate configuration bugs." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping are entirely different problems." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Different tokenizer issues: runtime post-processor refresh vs DiaConfig losing custom token IDs on save/load." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counting and progressive generation with inputs_embeds/past_key_values are unrelated." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "One is a warning about tie_word_embeddings during LoRA fine-tuning; the other is a save_pretrained regression for visual encoder keys." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen VL-related, but one is a from_pretrained weight_only load error and the other is a video vision_position_ids bug." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver image-size interpolation and bf16 dtype mismatches in SwitchTransformers/TimmWrapperModel are different issues." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are model/tokenizer loading failures, but they affect different checkpoints and likely different root causes." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Optional post_init policy for patchtsmixer is unrelated to Qwen3.5 num_labels propagation." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "One is a specific model load failure; the other is an image-processor dependency regression on PIL backends." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Sliding-window behavior for Qwen3-MoE and a Float8 storage lookup error are unrelated." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Config unwrapping for composite Qwen multimodal models and CPU-offload incompatibility in rotary embedding are different bugs." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "AddedToken construction error and ScandiBERT loading failure are not the same underlying problem." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both involve special tokens, but runtime post-processor updates and BigBird mask-token registration are distinct failures." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "TRL SFT unpacking for Qwen3.5 embeddings and trainer.evaluate() failing after train() are different trainer issues." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention sinkless-model AttributeError and Qwen config unwrapping are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both mention processor/model mismatches, but for different models and different concrete failures." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Gradient checkpointing in eval mode and gradient blow-up under ZeRO-3 are separate training behaviors." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Both describe HF_HUB_OFFLINE failures when loading tokenizer assets; 44843 pinpoints the same offline-mode network call via model_info()." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Tokenizer post-processor refresh and LayoutLMv2 NER/batched padding crashes are different tokenizer bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the set is heterogeneous, the two accepted soft pairs are strongly supported by the titles/body themes, and the claim that there is no cluster-wide canonical issue or PR is conservative. I did not see any soft-edge verdict that overstates the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 14, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:39692", + "issue:40444", + "issue:41720", + "issue:42915", + "issue:43295", + "issue:43322", + "issue:43335", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43596", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43818", + "issue:43819", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44220", + "issue:44488", + "issue:44661", + "issue:44671", + "issue:44811", + "issue:44843", + "issue:44898", + "issue:45072", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45479", + "issue:45685", + "issue:45704", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:43994|issue:44671", + "issue:43525|issue:43531", + "issue:45704|issue:45859", + "issue:45081|issue:45356", + "issue:41720|issue:45704", + "issue:45356|issue:45907", + "issue:39692|issue:43873", + "issue:43596|issue:44220", + "issue:43746|issue:43873", + "issue:40444|issue:43746", + "issue:42915|issue:43746", + "issue:44220|issue:44661", + "issue:43540|issue:44008", + "issue:30064|issue:36010", + "issue:43720|issue:43819", + "issue:43618|issue:43697", + "issue:45183|issue:45479", + "issue:43653|issue:43720", + "issue:43335|issue:43756", + "issue:43295|issue:45834", + "issue:43716|issue:44008", + "issue:43550|issue:45072", + "issue:44062|issue:44488", + "issue:43550|issue:43819", + "issue:43322|issue:45685", + "issue:44186|issue:44898", + "issue:44843|issue:45081", + "issue:43577|issue:43818", + "issue:43531|issue:43643", + "issue:43421|issue:44811", + "issue:43653|issue:43819" + ], + "prepared_review_unit_hash": "eaed07aaf41249208937961e5af799853d5b8006e10066cdae0a63050c6aeb05", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37427, + "estimated_input_tokens": 9357, + "estimated_eval_tokens": 18970 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is highly heterogeneous: tokenizer regressions, vision/multimodal bugs, dtype/offload issues, config/model-loading regressions, and CI/documentation problems. None of the soft pairs look like the same underlying bug, so no duplicate merges are justified.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Both involve model output quality, but one is SigLIP2 inference/pipeline misuse and the other is a CamemBERT masked-LM regression in v5; different models and failure modes." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Llama4Config missing pad_token_id and Qwen3-MoE sliding_window behavior are unrelated config/model bugs." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "T5 Apex RMSNorm memory leak and Qwen3_5Moe CPU offload incompatibility affect different code paths and components." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both touch mistral regex handling, but 45081 is a tokenizer crash on backend_tokenizer access while 45356 is a Kimi-K2.5 regression about codec handling and warning text; not the same bug." + }, + { + "left": "issue:41720", + "right": "issue:45704", + "accept": false, + "reason": "Qwen3 auto device-map cuda assert and T5 RMSNorm memory leak are unrelated runtime issues." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Kimi-K2.5 tokenizer regression is about Mistral regex/codec behavior; list_repo_files revision forwarding is a hub API bug." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 doc example errors and quantization failure are about example/model usage, while 43873 is a general offloading-with-quantization issue with no matching model/path shown." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Both cause runtime failures, but deepspeed zero3 init with BertModel and _torch_extract_fbank_features are different subsystems and symptoms." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "GraniteSpeech PEFT checkpoint loading and offloading with quantization are different loading/offload bugs." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "Qwen2.5-VL iterable dataset with multiple images and GraniteSpeech PEFT local checkpoint loading do not share the same code path." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Qwen2.5 MoE FP8 config failure and GraniteSpeech adapter loading are unrelated." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction and add-new-model-like TOKENIZER_MAPPING_NAMES handling are different tokenizer/model utilities." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError and Gemma3n audio_mel_mask name collision are separate multimodal bugs." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Void segmentation-map processing and the GenerationMixin import error are entirely unrelated." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading and DAC from_latents vs forward mismatch are different model internals." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "CLIPOutput attentions assignment and RTDetrV2 differing outputs are unrelated model regressions." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "XOR validation for input_ids/inputs_embeds errors and single-label classification with num_labels=1 zero-loss behavior are different validation vs loss bugs." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and BitNet packed-weight loading are different issues." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "SwitchTransformers sparse layer creation and Smollm3 RoPE layer dropping are unrelated model-configuration bugs." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "processor.tokenizer regression and Kosmos2.5 long OCR index error are different multimodal/tokenization failures." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Mistral image preprocessor dtype mismatch and Gemma3n audio variable collision are unrelated model-specific bugs." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Both mention SDPA/dtype/runtime, but Bamba torch.compile failure and SwitchTransformers/TimmWrapperModel bfloat16 mismatch are different code paths." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken special-argument conflict and inability to load cjvt/sleng-bert are not the same underlying tokenizer bug." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Bamba torch.compile+SDPA failure and DAC from_latents mismatch are unrelated model/runtime issues." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Llava Next segmentation fault and MPS histogram not implemented for Int in MoE are different backend/model problems." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes on NER/padding versus Perceiver non-default resolution classification failure are unrelated." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizer regex/hub behavior, but one is unconditional model_info() breaking offline mode and the other is a tokenizer backend attribute crash; different fixes." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "BLIP2 dtype propagation and Video-LLaVA missing temporal attention/shared weights are unrelated multimodal architecture bugs." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Qwen3-MoE sliding_window and trust_remote_code AutoConfig missing fields are different configuration issues." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "TokenizersBackend post-processor refresh on special-token changes and Whisper batch_decode skip_special_tokens behavior are different tokenizer APIs." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and DAC forward/from_latents mismatch are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 15, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:42175", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43644", + "issue:43720", + "issue:43749", + "issue:43782", + "issue:43825", + "issue:43827", + "issue:43994", + "issue:44060", + "issue:44186", + "issue:44291", + "issue:44368", + "issue:44442", + "issue:44448", + "issue:44479", + "issue:44485", + "issue:44509", + "issue:44561", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44821", + "issue:44877", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45381", + "issue:45406", + "issue:45584", + "issue:45701", + "issue:45834" + ], + "soft_pairs": [ + "issue:43643|issue:44877", + "issue:43540|issue:45381", + "issue:44448|issue:44671", + "issue:43782|issue:44977", + "issue:45584|issue:45834", + "issue:43644|issue:43749", + "issue:44561|issue:45020", + "issue:43825|issue:43994", + "issue:44485|issue:44509", + "issue:44821|issue:45084", + "issue:39692|issue:45834", + "issue:30064|issue:36331", + "issue:41720|issue:44991", + "issue:44186|issue:44442", + "issue:43825|issue:43827", + "issue:44479|issue:45834", + "issue:43577|issue:43582", + "issue:44805|issue:44936", + "issue:44671|issue:45701", + "issue:43606|issue:45072", + "issue:34634|issue:36010", + "issue:44610|issue:45072", + "issue:43782|issue:45325", + "issue:42175|issue:45081", + "issue:43720|issue:45072", + "issue:45081|issue:45406", + "issue:43749|issue:44291", + "issue:44060|issue:44368" + ], + "prepared_review_unit_hash": "bebac7435379fda6964eeee8a05a66da5814ddd5a78e9a888179d4ca86619093", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35675, + "estimated_input_tokens": 8919, + "estimated_eval_tokens": 18094 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of unrelated Transformers bugs with only loose thematic overlap around v5 regressions, loading, and processor/tokenizer issues. I do not see any soft pair that is clearly the same underlying bug or change.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45020 is the best broad umbrella candidate because it covers the recurring theme of recent-version breakages around remote_code/model loading, but it is still only a partial fit and not a true duplicate of the whole set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the most representative open issue for the cluster\u2019s shared theme of v5 regressions affecting model loading and remote-code models.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config/loading behavior, but one is about missing fields from trust_remote_code and the other is strict config blocking granite_speech; different failure modes and targets." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Different Qwen model families and different bugs: video processing failure vs still-image RoPE/position_id scaling." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Both are output regressions, but they affect different models and tasks (Pegasus generation vs CamemBERT masked LM)." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Different code paths: from_pretrained weight_only loading error vs flash-attention generation issue." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty transcription handling and Kosmos2.5 long-OCR index errors are unrelated bugs." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both concern loading/state handling, but junk non-persistent buffers and FSDP CPU RAM-efficient loading are not the same concrete bug." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "44561 is a specific regression from removing is_torch_fx_available; 45020 is a broader umbrella for remote_code breakages, not the same concrete issue." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "One is a pipeline error message around removed translation tasks; the other is a SigLIP2 docs/model mismatch plus quantization failure." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation is unrelated to stale docs that still mention removed pipeline tasks." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and a template compilation TypeError are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "SigLIP2 documentation errors and Kosmos2.5 long OCR index errors are different problems." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Image processor void segmentation maps and CustomTrainer compute_loss kwargs are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "Qwen3 device-mapping CUDA assert and tokenizer loading for EMBEDDIA/est-roberta are different failures." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer/model issues: LayoutLMv2 NER/padding crash versus AutoTokenizer failing FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Both mention removed v5 pipeline tasks, but one is an incorrect runtime message and the other is stale docs; related, not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Qwen video-input regression and Kosmos2.5 OCR index errors are separate model/input bugs." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "One is a dtype propagation bug in Blip2 loading; the other is an Apple Silicon TypeError in caching_allocator_warmup." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Mask shape mismatch IndexError and trainer.evaluate() failing after train are not the same issue." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT masked-LM regressions and general tokenization changes are not the same concrete bug." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "CPU-offload device mismatch for bark-small and bfloat16 dtype mismatches in other models are distinct failures." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset behavior and a GenerationMixin import error are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch and bfloat16 dtype mismatch in inference are different bugs." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen-VL bugs: weight_only loading failure versus still-image temporal position_id scaling." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Backend dependency packaging and a Mistral tokenizer regex crash are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to dtype mismatch regressions." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Both are attribute errors in tokenizer/processor internals, but they affect different components and causes." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both involve loading/empty-weights paths, but FSDP CPU RAM-efficient loading and an unexpected _is_hf_initialized argument are distinct regressions." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both are tied-weights warnings, but one is an incorrect internal tying bug and the other is a user-facing config warning on a different model." + } + ] + }, + "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": 16, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43452", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43638", + "issue:43645", + "issue:43650", + "issue:43653", + "issue:43696", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43746", + "issue:43819", + "issue:43854", + "issue:43906", + "issue:43927", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44811", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45020", + "issue:45042", + "issue:45084", + "issue:45356", + "issue:45459", + "issue:45488", + "issue:45538", + "issue:45600", + "issue:45803" + ], + "soft_pairs": [ + "issue:43650|issue:43906", + "issue:43582|issue:44857", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:43526|issue:44554", + "issue:45459|issue:45803", + "issue:34634|issue:36331", + "issue:45084|issue:45538", + "issue:43742|issue:45020", + "issue:43329|issue:45600", + "issue:43653|issue:44912", + "issue:43638|issue:44936", + "issue:43452|issue:44991", + "issue:43746|issue:44811", + "issue:43257|issue:43329", + "issue:44589|issue:45042", + "issue:43257|issue:43696", + "issue:43854|issue:44977", + "issue:38175|issue:44610", + "issue:36010|issue:43645", + "issue:39692|issue:44912", + "issue:43819|issue:43927", + "issue:43454|issue:43577", + "issue:43720|issue:44610", + "issue:43550|issue:44912", + "issue:44568|issue:45488", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43329|issue:44479", + "issue:36010|issue:36331", + "issue:44568|issue:45356" + ], + "prepared_review_unit_hash": "ea0bb5d84edaf897c24d727d7d33b49f4b7bb21f96ccdbea8c321e294b20f758", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37228, + "estimated_input_tokens": 9307, + "estimated_eval_tokens": 18870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs mostly overlap only at a broad subsystem level (tokenizers, audio, vision, loading, training) but describe different concrete failures, so none look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a clear global canonical here; the set spans many unrelated bugs, so any choice would be arbitrary.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Completely unrelated: a vague request vs an isolated reproduction of a different upstream issue." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Different failures and code paths: Apple Silicon allocator TypeError vs CUDA AMP image-loss crash." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Both audio-related, but one is chat-template sampling rate and the other is DAC latent decoding mismatch." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Different vision bugs in different models; no shared root cause is evident." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "Unrelated model families and failures; a processor label bug is not the same as an attention correctness issue." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both mention exception handling, but they are different bugs in different functions and should not be merged." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "Different APIs and failure modes: Bark voice preset vs trainer compute_loss signature." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated issues: template compilation error vs tokenizer max_length misconfiguration." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Both involve loading, but one is a specific MobileLLM key error and the other is a broad remote_code regression." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Different areas: multimodal token counting vs stale auto_mapping references in CI." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer special-token registration is unrelated to MXFP4 quantization loading fallback." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer/deepspeed failures with different triggers and symptoms." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both are model-loading/tokenizer issues, but the affected paths and reported bugs differ." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Unrelated: PEFT local checkpoint loading vs Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Different bugs: Qwen3 MoE weight conversion/loading vs undefined video-token helper names." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Different incompatibilities: missing Float8 storage vs torchvision requirement in PIL image processors." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Different Qwen3/OOM-loading issues with no shared root cause shown." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Same broad generation/loading area, but different models and failure mechanisms." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision-related, but one is zero probabilities and the other is processor/model input-size mismatch." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "Different compatibility regressions: GenerationMixin import failure vs Jupyter custom-model initialization." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Documentation/example errors are not the same as MXFP4 quantization fallback behavior." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "Different components and failures: DAC latent conversion vs Dia config save/load token IDs." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "One is weight tying causing bad generation; the other is dtype propagation on load." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Completely different subsystems: packed-weight loading vs image processor resolution mismatch." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "Different model/runtime problems: torch.compile+SDPA vs quantization loading fallback." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both tokenizer regressions, but different tokenizer classes and different broken behaviors." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Unrelated model sliding-window bug vs image processor torchvision dependency regression." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Both audio, but sampling-rate defaults and decode special-token handling are distinct bugs." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Possible thematic overlap on video VLMs, but the reports describe different regressions and are not clearly the same bug." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Different breakages: import path change vs trainer method signature change." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both tokenizer regressions, but on different models and different underlying tokenizer handling." + } + ] + }, + "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": 17, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:33357", + "issue:34567", + "issue:38175", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43697", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43927", + "issue:43931", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44488", + "issue:44560", + "issue:44756", + "issue:44821", + "issue:44849", + "issue:44898", + "issue:44912", + "issue:44938", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45137", + "issue:45357", + "issue:45381", + "issue:45405", + "issue:45538", + "issue:45701", + "issue:45759", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:43749|issue:44756", + "issue:44849|issue:45701", + "issue:43643|issue:45759", + "issue:34567|issue:40990", + "issue:43329|issue:43450", + "issue:43257|issue:43931", + "issue:43606|issue:45859", + "issue:43257|issue:43756", + "issue:43697|issue:45357", + "issue:44987|issue:45538", + "issue:44291|issue:45042", + "issue:42915|issue:43742", + "issue:43452|issue:43582", + "issue:42915|issue:44821", + "issue:44987|issue:45907", + "issue:33357|issue:34567", + "issue:41720|issue:43540", + "issue:44479|issue:45381", + "issue:42915|issue:45538", + "issue:43927|issue:44912", + "issue:42175|issue:43824", + "issue:43317|issue:45538", + "issue:43577|issue:45072", + "issue:43540|issue:44479", + "issue:43540|issue:44560", + "issue:44062|issue:44991", + "issue:42175|issue:44938", + "issue:45137|issue:45405", + "issue:42175|issue:44488", + "issue:38175|issue:44898" + ], + "prepared_review_unit_hash": "1f59b41624637a42b01bf872abbbc812e7ff0642a4933cc8a809d5e35f04c3a7", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36619, + "estimated_input_tokens": 9155, + "estimated_eval_tokens": 18566 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are clearly unrelated despite superficial theme overlap (often just the same subsystem/model family). One soft duplicate stands out: the Qwen video-input regression report and the qwen2.5-vl vision_position_ids report look like the same underlying bug.", + "confidence": 0.9, + "canonical_issue_reason": "issue:44479 is the broadest, clearest report of the Qwen v5.3.0 video-input regression; issue:45381 appears to be the same bug narrowed to qwen2.5-vl/vision_position_ids.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the best canonical issue because it captures the full regression scope across affected Qwen video models, while still matching the specific qwen2.5-vl symptom in issue:45381.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Different loading problems: FSDP CPU/RAM-efficient loading vs Apple Silicon mmap/OOM mitigation." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Different bugs: Qwen3.5 output_hidden_states regression vs a tokenizer/version change report." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Different config-loading failures: missing fields from trust_remote_code vs composite Qwen text_config unwrapping." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Unrelated: TrainerState token counter vs high perplexity on a specific model/dataset." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Both are video-related, but one is a multimodal token-counting code bug and the other is batched processor shape handling." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Both involve Qwen3 loading, but one is accelerate/deepspeed weight conversion and the other is a weight-shape mismatch for Qwen3-VL." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Same general CPU-offload area, but different models and concrete failures." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different model-specific issues: Qwen3 MOE weight conversion vs Smollm3 RoPE layer dropping." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "Different subsystems: RTDetrV2 output regression vs Qwen3.5 save_pretrained key naming." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Different tokenizer/model-loading problems; only loosely related by loading behavior." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Different failures: init_empty_weights signature mismatch vs PIL backend torchvision dependency handling." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Different model/config bugs: FineGrainedFP8Config vs MobileLLM loading key error." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Different domains: GGUF loader breakage vs AppleSilicon allocator warmup TypeError." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Different issues: Qwen3Moe quantization/config vs loading AutoImageProcessor from a URL." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Different code paths: model load failure vs list_repo_files failing to forward revision." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Completely unrelated: MacOS CLIP bus error vs TrainerState token counting." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Both mention Qwen and CUDA/video, but one is device mapping on A800 and the other is video-input processing in Qwen3OmniMoe." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Both describe the same Qwen video-input regression; 45381 is the specific qwen2.5-vl manifestation of the broader bug in 44479." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated: Qwen3Moe FP8 config failure vs CLIPTokenizer max_length issue." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Different loading/config bugs: DiaConfig save/load token IDs vs MXFP4 quantization fallback." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Unrelated: TensorFlow extra installation problem vs missing Qwen2_5_VL import." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Different issues: device_map/offload loading failure vs tokenizer max_length default." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both are dtype-related, but different models and different failure modes; not the same concrete bug." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Both are video-input reports, but the model and failure mode differ; not enough evidence of one underlying bug." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Different Qwen video-input failures affecting different models and error paths." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer-loading issues; the model-specific symptom is not the same as the AddedToken keyword bug." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Unrelated: backend installation issue vs Python 3.14 load failure." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "Completely unrelated: DeepSpeed ZeRO3 deque error vs PEFT version pin mismatch." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Unrelated: TensorFlow backend packaging vs a specific model load failure." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different vision-model bugs: zero probabilities on SigLIP2 vs Perceiver non-default resolution failure." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The canonicalization is grounded in the packet: issue:44479 is the broad Qwen v5.3.0 video-input regression, and issue:45381 is a narrower qwen2.5-vl manifestation of the same symptom. The soft-edge verdicts are generally conservative and stay within what the titles support; no pair is overstated as a duplicate without evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 18, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:28282", + "issue:29127", + "issue:34567", + "issue:34689", + "issue:36331", + "issue:41762", + "issue:42915", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43582", + "issue:43643", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43782", + "issue:43906", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44484", + "issue:44488", + "issue:44514", + "issue:44561", + "issue:44589", + "issue:44704", + "issue:44737", + "issue:44792", + "issue:44821", + "issue:44898", + "issue:44936", + "issue:44964", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45325", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45588", + "issue:45600", + "issue:45823" + ], + "soft_pairs": [ + "issue:28282|issue:34689", + "issue:44737|issue:45588", + "issue:43742|issue:44291", + "issue:42915|issue:43749", + "issue:43906|issue:45381", + "issue:43526|issue:45479", + "issue:28282|issue:29127", + "issue:43540|issue:45823", + "issue:43756|issue:45325", + "issue:43582|issue:43782", + "issue:43493|issue:43994", + "issue:34567|issue:36331", + "issue:44291|issue:44821", + "issue:44062|issue:45081", + "issue:43643|issue:45375", + "issue:43452|issue:44488", + "issue:44792|issue:44964", + "issue:45042|issue:45081", + "issue:43742|issue:44589", + "issue:43531|issue:44821", + "issue:45405|issue:45600", + "issue:43697|issue:45216", + "issue:43688|issue:43749", + "issue:44484|issue:44704", + "issue:43720|issue:44898", + "issue:44514|issue:45381", + "issue:41762|issue:44936", + "issue:43643|issue:44561" + ], + "prepared_review_unit_hash": "6d3eca9783ad63ca7a1d855bbf362c4b485c454df9fd189ef54724c4456ff49c", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36379, + "estimated_input_tokens": 9095, + "estimated_eval_tokens": 18446 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the proposed pairs mostly share only broad areas like loading, config, trainer, or multimodal code, but not the same concrete bug/change. I would not merge any of the soft edges.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43749 is the highest-signal issue in the set, with the most discussion and inbound references, and it represents a broad, user-impacting regression more than the other reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43749 is the best representative issue here because it is broad, well-discussed, and likely to anchor triage better than the narrower one-off reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Both are model-loading failures, but one is a missing PyTorch dependency message and the other is a specific Llama 3.2 Vision breakage; different bugs." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "Different code paths: XLNet CPU tensor placement vs. flash_attention sink/s_aux handling." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "A key-error while loading a specific model is not the same as an init_empty_weights signature regression." + }, + { + "left": "issue:42915", + "right": "issue:43749", + "accept": false, + "reason": "Both involve advanced loading/runtime settings, but one is Qwen3Moe FP8 behavior and the other is FSDP CPU RAM-efficient loading; distinct failures." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "The first is an isolated reproduction of an existing issue; the second is a Qwen2.5-VL vision position-id bug. No concrete match." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "BEiT image label reduction and sequence-classification loss degeneracy are unrelated behaviors." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "ImportError for missing PyTorch is unrelated to LayoutLMv3 box-validation error messaging." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Different models and different failures: Qwen3OmniMoe video processing vs Gemma4 device placement mismatch." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both mention RoPE/position handling, but they affect different models and different bugs (layer dropping vs. temporal scaling)." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError is unrelated to Qwen3VL weight_only loading." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": false, + "reason": "Both concern SigLIP2, but one is a HF-vs-JAX discrepancy and the other is bad outputs with AutoModel/pipeline; not clearly the same defect." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "TrainerState token counting not updating is not the same as CustomTrainer.compute_loss receiving an unexpected kwarg." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized and loading AutoImageProcessor from URL are different failure modes." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer AddedToken kwarg collision and Mistral regex patch crashing on backend_tokenizer are unrelated tokenizer bugs." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config fields, but one is AutoConfig losing fields under trust_remote_code and the other is a specific Qwen3_5MoeVisionConfig field being dropped by strict parsing." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "GGUF loading regression and a model-specific load failure are too different to be duplicates." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Both are multimodal load/test failures, but they target different models and different symptoms." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "PIL image processors requiring torchvision and a Mistral tokenizer regex crash are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "A MobileLLM key error and missing Float8 storage support are different loading/runtime issues." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and AutoImageProcessor URL loading are unrelated." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "A version pin on PEFT and stale auto_mappings references to removed configs are different maintenance issues." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "RTDetrV2 output divergence and Qwen3.5 save_pretrained regression are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization in OLMoE/GPT Oss is unrelated to FSDP CPU RAM-efficient loading." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "save_pretrained shard-size behavior and AutoProcessor kwarg forwarding are different API issues." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading and Perceiver non-default-resolution classification are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL-related, but one is batched chat-template padding and the other is video vision_position_ids; not the same bug." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading index error and trainer.evaluate() after train() are different failures." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Missing config fields under trust_remote_code and removal of is_torch_fx_available breaking remote-code models are separate compatibility problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 19, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:35141", + "issue:38175", + "issue:41720", + "issue:43295", + "issue:43329", + "issue:43452", + "issue:43531", + "issue:43550", + "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:44514", + "issue:44568", + "issue:44625", + "issue:44743", + "issue:44811", + "issue:44843", + "issue:44877", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45005", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45440", + "issue:45588", + "issue:45701", + "issue:45704", + "issue:45823" + ], + "soft_pairs": [ + "issue:24643|issue:29127", + "issue:43452|issue:43577", + "issue:44625|issue:44877", + "issue:43452|issue:44843", + "issue:44466|issue:45005", + "issue:43295|issue:45356", + "issue:44514|issue:45290", + "issue:43819|issue:44811", + "issue:44464|issue:44743", + "issue:43653|issue:44568", + "issue:44936|issue:45823", + "issue:30064|issue:33666", + "issue:43688|issue:45440", + "issue:38175|issue:43295", + "issue:44361|issue:44442", + "issue:43688|issue:45704", + "issue:43653|issue:44361", + "issue:28282|issue:32090", + "issue:41720|issue:43906", + "issue:28282|issue:33357", + "issue:43577|issue:43697", + "issue:43646|issue:43749", + "issue:28282|issue:35141", + "issue:43688|issue:45701", + "issue:44843|issue:44991", + "issue:43531|issue:43742", + "issue:43653|issue:43927", + "issue:43550|issue:43927", + "issue:44464|issue:44977", + "issue:43329|issue:45325", + "issue:43577|issue:45588" + ], + "prepared_review_unit_hash": "28c4afded6bdf549430a6140a208ba05460ceeea05d35ef782c05e6932d4b538", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37184, + "estimated_input_tokens": 9296, + "estimated_eval_tokens": 18848 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This looks like a noisy mix of mostly unrelated issue reports, with only loose thematic overlap around tokenizer/config/processor regressions in v5. I do not see any soft pair that is clearly the same underlying bug or change.", + "confidence": 0.69, + "canonical_issue_reason": "issue:44843 is the clearest concrete regression in a shared high-impact code path (`AutoTokenizer.from_pretrained` / tokenizer patching) and is representative of the broader v5 tokenizer-loading theme in this set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44843 is the most central and actionable issue among the loosely related tokenizer/config regressions, with a specific failure mode and an obvious shared entry point.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "Different domains and failure modes: DeepSpeed training weight-shape error vs LayoutLMv3 box/clarity issue." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "One is gguf/AutoTokenizer-Model loading breakage; the other is dtype propagation in BLIP2. Not the same bug." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config propagation/loading, but they are different fields and different failure paths." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "Both touch tokenizer loading, but one is gguf_file support and the other is an offline-mode Mistral regex/model_info regression." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Related tied-weights theme, but one is device-dependent lm_head.weight serialization and the other is broader translation-model tied-weight behavior; not clearly one concrete bug." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Both are regressions, but one is processor/tokenizer API breakage and the other is Kimi codec/regex warnings. Different code paths." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both crash in chat-template handling, but the triggers are different (batched padding vs tool-call messages with no content)." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "Different components entirely: DAC latent decoding vs Whisper processor batch_decode behavior." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both concern generation behavior, but one is compiled forward inconsistency and the other is recurrent-state reset with cache. Different bugs." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both are special-token-related tokenizer issues, but they affect different tokenizers and different code paths." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Training/eval lifecycle bug vs device-mapping forward mismatch in Gemma4 PLE. Not the same issue." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Both are multimodal-related at a high level, but one is segmentation map processing and the other is Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-adjacent, but one is auxiliary-loss normalization and the other is DeepSeekV3 implementation divergence." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Different symptoms and subsystems: SigLIP2 zero probabilities vs processor/tokenizer regression." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer-loading failures, but for different tokenizer classes and likely different parsing issues." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Aux-loss normalization bug vs T5 silently using apex RMSNorm memory-leak path. Not the same underlying problem." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Special-token registration bug vs MLukeTokenizer attribute error. Too different to merge." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "Both error on missing/unsupported types, but one is missing PyTorch import and the other is `_gpu_broadcast_one` with NoneType in Trainer." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Both mention runtime failures on large models, but the concrete causes are unrelated (cudaErrorAssert vs isolated reproduction of another issue)." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "ImportError for missing PyTorch vs Mac bus error in CLIP model usage. Different failure classes." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "BLIP2 dtype loading bug vs RTDetrV2 output divergence in v5. Not the same code path." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Both are v5 regressions, but one is custom model initialization and the other is FSDP CPU RAM efficient loading." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "Missing PyTorch import vs post_init reinitializing output embeddings after resizing. Unrelated bugs." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization vs generic tokenization changes. Too broad and not the same issue." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but one is offline-mode model_info behavior and the other is a specific model tokenizer load failure; not enough evidence of one bug." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Sliding-window Qwen3-MoE bug vs MobileLLM key error during load. Different concrete failures." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "BigBird special-token registration issue vs DiaConfig losing custom token IDs on save/load." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile+SDPA failure vs config persistence bug. Different layers of the stack." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency vs Qwen3.5 flash-attention generation bug. Same general area, but different problems." + }, + { + "left": "issue:43329", + "right": "issue:45325", + "accept": false, + "reason": "Both are multimodal/VL issues, but one is undefined helper usage in token counting and the other is RoPE position-id scaling." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "BLIP2 dtype issue vs flash_attention crash on `s_aux=None`. Different models and code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 20, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:28218", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:43122", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43688", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43825", + "issue:43844", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44625", + "issue:44821", + "issue:44849", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45357", + "issue:45405", + "issue:45584", + "issue:45812" + ], + "soft_pairs": [ + "issue:43577|issue:44554", + "issue:44479|issue:44625", + "issue:43550|issue:44361", + "issue:43122|issue:43906", + "issue:32090|issue:34567", + "issue:41720|issue:44464", + "issue:43504|issue:43550", + "issue:43504|issue:43720", + "issue:43504|issue:44610", + "issue:32090|issue:33666", + "issue:44849|issue:45357", + "issue:43452|issue:44451", + "issue:43742|issue:44821", + "issue:43278|issue:43688", + "issue:44568|issue:45812", + "issue:33666|issue:36010", + "issue:43493|issue:43825", + "issue:43262|issue:43295", + "issue:43525|issue:43572", + "issue:43606|issue:43927", + "issue:43720|issue:43927", + "issue:43756|issue:44913", + "issue:28218|issue:33357", + "issue:33666|issue:36331", + "issue:43493|issue:43844", + "issue:43720|issue:44361", + "issue:39692|issue:43493", + "issue:43278|issue:43844", + "issue:43540|issue:44977", + "issue:44964|issue:45405", + "issue:43334|issue:43572", + "issue:44625|issue:45584" + ], + "prepared_review_unit_hash": "c3b41160e4405c98d3140544511072dee6ba99e8a4ff06064ced3d2e126fc6fd", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37393, + "estimated_input_tokens": 9349, + "estimated_eval_tokens": 18954 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is largely heterogeneous; most items are distinct model-, trainer-, or config-specific bugs rather than true duplicates. No soft pair looks safely mergeable into one fix. The broadest representative issue is the Granite tokenizer regression.", + "confidence": 0.41, + "canonical_issue_reason": "Issue 45812 is the strongest representative of the tokenization-regression theme: broad impact, clear v4\u2192v5 breakage, and a concrete tokenizer symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45812 is the best standalone issue in this set because it is specific, high-impact, and most likely to attract or anchor related tokenizer fixes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "Different failures: Blip2 dtype casting vs MPS attention correctness." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Qwen video-input regression and Qwen3.5 num_labels propagation are different code paths." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Unrelated: torch.compile/SDPA issue vs tokenizer AttributeError." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "One is a tokenization regression; the other is a reproduction of a separate issue with no clear overlap." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast TypeError and token-count tracking are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Different inference bugs: auto device mapping assert vs compiled-forward chunked generation." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Legacy-field loading bug vs SDPA compile bug in a different model." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Different subsystems: model loading preset vs BitNet packed-weight loading." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Pretrained loading failure and processor image-size mismatch are not the same bug." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast error is unrelated to Qwen2-VL multi-GPU training." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen3.5 issues: hidden-states output vs save_pretrained visual-key regression." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "GGUF loading breakage and ScandiBERT load failure do not look like the same defect." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "MobileLLM key error and AutoImageProcessor URL loading are separate problems." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Mixed precision dtype drift and auxiliary-loss normalization are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and concrete behaviors." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Qwen2-VL training issue vs GenerationMixin import error are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation mismatch and pipeline translation-message bug are different concerns." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat-template sampling-rate default and processor/tokenizer regression are not the same bug." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both mention missing pad token fields, but they hit different configs and identifiers (id vs idx)." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch and DiaConfig save/load token-ID loss are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "BitNet packed-weight loading and DiaConfig token-ID persistence are different failures." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "RoPE-layer truncation bug and rotary_pct reload regression do not share a concrete code path." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer added-space behavior and MacOS CLIP bus error are clearly unrelated." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training issue vs custom compute_loss signature break are different problems." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 discrepancy and ZeRO-3 gradient explosion are not the same bug." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet accelerate loading and MLukeTokenizer task AttributeError are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Docs-example errors and implementation discrepancy in SigLIP2 are different issue types." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Training/evaluate dtype mismatch is unrelated to gradient growth under ZeRO-3." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Video-input processing failure and flash-attention generation bug are different code paths." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model load regression and unreleased PEFT minimum-version bump are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Qwen3-VL pad_token_id attribute error and StableLm pad_token_idx issue are different configs." + }, + { + "left": "issue:44625", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and Whisper empty-transcription generation are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 21, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:28218", + "issue:29942", + "issue:30333", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:39692", + "issue:43232", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43504", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43824", + "issue:43927", + "issue:43994", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44464", + "issue:44466", + "issue:44488", + "issue:44493", + "issue:44521", + "issue:44589", + "issue:44734", + "issue:44792", + "issue:44843", + "issue:44849", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45290", + "issue:45405", + "issue:45520", + "issue:45584", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43257|issue:43299", + "issue:43756|issue:45083", + "issue:44488|issue:44843", + "issue:43334|issue:45759", + "issue:45200|issue:45229", + "issue:43646|issue:44466", + "issue:43824|issue:44589", + "issue:39692|issue:43295", + "issue:45229|issue:45823", + "issue:44589|issue:45520", + "issue:33357|issue:33666", + "issue:43572|issue:44291", + "issue:43504|issue:43606", + "issue:43927|issue:44361", + "issue:44423|issue:44734", + "issue:43504|issue:43653", + "issue:43575|issue:45405", + "issue:44464|issue:45584", + "issue:43994|issue:44493", + "issue:43278|issue:43701", + "issue:43606|issue:44112", + "issue:44792|issue:45405", + "issue:29942|issue:30333", + "issue:44521|issue:45290", + "issue:28218|issue:34567", + "issue:43232|issue:44849" + ], + "prepared_review_unit_hash": "853688ee1cbf145803a8e7f2a6f775323ca49f07f18e4fc442a4fe721e971256", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 34989, + "estimated_input_tokens": 8748, + "estimated_eval_tokens": 17752 + }, + "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 that share broad keywords like model loading, multimodal support, generation, or tokenizer behavior. The soft pairs are topical lookalikes, but they do not appear to be the same underlying bug/change.", + "confidence": 0.41, + "canonical_issue_reason": "issue:43646 is the broadest representative of the cluster: a general Transformers 5.0 regression affecting custom model initialization, which overlaps with several other loading/init-style issues here.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best overall issue candidate because it is the most general and central to the cluster\u2019s common theme of regression in model initialization/loading.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen3/MoE loading, but one is about accelerate+deepspeed weight conversion and the other about multimodal config unwrapping; different failure modes." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "They are both model-architecture issues, but the reported bugs are unrelated: RoPE layer dropping vs a feature-extraction helper behaving unexpectedly." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "One is a specific model load failure, the other is an offline-hub regression in tokenizer patching; not the same code path." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Both touch Qwen VL/multimodal loading, but one is a missing pad_token_id error and the other is from_config not unwrapping text_config; related area, different bug." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Both mention Gemma 4, but one is a training input-type default issue and the other is a multi-GPU inference OOM; not the same underlying problem." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "General version regressions, but custom model initialization and tied-weight serialization are distinct behaviors and code paths." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Import error for a Qwen VL class and a missing Float8 storage type are unrelated bugs." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Both are model/example regressions, but one is a SigLIP2 doc example problem while the other is a custom multimodal tokenizer API breakage." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Both concern Gemma4 multi-GPU inference, but one is OOM and the other is a device mismatch during forward; different concrete failures." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Storage-type lookup failure and flash_attn import key error are unrelated infrastructure bugs." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "Both are multimodal/model-related, but CLIP bus error on macOS and Qwen2-VL multi-GPU training are not the same issue." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Both surfaced around the 5.0 transition, but missing pad_token_idx and unexpected _is_hf_initialized are separate API regressions." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Different models and different failure modes: legacy field load issue vs CPU offload device mismatch." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig token IDs being lost on save/load is unrelated to MLukeTokenizer AttributeError failures." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are server-side crashes, but one is multimodal input handling and the other is KV-cache continuation indexing; not the same bug." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Unrelated model-loading issue versus tokenizer special-token registration bug." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "Large-model tensor-parallel OOM and a PEFT version bump problem are entirely different." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency and Whisper empty-transcription handling after token alignment are different generation bugs." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and unexpected position-id keys are distinct symptoms with different likely causes." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "A dtype drift in evaluation and a resume_from_checkpoint key mismatch are not the same underlying defect." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "One is a real CPU-offload device mismatch, the other is a stale CI test; they are not the same bug." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A janus model test failure and a PEFT minimum-version bump are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures and MLFlow reporting after job failure are unrelated." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both involve apply_chat_template, but one is all-zero assistant masks for multimodal inputs while the other is a crash on tool-call assistant messages; different edge cases." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing after added tokens and TrainerState token counters are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "One concerns update_model_kwargs after sync_gpus, the other output_hidden_states in Qwen3.5; no shared 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": 2, + "component_count": 17, + "review_unit_index": 22, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:42915", + "issue:43295", + "issue:43334", + "issue:43388", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43540", + "issue:43572", + "issue:43582", + "issue:43701", + "issue:43824", + "issue:43844", + "issue:43873", + "issue:43957", + "issue:43975", + "issue:44315", + "issue:44464", + "issue:44466", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44792", + "issue:44849", + "issue:44898", + "issue:44936", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45325", + "issue:45356", + "issue:45412", + "issue:45446", + "issue:45520", + "issue:45563", + "issue:45701", + "issue:45823" + ], + "soft_pairs": [ + "issue:43844|issue:44964", + "issue:45084|issue:45520", + "issue:44554|issue:45446", + "issue:43582|issue:44977", + "issue:15354|issue:38175", + "issue:44568|issue:45701", + "issue:43540|issue:45200", + "issue:37428|issue:43957", + "issue:45072|issue:45198", + "issue:45200|issue:45823", + "issue:44315|issue:44849", + "issue:44554|issue:45356", + "issue:43493|issue:43701", + "issue:43295|issue:44610", + "issue:43873|issue:44464", + "issue:44466|issue:45127", + "issue:44898|issue:45412", + "issue:44792|issue:45563", + "issue:37428|issue:43824", + "issue:43572|issue:44987", + "issue:45200|issue:45325", + "issue:43572|issue:43957", + "issue:43844|issue:44936", + "issue:43295|issue:43450", + "issue:43334|issue:43525", + "issue:43824|issue:43975", + "issue:43295|issue:43873", + "issue:43388|issue:43526", + "issue:42915|issue:43824", + "issue:38175|issue:45412", + "issue:28218|issue:35141", + "issue:38175|issue:43493" + ], + "prepared_review_unit_hash": "d29a5f1708e952429fe81e1fcfa32ee484f707c95c8c45e266928ac5fbc2dbb4", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37531, + "estimated_input_tokens": 9383, + "estimated_eval_tokens": 19022 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated transformer bugs. The only clear duplicate-like pair is the missing `pad_token_id` config regression affecting two different model configs; all other soft pairs should stay separate.", + "confidence": 0.88, + "canonical_issue_reason": "issue:43334 is the clearest representative of the shared `pad_token_id`-missing regression and has the most explicit loading error; it also matches issue:43525 closely enough to treat as the same bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43334 is the best issue to keep as the canonical anchor: it is specific, reproducible, and captures the shared config-attribute failure more cleanly than the nearby duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "Different failures: DeepSpeed/ZeRO gradient growth vs model-loading breakage for Phi-4 multimodal." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Unrelated code paths: compile error on template nodes vs Python 3.13 flash-attn import lookup." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "Different bugs in different attention utilities: MPS correctness issue vs a version-check/import bug." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError is unrelated to Qwen3.5 flash-attention generation behavior." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "JIT scripting/export failure and SigLIP2 zero-probability issue are not the same bug." + }, + { + "left": "issue:44568", + "right": "issue:45701", + "accept": false, + "reason": "Both involve tokenization, but one is a specific special-token bug while the other is a broad version-regression report." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing error in Qwen3OmniMoe vs Gemma 4 text-only fine-tuning token-type handling." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Different import/load failures: missing `_flash_supports_window_size` vs meta-device loading breakage." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "Different subsystems: bfloat16 dtype mismatch in inference vs Wav2Vec2 save/tokenization failure." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Gemma 4 token-type-id defaulting and device-map forward mismatch are separate issues." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Model-init/Liger Kernel application issue is unrelated to Qwen3.5 hidden-state output bug." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness and tokenizer codec regression are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 implementation discrepancy vs checkpoint resume key mismatch are different problems." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor/tokenizer API regression is unrelated to OmDet-Turbo image-size mismatch." + }, + { + "left": "issue:43873", + "right": "issue:44464", + "accept": false, + "reason": "Quantization offloading behavior and compiled-forward chunked generation are different code-path bugs." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both mention weights, but one is serialization/device-dependent and the other is LoRA merge collapse with extended vocab." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver resize failure and RT-DETR memory leak are unrelated." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "A Janus test failure is not the same as a stale paged-generate warning." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are import-related, but they target different missing symbols/classes and different failure modes." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "StableLm pad-token config regression is unrelated to loading `physical-intelligence/fast` on newer transformers." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Token-type-id defaults and Qwen2.5-VL rope-position scaling are separate multimodal bugs." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Config attribute regression and meta-device loading breakage do not share the same underlying fix." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "Training-gradient anomaly and trainer.evaluate() failing after train are different issues." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor regression with `processor.tokenizer` is not the same as batched video shape handling." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": true, + "reason": "Both report the same concrete `AttributeError` for missing `pad_token_id` on config objects during model loading; a shared fix is plausible." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "Missing Qwen2_5_VL import and Deepseek tokenizer detokenization regression are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor API breakage and quantization offloading behavior are separate problems." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Different label-handling bugs in different utilities: metric gathering vs Beit image processor reduction." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "FineGrainedFP8Config failure on Qwen3Moe is unrelated to missing Qwen2_5_VL import." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 probability anomaly and RT-DETR memory release issue are unrelated." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer adding an extra space and output embeddings reinitialized after resize are distinct bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The canonical anchor choice for issue:43334 vs issue:43525 is conservative and supported by the titles, and the remaining soft-edge verdicts mostly stay on the safe side by rejecting only on clear topical separation. I don\u2019t see an overstatement that would require rejection." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 23, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:29942", + "issue:32090", + "issue:37428", + "issue:39692", + "issue:43262", + "issue:43278", + "issue:43335", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43856", + "issue:43901", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44351", + "issue:44360", + "issue:44442", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44610", + "issue:44743", + "issue:44779", + "issue:44857", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45381", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:44442|issue:45198", + "issue:43278|issue:43856", + "issue:44514|issue:44521", + "issue:43653|issue:44112", + "issue:43827|issue:43901", + "issue:43450|issue:43575", + "issue:43450|issue:43493", + "issue:44206|issue:45584", + "issue:45127|issue:45245", + "issue:44360|issue:44561", + "issue:43819|issue:45083", + "issue:43262|issue:43450", + "issue:44610|issue:44857", + "issue:43819|issue:44112", + "issue:37428|issue:43425", + "issue:43278|issue:43825", + "issue:43335|issue:43550", + "issue:43606|issue:45083", + "issue:44857|issue:45593", + "issue:44448|issue:44743", + "issue:45290|issue:45381", + "issue:45200|issue:45588", + "issue:29942|issue:32090", + "issue:37428|issue:44351", + "issue:39692|issue:43526", + "issue:43611|issue:43931", + "issue:44206|issue:45823", + "issue:44462|issue:44561", + "issue:44561|issue:44779", + "issue:43335|issue:43653", + "issue:43819|issue:44493", + "issue:43550|issue:44112" + ], + "prepared_review_unit_hash": "2a7a48602d9b848041ccee4dbf742de184eb6ec0a3b0dfe0aaaf53744378afb1", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37283, + "estimated_input_tokens": 9321, + "estimated_eval_tokens": 18898 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous: the soft pairs share broad subsystems or keywords but do not describe the same underlying bug/change closely enough to merge as duplicates. No soft edge is strong enough to accept. The best anchor issue is the multimodal `apply_chat_template` regression (#44521), which is the most central and discussed concrete user-facing bug in the set.", + "confidence": 0.58, + "canonical_issue_reason": "#44521 is the clearest central issue: it targets a concrete multimodal `apply_chat_template` bug, has the most inbound references/discussion among the set, and is more representative than the narrower or unrelated regressions.", + "canonical_pr_reason": null, + "best_issue_reason": "#44521 is the strongest global issue candidate because it describes a specific, reproducible API failure with broader applicability than the other items and appears to be the most actively referenced issue here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Both are tokenizer/loading problems, but they affect different models and failure modes (`AutoTokenizer` load vs save_pretrained/tokenization)." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "One is a dtype regression between train/eval; the other is a training memory issue. Same area, different bug." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both involve `apply_chat_template`, but one is a batched-input crash and the other is wrong assistant masks; not the same defect." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "Unrelated issues: BigBird tokenizer special-token decoding vs a GraniteSpeech CI device-override test." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs-related, but they cover different pipeline APIs and different deprecations/behavior changes." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Video processor shape bug vs OOM when loading a large model with tensor parallelism; no shared code-path." + }, + { + "left": "issue:43450", + "right": "issue:43493", + "accept": false, + "reason": "Different model families and failures: batched video processor shape vs SigLIP2 implementation mismatch." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Feature extractor argument regression vs Whisper empty-transcription failure; different processing paths." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA/tied-embeddings model collapse is unrelated to the category-count runtime error." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "Completely different topics: DSA indexer ReLU discussion vs v5 `is_torch_fx_available` removal breakage." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent/forward mismatch and a Qwen3-Omni helper-length bug are unrelated implementation issues." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate default vs batched video processor output shape." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor size mismatch vs AMP/CUDA crash in a different loss module." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "No overlap beyond both being model-related; the bugs are entirely different." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "Importing a removed flash-attention helper is not the same as a broad Torch 2.10 compatibility report." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype regression and a pipeline error-message/docs issue are distinct." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers config layer-count bug vs Bamba SDPA/torch.compile failure; different models and code paths." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to the Qwen3-Omni feature-length helper behavior." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "AMP crash in LwDetrImageLoss vs missing auxiliary losses in D-FINE; not the same underlying bug." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Different regressions: Pegasus output changes across versions vs recurrent state reset in modular Qwen3." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "One is chat-template tool-call crashing, the other is wrong video vision position ids; different failures." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 multimodal token-type defaults and flash_attention sinkless-model crash are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention test failures and `_gpu_broadcast_one` NoneType errors are different runtime problems." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and packages; not the same breakage." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 docs/model example problems are unrelated to BeitImageProcessorFast label reduction." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Base-model-prefix loading breakage and Qwen3-VL weight-shape mismatch are distinct loading failures." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Both mention device mismatch, but they involve different models, setups, and code paths." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Tokenizer.json precedence is unrelated to the v5 `is_torch_fx_available` removal regression." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Different breakages: remote-code import helper removal vs Deepseek tokenizer output regression." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "Sparse-layer config bug and BigBird tokenizer special-token issue are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC latent mismatch is unrelated to position-id key warnings across models." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure and GraniteSpeech CI stale test are different issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 24, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:40444", + "issue:43335", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43701", + "issue:43720", + "issue:43723", + "issue:43873", + "issue:43927", + "issue:44112", + "issue:44292", + "issue:44448", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45310", + "issue:45372", + "issue:45459", + "issue:45478", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45593", + "issue:45698", + "issue:45712", + "issue:45803", + "issue:45859" + ], + "soft_pairs": [ + "issue:43335|issue:43504", + "issue:45310|issue:45478", + "issue:29127|issue:32090", + "issue:44855|issue:45083", + "issue:45588|issue:45859", + "issue:43335|issue:45083", + "issue:39692|issue:44493", + "issue:44292|issue:45520", + "issue:44448|issue:44779", + "issue:38175|issue:44493", + "issue:43335|issue:45072", + "issue:43335|issue:45593", + "issue:43720|issue:44112", + "issue:44977|issue:45229", + "issue:40444|issue:43526", + "issue:34689|issue:35141", + "issue:43723|issue:44554", + "issue:43606|issue:44857", + "issue:44448|issue:44977", + "issue:44857|issue:45072", + "issue:44568|issue:45491", + "issue:28218|issue:32090", + "issue:43927|issue:45698", + "issue:44977|issue:45563", + "issue:45198|issue:45803", + "issue:29942|issue:35141", + "issue:43701|issue:45083", + "issue:45459|issue:45712", + "issue:43873|issue:44493", + "issue:37428|issue:44987", + "issue:43550|issue:45083", + "issue:45372|issue:45588" + ], + "prepared_review_unit_hash": "7a7984a3a8d71bd48e759aa74516c38a527fb39c169b2f9ffd21896de852ae3f", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37529, + "estimated_input_tokens": 9383, + "estimated_eval_tokens": 19022 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a bag of unrelated Transformers bug reports. The only clear duplicate pair is the Qwen3.5 MoE from_pretrained regression: 45310 and 45478. All other soft matches are superficial topic/subsystem similarity and should be rejected.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45310 is the original report in the only obvious duplicate pair; it names the concrete Qwen3.5 MoE from_pretrained regression and predates issue:45478.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best representative issue because it is specific, concrete, and has a true duplicate counterpart in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "Different bugs in different BEiT/SwitchTransformers code paths; only broad model-family similarity." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same Qwen3.5 MoE from_pretrained failure, same title, and 45478 is a later duplicate report of the same regression." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 error-message clarity vs Trainer/_gpu_broadcast_one NoneType crash; unrelated failures." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 IndentationError in DebertaV2 import vs qwen3_omni_moe feature-length helper behavior; different code paths." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Both involve offload/attention-related areas, but one is a flash_attention crash on s_aux=None and the other is a rotary embedding CPU-offload incompatibility." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "Different models and defects; one is sparse-layer config creation, the other is a helper-length calculation bug." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 docs example errors vs unexpected position-id keys across many models; not the same underlying bug." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime error vs Python 3.13 flash_attn import KeyError; different failure modes." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus v4/v5 output mismatch vs Deepseek tokenizer regression; both tokenizer/generation related but not the same bug." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 vs generic unexpected position-id keys; different symptoms and likely causes." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Sparse-layer config bug vs dtype mismatch in bfloat16 inference; unrelated issues." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation vs D-FINE auxiliary-loss behavior; different subsystems and outcomes." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "Both CI-related, but one is packed-weight loading with accelerate and the other is a stale device override test; not the same bug." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3.5 flash-attention generation issue vs Gemma4 multi-GPU CUDA OOM; different concrete problems." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "IterableDataset multi-image finetuning failure vs BeitImageProcessorFast reduce_labels bug; unrelated." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Llama 3.2 Vision model loading breakage vs embedding reinitialization after resize; both model-loading related but distinct root causes." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "AutoTokenizer v5 loading issue vs MPS attention correctness when value head dim differs; unrelated bugs." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch in Bark vs LwDetrImageLoss AMP/CUDA crash; different code paths and symptoms." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different models and regressions: Pegasus output mismatch vs Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "AMP/CUDA loss crash vs bfloat16 dtype mismatch in inference; not the same underlying issue." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer add_special_tokens regression vs Gemma3 NaN embeddings from sliding-window attention; different components." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer spacing bug vs Trainer GPU broadcast NoneType error; unrelated." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "DiaConfig losing custom token IDs after save/load vs from_pretrained loading wrong custom module; both persistence-related but different failures." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation failure vs a stale warning in paged generate; not the same bug." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure vs bare except swallowing errors in FuyuBatchFeature; different models and error mechanisms." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures vs output embedding reinitialization after resizing; unrelated." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "resume_from_checkpoint key mismatch vs qwen3_omni_moe feature-length helper behavior; distinct issues." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer error hiding when protobuf is absent vs leftover dummy classes in dummy_pt_objects.py; unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior issue vs unexpected position-id keys; only broad loading/runtime similarity." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "Missing flash-support import in Python 3.13 vs transformers>=5.1.0 model loading failure; different causes." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile + SDPA failure in Bamba vs qwen3_omni_moe helper-length bug; unrelated." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "ReasoningEffort import breakage in Gemma4 processor loading vs flash_attention s_aux=None crash; same broad area, different concrete failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet. The Qwen3.5 MoE pair (45310/45478) has identical titles and close timestamps, so treating 45310 as the canonical/original report is reasonable. The rest of the soft-edge rejections are conservative and do not overclaim beyond broad topic similarity." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 25, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:25251", + "issue:28218", + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:41720", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43257", + "issue:43278", + "issue:43329", + "issue:43381", + "issue:43412", + "issue:43421", + "issue:43653", + "issue:43873", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45823" + ], + "soft_pairs": [ + "issue:32090|issue:33357", + "issue:43412|issue:45588", + "issue:43873|issue:45229", + "issue:43278|issue:43329", + "issue:45245|issue:45563", + "issue:41720|issue:45229", + "issue:43976|issue:45440", + "issue:28218|issue:29127", + "issue:45372|issue:45406", + "issue:45372|issue:45459", + "issue:43065|issue:43994", + "issue:43066|issue:44462", + "issue:44857|issue:45588", + "issue:43278|issue:43381", + "issue:44448|issue:44466", + "issue:43065|issue:45412", + "issue:45588|issue:45823", + "issue:25251|issue:32090", + "issue:43653|issue:44743", + "issue:44186|issue:45198", + "issue:43994|issue:45412", + "issue:44206|issue:44479", + "issue:44451|issue:45520", + "issue:42915|issue:42994", + "issue:44361|issue:45198", + "issue:44871|issue:44977", + "issue:29942|issue:30064", + "issue:44265|issue:45198", + "issue:43421|issue:45491", + "issue:43257|issue:43278" + ], + "prepared_review_unit_hash": "3a32fc2f34823bf731ce44e59b2359f1c46298d98362b50e612e36019dc4c7fa", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36679, + "estimated_input_tokens": 9170, + "estimated_eval_tokens": 18596 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is largely a grab-bag of unrelated Transformers bugs rather than one tight duplicate cluster. I\u2019d use issue 45372 as the representative issue only because it is a clear, active Gemma4 regression with concrete repro context; otherwise most pairs should be kept separate.", + "confidence": 0.82, + "canonical_issue_reason": "Issue 45372 is the strongest representative because it is open, well-scoped, and has a concrete Gemma4 processor-loading failure with version-specific context.", + "canonical_pr_reason": null, + "best_issue_reason": "45372 is the best overall issue to anchor the cluster: it is actionable, reproducible, and more central than the other candidates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Different failures: trainer broadcast TypeError vs MacOS bus error in a CLIP model." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export failure and flash-attention sink handling are separate code paths and symptoms." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantization/offloading behavior is not the same bug as Gemma4 multi-GPU CUDA OOM." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Training/eval dtype drift is unrelated to the Qwen3.5 recurrent-state reset bug." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count runtime error and a stale generation warning are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Auto device-mapping assert and Gemma4 OOM are different model/runtime failures." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility issue is unrelated to DeepSeekV3MoE divergence from remote impl." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Added-token spacing bug is not the same as a LayoutLMv3 error-message clarity issue." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both are Gemma4-related, but one is a mistral_common import failure and the other is a missing _tokenizer attribute in serve." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma4 processor import breakage is distinct from protobuf-masked tokenizer error handling." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Dummy Conv2d placeholder in Sam3PixelDecoder is unrelated to Siglip2 bad outputs." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer decoder type mismatch and AutoTokenizer ignoring tokenizer.json are different tokenizer-loading bugs." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "AMP loss crash and flash_attention s_aux=None crash do not share the same failure mechanism." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype regression is unrelated to the eval-mode gradient-checkpointing restriction." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Pegasus output mismatch and lm_head.weight serialization inconsistency are separate issues." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Sam3PixelDecoder dummy layer bug is unrelated to RT-DETR memory not being released." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Flash-attention sink-less crash and Gemma4 PLE device mismatch are different forward-path problems." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k shape change is unrelated to Trainer broadcast of NoneType." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "Tokenizer special-token decode failure is unrelated to Qwen3.5 recurrent-state reset." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes and Wav2Vec2 save/tokenization failures affect different components." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported center arg in an extractor is not the same regression as Qwen video input handling." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Cannot load ScandiBERT and flash_attn KeyError on Python 3.13 are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "MOE weight conversion during loading is a different code path from quantized model saving." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer AttributeError is unrelated to Wav2Vec2 save_pretrained/tokenization failure." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma eos_token_id inconsistency is not the same as the Qwen3.5 flash-attention generation bug." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures and void segmentation-map processing are different issues." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export guard failures are unrelated to Wav2Vec2 save/tokenization failures." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime special-token post-processor updates and Gemma3 NaN embeddings are different bugs." + }, + { + "left": "issue:43257", + "right": "issue:43278", + "accept": false, + "reason": "Qwen3 MoE loading with deepspeed is unrelated to embedding dtype changes between train and eval." + } + ] + }, + "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": 26, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:39692", + "issue:42915", + "issue:43232", + "issue:43262", + "issue:43334", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43931", + "issue:44062", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44442", + "issue:44464", + "issue:44610", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45103", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45491", + "issue:45588", + "issue:45593", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:43756|issue:45440", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:32090|issue:33290", + "issue:44610|issue:45412", + "issue:45103|issue:45372", + "issue:43824|issue:44279", + "issue:45440|issue:45593", + "issue:43653|issue:44442", + "issue:43381|issue:43701", + "issue:43761|issue:45859", + "issue:43526|issue:45834", + "issue:29942|issue:36010", + "issue:43526|issue:44186", + "issue:29127|issue:33357", + "issue:43334|issue:43531", + "issue:29127|issue:35141", + "issue:44464|issue:45491", + "issue:44977|issue:45245", + "issue:42915|issue:43931", + "issue:44442|issue:45072", + "issue:43262|issue:44206", + "issue:43526|issue:44857", + "issue:43232|issue:43388", + "issue:44062|issue:45907", + "issue:43441|issue:45588", + "issue:44743|issue:44811", + "issue:43575|issue:43701" + ], + "prepared_review_unit_hash": "59bff6e8367c5337cea820e5853cae93e0737886a39b3c1c68d0f0cf2dd8cfd3", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36186, + "estimated_input_tokens": 9047, + "estimated_eval_tokens": 18350 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is heterogeneous: the soft pairs span unrelated bugs in training, model loading, processors, generation, and docs. All soft-edge candidates should be rejected as duplicate matches.", + "confidence": 0.94, + "canonical_issue_reason": "issue:29127 is the most central of the weakly related items and is a concrete, self-contained bug report, but the batch is not a true duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to pick a representative issue, issue:29127 has the clearest failure description; still, there is no strong global canonical because the items are unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Different bugs: RoPE layer selection in Smollm3 vs a divergence between native and remote DeepSeekV3 implementations." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error on CLIP loading is unrelated to a SigLIP2 doc example/model-processor mismatch and quantization failure." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity is unrelated to TrainerState's num_input_tokens_seen not updating." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "One is a NoneType broadcast error in Trainer; the other is an OOM issue with Adafactor in DeepSpeed." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor output-size mismatch is unrelated to RT-DETR memory not being released on deletion." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation parsing and a ReasoningEffort import break are distinct code paths and failure modes." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Missing Qwen2.5-VL export/import is not the same as a generic dependency issue." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepSeekV3 implementation divergence is unrelated to D-FINE auxiliary-loss behavior when denoising is off." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and AutoTokenizer loading FastSpeech2ConformerTokenizer are different tokenizer bugs." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to a resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVision hidden_states being None is unrelated to Qwen3_5MoeTextRotaryEmbedding CPU-offload compatibility." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BEiT reduce_labels returning one label and Kosmos2.5 long-ocr index errors are different failures." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention test failures are unrelated to GenerationMixin import resolution." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "A BEiT label-reduction bug is not the same as LayoutLMv2Tokenizer crashing on NER/padding inputs." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error-message wording is unrelated to a CLIP MacOS bus error." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id in Qwen3-VL text config is different from a sliding_window issue in Qwen3-MoE." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "Poor error messaging in LayoutLMv3 has no overlap with token-embedding reinitialization after resize." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Chunked generation with compiled forward and Gemma3 NaNs from sliding-window/all-padding behavior are different bugs." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation issues are unrelated to the 2^24 category limit runtime error." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FineGrainedFP8Config on Qwen3Moe and Qwen3-VL weight-shape mismatch are separate model-loading problems." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer load failure and bf16 dtype mismatches are unrelated failures." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sample-rate defaults are unrelated to LasrFeatureExtractor passing an unsupported center argument." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "BEiT reduce_labels returning one label is unrelated to LwDetrImageLoss crashing under float16 AMP on CUDA." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs after sync_gpus and gather_for_metrics dropping tuple labels are different subsystems and bugs." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken special-argument duplication is unrelated to list_repo_files not forwarding revision." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Ministral-3 flash-attention failure and s_aux=None in flash_attention.py are separate flash-attention issues." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Recurrent states resetting in modular_qwen3_5.py is unrelated to Whisper batch_decode ignoring skip_special_tokens." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Tensor-parallel OOM when loading Qwen2-57B-A14B is unrelated to a resume_from_checkpoint key mismatch." + } + ] + }, + "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": 27, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:33290", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41628", + "issue:42907", + "issue:43316", + "issue:43381", + "issue:43493", + "issue:43525", + "issue:43550", + "issue:43575", + "issue:43611", + "issue:43643", + "issue:43646", + "issue:43720", + "issue:43723", + "issue:43749", + "issue:43761", + "issue:43827", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44079", + "issue:44188", + "issue:44190", + "issue:44387", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44743", + "issue:44871", + "issue:44898", + "issue:44913", + "issue:45003", + "issue:45216", + "issue:45290", + "issue:45372", + "issue:45440", + "issue:45479", + "issue:45491", + "issue:45698", + "issue:45759", + "issue:45803" + ], + "soft_pairs": [ + "issue:43575|issue:44387", + "issue:43646|issue:44077", + "issue:45003|issue:45440", + "issue:43761|issue:44079", + "issue:43723|issue:45479", + "issue:44442|issue:45803", + "issue:43761|issue:44188", + "issue:43316|issue:43525", + "issue:44479|issue:45290", + "issue:42907|issue:45698", + "issue:44442|issue:44898", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:39692|issue:45491", + "issue:33290|issue:35141", + "issue:33290|issue:34689", + "issue:43381|issue:43873", + "issue:43931|issue:45216", + "issue:43493|issue:43827", + "issue:43550|issue:44743", + "issue:44077|issue:44479", + "issue:43720|issue:44442", + "issue:43316|issue:45759", + "issue:41628|issue:45372", + "issue:43643|issue:44913", + "issue:43749|issue:43931", + "issue:33290|issue:36331", + "issue:34689|issue:36010", + "issue:43873|issue:44871", + "issue:43381|issue:43856", + "issue:44190|issue:44496" + ], + "prepared_review_unit_hash": "8f3c3f0d7d5e431e1c56b7493e4968526eef2978f8a964173f419a233b577682", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37229, + "estimated_input_tokens": 9308, + "estimated_eval_tokens": 18872 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are still best treated as non-duplicates. The one previously over-accepted edge, issue:43761 vs issue:44079, is related by symptom and mechanism, but the packet only supports a plausible connection\u2014not a confident same-bug match\u2014so it should stay rejected.", + "confidence": 0.86, + "canonical_issue_reason": "issue:44079 is the best representative of the ModelOutput key-assignment bug family because it states the framework-level mechanism directly; issue:43761 looks like a possible downstream symptom, but not enough to collapse the two into one issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44079 is the strongest cluster representative: it describes the underlying ModelOutput bug in its most general form, while the CLIPVisionModel report is narrower and less conclusive as a duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is tensor-parallel loading and the other is int4/CUDA reserved-memory behavior; different code paths and fixes." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Both involve initialization semantics, but they point to different model-specific regressions rather than the same bug." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils is unrelated to DeepSeekV3MoE implementation divergence." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "The CLIPVisionModel symptom is plausibly related to the ModelOutput bug, but the packet only supports inference, not a confident same-underlying-bug duplicate." + }, + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer loading in v5 and a zero-loss sequence-classification bug are unrelated subsystems and failure modes." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "A tokenizer load failure is unrelated to FuyuBatchFeature's bare-except error swallowing." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "ModelOutput handling and attention-kernel divergence under torch.compile are different bugs." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config API issues, but they concern different models and different missing/discrepant fields." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression and chat-template tool-call crash are separate code paths." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Saving dequantized models and loading the wrong custom module after save_pretrained are different persistence bugs." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer loading failure is unrelated to Perceiver non-default-resolution image classification." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "DeepSpeed/Adafactor OOM and TrainerState token-count tracking are unrelated." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both are model-loading regressions, but they involve different release changes and different root causes." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "Documentation example errors and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "Optimizer OOM and embedding reinitialization in post_init are unrelated." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Optimizer memory blow-up and Llama model-loading breakage are different failures." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and quantization offloading are unrelated issues." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "A Qwen3-VL weight-shape mismatch and a Qwen3.5 save_pretrained regression are not the same bug." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation mismatch and docs still referencing pipeline() are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "torch.compile+SDPA failure in Bamba and recurrent-state reset in modular_qwen3_5 are different model-path bugs." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTSTMixer post_init allowance and Qwen video-input regression do not share a concrete code path." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet accelerate-loading unpacking bug is unrelated to AutoTokenizer loading FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config behavior, but one is a Gemma3TextConfig API discrepancy and the other is Qwen multimodal text_config unwrapping." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Both are import errors, but they stem from different dependencies and different processor-loading paths." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct resetting on reload are different serialization/reload bugs." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and Qwen3-VL shape mismatch are unrelated loading problems." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "OOM during optimizer use and CustomTrainer compute_loss signature mismatch are unrelated training issues." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama model-loading regression and GenerationMixin import failure are separate API breakages." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization offloading behavior and Gemma-3 eos_token_id inconsistency are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:43856", + "accept": false, + "reason": "Eval-mode gradient checkpointing and Qwen3 MoE memory inefficiency are different training/memory concerns." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an example script and an unrecognized model/config issue are unrelated." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary is mostly grounded, but one soft-edge verdict is too strong: it marks issue:43761 vs issue:44079 as a match even though the packet labels that pair deterministic_accept=false. From the packet alone, the CLIPVisionModel symptom may be compatible with the ModelOutput bug, but that is still an inference, not enough to override the conservative label. The other negatives look appropriately cautious." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 28, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:25251", + "issue:28282", + "issue:41950", + "issue:42175", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43452", + "issue:43475", + "issue:43504", + "issue:43540", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43673", + "issue:43688", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43825", + "issue:44077", + "issue:44162", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44534", + "issue:44617", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45137", + "issue:45200", + "issue:45406", + "issue:45584", + "issue:45698" + ], + "soft_pairs": [ + "issue:44855|issue:45137", + "issue:43381|issue:43742", + "issue:43316|issue:44877", + "issue:42175|issue:43316", + "issue:43540|issue:44514", + "issue:43673|issue:44743", + "issue:25251|issue:28282", + "issue:43404|issue:43441", + "issue:43065|issue:44617", + "issue:44162|issue:44792", + "issue:43388|issue:43688", + "issue:43295|issue:43825", + "issue:41950|issue:43475", + "issue:16998|issue:22355", + "issue:44077|issue:44534", + "issue:44871|issue:45584", + "issue:45127|issue:45200", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43761|issue:44479", + "issue:43295|issue:44871", + "issue:42617|issue:43575", + "issue:43575|issue:43742", + "issue:43452|issue:44496", + "issue:43646|issue:44913", + "issue:44734|issue:45406", + "issue:43504|issue:45698" + ], + "prepared_review_unit_hash": "9b8b8c4d93af672243b96922fd06fe48e57df1548026215c56917ec9eca0ce03", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35714, + "estimated_input_tokens": 8929, + "estimated_eval_tokens": 18114 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is heterogeneous: mostly unrelated Transformers bug reports spanning different models, subsystems, and failure modes. I did not find any soft pair that clearly represents the same underlying bug/change, so all soft edges are rejected.", + "confidence": 0.35, + "canonical_issue_reason": "issue:43646 is the broadest and most umbrella-like report in the set, centered on a general v5 custom model initialization regression rather than a model-specific symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best representative because it describes a wide API-level regression that can subsume multiple narrower loading/init failures, even though the cluster is not a true duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 import/parsing failure vs DeepSpeed ZeRO3 deque underflow; unrelated code paths." + }, + { + "left": "issue:43381", + "right": "issue:43742", + "accept": false, + "reason": "Gradient checkpointing in eval mode vs MobileLLM config loading KeyError; different bugs." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API mismatch vs granite_speech strict-config loading; both config-related but not the same failure." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Packaging backend omission vs Gemma3 config API discrepancy; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video-input processing error vs batched chat template padding crash; different functions and symptoms." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Chunked prefill cache missing vs recurrent-state reset with cache; both cache-related but different concrete code paths." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline top_k nesting bug vs missing PyTorch ImportError; unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Weight tying bug vs FlashAttention failure in a related model family, but not the same underlying defect." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d implementation vs CUDA OOM in Sam3Video; not the same bug." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 breakage vs janus image-generation test failure; different models and issues." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Last-batch metric gathering bug vs auxiliary-loss normalization bug; different training logic." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor/tokenizer regression vs incorrect pipeline error text; both regressions but distinct code paths." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification processor selection bug vs SAM3 vision output attribute error; unrelated." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "model_max_length question vs missing transformers.onnx module; no overlap." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "patchtsmixer post_init validation vs non-persistent buffers junk fill; unrelated." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Gemma eos_token_id mismatch vs Whisper empty-transcription generation failure; different model-specific bugs." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge/tied embeddings collapse vs Gemma 4 mm_token_type_ids defaulting; separate issues." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile/SDPA failure vs checkpoint key mismatch; unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch vs checkpoint key mismatch; unrelated." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression vs Qwen video-input regression; different model families and failures." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Custom processor/tokenizer regression vs Gemma eos_token_id inconsistency; different APIs." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel launch issue vs tensor-parallel OOM while loading a model; not the same bug." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Model loading OOM vs MobileLLM config KeyError; unrelated." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "gguf_file/from_pretrained breakage vs unrecognized model_type in config; both loading-related but not the same concrete issue." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Broad custom model initialization regression vs GPTNeoXConfig rotary_pct reload issue; different scopes and symptoms." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation tensor indexing bug vs Gemma4Processor missing _tokenizer; both serve bugs but unrelated." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Legacy field blocking BEiT preset load vs wrong custom module after save/load; different pretrained-loading failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 29, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:41720", + "issue:43065", + "issue:43335", + "issue:43388", + "issue:43575", + "issue:43582", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44060", + "issue:44190", + "issue:44242", + "issue:44462", + "issue:44464", + "issue:44479", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44737", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45290", + "issue:45357", + "issue:45362", + "issue:45381", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45803", + "issue:45907" + ], + "soft_pairs": [ + "issue:43575|issue:43873", + "issue:44617|issue:45584", + "issue:43931|issue:44060", + "issue:43761|issue:44242", + "issue:32090|issue:35141", + "issue:45563|issue:45584", + "issue:44464|issue:44871", + "issue:44792|issue:44977", + "issue:43065|issue:44610", + "issue:44479|issue:44734", + "issue:43827|issue:43994", + "issue:44521|issue:45381", + "issue:44534|issue:44913", + "issue:44464|issue:45563", + "issue:43906|issue:45290", + "issue:44933|issue:45362", + "issue:44190|issue:44964", + "issue:41720|issue:45245", + "issue:44792|issue:45600", + "issue:44855|issue:45588", + "issue:44737|issue:45803", + "issue:43388|issue:43582", + "issue:44462|issue:45907", + "issue:45127|issue:45357", + "issue:43335|issue:44855", + "issue:44938|issue:45542" + ], + "prepared_review_unit_hash": "84f3ac0c9ffd8d9519d1b84777bcea945d06711389c328f3b8d357c1560acc9c", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35068, + "estimated_input_tokens": 8767, + "estimated_eval_tokens": 17790 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The proposed soft pairs are mostly superficial similarities across different models/features rather than true duplicates. I did not find any pair that clearly shares the same concrete bug or change path.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43873 is the strongest representative of this set if a single issue must be chosen: it has the broadest user impact, the most discussion, and inbound references. The rest of the items are mostly isolated, unrelated bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best overall issue candidate because it is the most active and central report in the list, while the other issues are largely one-off model- or feature-specific problems.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43575", + "right": "issue:43873", + "accept": false, + "reason": "Both concern memory/quantization behavior, but one is a TP OOM on a specific model and the other is an offloading bug; different failure modes and likely different fixes." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Sam3Video CUDA OOM and Whisper empty-transcription generation failure are unrelated model/code-path bugs." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Different Qwen variants and different problems: a load-time shape mismatch vs an incorrect tied-weights warning." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "CLIP hidden_states regression and MoE load-balancing-loss behavior are separate features and code paths." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error and embedding reinit after resize are unrelated training/model-init issues." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "A stale warning in paged generate is not the same bug as Whisper crashing on empty transcription after align_special_tokens." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Chunked generation/compiled forward inconsistency and Gemma eos_token config mismatch are unrelated." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation issue are different model paths and symptoms." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "A dummy Conv2d in Sam3PixelDecoder and an OmDet-Turbo processor size mismatch are different bugs." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Both touch multimodal/runtime behavior, but one is a video-input regression and the other is a KV-cache indexing crash in serve." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() and SigLIP producing nonsense with AutoModel/pipeline are not the same underlying issue." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal chat/template problems, but the assistant-mask bug and wrong vision_position_ids are distinct processing failures." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer junk-fill and GPTNeoX rotary_pct reload loss are unrelated configuration/runtime bugs." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Different generate-related symptoms: compiled-forward inconsistency versus a stale warning about num_return_sequences." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "The first is only a reproduction of an earlier issue; there is not enough evidence that it is the same concrete assistant-message/tool-call crash." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing image_utils import and Qwen3.5 chat crash are unrelated." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading failure and model loading failure for Phi-4 multimodal are different failure surfaces." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "CUDA assert during auto device mapping and the 2^24 categories limit error are unrelated." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus image-generation test failure and stale auto_mappings references to removed configs are different problems." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 IndentationError from torch.jit parsing and a flash-attention None-aux crash are unrelated." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "XLNet CPU allocation bug and Fuyu bare-except error handling are unrelated code paths." + }, + { + "left": "issue:43388", + "right": "issue:43582", + "accept": false, + "reason": "Metric-gather label dropping and Apple Silicon warmup TypeError are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer loading ignores tokenizer.json, while the other issue is about forwarding revision in list_repo_files; different APIs and fixes." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge collapse with extended vocab and Qwen3.5 visual encoder key saving are different model-state serialization bugs." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and DebertaV2 import parsing on Python 3.13 are unrelated." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 load failure and tensorboard-without-TensorFlow backend error are different environment/setup issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 30, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "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:43540", + "issue:43550", + "issue:43643", + "issue:43644", + "issue:43650", + "issue:43976", + "issue:44016", + "issue:44077", + "issue:44079", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44466", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44855", + "issue:44913", + "issue:44964", + "issue:45003", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45375", + "issue:45406", + "issue:45446", + "issue:45584", + "issue:45600", + "issue:45632", + "issue:45803" + ], + "soft_pairs": [ + "issue:44077|issue:44079", + "issue:43976|issue:44855", + "issue:43644|issue:44913", + "issue:43550|issue:44190", + "issue:43540|issue:44734", + "issue:44112|issue:45600", + "issue:44496|issue:45803", + "issue:45276|issue:45584", + "issue:43335|issue:44190", + "issue:43650|issue:44220", + "issue:43116|issue:44190", + "issue:45245|issue:45584", + "issue:43295|issue:45276", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:41950|issue:44016", + "issue:36246|issue:38617", + "issue:44186|issue:44734", + "issue:38175|issue:43065", + "issue:44683|issue:45446", + "issue:44466|issue:44913", + "issue:42175|issue:44279", + "issue:44016|issue:44220", + "issue:44734|issue:45632", + "issue:43404|issue:45216", + "issue:44561|issue:45632", + "issue:44246|issue:45003", + "issue:43643|issue:44496", + "issue:45406|issue:45632", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:42907|issue:43441" + ], + "prepared_review_unit_hash": "c9b04c6b9931812b2041cd33ac30e161a5bb00b2b2ce887552d55d5bb6e90cff", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37403, + "estimated_input_tokens": 9351, + "estimated_eval_tokens": 18958 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers bugs (imports, configs, model-specific regressions, pipelines, and notebooks). None of the suggested soft edges look like true duplicates.", + "confidence": 0.91, + "canonical_issue_reason": "issue:43644 is the broadest release-level regression in the set and best captures the shared \"v5 breakage\" theme, while most other issues are narrower model-, pipeline-, or environment-specific bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the strongest representative issue because it describes a general Transformers v5 regression rather than a single model or example-script failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44077", + "right": "issue:44079", + "accept": false, + "reason": "Different bugs: one is about `patchtsmixer` `post_init`, the other about `ModelOutput` key handling." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Both are version/runtime failures, but one is a Python version compatibility issue and the other is a DebertaV2 import/parser problem on Python 3.13." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Both touch v5 serialization/config behavior, but one is about non-persistent buffers and the other is a GPTNeoX config reload bug." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "Unrelated: torch.compile/SDPA failure in Bamba vs a local dataset loading issue in an image-classification example." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Different code paths: Qwen3OmniMoe video-input validation vs transformers serve KV-cache continuation indexing." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "Both affect CI, but one is a GraniteSpeech stale-test failure and the other is a broken auto_mappings reference to removed configs." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "Different failures: unrecognized model/config loading vs a bare-except bug in Fuyu tensor conversion." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Both are generation-related, but one is Gemma4 embedding resizing and the other is Whisper empty-transcription handling after token alignment." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "Different subsystems: SwitchTransformers config construction vs an example script failing to load a local dataset." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Unrelated issues in different areas: a data-related request vs a torch fbank feature extraction bug." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Both are example-script problems, but they affect different scripts and different failure modes." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Different problems: category-cardinality limit vs Whisper generation on empty transcription." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "One is a processor/tokenizer regression, the other is a Gemma4 resize-token-embeddings bug." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Both are config-related, but they concern different multimodal model families and different missing/default fields." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they involve different symbols and different API exposure problems." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Different issues entirely: video-classification pipeline behavior vs a notebook syntax error." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are import failures, but for different missing names and different call sites." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Different bug classes: LayoutLMv2 tokenizer padding/NER crash vs server KV-cache continuation indexing." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Different models and failures: SigLIP2 zero probabilities vs a dummy Conv2d in Sam3PixelDecoder." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both touch flex_attention, but one is a compiled flex_attention failure on torch >= 2.9 and the other is a version-check/import bug for AuxRequest." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Both involve serialization/config state, but one is tied `lm_head.weight` serialization and the other is GPTNeoX `rotary_pct` reloading." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Packaging/dependency complaints, but not the same dependency or failure mode." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "A notebook syntax error and a feature-extraction bug are unrelated." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve KV-cache tensor indexing and `trust_remote_code` cache-path collision are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Both mention weight tying/serialization, but one is Mistral3 lm_head tying and the other is Qwen3.5 checkpoint save correctness." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Both involve `trust_remote_code`, but one is a removed helper breaking remote models and the other is a local cache path collision." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Different import-related issues: slow `import transformers` vs unsafe `sys.modules` access in modeling_utils." + }, + { + "left": "issue:45406", + "right": "issue:45632", + "accept": false, + "reason": "A Gemma4Processor missing `_tokenizer` and a trust_remote_code cache collision are unrelated." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Different model-loading failures: Phi-4-multimodal loading vs stale Sam3LiteText references in auto_mappings." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI test failure in GraniteSpeech and a Phi-4-multimodal loading issue are not duplicates." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Different model families and bugs: saving dequantized models vs Ministral-3 FlashAttention failure." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 31, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43673", + "issue:43824", + "issue:43854", + "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:44683", + "issue:44779", + "issue:44933", + "issue:44964", + "issue:44987", + "issue:45020", + "issue:45042", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45325", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45584", + "issue:45593", + "issue:45600", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43854|issue:44964", + "issue:43295|issue:45335", + "issue:44016|issue:44062", + "issue:43976|issue:44987", + "issue:43673|issue:44336", + "issue:44496|issue:45042", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:43824|issue:44933", + "issue:43299|issue:45216", + "issue:45335|issue:45584", + "issue:44075|issue:44368", + "issue:43976|issue:44279", + "issue:43901|issue:44496", + "issue:43381|issue:45593", + "issue:43299|issue:45357", + "issue:44496|issue:45759", + "issue:44351|issue:45278", + "issue:41950|issue:45020", + "issue:44521|issue:45325", + "issue:44242|issue:45200", + "issue:43976|issue:45405", + "issue:43479|issue:43525", + "issue:41950|issue:45823", + "issue:43577|issue:45216", + "issue:38175|issue:44617", + "issue:44683|issue:45542", + "issue:44279|issue:45405", + "issue:43299|issue:43854", + "issue:39692|issue:43901", + "issue:43295|issue:44779" + ], + "prepared_review_unit_hash": "d7c1721ae71f2baebce8f8b267a9a49eed8de544436f21457ce4338d6909656d", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36355, + "estimated_input_tokens": 9089, + "estimated_eval_tokens": 18434 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: the soft pairs share broad transformer/modeling themes, but they are not the same concrete bug or change. I rejected all soft edges because the titles point to different code paths, models, or failure modes.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue stands out; these reports are too diverse to safely collapse into one duplicate hub.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a strong global representative for the whole cluster; the closest broad umbrella is still too general to serve as a true duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Both are model-loading failures, but for different checkpoints and likely different root causes." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "One is a processor/tokenizer regression; the other is an embedding resize bug in t5gemma." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error vs AddedToken argument conflict; unrelated failure modes." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "A Python version compatibility issue and a model-loading failure are not the same bug." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Cache handling in generation vs ANSI formatting in loading_report are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model config vs PIL/torchvision dependency handling are different issues." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and auto_mappings cleanup are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "ImageProcessorFast label reduction bug vs text-classification docs mismatch." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Different import errors in different modules with different missing symbols." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both involve Qwen models, but one is a load failure and the other is a bad save_pretrained regression." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize behavior and Whisper empty-transcription generation are unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "SGD argument handling and a tie_word_embeddings warning are different problems." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python version support and a generic dependency issue are not the same bug." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs for return_all_scores versus model config loading failure." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing eval-mode behavior and D-FINE auxiliary losses are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both are Qwen3.5-related, but one is a loading regression and the other is an incorrect save_pretrained key layout." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Different config-loading regressions affecting different model families and code paths." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "A specific missing import and a broad upgrade-related import breakage are not the same concrete issue." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup and remote_code model breakage are too broad to equate." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Chat-template assistant masks and Qwen2.5-VL rope indexing are different multimodal bugs." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "MoE load-balancing loss logic vs mm_token_type_ids defaulting are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python compatibility and an unreleased dependency pin are different release issues." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Multimodal config default initialization and missing pad_token_id on Llama4Config are different config bugs." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Processor lookup for video classification and Gemma4 device placement are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype propagation and Qwen3.5 checkpoint saving are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are completely different failure modes." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Torch flex_attention compilation and tensorboard/TensorFlow backend setup are unrelated." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A generic dependency issue and a minimum-version bump are not the same bug." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Different model families and different failure points in loading." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "A broken docs example for SigLIP2 and a text-classification docs note are not the same issue." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Processor/tokenizer regression and Deepseek tokenizer output regression are different code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 32, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:33290", + "issue:41950", + "issue:42175", + "issue:42994", + "issue:43065", + "issue:43262", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43650", + "issue:43653", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43784", + "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:44987", + "issue:45081", + "issue:45276", + "issue:45290", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45656", + "issue:45712", + "issue:45823", + "issue:45834", + "issue:45907" + ], + "soft_pairs": [ + "issue:44462|issue:45081", + "issue:41950|issue:43650", + "issue:45081|issue:45907", + "issue:44297|issue:44462", + "issue:33290|issue:45656", + "issue:44016|issue:44291", + "issue:45600|issue:45712", + "issue:43441|issue:45834", + "issue:43450|issue:44279", + "issue:42994|issue:43317", + "issue:43065|issue:44898", + "issue:44261|issue:44263", + "issue:44466|issue:45276", + "issue:43441|issue:44683", + "issue:43650|issue:45290", + "issue:44623|issue:45397", + "issue:44623|issue:44749", + "issue:43653|issue:45593", + "issue:43723|issue:44162", + "issue:43784|issue:45542", + "issue:43262|issue:44521", + "issue:44671|issue:44779", + "issue:43673|issue:43761", + "issue:44361|issue:45593", + "issue:44016|issue:45823", + "issue:42175|issue:43976", + "issue:43901|issue:43994", + "issue:44987|issue:45542" + ], + "prepared_review_unit_hash": "614aac9c4b28002158c76b58aa773ce448e2fb83392d68db2c3a33d7d28d4ebc", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36048, + "estimated_input_tokens": 9012, + "estimated_eval_tokens": 18280 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is highly heterogeneous: most pairs are only superficially similar (often both about tokenizers, processors, or v5 regressions) but describe different code paths and fixes. I do not see a true duplicate cluster; all soft edges should be rejected.", + "confidence": 0.9, + "canonical_issue_reason": "No single issue cleanly represents the cluster because the items span unrelated tokenizer-loading, serialization, vision/audio processor, quantization, backend, and CI problems. If an anchor is required, issue 44462 is the closest broad tokenizer-loading regression, but it does not cover the rest.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44462 is the most central and actionable among the tokenizer-related reports: it has a concrete reproducible failure around AutoTokenizer and repository tokenizer files. It is still only a partial fit for the overall set, which is too mixed to have a strong canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Both involve tokenizers, but one is AutoTokenizer ignoring tokenizer.json while the other is a Mistral regex crash during tokenizer loading. Different bugs and likely different fixes." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "Unrelated: video-classification processor lookup vs a vague data request issue. No shared bug path." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer regex crash and list_repo_files revision forwarding are unrelated subsystems." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch is different from AutoTokenizer ignoring tokenizer.json on load." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both mention deepspeed/optimizer behavior, but OOM with Adafactor and double optimizer.step are distinct failure modes." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error is unrelated to init_empty_weights TypeError during model loading." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both are CI/repo-maintenance flavored, but one is stale auto_mappings references and the other is leftover dummy classes. Different fixes." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "Different models and failures: FlashAttention regression vs long OCR index error." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video batch-shape bug and a dependency issue are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Both touch quantization/dequantization, but saving quantized models and device_map offload loading are different code paths." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Both are vision-model issues, but a dummy Conv2d placeholder and Perceiver resolution handling are not the same bug." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "Different models and code paths: MLA layernorm epsilon mismatch vs torch.split return-value handling." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Both involve Gemma4 serialization/embedding behavior, but one is tied lm_head.weight serialization and the other is resize_token_embeddings propagation." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "FlashAttention failure for a specific model is not the same as compiled flex_attention breaking on torch>=2.9." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "Unrelated: vague data request vs apply_chat_template crash on tool-call assistant messages." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "processor.save_pretrained missing files and gemma-4 zero3 from_pretrained are distinct issues." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Saving processor files and training slowdown after upgrade are not the same underlying bug." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "AutoTokenizer loading regression and ESM2 model breakage are different failures." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Both are import/backend-related, but one is a missing nn import and the other is a TensorFlow backend packaging issue." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant-mask generation." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Two separate v5 regressions on different models/tokenizers; no evidence they share the same code defect." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache chunked-prefill bug and CLIPVision hidden_states regression are unrelated." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer task error and D-FINE auxiliary-loss issue share nothing substantive." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error is unrelated to Gemma4 device-mapping mismatch." + }, + { + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "Different packaging/runtime problems: missing TensorFlow in a torch install vs Python version compatibility." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to SigLIP2 bad outputs." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Model-loading failure for a specific repo and a TensorFlow backend install issue are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 33, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:43122", + "issue:43299", + "issue:43352", + "issue:43450", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43596", + "issue:43643", + "issue:43650", + "issue:43673", + "issue:43824", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:44162", + "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:45200", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45397", + "issue:45561", + "issue:45563", + "issue:45593" + ], + "soft_pairs": [ + "issue:43122|issue:43650", + "issue:43824|issue:43976", + "issue:43525|issue:43881", + "issue:44297|issue:45397", + "issue:43525|issue:43643", + "issue:44188|issue:44336", + "issue:43450|issue:44617", + "issue:42491|issue:43299", + "issue:44589|issue:45362", + "issue:43901|issue:44246", + "issue:41628|issue:43976", + "issue:45561|issue:45563", + "issue:44242|issue:45593", + "issue:44336|issue:44373", + "issue:43352|issue:45250", + "issue:44295|issue:45397", + "issue:41950|issue:44220", + "issue:44246|issue:44496", + "issue:43531|issue:45362", + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:43526|issue:45003", + "issue:44336|issue:44485", + "issue:45003|issue:45561", + "issue:43673|issue:44561", + "issue:44246|issue:44871", + "issue:44242|issue:44857", + "issue:44162|issue:45200", + "issue:36246|issue:43596", + "issue:44295|issue:44749", + "issue:44779|issue:45292" + ], + "prepared_review_unit_hash": "93642bd330585083ab3115e0dbc6b862b8294319cb6db69ddb561a24d83d40d5", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36598, + "estimated_input_tokens": 9150, + "estimated_eval_tokens": 18556 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are broadly heterogeneous: unrelated import errors, model-loading regressions, tokenizer behavior changes, loss-computation bugs, and docs/test/reporting problems. No duplicate cluster is strong enough to merge into a single canonical item.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a reliable canonical representative; even the closest matches point to different model families or different failure modes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenizer behavior regression vs an unrelated low-quality placeholder issue; no shared bug." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Specific Qwen2.5-VL import failure vs a Python version compatibility complaint; different root causes." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config vs GLM-4V loading failure; different models and failure points." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch vs gemma-4 Zero3 loading; unrelated." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Config attribute missing vs trust_remote_code returning incomplete config; not the same bug." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "torch.compile attention-kernel divergence vs ANSI escape output in loading_report; unrelated subsystems." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Incorrect batched video processor shape vs CUDA OOM in Sam3Video; different classes of problem." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Qwen3 MoE version incompatibility for LoRA loading vs Qwen3VL MoE model loading breakage; similar family, different code paths and symptoms." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Float8 storage type error vs Qwen3.5 chat crash; no concrete overlap." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs/behavior mismatch vs intermittent import slowness; unrelated." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Missing AutoImageProcessor export vs Python 3.9/3.10 compatibility; different issues." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "xdist file race vs stale warning in generate(); unrelated." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Missing load-balancing loss in MoE routing vs missing auxiliary losses for D-FINE denoising; different models and conditions." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "Terminal ANSI formatting bug vs wrong docstring for position_ids; not duplicates." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Specific model not supporting Flash Attention 2.0 vs a generic Flash Attention topic; too broad and not same bug." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "position_ids buffer access error vs gemma-4 Zero3 loading; different failure modes." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification pipeline image-processor lookup vs fbank feature extraction issue; unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Slow imports vs unrecognized model/config missing model_type; no shared root cause." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Sliding-window bug in Qwen3-MoE vs Qwen3.5 chat crash; similar model family but not the same concrete problem." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Missing Qwen2_5_VL symbol vs missing is_offline_mode from huggingface_hub; unrelated import errors." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing exports from different modules; same symptom class, different underlying issues." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BEiT image-processor label reduction bug vs unsafe sys.modules access in modeling_utils; unrelated." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI escape output bug vs GLM-5 RoPE implementation discussion; not duplicates." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "Internal module access bug vs pytest-xdist race; different areas entirely." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Missing cache in chunked_prefill vs removal of is_torch_fx_available breaking trust_remote_code; different APIs and failures." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import slowness vs Gemma eos_token_id config inconsistency; unrelated." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Missing router load-balancing loss vs AMP/CUDA crash in LwDetrImageLoss; not the same bug." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 broken loading vs Gemma 4 mm_token_type_ids defaulting; different models and code paths." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Qwen2_5_VL import failure vs deepspeed Zero3/BertModel index error; unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "position_ids buffer error vs tokenizer/filtering slowdown after upgrade; different symptoms and layers." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Deepseek tokenizer regression vs resize_token_embeddings not updating output embeddings; different subsystems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 34, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:42886", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43540", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43901", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44246", + "issue:44297", + "issue:44336", + "issue:44368", + "issue:44466", + "issue:44496", + "issue:44623", + "issue:44734", + "issue:44869", + "issue:44877", + "issue:44933", + "issue:44977", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45278", + "issue:45292", + "issue:45335", + "issue:45356", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45656", + "issue:45701", + "issue:45759" + ], + "soft_pairs": [ + "issue:44877|issue:45375", + "issue:45292|issue:45584", + "issue:45292|issue:45701", + "issue:43901|issue:45003", + "issue:42886|issue:45229", + "issue:44496|issue:45003", + "issue:44987|issue:45459", + "issue:43232|issue:44336", + "issue:43065|issue:43408", + "issue:45375|issue:45759", + "issue:43257|issue:45137", + "issue:43262|issue:44246", + "issue:44060|issue:44077", + "issue:44995|issue:45200", + "issue:43475|issue:43540", + "issue:44466|issue:45335", + "issue:43653|issue:44162", + "issue:44995|issue:45588", + "issue:44368|issue:45563", + "issue:44368|issue:44977", + "issue:45397|issue:45656", + "issue:43673|issue:44734", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44933|issue:45459", + "issue:44869|issue:45356", + "issue:43232|issue:43673", + "issue:44297|issue:44623", + "issue:43673|issue:45278", + "issue:43646|issue:44162" + ], + "prepared_review_unit_hash": "c50f5c71a19dddfc16b08677609cdde094380f44662c0482d8aefc36b7e7077a", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36664, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a mix of unrelated Transformers issues that only share broad themes like model loading, tokenization, generation, or config handling. None of the soft pairs look like true duplicates or mergeable PR-equivalents, so I rejected them all.", + "confidence": 0.28, + "canonical_issue_reason": "issue:45278 is the broadest umbrella symptom in the set: a general upgrade regression causing multiple import/load failures. It is the closest representative of the cluster, though the rest are mostly narrower model-specific bugs rather than duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best single representative because it is broad, user-facing, and captures the general upgrade-breakage theme better than the more specialized model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both are strict-config style bugs, but they affect different models and different missing fields; not the same underlying defect." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "resize_token_embeddings mismatch and Whisper empty-transcription failure are unrelated code paths." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "One is an embedding-resize bug; the other is a version-dependent tokenization change complaint." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mentioning return_all_scores and unsafe sys.modules access are unrelated." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline cache loading failure and Gemma4 multi-GPU CUDA OOM are different problems." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model/config loading and sys.modules access are distinct failure modes." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Both involve tokenizer loading, but one is a model-load regression and the other is an exception-suppression bug in decode handling." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs sync issue and ANSI terminal output issue are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Same SAM3 family, but a dummy Conv2d in the pixel decoder is not the same bug as the tracker-type warning." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both are Qwen multimodal config issues, but one is a missing field and the other is an unwrap-text_config initialization bug." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Accelerate+DeepSpeed weight conversion and ZeRO3 deque underflow are different loading failures." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate default and slow import are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Tied-weights warning behavior and patchtsmixer post_init policy are not the same defect." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "A stale indexer cache crash and a missing mm_token_type_ids default are different bugs." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Both touch video models, but the SAM3 attribute error and Qwen3OmniMoe video ValueError are separate code paths." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both concern tied/resized embeddings, but serialization inconsistency and decoder.embed_tokens resize behavior are not the same issue." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and ESM2 breakage are unrelated." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "A stale cache crash and a flash-attention s_aux=None AttributeError are different problems." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "One is a tied-embeddings warning, the other a stale num_return_sequences warning." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "A warning about tie_word_embeddings is not the same as a flash-attention generation failure." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma4 ZeRO3 from_pretrained failure and optimizer step being called twice under DeepSpeed are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation/cache, but chunked_prefill cache absence and serve KV-cache continuation indexing are different bugs." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "DeepSpeed deque underflow and stale Sam3LiteText config references are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and tie_word_embeddings warning are different issues." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "A missing import from image_utils and tokenizer error masking are unrelated." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer/decoding regressions, but they affect different models and different root causes." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both are generation-related, but sync_gpus kwargs handling and chunked_prefill cache behavior are not the same bug." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "save_pretrained tokenizer-class mismatch and processor.save_pretrained missing files are different serialization bugs." + }, + { + "left": "issue:43673", + "right": "issue:45278", + "accept": false, + "reason": "Generation cache behavior and broad import errors after upgrade are not the same issue." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Both are broad regressions, but they concern different models and different failure surfaces." + } + ] + }, + "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": 35, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:42994", + "issue:43232", + "issue:43377", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43526", + "issue:43643", + "issue:43673", + "issue:43704", + "issue:43824", + "issue:43873", + "issue:44038", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44361", + "issue:44496", + "issue:44623", + "issue:44661", + "issue:44749", + "issue:44792", + "issue:44933", + "issue:44945", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45200", + "issue:45230", + "issue:45310", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45478", + "issue:45561", + "issue:45656", + "issue:45712", + "issue:45753" + ], + "soft_pairs": [ + "issue:44361|issue:44749", + "issue:44623|issue:45656", + "issue:42994|issue:43482", + "issue:28282|issue:30990", + "issue:44749|issue:45656", + "issue:44749|issue:45310", + "issue:43475|issue:43643", + "issue:42371|issue:45092", + "issue:43475|issue:45381", + "issue:45230|issue:45397", + "issue:44038|issue:44623", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:42994|issue:43525", + "issue:43475|issue:44661", + "issue:45375|issue:45478", + "issue:42673|issue:43704", + "issue:43232|issue:44188", + "issue:45310|issue:45375", + "issue:43873|issue:44945", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:44945|issue:45753", + "issue:44222|issue:45310", + "issue:42222|issue:45200", + "issue:42994|issue:43824", + "issue:43232|issue:44792", + "issue:36010|issue:41628", + "issue:42175|issue:45712", + "issue:43673|issue:44188", + "issue:44038|issue:45310", + "issue:43377|issue:44242", + "issue:43526|issue:45561", + "issue:44496|issue:45561" + ], + "prepared_review_unit_hash": "889681603087fe1a5943d53c9619b2edf887dc15a9a9d7d5894d28451746e191", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37628, + "estimated_input_tokens": 9407, + "estimated_eval_tokens": 19070 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous, but it contains more than one duplicate-looking pocket: the Qwen3ForCausalLM VRAM leak pair (42673/43704) is a clear duplicate relationship, and 45310/45478 also look like the same Qwen3.5-MoE from_pretrained bug by title. I\u2019d keep 42673 as the canonical issue for the leak pair, while being conservative about broader cluster sameness.", + "confidence": 0.66, + "canonical_issue_reason": "42673 is the earlier, more detailed report of the Qwen3ForCausalLM VRAM leak and has stronger discussion context than 43704.", + "canonical_pr_reason": null, + "best_issue_reason": "42673 is the strongest issue to anchor the cluster because it cleanly subsumes 43704 and is the most developed report of a clearly duplicated bug; the rest of the cluster appears to split into separate issue pockets.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "Different failures: tokenizer/task AttributeError vs performance slowdown after upgrade." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Unrelated code paths: processor.save_pretrained file omissions vs deepspeed optimizer stepping twice." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Both involve quantization/loading, but one is a save failure and the other is a GGUF load failure; not the same bug." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "PyTorch missing ImportError is unrelated to Sentence Transformers getting stuck while loading." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Performance regression after upgrade is not the same as duplicate optimizer-step behavior under deepspeed." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Different issues: slowdown regression vs Qwen3.5-MoE from_pretrained error." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "Both are field/attribute-related, but they affect different model/config paths and have different causes." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 behavior settings are unrelated to meta-init incompatibility for old InternVL2 remote-code checkpoints." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Different model-specific bugs: missing attribute on SAM 3 Video vs wrong vision_position_ids on Qwen2.5-VL." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "Generic bug report is not the same concrete issue as Gemma-4 ZeRO3 from_pretrained failure." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe/transformers v5 incompatibility is unrelated to processor.save_pretrained missing files." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import errors, but they concern different symbols and likely different export paths." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Tokenizer regex crash and auto_docstring crash are unrelated code-path failures." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving failure is unrelated to Llama4Config missing pad_token_id." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Different model/processor plumbing bugs; no shared concrete failure." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same model family, but one is a missing config field and the other is a from_pretrained error; not enough to merge as duplicates." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same exact bug report: Qwen3ForCausalLM VRAM leak when used in multiple dataloader threads." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to attention-kernel divergence under torch.compile." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Different Qwen3.5-MoE symptoms: from_pretrained error vs missing deepstack_visual_indexes field." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization offloading issue is not the same as incorrect pipeline-parallel LLM output." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports: AutoImageProcessor vs HybridCache." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "FP8 accuracy regression and FP8 save_pretrained failure are different bugs." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline-parallel output corruption is unrelated to an infinite loop on a specific image." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "FP8 save_pretrained moe and Qwen3.5-MoE from_pretrained error are different issues." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Broken vitpose models and Gemma 4 mm_token_type_ids defaults are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Saving quantized models and missing Qwen2_5_VL import are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs update bug is unrelated to the janus image-generation test failure." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they involve different APIs and likely different regressions." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Packaging/backend dependency issue is distinct from dummy_pt_objects cleanup and dir(transformers) leakage." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Chunked_prefill cache regression is unrelated to attention-kernel divergence under compile." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Different Qwen model variants and different failure modes; not the same concrete bug." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Missing padding-mask batching bug is unrelated to load-balancing loss omission." + }, + { + "left": "issue:43526", + "right": "issue:45561", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to xdist captured_info.txt race." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized model/config issue is unrelated to the xdist race condition." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The Qwen3ForCausalLM leak pairing (42673/43704) is plausible, but the summary overstates the cluster\u2019s heterogeneity by saying it is the only clear duplicate pair. The packet also contains two issues with the same title, 45310 and 45478, which looks like another duplicate pair. Please keep the summary more conservative and acknowledge that there may be more than one duplicate relationship in the set." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 36, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43278", + "issue:43479", + "issue:43504", + "issue:43644", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43976", + "issue:44060", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44448", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44869", + "issue:44933", + "issue:44964", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45310", + "issue:45356", + "issue:45405", + "issue:45561", + "issue:45656", + "issue:45712", + "issue:45812" + ], + "soft_pairs": [ + "issue:43504|issue:45561", + "issue:44964|issue:45137", + "issue:42898|issue:44568", + "issue:42175|issue:44933", + "issue:30990|issue:35141", + "issue:43479|issue:44869", + "issue:43976|issue:44933", + "issue:43479|issue:44079", + "issue:42898|issue:45812", + "issue:43784|issue:43824", + "issue:44188|issue:44373", + "issue:44623|issue:45310", + "issue:43278|issue:45137", + "issue:44734|issue:45103", + "issue:30333|issue:33290", + "issue:43723|issue:44568", + "issue:42898|issue:45356", + "issue:44060|issue:45125", + "issue:43874|issue:45092", + "issue:42898|issue:44779", + "issue:45405|issue:45712", + "issue:42898|issue:44448", + "issue:44295|issue:45656", + "issue:44933|issue:45712", + "issue:44222|issue:44297", + "issue:44297|issue:45656", + "issue:43479|issue:43644", + "issue:44206|issue:45103", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:41628|issue:42757", + "issue:22355|issue:28282", + "issue:30333|issue:36331" + ], + "prepared_review_unit_hash": "9f8ca32d8cbb559640ebb7995e13caf5054e393b68a6e67036f9d20f23404284", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37643, + "estimated_input_tokens": 9411, + "estimated_eval_tokens": 19078 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These soft pairs are overwhelmingly unrelated. They span different subsystems (tokenizers, model loading, training loops, deepspeed, multimodal processors, imports, docs, and packaging), so none should be merged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "No canonical issue: the candidate pairs are heterogeneous and do not appear to describe the same underlying bug.", + "canonical_pr_reason": null, + "best_issue_reason": "No single best issue for duplicate anchoring; even the broadest regression reports are still model- or subsystem-specific and do not cover the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43504", + "right": "issue:45561", + "accept": false, + "reason": "Legacy field loading failure and pytest-xdist file-race are unrelated bugs in different code paths." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Phi-4 multimodal model loading and DeepSpeed ZeRO3 deque underflow are different failures with no shared root cause." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions, but one is a v5 cleanup behavior change and the other is missing BOS/EOS insertion for a specific tokenizer." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Packaging/backend dependency mismatch and a missing image_utils import are unrelated." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence-transformers loading hang and embedding reinitialization after resize are different model lifecycle problems." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Phi4MultimodalConfig defaults and Whisper timestamp decoding are unrelated multimodal issues." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version compatibility and a missing image_utils symbol are different classes of failure." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Config default initialization and ModelOutput key assignment are unrelated internals." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both involve tokenizers, but they affect different models and different regression mechanisms." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Sentence-transformers import NameError and missing Qwen2_5_VL export are unrelated import failures." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "A torch.compile attention-kernel bug and a docstring issue do not share a concrete code-path problem." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Missing processor save artifacts and Qwen3.5 MoE from_pretrained errors are different bugs." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift in eval and DeepSpeed deque popping are unrelated." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "KV-cache continuation crash and auto-docstring annotation handling are separate areas with no common fix." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLFlow status reporting on failed jobs and Adafactor OOM are different training issues." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Generic tokenizer loading regression and add_special_tokens behavior for one tokenizer are not the same bug." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer regressions affecting different models and different failure modes." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Incorrect tied-weights warning and missing tensor-parallel plan are distinct Qwen3-family issues." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing image patch count method and remote-code meta-init incompatibility are separate multimodal-loading problems." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but they concern different model families and outputs." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "A version pin not yet released and leftover dummy classes failing repo checks are unrelated maintenance issues." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Tokenization cleanup behavior and Pegasus output differences are not the same underlying bug." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "position_ids buffer access and double optimizer stepping with deepspeed are unrelated training/runtime issues." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Missing import from image_utils and dummy class leakage in dir(transformers) are different export/cleanup problems." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "FP8 save_pretrained behavior and tokenizer_class metadata mismatch are different save paths and should not be merged." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save metadata and duplicated optimizer steps are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Default multimodal config initialization and non-persistent buffer junk are different initialization bugs." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature extractor argument handling and auto-docstring annotation parsing are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Model FP8 save_pretrained and processor save_pretrained missing files are not the same failure." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FP8 accuracy regression and missing processor files are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they involve different symbols and different packages." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Missing transformers.onnx module and missing PyTorch dependency are separate import-time problems." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLFlow reporting on failed jobs and Trainer compute_loss signature change are different training-stack issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 37, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:30990", + "issue:34689", + "issue:35141", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42994", + "issue:43232", + "issue:43479", + "issue:43576", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44060", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44568", + "issue:44623", + "issue:44871", + "issue:44913", + "issue:44977", + "issue:44991", + "issue:45092", + "issue:45103", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45593", + "issue:45753", + "issue:45834" + ], + "soft_pairs": [ + "issue:30333|issue:34689", + "issue:43232|issue:45834", + "issue:44222|issue:44484", + "issue:28282|issue:30333", + "issue:44297|issue:45310", + "issue:43723|issue:44977", + "issue:30333|issue:35141", + "issue:44263|issue:45092", + "issue:44483|issue:45406", + "issue:44263|issue:44360", + "issue:44514|issue:45103", + "issue:44373|issue:44485", + "issue:44295|issue:44623", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:44261|issue:45092", + "issue:43723|issue:44991", + "issue:30990|issue:38175", + "issue:43723|issue:44442", + "issue:41628|issue:43824", + "issue:43479|issue:44913", + "issue:39401|issue:44568", + "issue:42831|issue:45310", + "issue:42886|issue:42994", + "issue:44263|issue:44373", + "issue:42757|issue:45278", + "issue:42831|issue:44038", + "issue:43756|issue:44060", + "issue:43232|issue:45593", + "issue:43576|issue:43784", + "issue:42831|issue:45753" + ], + "prepared_review_unit_hash": "9e6f88b24e4a375b00b23c3da707746c3ea35b71fb8aae4cdaea180c24c63098", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36700, + "estimated_input_tokens": 9175, + "estimated_eval_tokens": 18606 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly noisy and heterogeneous. Several items are vaguely about Transformers v5 import/loading regressions, but none of the soft pairs look like the same concrete bug or fix.", + "confidence": 0.81, + "canonical_issue_reason": "issue #45278 is the broadest umbrella in the set: it summarizes multiple import failures after upgrading to v5, which best matches the cluster\u2019s loose theme better than the narrower tokenizer/model-specific reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45278 is the best single issue to anchor the cluster because it is broad, current, and captures the repeated import-regression pattern without overfitting to one model or API.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "Different problems: MLflow job-status reporting vs a specific model-loading regression." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation bookkeeping after sync_gpus is unrelated to Kosmos2.5 OCR position indexing." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 save_pretrained failure is a concrete serialization bug; max_shard_size question is a separate API/behavior issue." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "ImportError for missing PyTorch and MLflow reporting on training failure are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer_class metadata mismatch in save_pretrained is not the same as Qwen3.5 MoE from_pretrained loading failure." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Both involve loading, but one is tokenizer loading in v5 and the other is Qwen3.5 flash-attention generation behavior." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Training-job reporting and embedding reinitialization in post_init are unrelated bugs." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "torch.split/indexer logic and remote-code meta-initialization compatibility are different code paths." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat-completions request handling and Gemma4Processor missing _tokenizer are separate serving failures." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA/indexer internals, but one is a torch.split issue and the other is a missing ReLU; not the same bug." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Qwen2_5_VL batched chat-template crash is unrelated to the auto_docstring annotations crash." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Wrong docstring for position_ids is documentation-only; GLM-5 RoPE is an implementation issue." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Buffer registration/readback error is unrelated to processor.save_pretrained missing files." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading regression and eos_token_id config inconsistency are different failures." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Meta-initialization incompatibility for old checkpoints is not the same as incorrect visual encoder keys on save." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA rms_norm_eps precision issue is unrelated to InternVL2 meta-init incompatibility." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-load complaints, but they concern different models and likely different failure modes." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence-Transformers loading hangs and SigLIP2 zero probabilities are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Generic AutoTokenizer load failure and FastSpeech2ConformerTokenizer load failure are not clearly the same underlying bug." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Missing AutoImageProcessor and missing Qwen2_5_VLForConditionalGeneration are different import symbols, not one duplicate." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Phi4Multimodal config initialization and GPTNeoX rotary_pct reload behavior are unrelated config bugs." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Offset_mapping is a tokenizer alignment bug; missing BOS/EOS on add_special_tokens is a different tokenizer behavior." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy drift and Qwen3.5 MoE from_pretrained failure are unrelated." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline cache tokenizer loading and quantized model saving are separate subsystems." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "DSA indexer torch.split behavior and a wrong docstring are not the same issue." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "A missing huggingface_hub symbol and broad v5 import errors overlap only at a very high level, not the same concrete bug." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "FineGrainedFP8 accuracy and Qwen3-VL-Moe bug reports are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Smollm3 RoPE-layer loss and Qwen3-Next tied-weight warning concern different model implementations." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwarg update logic is unrelated to D-FINE auxiliary-loss handling." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Broken transformers env command and sentence-transformers import NameError are separate regressions." + }, + { + "left": "issue:42831", + "right": "issue:45753", + "accept": false, + "reason": "FineGrainedFP8 accuracy and Qwen3_5 infinite-loop behavior are different bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 38, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:30990", + "issue:33357", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44117", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44360", + "issue:44373", + "issue:44485", + "issue:44488", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44743", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:45200", + "issue:45278", + "issue:45290", + "issue:45600" + ], + "soft_pairs": [ + "issue:42886|issue:43066", + "issue:22355|issue:28218", + "issue:43122|issue:44521", + "issue:42371|issue:44263", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:43232|issue:44743", + "issue:42907|issue:44945", + "issue:44704|issue:45290", + "issue:41628|issue:45278", + "issue:44295|issue:44297", + "issue:43976|issue:44945", + "issue:43122|issue:44514", + "issue:39401|issue:44488", + "issue:43784|issue:45600", + "issue:42907|issue:43937", + "issue:43408|issue:43475", + "issue:44360|issue:44485", + "issue:44261|issue:44373", + "issue:44625|issue:44829", + "issue:39401|issue:44521", + "issue:43116|issue:45200", + "issue:29127|issue:30990", + "issue:42907|issue:44964", + "issue:43122|issue:44779", + "issue:44038|issue:44297", + "issue:44038|issue:44295", + "issue:42907|issue:43452", + "issue:36296|issue:43116", + "issue:43824|issue:44351", + "issue:44038|issue:44222", + "issue:42757|issue:44351" + ], + "prepared_review_unit_hash": "2513658dccefc7cb679dc3fed5776ce5caae9301bb0a344e9d94f3e2ea0abc3b", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36833, + "estimated_input_tokens": 9209, + "estimated_eval_tokens": 18674 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is a loose collection of mostly unrelated Transformers issues; none of the soft pairs look like the same underlying bug/change, so I reject all soft edges. The best representative issue is the broad import-regression report (#45278), but only as a loose umbrella example rather than a true duplicate canonical.", + "confidence": 0.18, + "canonical_issue_reason": "#45278 is the broadest, most umbrella-like report in the set: it describes many import errors after an upgrade and can loosely represent several import-breakage themes present here.", + "canonical_pr_reason": null, + "best_issue_reason": "#45278 is the strongest single issue representative because it is a general regression report, open, and closer to the recurring import-related failures than the more one-off model/tokenizer bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline-cache tokenizer loading and a tokenizer decoder-type mismatch are different failure modes in different code paths." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "ONNX import failure and extra-space tokenization behavior are unrelated bugs." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Version-to-version tokenization drift is not the same as multimodal assistant_mask generation failing." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 configuration guidance and a torch.split return-value issue are unrelated." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor kwargs forwarding are different from_pretrained plumbing bugs." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "A load hang in sentence-transformers and a MacOS bus error on CLIP are not the same bug." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Generation kwargs updating and recurrent-state reset in Qwen3.5 are different code paths." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized models and wrong outputs under pipeline parallelism are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor cached_file kwargs and chat_template crashes on tool-call assistant messages are distinct issues." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "A single missing import and a broad collection of import errors after upgrade are related only at a very high level, not the same concrete bug." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Reading a position_ids buffer and tokenizer_class metadata mismatching on save_pretrained are different serialization/state problems." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version incompatibility and pipeline-parallel output corruption are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenizer behavior differences across versions and batched chat_template crashes are different bugs." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping errors and a model load failure for cjvt/sleng-bert are unrelated." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "A NameError importing sentence-transformers and stale auto_mappings references are different import breakages." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Model save failures and invalid GenerationConfig reports do not describe the same problem." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "A model-type warning and a missing fpn_position_embeddings attribute are different SAM3 issues." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "Missing ReLU in the DSA indexer and GLM-5 RoPE implementation are unrelated model-specific bugs." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A precision bug in MLA q_a_layernorm and a wrong docstring for position_ids are not the same change." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation and flash_attention_3 training degeneration are different failures." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Qwen3 offset_mapping and multimodal assistant_masks are different tokenizer/processor bugs." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Empty multi-label classification outputs and mm_token_type_ids defaulting are unrelated example/model issues." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "Error-message clarity in LayoutLMv3 and a loading hang in Sentence Transformers are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Dequantized-save failures and inability to load a multimodal Phi-4 model are different bugs." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "General tokenization drift across versions and DeepSeek tokenizer regressions are not the same underlying issue." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "A Qwen3-VL-Moe bug and tokenizer_class metadata mismatch on save_pretrained are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "These both mention moe, but one is a model behavior bug and the other is FP8 save_pretrained handling; not the same concrete code path." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Missing is_offline_mode and missing HybridCache are separate import errors with different fixes." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models and gguf_file handling in from_pretrained are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "A tensor-parallel training bug and a multi-label example script bug are different layers of the stack." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Missing Qwen2_5_VLForConditionalGeneration and missing HybridCache imports are different symbols and different regressions." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe loading/behavior and FP8 save_pretrained in moe are related only by subsystem, not by the same bug." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Qwen3-VL-Moe behavior and position_ids buffer access are unrelated." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "These are separate missing-import reports for different names and should not be merged." + } + ] + }, + "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": 39, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42907", + "issue:43064", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43278", + "issue:43441", + "issue:43493", + "issue:43673", + "issue:43784", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44222", + "issue:44291", + "issue:44485", + "issue:44704", + "issue:44779", + "issue:44936", + "issue:44945", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45083", + "issue:45216", + "issue:45278", + "issue:45405", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753" + ], + "soft_pairs": [ + "issue:45216|issue:45478", + "issue:43278|issue:44945", + "issue:43066|issue:44779", + "issue:43493|issue:45753", + "issue:42907|issue:44222", + "issue:43122|issue:44977", + "issue:43992|issue:44704", + "issue:43784|issue:45446", + "issue:38617|issue:45278", + "issue:42673|issue:45072", + "issue:43937|issue:44485", + "issue:22355|issue:29127", + "issue:42371|issue:43874", + "issue:42222|issue:43441", + "issue:43064|issue:43673", + "issue:43976|issue:45446", + "issue:44075|issue:44936", + "issue:43116|issue:43493", + "issue:43116|issue:43825", + "issue:44038|issue:45478", + "issue:44222|issue:45478", + "issue:45083|issue:45446", + "issue:43937|issue:45563", + "issue:33453|issue:39401", + "issue:44117|issue:45588", + "issue:39401|issue:44779", + "issue:43827|issue:45446", + "issue:43937|issue:44977", + "issue:42673|issue:43906", + "issue:44291|issue:45071", + "issue:45405|issue:45446" + ], + "prepared_review_unit_hash": "87ab9625cd4691659aaefe0302892544a74aebeb5df6865b4e7f12baadf7dbbe", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "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": "This cluster is mostly a loose collection of Transformers v5-era regressions across tokenization, model loading, generation, and import-time breakages. The titles overlap on version upgrades and model families, but the concrete failure modes are different enough that I don\u2019t see true duplicate pairs here.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45278 is the broadest and most current umbrella-style report in the set: multiple import errors after upgrading to 5.5.0. It is the best anchor for related upgrade/import regressions, even though the rest of the cluster is not actually one duplicate bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best representative issue because it is open-ended, upgrade-focused, and broad enough to serve as the cluster anchor for nearby version-regression reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen3.5/MoE save/load regressions around 5.4.0, but one is about save_pretrained producing a bad checkpoint and the other is a from_pretrained loading error. Related family, not the same concrete bug." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "BF16/FP32 dtype drift in evaluate is unrelated to incorrect outputs under pipeline parallelism." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both involve tokenizer behavior in v5, but one is a decoder-type mismatch and the other is incorrect DeepSeek tokenization results. Different failure modes." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "SigLIP2 implementation mismatch and a Qwen3.5 image-specific infinite loop are distinct model bugs." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both touch saving quantized models, but one is dequantized Ministral/Devstral save failure and the other is FP8 MoE save_pretrained. Not the same code-path problem." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer-version output changes and a flash-attention generation failure for Qwen3.5 are unrelated." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "UMT5 weight-loading and AutoProcessor forwarding kwargs to cached_file are different APIs and bugs." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import NameError and a flex_attention version-check issue are unrelated import-time breakages." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Both are import errors after upgrading, but one is a specific missing symbol and the other is a broad report of many import errors. Not the same underlying bug." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "A VRAM leak in multi-dataloader-thread Qwen3ForCausalLM use is unrelated to dtype mismatches in inference." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "Invalid GenerationConfig for GLM-5 and a GLM-5 RoPE implementation discussion are separate issues." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Missing transformers.onnx module and a LayoutLMv3 error-message clarity issue are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 API guidance and a missing get_number_of_image_patches method in GLM46V are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Broken VitPose models and a Ministral-3 flash-attention failure are different model-specific regressions." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Wrong optimizer state handling with FSDP2/PEFT and a missing cache during chunked_prefill are different training vs generation bugs." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility and a PyTorch version check for AuxRequest import are not the same defect." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Unused SGD arguments and trainer.evaluate failing after train do not share the same code path." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Example-script multi-label classification output and SigLIP2 implementation mismatch are unrelated." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "A classification example returning empty results is unrelated to pipeline() suggesting unsupported translation tasks." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3-family MoE models, but one is a broader Qwen3-VL-Moe issue and the other is a Qwen3.5 from_pretrained error. Not the same concrete bug." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "FP8 save_pretrained for MoE and a Qwen3.5 from_pretrained failure are different save vs load problems." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "A helper-function bug in qwen3_omni_moe and a version-check import issue are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GLM-5 generation config validation and a stale warning in paged generate() are different generation-layer bugs." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Tokenizer loading regression and Qwen3 offset_mapping errors are both tokenizer-related but not the same failure." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and a flash_attention AttributeError on s_aux=None are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different models and symptoms (offset_mapping vs incorrect outputs)." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing pipeline() and a PyTorch version-check import bug are unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GLM-5 invalid generation config and Qwen3.5 flash-attention generation failures are different model-specific problems." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "A VRAM leak in dataloader-threaded generation and an isolated reproduction of another issue are not the same bug." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument handling and PretrainedConfig type-checking are separate v5 compatibility issues." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "An unreleased PEFT minimum version bump and a flex_attention import version check are unrelated release/compatibility issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 40, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42617", + "issue:42673", + "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:43874", + "issue:43937", + "issue:43986", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44496", + "issue:44829", + "issue:44933", + "issue:45071", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45459", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45561", + "issue:45656" + ], + "soft_pairs": [ + "issue:43450|issue:43986", + "issue:45341|issue:45561", + "issue:44117|issue:45081", + "issue:38617|issue:41628", + "issue:39401|issue:43421", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:42673|issue:43582", + "issue:44484|issue:45310", + "issue:42371|issue:44261", + "issue:43408|issue:43742", + "issue:42617|issue:45341", + "issue:44933|issue:45278", + "issue:42222|issue:45542", + "issue:42673|issue:43577", + "issue:43937|issue:44496", + "issue:42175|issue:42222", + "issue:38617|issue:44220", + "issue:44075|issue:45656", + "issue:44483|issue:45464", + "issue:42371|issue:42831", + "issue:43066|issue:43122", + "issue:43012|issue:43577", + "issue:43673|issue:45341", + "issue:44484|issue:45478", + "issue:44410|issue:45478", + "issue:43874|issue:44261", + "issue:43097|issue:44493", + "issue:44263|issue:44485", + "issue:43012|issue:43408", + "issue:42222|issue:45459", + "issue:41628|issue:45071" + ], + "prepared_review_unit_hash": "8056a92d962830c99ba69fa53c8d9262014d3ce1f9c4ae5eec76b32c3262c919", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36975, + "estimated_input_tokens": 9244, + "estimated_eval_tokens": 18744 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous: import/API regressions, tokenizer issues, model-loading bugs, optimizer problems, and backend/config complaints. I did not find any soft-edge pair that is clearly the same underlying bug/change. The only obvious duplicate-looking item in the list is the repeated Qwen3.5 MoE from_pretrained report (issue:45310 and issue:45478), but that pair was not part of the supplied soft edges.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45310 is the cleanest concrete bug report to anchor the only near-exact duplicate-looking thread in this set; issue:45478 repeats the same Qwen3.5 MoE from_pretrained error title and reads like a later duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best issue anchor because it is specific, reproducible, and has a later same-title twin (issue:45478), making it the most plausible canonical issue among the listed items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Different failures: incorrect batched video processor shape vs AutoProcessor crashing without torchvision." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "A general testing_utils bug is not the same as a pytest-xdist race on captured_info.txt." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping None handling and Mistral regex patching are separate tokenizer code paths." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Two unrelated import errors: missing layer_type_validation vs missing AutoImageProcessor." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Offset-mapping corruption and runtime special-token/post-processor sync are different tokenizer bugs." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "qwen3next missing projections is a model-architecture bug, not the Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "FlashAttention-3 training degeneration is unrelated to Qwen3.5 save_pretrained checkpoint regression." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM threads and an Apple Silicon TypeError are different issues." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "max_shard_size behavior in save_pretrained is unrelated to the Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API guidance and MLA rms_norm_eps precision mismatch are not the same bug." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "sam3_tracker model-type warning and MobileLLM key error are separate loading problems." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "3d_parallel.py runtime failure is unrelated to the testing_utils bug." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": false, + "reason": "A specific missing import from image_utils is not the same as a broad import-error regression report." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "Broken vitpose models and tf-backend detection without TensorFlow are unrelated backend/model issues." + }, + { + "left": "issue:42673", + "right": "issue:43577", + "accept": false, + "reason": "A dataloader-thread VRAM leak is not the same as dtype propagation staying float32 in Blip2." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "GenerationConfig validation failure and missing model_type in config.json are distinct loading/config problems." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "TensorFlow not included in the torch extra and broken vitpose models are not the same underlying bug." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "ImportError for a missing symbol and an fbank feature-extraction bug do not share the same code-path." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "SGD args being ignored and optimizer.step() being called twice with deepspeed are separate optimizer bugs." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Generic /v1/chat/completions request rejection is not the same as streaming inference failing on Qwen3.5-0.8B." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 behavior guidance and FineGrainedFP8 accuracy loss are different GPU/numerics issues." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Wrong tokenizer decoder type and tokenization drift across 4.57.3 to 5.0 are related only at a very broad level, not the same bug." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "A compile-time float32 warning on bfloat16 models is not the same as Blip2 dtype fields staying float32 on load." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "Missing GenerationMixin cache during chunked_prefill is unrelated to a testing_utils bug." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "save_pretrained shard-size behavior is unrelated to the Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "qwen3next missing projections and Qwen3.5 MoE from_pretrained are different model-loading/architecture problems." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing get_number_of_image_patches in an image processor and an MLA layernorm epsilon issue are unrelated." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Removed tie_embeddings_and_encoder_decoder and unexpected position-id keys are different compatibility regressions." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "torch.split indexing values in GlmMoeDsaIndexer is not the same as the GLM-5 RoPE implementation discussion." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "bfloat16 compile warning and sam3 model-type mismatch are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "Vitpose breakage and protobuf-related tokenizer error masking are different subsystems." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Missing AutoImageProcessor import and PreTrainedConfig type-checking breakage are unrelated regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 41, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:38617", + "issue:42757", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43335", + "issue:43352", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43502", + "issue:43531", + "issue:43824", + "issue:43825", + "issue:43873", + "issue:43874", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44380", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44987", + "issue:45003", + "issue:45071", + "issue:45103", + "issue:45245", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45542", + "issue:45588" + ], + "soft_pairs": [ + "issue:43441|issue:44829", + "issue:45071|issue:45542", + "issue:43931|issue:44410", + "issue:45003|issue:45341", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43097|issue:43452", + "issue:43986|issue:45341", + "issue:44117|issue:44987", + "issue:43986|issue:44484", + "issue:43408|issue:44368", + "issue:43976|issue:45071", + "issue:43874|issue:44263", + "issue:44829|issue:45245", + "issue:43531|issue:45341", + "issue:43986|issue:45372", + "issue:38617|issue:42757", + "issue:44261|issue:44485", + "issue:43064|issue:44315", + "issue:44410|issue:45375", + "issue:38617|issue:44351", + "issue:43097|issue:45588", + "issue:44062|issue:44117", + "issue:44038|issue:44410", + "issue:44704|issue:45103", + "issue:43502|issue:43992", + "issue:43097|issue:43873", + "issue:43986|issue:44117", + "issue:43824|issue:43986", + "issue:43066|issue:43906", + "issue:43097|issue:43901", + "issue:43825|issue:44655", + "issue:43992|issue:44484", + "issue:43352|issue:44380" + ], + "prepared_review_unit_hash": "5d53d1c406b599f366300c1babf83e7b4de98b5f5f7aeb433308afe89ea083f2", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 37372, + "estimated_input_tokens": 9343, + "estimated_eval_tokens": 18942 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "A heterogeneous set of mostly unrelated Transformers issues: import/load failures, model-specific regressions, config bugs, and docs/API mismatches. None of the soft-edge pairs look like the same underlying bug or change.", + "confidence": 0.94, + "canonical_issue_reason": "issue:43097 is the broadest, most representative v5 regression in the set: a clear API/config removal with widespread user impact, closer to the cluster\u2019s general breakage theme than the narrower model-specific reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43097 is the best single issue to anchor this cluster because it is high-signal, broadly relevant, and clearly describes a concrete Transformers v5 compatibility break.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Unsupported Flash Attention 2 error vs. degenerate training with Flash Attention 3; different symptoms and code paths." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "PretrainedConfig type-checking regression vs. tensorboard/TF backend import problem; unrelated subsystems." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch vs. qwen3next missing projections; different models and failures." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "Unsafe sys.modules access vs. a testing_utils bug; unrelated areas of the codebase." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Both are Qwen3-VL family issues, but one is a load-time shape mismatch and the other is a Qwen3-VL-MoE support problem; not the same bug." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug vs. PretrainedConfig type-checking regression; distinct code paths." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed tie_embeddings behavior vs. gguf_file handling in AutoTokenizer/AutoModel loading; different failures." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "AutoProcessor/video-model crash without torchvision vs. testing_utils bug; unrelated issues." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES None handling vs. loading physical-intelligence/fast; both loader-related but different root causes." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "Processor/torchvision crash vs. a save_pretrained shard-size question; unrelated." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "sam3_video/sam3_tracker type warning vs. tie_word_embeddings warning; not the same underlying problem." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "Python version compatibility issue vs. type-checking regression; separate bugs." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Missing image-patch method vs. torch.split return-value issue in a different model component." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "FlashAttention 3 training degeneration vs. category-count runtime limit; unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Qwen3-MoE sliding-window bug vs. testing_utils bug; no shared code path." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Processor loading without torchvision vs. ReasoningEffort import failure; both load-time errors but different dependencies and fixes." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Different missing imports from different modules/packages; only superficial similarity." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "MLA layernorm epsilon config bug vs. GLM-5 RoPE implementation issue; distinct model logic." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Optimizer-state corruption with FSDP2+PEFT vs. Liger Kernel application with model_init; different training integrations." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "qwen3next missing projections vs. missing deepstack_visual_indexes field; different config/model fields." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "layer_type_validation import error vs. HybridCache import error; unrelated missing exports." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Config/API removal issue vs. flash_attention.py s_aux=None crash; different subsystems and fixes." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken keyword collision vs. TOKENIZER_MAPPING_NAMES None assumption; unrelated tokenizer bugs." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL-MoE loading bug vs. qwen3next projection omission; different model variants and code paths." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "AutoProcessor kwargs propagation vs. docstring annotation crash under future annotations; unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "local_files_only still triggers network access vs. missing embed_tokens.weight in UMT5Encoder; unrelated." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "API removal/regression report vs. offloading-with-quantization behavior issue; not the same bug." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Video-model loading without torchvision vs. tokenizer mapping None issue; different failure modes." + }, + { + "left": "issue:43824", + "right": "issue:43986", + "accept": false, + "reason": "Missing Qwen2_5_VLForConditionalGeneration export vs. video-model/torchvision crash; distinct missing symbols." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Wrong tokenizer decoder type vs. an isolated reproduction of a different issue; insufficient evidence of sameness." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline translation-task messaging bug vs. saving Pipeline objects; different pipeline behaviors." + } + ] + }, + "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": 42, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42757", + "issue:42886", + "issue:42898", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43381", + "issue:43475", + "issue:43502", + "issue:43525", + "issue:43526", + "issue:43550", + "issue:43582", + "issue:43611", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43867", + "issue:43901", + "issue:43937", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44230", + "issue:44263", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:44938", + "issue:45216", + "issue:45290", + "issue:45381", + "issue:45440", + "issue:45479", + "issue:45753" + ], + "soft_pairs": [ + "issue:43208|issue:43550", + "issue:43012|issue:43550", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:42907|issue:45753", + "issue:42907|issue:44655", + "issue:44380|issue:45479", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:43208|issue:43526", + "issue:36683|issue:43582", + "issue:44483|issue:44514", + "issue:43012|issue:44683", + "issue:43618|issue:43761", + "issue:43618|issue:44380", + "issue:42757|issue:43824", + "issue:38617|issue:43502", + "issue:44038|issue:44230", + "issue:44483|issue:45290", + "issue:43299|issue:43867", + "issue:44483|issue:45381", + "issue:43756|issue:44485", + "issue:43299|issue:45753", + "issue:43901|issue:44655", + "issue:36683|issue:43475", + "issue:42994|issue:44655", + "issue:43352|issue:43937", + "issue:43867|issue:45216", + "issue:44077|issue:44380", + "issue:36010|issue:42757", + "issue:42898|issue:43066", + "issue:36683|issue:44077", + "issue:43611|issue:44655", + "issue:43976|issue:44938", + "issue:44263|issue:45440", + "issue:36683|issue:43525" + ], + "prepared_review_unit_hash": "933d243d8e51ebe703a7eb203f9ffd54da3314c3cdc9ad024ba4791132b25bfc", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38206, + "estimated_input_tokens": 9552, + "estimated_eval_tokens": 19360 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a duplicate set; it mixes unrelated Transformers issues across imports, config attributes, tokenizer behavior, model loading/saving, generation, and backend-specific regressions. The soft pairs mostly share only broad keywords like \"v5\", \"load\", \"save\", or a model family name, not the same concrete bug.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training bugs for sub-7B models and a Bamba torch.compile/SDPA failure are different models and different failure modes." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "One is a bfloat16 warning during compile; the other is a specific Bamba compile/runtime failure. Same broad area, not the same bug." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both mention warnings, but one is a PyTorch precision warning and the other is a tie_word_embeddings config warning in a different workflow." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading and gradient checkpointing in eval mode are unrelated code paths." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized models and an infinite-loop image generation bug are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Both involve saving, but one is dequantized model serialization and the other is saving Pipeline objects." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "GPT2 attention scaling with SDPA/FlashAttention and zero-loss sequence classification are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Flash Attention 2 support for Nemotron and Python version compatibility are different issues." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption and GPT2 attention scaling are different training/inference bugs." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs and a BeitImageProcessorFast label reduction bug do not overlap." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Gemma3Config missing vocab_size and an Apple Silicon TypeError in caching_allocator_warmup are unrelated." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Chat/completions request rejection and a batched apply_chat_template crash are different layers and different symptoms." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "A bfloat16 precision warning is not the same as compiled flex_attention breaking on torch>=2.9." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP regressions, but one drops attentions and the other drops hidden_states; different outputs and code paths." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP attentions regression and GPT2 attention scaling are unrelated." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Missing is_offline_mode in huggingface_hub and missing Qwen2_5_VLForConditionalGeneration in transformers are separate import errors." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Importing layer_type_validation and making API requests despite local_files_only=True are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Qwen3-VL-Moe loading breakage and fp8 inference support for Qwen3.5 MoE are not the same bug." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "A /v1/chat/completions acceptance problem and a tool-call chat-template crash are different request paths." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-Moe loading failures and a state_dict-sorting load error are distinct load-time issues." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "API request validation and incorrect vision_position_ids in Qwen2.5-VL video input are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Smollm3 RoPE-layer dropping and GLM-5 RoPE implementation discussion are different models and different defects." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Qwen3VL-Moe loading breakage and a Qwen3.5 infinite-loop image bug are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "A docs mismatch about return_all_scores and a pipeline save_pretrained failure are unrelated." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config missing vocab_size and Sam3VisionEncoderOutput missing fpn_position_embeddings are different attribute regressions." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model saving failure and Pipeline.save_pretrained failure are both save-related but affect different object types and code paths." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Nemotron FlashAttention support and GLM-5 GenerationConfig validation are unrelated." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "A load error when state_dict is sorted and a Qwen3.5 save_pretrained regression are different checkpoint issues." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "PatchTSMixer post_init restrictions and GPT2 attention scaling with SDPA/FlashAttention are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "GenerationMixin missing from transformers.generation and is_offline_mode missing from huggingface_hub are separate import regressions." + }, + { + "left": "issue:42898", + "right": "issue:43066", + "accept": false, + "reason": "A clean_up_tokenization_spaces behavior change and a wrong tokenizer decoder type are both tokenizer regressions but not the same bug." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Gemma3Config missing vocab_size and patchtsmixer post_init policy are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "base_model_prefix loading breakage and Pipeline.save_pretrained failure are different serialization/loading paths." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Python-version support problems in 5.1.0 and Python 3.14 load failure are both compatibility issues but not the same one." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "A torch.split return-value bug in GlmMoeDsaIndexer and DeepseekV3MoE divergence are different model internals." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Missing vocab_size on Gemma3Config and missing pad_token_id on Llama4Config are similar only in that both are config attributes, but they affect different models and code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 43, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42890", + "issue:43010", + "issue:43064", + "issue:43352", + "issue:43502", + "issue:43575", + "issue:43618", + "issue:43723", + "issue:43867", + "issue:43931", + "issue:43976", + "issue:43992", + "issue:44062", + "issue:44075", + "issue:44077", + "issue:44112", + "issue:44188", + "issue:44242", + "issue:44246", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44484", + "issue:44492", + "issue:44556", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45561", + "issue:45593", + "issue:45600", + "issue:45850" + ], + "soft_pairs": [ + "issue:43352|issue:45593", + "issue:43618|issue:45216", + "issue:44188|issue:44380", + "issue:36683|issue:44242", + "issue:43064|issue:44492", + "issue:43352|issue:43931", + "issue:43010|issue:45278", + "issue:43992|issue:45310", + "issue:43867|issue:45375", + "issue:41669|issue:44246", + "issue:44355|issue:44855", + "issue:36683|issue:43064", + "issue:42890|issue:45561", + "issue:44938|issue:45071", + "issue:43867|issue:45357", + "issue:43010|issue:45850", + "issue:43992|issue:45478", + "issue:43010|issue:43976", + "issue:44938|issue:45381", + "issue:43618|issue:44077", + "issue:44360|issue:45440", + "issue:36296|issue:43575", + "issue:28282|issue:33453", + "issue:43867|issue:44484", + "issue:43618|issue:44857", + "issue:43618|issue:44977", + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:43010|issue:44075", + "issue:43723|issue:44556" + ], + "prepared_review_unit_hash": "218bdf440d4df1bb5149181c96859c71df6dbf6327c4abf6096fec450dace22f", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36853, + "estimated_input_tokens": 9214, + "estimated_eval_tokens": 18684 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of Transformers bug reports, mostly version-regression and model-specific loading/training issues. The soft pairs share broad themes at best, but none look like the same concrete bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.76, + "canonical_issue_reason": "Issue 45278 is the closest umbrella report in this set because it captures the broad post-v5 import/regression theme, but it is still only a thematic representative, not a true duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "45278 is the best single issue to stand in for the cluster because it is the broadest and most general description among the reports, though the cluster is too heterogeneous for a strong canonical fit.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43352", + "right": "issue:45593", + "accept": false, + "reason": "Different models and failure modes: FlashAttention 2 support error vs auxiliary-loss behavior in D-FINE." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "Unrelated regressions: missing CLIP attentions field vs Qwen3.5 save_pretrained key corruption." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "Both touch attention backends, but one is torch.compile divergence and the other is GPT2 scaling ignored under SDPA/FlashAttention; different bugs." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3 config attribute missing vs MoE load-balancing loss gating; no shared underlying defect." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Training/optimizer state bug vs a cache strategy typo; clearly unrelated." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Different model-loading problems with different roots: unsupported FlashAttention 2 vs Qwen3-VL tensor shape mismatch." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Cache no_grad decoration issue is unrelated to broad import errors after upgrading to v5.5.0." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different load/save regressions affecting different Qwen models and different failure points." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "State-dict sorting/load error vs missing config field dropped by strict handling; not the same bug." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": false, + "reason": "Both concern import performance, but one identifies a concrete import-* cause while the other is only a vague slowdown report." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Compiled Python file errors vs a Python 3.13 IndentationError from torch.jit parsing; different code paths." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Config attribute regression vs FSDP2/PEFT optimizer-state corruption; unrelated." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Both are flaky test/CI issues, but the failing mechanisms differ: missing set_seed vs xdist race on captured_info.txt." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Python-version import failure vs PretrainedConfig typing regression; not the same concrete issue." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Load-time state_dict issue vs save_pretrained writing wrong visual encoder keys; opposite sides of the serialization flow and different models." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "A specific cache-update no_grad bug does not match a generic complaint that v5 breaks many models." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen/UMT5 loading regressions with different missing keys and error paths." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache update autograd issue is unrelated to Python 3.9/3.10 compatibility." + }, + { + "left": "issue:44938", + "right": "issue:45381", + "accept": false, + "reason": "Python 3.14 load failure vs Qwen2.5-VL video position-id bug; unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "Different model API regressions: CLIP attentions field vs patchtsmixer post_init policy." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer activation bug vs DeepseekV3MoE implementation drift; unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Both mention tensor parallelism, but one is a training bug and the other is an OOM on loading a huge model; not the same defect." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "ImportError about missing PyTorch is unrelated to tokenizer-loading regression." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Model load error vs a question about default shard size; no duplicate evidence." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "CLIP output attentions regression and an AMP float16 crash in LwDetrImageLoss are unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Different models and symptoms: CLIP attentions assignment vs Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "Test flakiness from missing set_seed is unrelated to Phi-4 multimodal load failure." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "Local-files-only network leakage vs AddedToken constructor argument duplication; different subsystems." + }, + { + "left": "issue:43010", + "right": "issue:44075", + "accept": false, + "reason": "Cache update autograd bug is unrelated to SGD arguments being ignored." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer-loading regression vs checkpoint reload incompatibility after version upgrades; similar domain but different concrete failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 44, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43065", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43526", + "issue:43576", + "issue:43673", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:44222", + "issue:44230", + "issue:44261", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44387", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44655", + "issue:44749", + "issue:44908", + "issue:44938", + "issue:44961", + "issue:45071", + "issue:45125", + "issue:45341", + "issue:45362", + "issue:45375", + "issue:45468", + "issue:45478", + "issue:45850" + ], + "soft_pairs": [ + "issue:42548|issue:44351", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:44387|issue:44556", + "issue:43010|issue:43065", + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:43010|issue:43232", + "issue:30990|issue:31795", + "issue:45125|issue:45478", + "issue:45125|issue:45375", + "issue:30333|issue:33453", + "issue:43502|issue:44222", + "issue:43299|issue:44556", + "issue:44315|issue:44360", + "issue:42831|issue:43874", + "issue:43502|issue:44961", + "issue:30333|issue:36296", + "issue:44355|issue:45071", + "issue:44222|issue:44230", + "issue:44355|issue:44655", + "issue:43827|issue:44961", + "issue:33453|issue:34689", + "issue:42757|issue:43576", + "issue:33453|issue:36296", + "issue:43576|issue:43824", + "issue:43576|issue:45071", + "issue:31795|issue:38617", + "issue:41628|issue:42548", + "issue:44961|issue:45468", + "issue:38617|issue:43576", + "issue:43673|issue:44492", + "issue:43576|issue:44938", + "issue:44908|issue:44961", + "issue:44485|issue:44961", + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:45362|issue:45850", + "issue:44261|issue:44360" + ], + "prepared_review_unit_hash": "c8adefc2b256768e1ed7ac312899f2914d137ea48128e9a440d29ef2b9d1667d", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 40, + "serialized_chars": 39017, + "estimated_input_tokens": 9755, + "estimated_eval_tokens": 19766 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a loose collection of unrelated Transformers regressions, import/load failures, cache bugs, docs issues, and a few model-specific problems. I found no soft-edge pair that clearly shares the same underlying bug or change.", + "confidence": 0.78, + "canonical_issue_reason": "issue:44556 is the clearest concrete version-compatibility regression in the set: a user-facing reload failure after upgrading from v4.57 to v5.2/v5.3. It is more representative than the narrower model-specific or docs-only items.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44556 is the best single issue to keep as the cluster anchor because it is specific, actionable, and sits near the main theme of v5 breakage/loading regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols (`PreTrainedModel` vs `HybridCache`) and likely different breakpoints." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "One is test flakiness from missing `set_seed()`, the other is a different testing_utils bug; not the same failure." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained on MoE vs missing `_tp_plan` for tensor parallelism are distinct code paths and symptoms." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization OOM and checkpoint reload compatibility after upgrade are different bugs." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "`no_grad` decoration for cache update and a dummy Conv2d in Sam3PixelDecoder are unrelated fixes." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Offline-mode network calls and GLM-5 RoPE implementation are different issues." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python-file errors and a slowdown after upgrade are different failure modes." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Cache update decoration and generation kwargs after `sync_gpus` are separate generation bugs." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Loading stall for Sentence Transformers vs documentation confusion in `model.forward` are unrelated." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but one is missing tensor-parallel metadata while the other is a `from_pretrained` failure; root causes differ." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Missing `_tp_plan` and missing `deepstack_visual_indexes` are different config omissions." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLflow failure reporting and tokenizer loading regression are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Local-files-only network requests and FP8 save_pretrained on MoE are different bugs." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both are loading regressions, but they affect different models and have different concrete failure points." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel not applied via `model_init` and a missing ReLU in DSA indexer are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FP8 accuracy issue and missing processor method causing multimodal token counting failure are distinct." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "Offline API-call bug and an unrelated issue titled `racoon` are not the same." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLflow reporting and tensor-parallel training bug are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file loading errors and `PretrainedConfig` type checking are different problems." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Save-pretrained FP8 MoE support and inference support for Qwen3-VL/Qwen3.5 FP8 are not the same concrete bug." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled Python-file errors and pipeline save_pretrained are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs referencing removed `pipeline()` and an unrelated `racoon` issue do not match." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 Vision model loading breakage are different model/load paths." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "`is_offline_mode` import error and broken `transformers env` command are unrelated." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression and tensor-parallel training bug are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Broken env command and Qwen2_5_VL import error are different issues." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Broken env command and config type-checking regression are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Docs confusion and an import error are different categories of issue." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import errors, but for different missing symbols; no clear shared root cause." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "`racoon` and Gemma-4 audio positional encoding are unrelated." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "Different failures: missing import vs broken CLI command." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Missing generation cache in chunked prefill and a cache-strategy typo are not the same bug." + }, + { + "left": "issue:43576", + "right": "issue:44938", + "accept": false, + "reason": "Broken env command and Python 3.14 load failure are unrelated." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs bug and unrelated `racoon` issue do not match." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "GLM-5 RoPE implementation and unrelated `racoon` issue are not the same." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor-parallel training bug and a docs mismatch about `return_all_scores` are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Importing `AutoImageProcessor` and errors running compiled Python files are different failures." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training bug and BeitImageProcessorFast label reduction bug are unrelated." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "A Qwen3.5 chat crash and a broad meta complaint that v5 breaks many models are not the same concrete bug." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "MLA precision issue and missing ReLU in the DSA indexer are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 45, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43827", + "issue:43874", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44246", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44945", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478", + "issue:45542", + "issue:45753", + "issue:45850" + ], + "soft_pairs": [ + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:44273|issue:45003", + "issue:44393|issue:45753", + "issue:43576|issue:44556", + "issue:44038|issue:45125", + "issue:44393|issue:45071", + "issue:43525|issue:45850", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:44492|issue:45850", + "issue:43572|issue:45850", + "issue:42371|issue:44492", + "issue:44704|issue:44908", + "issue:42890|issue:44908", + "issue:45278|issue:45850", + "issue:43408|issue:44315", + "issue:44246|issue:44273", + "issue:43976|issue:44393", + "issue:43352|issue:44393", + "issue:43576|issue:44908", + "issue:44297|issue:45230", + "issue:44908|issue:45071", + "issue:44295|issue:45230", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:43874|issue:45850", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:44315|issue:44829", + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:43576|issue:44273", + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:43519|issue:44485", + "issue:43519|issue:44908" + ], + "prepared_review_unit_hash": "1490750601a2ce5345f60a94f8978aa2397bdfb6de30fa98db27286718d26c20", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 41, + "serialized_chars": 39314, + "estimated_input_tokens": 9829, + "estimated_eval_tokens": 19914 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of Transformers v5 regression reports across import/loading, config, cache, and model-specific issues. The shared theme is broad upgrade breakage, but the soft pairs usually describe different concrete failure paths, so I would not merge them as duplicates.", + "confidence": 0.83, + "canonical_issue_reason": "issue:45278 is the best umbrella issue here: it captures the broad v5 upgrade/import-breakage pattern that recurs across several reports, even though the set is not a true duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most representative user-facing report of the shared v5 regression theme and is broad enough to anchor triage without overfitting to one model or code path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "One is a specific processor.save_pretrained bug; the other is an unspecific placeholder issue. No clear same code path." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading failures and undefined tf backend errors are different problems." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading behavior does not match modeling_utils sys.modules access." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Both are Qwen3-VL/Qwen3.5-related, but one is 2D box output hallucination and the other is an infinite loop on a specific image." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Generic transformers env command breakage is not the same as checkpoint reload incompatibility after upgrading." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Qwen3-VL-Moe bug and missing tensor-parallel plan are different model-level failures." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "A model output quality bug is unrelated to PretrainedConfig type checking breakage." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Specific Llama4Config pad_token_id error is not the same as a broad complaint that many models break." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star slowdown and missing GenerationMixin cache in chunked prefill are different issues." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Checkpoint reload after upgrade and old remote-code checkpoint/meta-init incompatibility are related only at a very broad version-upgrade level." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "Cache-strategy typo is not the same as a generic v5 breakage report." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is a specific config regression, not a general 'many models break' report." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 settings and cache-strategy typo are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs forwarding and inverse_sqrt scheduler kwargs are different APIs and failures." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Test flakiness from missing set_seed is unrelated to scheduler kwargs handling." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Both are broad v5 complaint titles, but they do not identify the same concrete bug or code path." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "sam3_tracker type warning and Liger Kernel not applied with model_init are unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import taking long sometimes is not the same as lazy loading not working properly." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility and Qwen3-VL box output issues are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support missing and Qwen3-VL 2D box hallucination are different model concerns." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken env command and scheduler kwargs ignore are different subsystems." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch is not the same as a vague placeholder bug report." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "position_ids buffer access error does not match a generic bug placeholder." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star slowdown and missing HybridCache import are distinct import-time issues." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Package import slowdown and a testing_utils typo are not the same bug." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache-strategy typo and incorrect output under pipeline parallelism are unrelated." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "Missing multimodal token helper in GLM46V is a specific AttributeError, not a broad version-wide breakage report." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Two Qwen3.5/Qwen3-VL reports, but one is box-output hallucination and the other is from_pretrained failure; different code paths." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "post_init policy enforcement and tied-weight-key AttributeError are different model-internal validation bugs." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() and scheduler kwargs are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel application with model_init and flash_attention_3 training degeneration are different problems." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Documentation confusion in model.forward and tokenizer loading regression are not the same underlying issue." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import slowdown and inverse_sqrt scheduler kwargs are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Broken env command and lazy loading failure are different areas." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Pipeline save_pretrained failure and tied-weight key handling are separate save/load bugs." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer discussion and Gemma-4 audio positional encoding are unrelated." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Two generic Qwen3.5/Qwen3 Moe reports, but the former is unspecific while the latter is a concrete from_pretrained error." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading and scheduler kwargs are different code paths." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are distinct model-specific bugs." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Timestamp calculation in a processor and scheduler kwargs handling are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 46, + "review_unit_count": 46, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-396", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:37428", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43606", + "issue:43618", + "issue:43704", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45290", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45850" + ], + "soft_pairs": [ + "issue:31795|issue:34689", + "issue:41669|issue:43704", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468", + "issue:44261|issue:45468", + "issue:43704|issue:45341", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:44492|issue:44998", + "issue:44998|issue:45850", + "issue:43618|issue:44998", + "issue:44998|issue:45341", + "issue:43525|issue:44861", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:31515|issue:31795", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "fccaac278417efc62b8c94622e76222ee5da07b4e60813450adaebce4c4ee012", + "component_budget": { + "node_count": 396, + "item_count": 396, + "soft_pair_count": 1487, + "serialized_chars": 766218, + "estimated_input_tokens": 191555, + "estimated_eval_tokens": 383366 + }, + "budget": { + "node_count": 36, + "item_count": 36, + "soft_pair_count": 31, + "serialized_chars": 29500, + "estimated_input_tokens": 7375, + "estimated_eval_tokens": 15006 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: a few issues are about Transformers v5/model-loading regressions, but most are unrelated runtime, tokenizer, training, or documentation bugs. None of the soft pairs look like the same concrete bug/change closely enough to merge as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the broadest umbrella report about widespread breakage since v5, so it best represents the cluster theme, though it is too general to be a true duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Docs confusion about input_ids/past_key_values is not the same as a tokenizer/model loading regression." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import * performance cleanup and a VRAM leak in multithreaded causal LM use are different problems." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Documentation ambiguity is unrelated to the flash-attention import error." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger-kernel application with model_init and v5 meta-init incompatibility for old InternVL2 checkpoints are different code paths." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in multi-threaded inference and RoPE implementation concerns are not the same bug." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 API guidance is unrelated to the VRAM leak issue." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "Unexpected network/API requests with local_files_only=True is different from a Qwen3VL timestamp calculation bug." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Timestamp computation in a processor and missing saved files are separate processor bugs." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Qwen3VL timestamp math is unrelated to the multi-thread VRAM leak." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return handling in an indexer is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch and audio positional encoding are different failure modes." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Missing rms_norm_eps causing precision error is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:43704", + "right": "issue:45341", + "accept": false, + "reason": "A runtime VRAM leak and a testing_utils bug are not the same underlying issue." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both concern tokenizer changes in v5, but one is a broad behavior difference while the other is a specific wrong decoder type bug." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs being ignored is unrelated to the unrelated 'Unemployment' issue." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight-key lookup crash and apply_chat_template tool-call crash affect different subsystems and code paths." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "Cache-strategy typo is unrelated to the unrelated 'Unemployment' issue." + }, + { + "left": "issue:44998", + "right": "issue:45850", + "accept": false, + "reason": "'Unemployment' is unrelated to the broad v5 model-breakage report." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIPOutput attentions regression is unrelated to the unrelated 'Unemployment' issue." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "'Unemployment' is unrelated to the testing_utils bug." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config and tied-weight-key crashes are different config/code-path bugs." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to the tied-weight-key AttributeError." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow from_pretrained checkpoint loading and an ImportError for layer_type_validation are unrelated." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support and missing processor save files are different feature/bug reports." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLFlow job-status reporting after failed training and slow checkpoint loading are unrelated." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Slow checkpoint loading and a tensor-parallel training bug are different issues." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Checkpoint loading performance and model.forward documentation confusion are not duplicates." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "FP8 inference support and a Qwen3.5 MoE from_pretrained error are different concrete bugs." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow checkpoint loading is not the same as a tokenizer-loading regression." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching not supporting audio models and FP8 inference support 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": 3, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "a489d63ab653c2cac4a69a33ed564d7aa619e8268d41478cba7fe1bc400c1192", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1589, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: one requests Flash Attention 2 support for more architectures, the other requests GGUF support for more architectures. They are related only at the broad level of model-format/attention support, but they describe different changes and code paths.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the two issues target different features and underlying implementation work.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a clear representative of the other; if one must be chosen as the cluster anchor, issue #26350 is slightly older and has more discussion, but it is not a duplicate of #33260.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different feature requests (Flash Attention 2 vs GGUF support) with no evidence of the same bug or change; not the same underlying work." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-4", + "nodes": [ + "issue:27088", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "f97fca90c2f02dd169dd2df3e67154172cac3fff0ebe8095a61c01d959695273", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4454, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4454, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are near-identical i18n translation request issues, but only one is specific to Turkish; the others are generic placeholder translation tickets and should not be merged as duplicates without matching language context.", + "confidence": 0.57, + "canonical_issue_reason": "issue:27088 is the only concrete, language-specific ticket (Turkish) and is the most actionable representative of the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:27088 best captures the actual user-facing request; the other issues look like templated placeholders rather than a distinct, identifiable translation task.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Same broad translation template, but the language context is different/unspecified; not enough to treat as the same underlying issue." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Both are translation requests, but one is specifically Turkish and the other is a generic placeholder; likely separate tickets." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "The titles are similar, but the generic placeholder issue does not clearly refer to the same language or exact task as Turkish docs translation." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "These look like repeated template issues, but there is no evidence they target the same language or identical change." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Highly similar wording alone is not enough; the placeholder titles suggest separate translation requests rather than duplicates." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "No concrete evidence that these two placeholder issues are the same language/docs translation request." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 5, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-15", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:36879|issue:37015", + "issue:37015|issue:42503", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43671|issue:43909", + "issue:43837|issue:43909", + "issue:43837|issue:45322", + "issue:43837|issue:44121", + "issue:43909|issue:44205", + "issue:44121|issue:45322", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177" + ], + "prepared_review_unit_hash": "0e67f930024631b32b23df643746a0f333d39d0e599dd1b616030c40cd58f7e0", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates; they are separate model-request issues across different models, architectures, and modalities. The similarity is mostly generic 'add support' wording.", + "confidence": 0.98, + "canonical_issue_reason": "No clear canonical duplicate exists because the cluster spans many distinct model requests rather than one underlying bug/change.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43671 is the closest hub among the Qwen3 speech-related requests, but it is still not a good duplicate canonical for the heterogeneous cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "EuroBert config vs DEIMv2; only the generic 'add model' intent matches." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config vs Qwen3-TTS support; different model and modality." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert vs RF-DETR are unrelated model additions." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are different vision models, not the same change." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR is a detection model; LFM2.5 Audio is an audio model." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR vs weight-sparse transformer: different code paths and model families." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR vs Qwen3-ASR; unrelated model requests." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR vs Qwen3-TTS; unrelated model and modality." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT vs Qwen3-ASR are different model integrations." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT and the sparse transformer request are distinct model changes." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT vs LFM2.5 Audio; unrelated requests." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are different model requests." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT vs ModernVBERT; separate model additions." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture vs Qwen3-ASR; different model and modality." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 vs sparse transformer; not the same underlying change." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 vs ModernVBERT; distinct model requests." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 vs Voxtral TTS; different model family and task." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 vs Qwen3-TTS; unrelated model additions." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT models vs Qwen3-ASR; different families." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT vs Qwen3-TTS; not the same change." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT request vs general BERT-like RoPE proposal; too broad to be duplicates." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "General BERT-like RoPE proposal vs Voxtral TTS support; different scope and model." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Both are Qwen3 requests, but TTS and ASR are different concrete capabilities/code paths." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS vs Voxtral TTS; different model integrations." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS vs DeepSeek-OCR2; unrelated." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS vs sparse transformer; different model and implementation." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS vs LFM2.5 Audio; different audio model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR vs LFM2.5 Audio; distinct speech/audio models." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR vs EUPE; unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR vs sparse transformer; different change." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio vs SAM3-LiteText; different families and modalities." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Sparse transformer vs EUPE; unrelated." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR vs Voxtral TTS; different model integrations." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT vs Voxtral TTS; unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR vs DeepSeek-OCR2; different modalities and code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 6, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-37934-6", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031" + ], + "soft_pairs": [ + "issue:37934|issue:43668", + "issue:42936|issue:43240", + "issue:42936|issue:44031", + "issue:42936|issue:43813", + "issue:42936|issue:43668", + "issue:43240|issue:43668", + "issue:43668|issue:44031", + "issue:43668|issue:43813" + ], + "prepared_review_unit_hash": "94c8ad2dfe9f4ad52670dd2ae5ed717236f23c9a71b0f044f50929b36b47fff0", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6294, + "estimated_input_tokens": 1574, + "estimated_eval_tokens": 3404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are unrelated issue reports clustered only by weak textual similarity; they do not appear to describe the same underlying bug or change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Different components and failure modes: Llama4 norm implementation vs ModernBERT config type hint. No shared code path or concrete bug." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2Former ignore_value handling is unrelated to loss kwargs propagation; different models and different defects." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Mask2Former loss-parameter issue is unrelated to tokenizer regex warnings; no same underlying bug." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former ignore_value bug and a typo in a quantization attribute name are unrelated." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Model-specific ignore_value behavior and a ModernBERT config annotation typo are not the same issue." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss kwargs forwarding bug and config type-hint typo affect different subsystems and code paths." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "ModernBERT norm_eps type hint problem is unrelated to tokenizer regex warnings after 4.57.3." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "A config annotation typo does not match a quantization-operation typo; different targets and fixes." + } + ] + }, + "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": "e11bf4f0a21561d451af3409dc9fb46a65a6b3995c3e8a323ccfca80089af33e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues do not appear to describe the same underlying change. One is a vague request around block decoding, while the other is a specific request for DeepSeek v3.2 support.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 43037 is the more concrete and identifiable request; 41084 is too vague to serve as a clear representative.", + "canonical_pr_reason": null, + "best_issue_reason": "43037 is the best issue anchor because it has a specific product/version target, whereas 41084 is underspecified and broader.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "These look like different feature requests with no explicit linkage: block decoding vs DeepSeek v3.2 support." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 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": "114ba5b76567f4f00d390d9ab55b7f4daf53eb6979a8d4f739b058f8c5f3acd9", + "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 closed issues are both about Trainer custom behavior, but they target different concerns: one is about `remove_unused_column` customizability, the other about FLOPS estimation for custom trainers. They do not look like the same underlying bug.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must be retained as the cleaner representative, #43598 is the more concrete Trainer API/customization concern; #43600 is a separate performance-accounting topic.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Different trainer behaviors are being discussed: column pruning vs FLOPS estimation. They share a subsystem but not the same bug or change, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "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": "1b4bb1502904aadeaef581fccc2a20753843af5a15dd389226c612a093f5f974", + "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": "The two issues are both about adding support for Qwen models, but they target different model families and different AutoModel heads, so they are not duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43684 is the broader, more general request about registering Qwen3-Omni with AutoModel and AutoModelForConditionalGeneration; issue:44405 is a separate, narrower request for AutoModelForSequenceClassification support on Qwen3.5.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different underlying feature requests: Qwen3-Omni model registration vs Qwen3.5 sequence-classification support. They share a broad ecosystem theme but not the same code-path change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "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": "ad031eca7391db36422f1274cf316f2dc0fe1606c764a3294bcc691563386432", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4261, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4261, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The three issues titled \"huggingface\" look like near-identical duplicates and likely describe the same report; the \"Fett\" issue appears unrelated. With no substantive body text or linked targets, triage has to rely mostly on the repeated title and close similarity.", + "confidence": 0.74, + "canonical_issue_reason": "Issue #43845 is the earliest of the near-identical \"huggingface\" reports and is as good a representative as any of that duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "#43845 is the best issue candidate because it is the earliest in the cluster and matches the other two \"huggingface\" issues most closely.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no supporting body/target evidence; likely unrelated." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no supporting body/target evidence; likely unrelated." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles and no supporting body/target evidence; likely unrelated." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same title, close creation time, and no evidence of distinct underlying reports." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same title and highly similar placeholder-style reports; likely duplicates." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same title and highly similar placeholder-style reports; likely duplicates." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The conclusions are grounded in the packet: the three \"huggingface\" issues share the same title, have close timestamps, and show strong soft-similarity, while #43835 has a clearly different title and only weak similarity. The verdicts are conservative overall, and the representative choice of the earliest huggingface issue is reasonable." + }, + "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": "dc161b0e75081b0c43c6f114de3523cc27a5b030635a82f6461264839369e2ab", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All five issues are low-information or spam-like and do not describe the same concrete bug or change. There is no credible duplicate cluster here; at most they are similarly malformed submissions.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 44371 is a reasonable placeholder canonical because it is the earliest of the near-empty spam-like issues, but it is not meaningfully better than the others.", + "canonical_pr_reason": null, + "best_issue_reason": "44371 is the least-bad representative only by chronology; none of the issues contains enough substance to serve as a true canonical bug report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Same generic spam-like title, but no underlying bug/change is described and there is no evidence they refer to the same report." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are empty spam submissions, but that is not enough to treat them as the same concrete issue." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam-like, the other is a generic documentation suggestion; they are not the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Completely different titles and no shared technical context; unrelated." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "Documentation enhancement request versus spam-like post; no shared defect or change." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Different intent and no evidence of the same underlying problem." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Identical spam-like titles, but with no substantive content or explicit linkage, they should not be merged as a confirmed duplicate bug/change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Unrelated titles and no technical overlap." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "Unrelated titles and no technical overlap." + } + ] + }, + "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": "90421f4e2ae5d52e16df810089c106d3f26c372e26cc58b542a5e5236257bdb2", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues look very likely to be duplicates: they share the exact same title and a strong soft-similarity signal. However, the packet does not prove their bodies are identical, so the duplication claim should stay cautious. #45145 is the better canonical representative because it already has one inbound reference.", + "confidence": 0.84, + "canonical_issue_reason": "#45145 is the safer canonical issue because it has the same title as #45151 and is the only one with an inbound reference. The evidence supports a likely duplicate pair, but not a claim that the bodies are the same.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best issue to keep as the representative since it matches #45151 on title, has the only inbound linkage, and there is no stronger evidence favoring #45151.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": true, + "reason": "Identical titles plus a soft-similarity signal make this look like the same underlying issue, even though the packet does not establish body identity." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Reject: the conclusion is too strong for the packet. The issues do have identical titles and a soft-similarity signal, but the packet does not show that their bodies are the same\u2014only similar lengths and a soft_similarity edge. Saying they are duplicates with \u2018same title/body\u2019 and \u2018nearly identical bodies\u2019 overstates the evidence. The inbound reference on #45145 is a reasonable conservative point, but the duplicate/canonical claim should be phrased more cautiously." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "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": "31d19a648781f5bdc2681092bf7eb9473586f8382fd7a83537ed83686fb03105", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate 4-bit inference bugs: one is a Gemma4/audio-module torch.finfo(uint8) TypeError, the other is a BitsAndBytesConfig lm_int8_skip_modules regression that removes the default lm_head exclusion and triggers an AssertionError. They should not be treated as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different failure modes and code paths: Gemma4 audio-module uint8 handling vs BitsAndBytesConfig skip-module exclusion logic. They share a broad 4-bit inference context but not the same underlying bug or fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 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": "fe18c5feab7c741564e440293cc674d13e8cf84c0e93c8bce74f0df139811311", + "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 just different personal-name/date strings with no shared bug report, code context, or discussion. They do not look like duplicates; this looks more like unrelated/spam entries.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: the titles point to different people and different dates, with no evidence they describe the same underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "If one must be selected, issue 45762 is only marginally preferable because it was created first, but it is not a true canonical duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "The titles reference different names and birth dates, and there is no shared bug, feature, or code context. They do not appear to describe the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "88db9dcd1f4a9b091dec6d2a7205f9785010188b05dc0c91d5669cf526304492", + "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": "Two closed issues with no body, links, or technical context; they only share a loose naming/date pattern and do not look like the same underlying bug report.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 45764 is not meaningfully distinguishable from 45765 as a duplicate candidate, but if one must be chosen, 45764 is simply the first and no evidence favors either as the canonical report.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a strong canonical ticket because neither contains any actionable bug description; 45764 is marginally preferable only by ordering, not by content.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "No substantive issue content, explicit linkage, or shared technical subject; the titles are just different personal-name/date strings and do not indicate 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": 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": "c41efad3a06d73b826b264e21627476395e30915279369a895d36a18adf13bb3", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5722, + "estimated_input_tokens": 1431, + "estimated_eval_tokens": 3118 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5722, + "estimated_input_tokens": 1431, + "estimated_eval_tokens": 3118 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster appears to split into two likely duplicate issue pairs\u201445870/45871 and 45872/45873\u2014plus one unrelated dataset promo issue (45869). The duplicate calls should be treated as likely duplicates based on identical titles and matching body lengths, but not as proven exact body matches since the bodies are not shown.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 45870 is the earliest representative of the strongest likely-duplicate pair ('Example: Financial time series prediction with DataForge'); it is the cleanest canonical choice in that pair, though the exact body text is not visible here.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45870 is the best global representative because it anchors one of the likely duplicate pairs, is earliest among its duplicate mate, and the remaining items are either a separate similar pair or a different dataset promo topic.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Different topics: a dataset bundle promo versus a DataForge example issue." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Different topics: a dataset bundle promo versus a DataForge example issue." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Identical title and matching body length strongly suggest the same issue; likely duplicates, though the body text itself is not visible." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Different titles and only soft-similarity signal; this looks like a separate DataForge topic, not the same underlying issue." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Different titles and only soft-similarity signal; this looks like a separate DataForge topic, not the same underlying issue." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Different titles and only broad topical overlap; not enough evidence that they are the same issue." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Different titles and only broad topical overlap; not enough evidence that they are the same issue." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Identical title and matching body length strongly suggest the same issue; likely duplicates, though the body text itself is not visible." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Reject: the analyst overstates the evidence by calling 45870/45871 and 45872/45873 \u201cexact duplicate title/body\u201d pairs. The packet only shows identical titles and matching body lengths, plus soft-similarity signals; it does not provide the bodies to confirm exact duplication. A conservative reading is that these are likely duplicates, not proven exact matches. The rest of the verdicts are broadly conservative, but the summary and canonical reasoning need to be downgraded accordingly." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 28, + "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-39895-14", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:45795", + "pull_request:45899" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:41855|pull_request:43424", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:45899", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:44827", + "pull_request:43995|pull_request:45213", + "pull_request:43995|pull_request:45899", + "pull_request:44827|pull_request:45899", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:45795", + "pull_request:44827|pull_request:45655", + "pull_request:45170|pull_request:45899", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:45213|pull_request:45899", + "pull_request:45795|pull_request:45899", + "pull_request:43823|pull_request:45795", + "pull_request:43823|pull_request:45899", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "5e14f3cde3d6565f00479a9ce3250515c28e0b2b1fbb9f4e40d37044e8b655e3", + "component_budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 26, + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 + }, + "budget": { + "node_count": 14, + "item_count": 14, + "soft_pair_count": 26, + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: model additions, docs updates, tokenizer utility changes, and unrelated bug fixes. The only clear duplicate pair is the two fixed_cross_entropy PRs against issue 43240; the rest should not be merged as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43251 is the strongest canonical PR: it directly targets issue 43240, has the fuller implementation, and 43254 is the near-identical alternative in the same file/function.", + "best_issue_reason": null, + "best_pr_reason": "PR 43251 is the best representative of the only true duplicate pair in this set; the remaining PRs are unrelated changes and not suitable for consolidation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Unrelated PRs: VideoPrism model/docs implementation vs an ExecuTorch dynamic-shapes test." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Unrelated changes: Mistral tokenizer helper methods vs adding the MobileLLM model." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer API addition and ExecuTorch export test are different code paths and problems." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-loading robustness vs adding a new model; different underlying changes." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Cross-entropy kwarg handling is unrelated to a new MobileLLM model implementation." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Different fixes: loss utility kwargs vs Mistral4 test/model adjustments." + }, + { + "left": "pull_request:43424", + "right": "pull_request:45899", + "accept": false, + "reason": "ExecuTorch export tests vs continuous batching docs; not the same bug/change." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch exportability test and Mistral4 test/model fixes are unrelated." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Dynamic-shape export testing has no overlap with adding MobileLLM." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "Adding MobileLLM is unrelated to a core config-resolution order fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "New model addition vs Falcon output-collection refactor; different code paths." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output-interface refactor is unrelated to Mistral4 test fixes." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon model refactor and model-creation skill addition are not the same change." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45899", + "accept": false, + "reason": "Falcon model refactor vs docs for continuous batching decode fast path; unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45899", + "accept": false, + "reason": "Mistral4 test/model fixes do not match the continuous batching decode fast-path docs change." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes and CLIP-like layrnorm renaming are different subsystems and fixes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45795", + "accept": false, + "reason": "Mistral4 test/model changes are unrelated to docs for adding audio/video processors." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test fixes vs class config resolution order fix; different concrete problems." + }, + { + "left": "pull_request:45170", + "right": "pull_request:45899", + "accept": false, + "reason": "Weight-renaming for CLIP-like models is unrelated to docs about decode fast path." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 bugfix/test PR is unrelated to the model-creation skill draft PR." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "A new MobileLLM model and a model-creation skill are different artifacts, not the same bug/change." + }, + { + "left": "pull_request:45213", + "right": "pull_request:45899", + "accept": false, + "reason": "Model-creation skill content is unrelated to continuous batching documentation." + }, + { + "left": "pull_request:45795", + "right": "pull_request:45899", + "accept": false, + "reason": "Docs for audio/video processors and docs for decode fast path address different documentation topics." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45795", + "accept": false, + "reason": "New MobileLLM model implementation vs docs for audio/video processors; unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45899", + "accept": false, + "reason": "MobileLLM addition is unrelated to continuous batching decode-path docs." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Same concrete code-path and same target issue 43240: both modify fixed_cross_entropy in loss_utils.py to forward cross_entropy kwargs; they are plausible alternatives to one merged fix." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only clearly mergeable duplicate pair is 43251/43254: both target issue 43240 and modify the same fixed_cross_entropy path. The other rejected pairs are sufficiently different in file, subsystem, or change intent to not look like a single bugfix PR." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 28, + "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": "d30d8b0ddbd9e8781b153144714ad2812140dd84262509fb17cb8613858e4ff3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7226, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7226, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs work on VibeVoice, but they target different scopes: PR 40546 is the base implementation, while PR 42781 is a later VibeVoice Realtime expansion with additional acoustic tokenizer and generation changes. They are related, but not the same concrete change, so they should not be deduplicated.", + "confidence": 0.83, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42781 is the broader, newer VibeVoice effort and includes the realtime/acoustic-tokenizer path, so it is the better cluster representative than the initial base implementation in PR 40546.", + "best_issue_reason": null, + "best_pr_reason": "PR 42781 is the strongest representative of the VibeVoice work because it covers the more complete realtime feature set and related model components rather than only the initial implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "They share the same model family and several files, but 40546 is the initial VibeVoice implementation while 42781 adds VibeVoice Realtime plus acoustic-tokenizer/generation changes. Different feature scopes, so 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": 3, + "component_count": 28, + "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": "481515828b615765673249d55baa3ee2dc272908e55bb32d0e1fe3dacae8da48", + "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 pull requests are unrelated: one adds covariate forecasting support to TimesFM, while the other adds image classification support for DINOv3ViT. They do not describe the same underlying bug or change.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models and different feature areas (TimesFM time-series covariates vs. DINOv3 image classification); no shared code-path problem or mergeable duplicate change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 28, + "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": 28, + "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": "573d5579612f3407391159f5bd0fa545c67c76040b7ac5930ee1a9ec0d1cbb53", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10404, + "estimated_input_tokens": 2601, + "estimated_eval_tokens": 5458 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10404, + "estimated_input_tokens": 2601, + "estimated_eval_tokens": 5458 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three unrelated model-addition pull requests. They share the usual Transformers boilerplate for registering new models, but each introduces a different model family and codepath, so none are duplicates or mergeable as one 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:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different model families and implementations: DeepSeek OCR vs Isaac. Shared auto-registry/docs scaffolding is generic new-model plumbing, not the same underlying bug or feature." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different additions: Isaac vs Kimi2-6. They touch similar registration files, but they introduce separate model codepaths and cannot 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": 6, + "component_count": 28, + "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": "12e149d25faaae870ac02e44d6882e9bde52e5c6891252ec1ffa847923f26998", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs both upgrade GitHub Actions in workflow files, but they target different actions and different change themes: one is for Node 24 compatibility of core GitHub actions, the other is a docker/build-push-action version bump. They are related in broad area only, not the same underlying change.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "42975 is the broader and more representative workflow-actions upgrade, centered on Node 24 compatibility across many workflows; 42976 is a separate docker/build-push-action bump.", + "best_issue_reason": null, + "best_pr_reason": "42975 is the best single representative of the cluster because it captures the broader GitHub Actions compatibility work, while 42976 is a distinct docker-action upgrade.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Different concrete changes: 42975 updates checkout/cache/upload-artifact for Node 24 compatibility, while 42976 bumps docker/build-push-action to v6 in docker image workflows. They share the broad CI subsystem but not the same underlying bug or mergeable PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-7", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:43973", + "pull_request:44601", + "pull_request:45490", + "pull_request:45838" + ], + "soft_pairs": [ + "pull_request:42978|pull_request:43448", + "pull_request:42978|pull_request:43451", + "pull_request:42978|pull_request:45490", + "pull_request:43448|pull_request:43451", + "pull_request:43448|pull_request:45490", + "pull_request:43451|pull_request:45490", + "pull_request:43973|pull_request:45838", + "pull_request:44601|pull_request:45838", + "pull_request:45490|pull_request:45838" + ], + "prepared_review_unit_hash": "bd699948f2538e4252e276ee7c51399977268ab5b6b410f92e3c0f81ae45731c", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23513, + "estimated_input_tokens": 5879, + "estimated_eval_tokens": 12014 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 23513, + "estimated_input_tokens": 5879, + "estimated_eval_tokens": 12014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs only look similar at a broad level because they add models or touch shared auto/docs plumbing, but they are different model families or an unrelated distributed-loading feature. None of the soft edges represent the same underlying change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No true canonical PR: the set mixes unrelated model additions (ViT NEPA, Molmo, Molmo2, Lfm2Audio, CTSM, PP-OCRv6) plus an unrelated pipeline-parallel runtime change, so there is no single duplicate target.", + "best_issue_reason": null, + "best_pr_reason": "If forced to pick one representative, pull_request:45838 is the strongest standalone PR because it has a coherent feature scope around PP-OCRv6 text recognition variants and a substantial, self-contained implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different model additions: ViT NEPA vs Molmo. Shared auto/docs files are just common registration plumbing, not the same change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different model additions: ViT NEPA vs Molmo2. They are separate model families despite both touching Transformers registration files." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "Different model additions: ViT NEPA vs CTSM. Same broad subsystem, but not the same bug or feature." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are related by naming, but the PRs add distinct model implementations and docs, not one concrete change." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM are unrelated model families; overlap is limited to generic auto/docs updates." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are separate model additions with different codepaths and model docs." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45838", + "accept": false, + "reason": "Lfm2 audio support vs PP-OCRv6 text recognition support are unrelated model additions; only the surrounding registration/docs files overlap." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45838", + "accept": false, + "reason": "Distributed pipeline-parallel loading support is unrelated to PP-OCRv6 model support; they do not fix the same code-path problem." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45838", + "accept": false, + "reason": "CTSM model support and PP-OCRv6 text recognition support are different features, with only generic registry/docs overlap." + } + ] + }, + "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": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-4", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815", + "pull_request:45892" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43291|pull_request:45892", + "pull_request:43665|pull_request:44815", + "pull_request:43665|pull_request:45892", + "pull_request:44815|pull_request:45892" + ], + "prepared_review_unit_hash": "0019a58ca6bf35b117f8153601fd391b1f234580e641c1ae440f699efe956acb", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10707, + "estimated_input_tokens": 2677, + "estimated_eval_tokens": 5610 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10707, + "estimated_input_tokens": 2677, + "estimated_eval_tokens": 5610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates: they target unrelated subsystems and fixes (Whisper tokenization/tests, CLIP/ViT test edits, FP8 dequantization/loading, and DeepSeek v4 implementation/docs).", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR fits this cluster because the PRs do not share the same underlying bug or change; they are separate, unrelated changes. If one must be named as the most substantive standalone fix, 44815 is the most coherent, but it is not a duplicate of the others.", + "best_issue_reason": null, + "best_pr_reason": "44815 is the best standalone PR in terms of completeness and technical coherence: it addresses a specific FP8 dequantization/loading path across code and tests. The others are either test-only/placeholder-like or concern different models and features.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Whisper tokenizer decode/test fix vs. CLIP/ViT test edits; different models and different problems." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper batch/timestamp decode logic is unrelated to FP8 dequantization and model loading." + }, + { + "left": "pull_request:43291", + "right": "pull_request:45892", + "accept": false, + "reason": "Whisper tokenizer/tests and DeepSeek v4 model/docs are separate code paths with no shared concrete bug." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "Test-only changes for CLIP/ViT do not match an FP8 dequantization/loading fix." + }, + { + "left": "pull_request:43665", + "right": "pull_request:45892", + "accept": false, + "reason": "CLIP/ViT test edits are unrelated to DeepSeek v4 model implementation and docs." + }, + { + "left": "pull_request:44815", + "right": "pull_request:45892", + "accept": false, + "reason": "FP8 quantization/dequantization changes are unrelated to DeepSeek v4 architecture and test/doc updates." + } + ] + }, + "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": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-2", + "nodes": [ + "pull_request:43488", + "pull_request:43532" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532" + ], + "prepared_review_unit_hash": "75cfd2b35a876a9ef79fbb8e838326a0bb4bbe8959700ce00a4212eb9a27d6b9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4562, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4562, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are not duplicates: one is a small packaging/setup change, while the other rewrites CI/workflow and testing utility behavior. They only overlap on a Vit test file, which is incidental.", + "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:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Different underlying changes and code paths: PR 43488 is about setup/version/dependency metadata, while PR 43532 changes CI workflows and testing/notification utilities. Shared Vit test filenames do not make them the same fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 28, + "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": "d348b222343b51bf6a4e36bd81e6bdd308c46ea5a4e2885d493a3d67cbdf4713", + "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 related but distinct PRs adding different segmentation pipelines: one for promptable concept segmentation and one for promptable visual segmentation. They share scaffolding and docs wiring, but the underlying task/model support differs, so they should not be treated as duplicates.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43613 is the broader, more fully integrated pipeline addition, with support across SAM/EdgeTam-related models and dedicated tests/docs. It is the better representative of this cluster than the narrower concept-segmentation PR.", + "best_issue_reason": null, + "best_pr_reason": "PR 43613 is the best representative because it covers the more general promptable visual segmentation feature and includes more complete implementation and validation work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Do not merge: they add different pipelines for different tasks/code paths (concept segmentation vs visual segmentation). Shared docs/registry updates are not enough to make them 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": 11, + "component_count": 28, + "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": "f742b799f08897de5b079c7e840ca2a912367f734e4500eb1ecd65ebc5d36125", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are related to `trainer.py` extensibility, but they address different behaviors: gradient-accumulation loss scaling vs. dataset column filtering/signature inspection. They are not duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Reject: PR 43651 changes training-step loss scaling for gradient accumulation, while PR 43663 adds a helper for model signature-based column filtering. Different code paths and different underlying 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": 12, + "component_count": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-3", + "nodes": [ + "pull_request:43656", + "pull_request:43836", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842", + "pull_request:43836|pull_request:43842" + ], + "prepared_review_unit_hash": "8e5aebd9e28b93dbaaa57714a0b143d8e3d3b30bca7a6cd8cc55a229bf96b7b8", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5993, + "estimated_input_tokens": 1499, + "estimated_eval_tokens": 3254 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "PR 43842 is the clearest targeted fix for the `TypeAdapter` NameError in `src/transformers/cli/serve.py`. The other two PRs touch the same file and related tracking issue, but the shown diffs are too broad/indirect to treat them as the same concrete bugfix or safely mergeable duplicates.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43842 is the most precise fix: it directly imports `TypeAdapter` under `TYPE_CHECKING` and stringifies the annotation to avoid the NameError, with the smallest and most focused change set.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 is the best global representative because it addresses the exact runtime name-resolution problem with minimal scope, unlike the other PRs whose previews show broader annotation cleanup.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "The shared file alone is not enough here: the visible changes in 43656 are mostly `__future__` annotations and broader type-annotation cleanup, not a clear fix for the same `TypeAdapter` NameError. The evidence does not support treating them as the same bugfix." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": false, + "reason": "Both PRs target `serve.py` and share issue linkage, but 43836 looks like a broader annotation refactor while 43842 is a narrow `TypeAdapter` import/string-annotation fix. That is related, but not enough to conclude the same underlying change or a safe duplicate merge." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary overstates the evidence. PR 43656 does touch `serve.py`, but the shown changes are about adding `__future__` annotations and adjusting other type annotations; the packet does not support calling it the same `TypeAdapter` NameError fix as 43842. For 43836 vs 43842, the shared file and issue target show relatedness, but the diffs are not enough to conclude they are the same bugfix or safely mergeable into one PR; 43836 looks like a broader annotation cleanup, while 43842 is a narrow `TypeAdapter` import/annotation change. The conservative conclusion is that 43842 is the clearest targeted fix, but the other pairings should not be accepted on this evidence." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 28, + "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": 28, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44066|pull_request:44071", + "pull_request:44018|pull_request:44068", + "pull_request:44066|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44116", + "pull_request:44068|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44086", + "pull_request:44018|pull_request:44085", + "pull_request:44071|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44098|pull_request:44101", + "pull_request:44059|pull_request:44722", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44073|pull_request:44161", + "pull_request:44056|pull_request:44101", + "pull_request:44018|pull_request:44059", + "pull_request:44059|pull_request:44068", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44018", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:44018|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44018|pull_request:44129", + "pull_request:44010|pull_request:44073", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44071|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "df5ef87b77dd602b21836eba54907360aaafe300ae8553a0c763be43b534db1e", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84885, + "estimated_input_tokens": 21222, + "estimated_eval_tokens": 42700 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75083, + "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 collection of model-specific standardized output-tracing refactors rather than one broad duplicate. The only convincing duplicate subclusters are GPT-J/CodeGen and GPT-Neo. #43979 is a shared umbrella tracker for part of the cluster, but many PRs do not explicitly target it.", + "confidence": 0.87, + "canonical_issue_reason": "#43979 is the best issue anchor because it is the shared umbrella tracker explicitly referenced by several PRs in the cluster and best captures the recurring standardized output-tracing refactor theme, though many PRs do not link it.", + "canonical_pr_reason": "PR #44722 is the best PR anchor because it most clearly represents the GPT-J/CodeGen duplicate subcluster, with concrete overlap in modeling_gptj.py and modeling_codegen.py and an explicit #43979 link.", + "best_issue_reason": "#43979 is the strongest issue anchor for the cluster as a whole because it is the recurring tracker for the standardized output-tracing work, but it should be described conservatively as shared by several PRs rather than most.", + "best_pr_reason": "PR #44722 is the cleanest single PR representative of the shared GPT-J/CodeGen refactor, and it best captures the concrete duplicate change among the cluster's PRs.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families and different code paths; same umbrella refactor theme only." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Cvt/FNet and DeBERTa v2 are unrelated model implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors in modeling_gptj.py and look like duplicate iterations of the same concrete change." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet/ResNet and EfficientNet are different vision-model code paths; only the refactor style matches." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet and GPT-J/CodeGen are unrelated model implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen and EfficientNet do not share the same concrete bug or code path." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa v2 are unrelated model-specific refactors." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen and MGP-STR are different model code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are separate model implementations; shared theme is too broad." + }, + { + "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 be duplicate versions of the same change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are different model-specific refactors." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are distinct model refactors, not one duplicate fix." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated concrete changes." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen are different model code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are separate model refactors with no shared concrete fix." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different model-specific refactors." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT do not share the same underlying bug or change." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert/XLM are different model families and separate changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are distinct model refactors, even if both are output-tracing related." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert/XLM are unrelated concrete changes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are different implementations; shared theme is too broad." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 and MGP-STR are unrelated model-specific changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44059", + "accept": false, + "reason": "GPT-Neo and GPT-2 are separate model refactors, not one duplicate bug fix." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are different model code paths." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are unrelated model changes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 and GPT-J/CodeGen are different model-specific refactors." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are unrelated concrete changes." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert/XLM are unrelated model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44074", + "accept": false, + "reason": "GPT-Neo and TextNet do not share the same concrete code-path change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "ViLT and LongT5 are unrelated model-specific refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert/XLM are distinct model refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and SegFormer are different models and different code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet and MPNet are unrelated changes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are separate model implementations; only the refactor style matches." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44161", + "accept": false, + "reason": "TextNet and LongT5 are unrelated model-specific refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are different concrete changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are unrelated model refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 do not share the same underlying bug or change." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT and SpeechT5 are different model code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert and MPT are unrelated concrete changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo and SpeechT5 are different model-specific refactors." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert and DeBERTa v2 are unrelated code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa v2 and TextNet are different model changes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J/CodeGen standardized output-tracing refactor; 44722 consolidates the same underlying change." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both touch GPT-J output tracing in the same file and appear to be the same underlying refactor, with 44722 as the consolidated version." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J and SpeechT5 are unrelated model implementations." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "Cvt/FNet and RegNet/ResNet are different model families." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "Cvt/FNet and SpeechT5 are unrelated concrete changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa v2 and SpeechT5 are distinct model-specific refactors." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa v2 and Vits are unrelated model implementations." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster-level summary is mostly grounded, but one anchor claim is overstated: `#43979` is clearly a shared umbrella issue, yet the packet does not show it as the target for *most* PRs in the cluster. Several PRs have no explicit issue link. Please keep that wording conservative. The duplicate judgments that are accepted look plausible, especially the GPT-J/CodeGen pair and the GPT-Neo pair, but the issue-anchor rationale needs to be tightened before accepting." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 28, + "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": "b201d2d159faa142de47b4beaa44e6f59c1600100ca6b7b532a6566c340cd4b2", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84885, + "estimated_input_tokens": 21222, + "estimated_eval_tokens": 42700 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17123, + "estimated_input_tokens": 4281, + "estimated_eval_tokens": 8818 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are model-specific refactors to standardized output tracing/capture across different architectures, not the same underlying bug or change. The cluster is thematically related, but the PRs should remain separate.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44129 is the best representative: it is a clear output-tracing refactor, has an explicit issue target, and the diff is self-contained and easy to understand.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 is the strongest standalone example of the cluster because it directly implements the standardized output capture pattern with an explicit tracked issue, making it the clearest anchor for this theme.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Both are output-tracing refactors, but they touch different model code paths (FocalNet vs ImageGPT). They are not the same fix and would not be merged as one PR." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "These are separate model migrations to the same tracing pattern, but VisualBert and TextNet are unrelated code paths. Similar subsystem is not enough for duplicate PR merging." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet and VisualBert each refactor their own output-capture logic; this is a shared pattern, not the same concrete bug or change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "Different models and different forward/output machinery. The overlap is only the standardized tracing approach, so this is not a duplicate change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated implementations. These PRs share the migration theme but not the same underlying code-path problem." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 are separate model-specific refactors. The shared issue label/theme is insufficient to treat them as the same PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "nodes": [ + "pull_request:43998", + "pull_request:43999", + "pull_request:44000", + "pull_request:44001", + "pull_request:44002", + "pull_request:44003", + "pull_request:44004", + "pull_request:44025", + "pull_request:44026", + "pull_request:44027", + "pull_request:44028", + "pull_request:44029", + "pull_request:44030" + ], + "soft_pairs": [ + "pull_request:43998|pull_request:44002", + "pull_request:43998|pull_request:44000", + "pull_request:43998|pull_request:44001", + "pull_request:43998|pull_request:44003", + "pull_request:43998|pull_request:44029", + "pull_request:43999|pull_request:44001", + "pull_request:43999|pull_request:44002", + "pull_request:43999|pull_request:44025", + "pull_request:43999|pull_request:44026", + "pull_request:43999|pull_request:44027", + "pull_request:44000|pull_request:44001", + "pull_request:44000|pull_request:44002", + "pull_request:44000|pull_request:44003", + "pull_request:44000|pull_request:44025", + "pull_request:44001|pull_request:44002", + "pull_request:44001|pull_request:44003", + "pull_request:44001|pull_request:44025", + "pull_request:44002|pull_request:44029", + "pull_request:44002|pull_request:44003", + "pull_request:44003|pull_request:44028", + "pull_request:44003|pull_request:44004", + "pull_request:43998|pull_request:44004", + "pull_request:44001|pull_request:44004", + "pull_request:44002|pull_request:44004", + "pull_request:44000|pull_request:44004", + "pull_request:44025|pull_request:44026", + "pull_request:44025|pull_request:44027", + "pull_request:44025|pull_request:44028", + "pull_request:44025|pull_request:44029", + "pull_request:44025|pull_request:44030", + "pull_request:44026|pull_request:44029", + "pull_request:44026|pull_request:44027", + "pull_request:44026|pull_request:44028", + "pull_request:44026|pull_request:44030", + "pull_request:44027|pull_request:44028", + "pull_request:44027|pull_request:44029", + "pull_request:44027|pull_request:44030", + "pull_request:44028|pull_request:44029", + "pull_request:44028|pull_request:44030", + "pull_request:44029|pull_request:44030" + ], + "prepared_review_unit_hash": "58295d7bcd5a48d5222e354f40d27830f845787b19c29eb593df82a7a9808286", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40173, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40173, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All items are refactor-style pull requests for output tracing in different model families. They are thematically similar but not duplicate code-path changes, so I reject every soft edge. I treat PR #44003 as the best canonical representative because it is the most substantial multi-file tracing refactor among the set.", + "confidence": 0.82, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #44003 is the strongest representative of the cluster: it is a broader multi-file output-tracing refactor spanning related Mamba/FalconMamba code, whereas the others are narrower model-specific variants.", + "best_issue_reason": null, + "best_pr_reason": "PR #44003 best captures the shared pattern while still being the most substantial implementation in the group; it is the most suitable single representative for triage.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Same refactor theme, but timm_backbone and upernet are different model code paths; not one mergeable bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Both are output-tracing refactors, but for different models (timm_backbone vs vision_text_dual_encoder); not duplicates." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model families and implementations; similar tracing cleanup, not the same underlying change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "timm_backbone and mamba/falcon_mamba are unrelated code paths; only the refactor style matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "CodeGen and timm_backbone fix different components; cannot be merged as one concrete fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Different models and execution paths; same tracing refactor pattern only." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "MobileNetV1 and UnivNet are unrelated model implementations; not the same bug/change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "MobileNetV1 vs UperNet: same refactor motif, different model code paths." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families (MobileNetV1 vs Depth Anything); not a duplicate fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "MobileNetV1 and VisionEncoderDecoder touch unrelated forward paths; only broadly similar." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "MobileNetV1 and SpeechEncoderDecoder are different subsystems; not one mergeable change." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Vision-text dual encoder and UnivNet are different model code paths; similarity is only mechanical." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models (vision-text dual encoder vs UperNet); not the same underlying issue." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Vision-text dual encoder and Mamba/FalconMamba are unrelated implementations; not duplicates." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "CodeGen and vision-text dual encoder address different forward/tracing code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families and target code paths; only the refactor pattern matches." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "UnivNet and UperNet are unrelated model implementations; not one concrete fix." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different architectures and files; similar output-tracing cleanup only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet and CodeGen fix different model-specific forward methods." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "UperNet and RWKV are different subsystems; same theme, different change." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "UperNet and Mamba/FalconMamba are unrelated model code paths; not duplicates." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "Mamba/FalconMamba and SuperPoint are different models; only broadly similar tracing refactor." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Different concrete implementations (Mamba vs CodeGen); not the same fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Depth Anything and VisionEncoderDecoder are different model wrappers; not one underlying bug." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Depth Anything and SpeechEncoderDecoder are separate code paths; similarity is superficial." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Depth Anything and SuperPoint target different models and forward logic." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Depth Anything and RWKV are unrelated model families; not duplicates." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Depth Anything and DPR touch different model-specific tracing paths." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are distinct wrappers; same style, different change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Different model families and forward paths; not the same concrete fix." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "VisionEncoderDecoder and RWKV are unrelated implementations; not a duplicate." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Different model code paths (vision encoder-decoder vs DPR); only the refactor pattern is shared." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated models; not one mergeable change." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "SpeechEncoderDecoder and RWKV are different subsystems; similar tracing cleanup only." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "SpeechEncoderDecoder and DPR fix different model-specific forward code." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are different model families; not the same underlying issue." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "SuperPoint and DPR target different code paths; not duplicates." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are unrelated models; only broad output-tracing similarity." + } + ] + }, + "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": 28, + "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": "93b3cc655fc6b6a6ab072af555e2a9ecab39179a0b07f42edbf295a4977c19b9", + "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 PenguinVL, DeepSeek-OCR-2, and Voxtral TTS. They overlap on standard Transformers boilerplate, but each targets a different model and codepath, so none should be treated as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR is a true duplicate of the others; if one must be picked as the representative, PR 45075 is the strongest candidate because it is the most complete, has the highest review activity, and includes an explicit issue target.", + "best_issue_reason": null, + "best_pr_reason": "PR 45075 is the best overall representative of the cluster because it is the most developed integration and most clearly tied to a tracking issue, even though the other PRs are distinct model additions.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different model additions: PenguinVL vs Voxtral TTS. Shared framework/doc boilerplate is expected, but they implement different architectures and targets." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "Different model additions: PenguinVL vs DeepSeek-OCR-2. Similar Transformers wiring does not make them the same underlying change." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "Different model additions: DeepSeek-OCR-2 vs Voxtral TTS. They touch overlapping auto/docs files, but the concrete model codepaths are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 28, + "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": "05976633c21674e22b5b69e8bb51a34dd9b02792d19bd022d04302baa2f1b882", + "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": "Both PRs are about module/kernel fusion in Transformers, but they implement different layers of the feature: one introduces a generic Module Fusion API, while the other wires up n-to-1 kernel fusion through KernelConfig and integration hooks.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #44979 is the better canonical PR because it introduces the foundational Module Fusion API and core abstraction; PR #45363 is a more specific follow-on feature built on top of that mechanism.", + "best_issue_reason": null, + "best_pr_reason": "PR #44979 is the best representative of the cluster since it is the more general and central change, whereas #45363 is a narrower application of fusion for a particular kernel-config path.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Do not treat these as duplicates: they target related fusion work, but #44979 adds a general module fusion API and #45363 adds a specific n-to-1 kernel fusion integration. They could coexist in one codebase and are not the same concrete change or bug fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 28, + "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": "f8ae818d88b38cc06394fa7288d4b93cf10c7826ed5b3b33ab3b10514b4491ff", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs fix the same AttributeError in `_patch_mistral_regex` by switching from `tokenizer.backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer`; the later PR also adds test coverage, so they are duplicates with 45317 the stronger candidate.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45317 is the more complete fix: it addresses the same code path as 45086 and adds tests, so it is the best canonical PR in this cluster.", + "best_issue_reason": null, + "best_pr_reason": "45317 is best overall because it implements the same bug fix as 45086 but includes validation/tests and is therefore the most complete representative.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same concrete bug and same patch site in `src/transformers/tokenization_utils_tokenizers.py`; both fix the `_patch_mistral_regex` AttributeError, and 45317 is just the more complete version with tests." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 28, + "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": "4e064c3b2e352152ffd0e8e79d784c19270a2c9765a227102ee5470bca276e5d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two related NemotronH pull requests, but they target different changes: one is a narrow checkpoint-conversion/mapping refactor, the other is a broader architecture split introducing nemotron_h_dense and nemotron_h_sparse plus docs/tests. They are not duplicates.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the better representative because it captures the broader end-state change: the NemotronH model family split, auto/model registration, docs, and tests. PR #45115 is a narrower preprocessing/conversion-mapping adjustment.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 is the strongest standalone PR in the cluster because it is the more complete feature refactor and includes user-facing documentation and test coverage, whereas #45115 only addresses conversion mapping for checkpoint key renaming.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Not the same underlying change. #45115 updates conversion mappings for NemotronH weight-key renaming, while #45569 splits NemotronH into dense/sparse variants with model/config/doc/test updates. Different scope and code paths." + } + ] + }, + "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": 28, + "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": "5f2d17eb3d5bb4dbbe1ae43a465ab11c85946a0b3e21d2ed5743fee2010ceb35", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related heterogeneous-config/modeling efforts, but they are not the same fix: one PR adds per-layer config support, while the other adds broader heterogeneous model/runtime support. They share infrastructure files, yet target different layers of the feature and should not be deduplicated.", + "confidence": 0.85, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the more comprehensive umbrella change: it covers heterogeneous model support and includes the runtime/modeling paths that depend on per-layer config handling.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the strongest standalone representative because it spans the actual model-side behavior and cache/modeling integration, whereas #45333 is mainly the config-side prerequisite.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature work, but not the same concrete bug/change. #45333 adds per-layer configuration support; #45332 adds heterogeneous model/runtime support on top of that. They could be part of one roadmap, but not one merged PR for a single underlying fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 28, + "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": "7625eb0fb113900122d04cbb199607cddab7bc77f8846f90189266e234c1fac6", + "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": "Both PRs are typing-related, but they are not the same change: one is a broad repo-wide type-checking enablement pass, while the other adds specific typing protocols and support helpers in modeling/modeling_utils paths.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45415 is the broader, more representative repo-wide typing/type-checking pass and best captures the cluster\u2019s main theme.", + "best_issue_reason": null, + "best_pr_reason": "PR #45415 is the best single representative because it covers the widest surface area of the typing cleanups and is the most general change in the cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "They are related by theme, but not the same concrete code-path problem; #45415 is a broad type-checking sweep across many files, while #45425 adds specific typing protocols and fixes in modeling_utils/PEFT-related code. They would not plausibly be merged into one PR as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 22, + "component_count": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45487-3", + "nodes": [ + "pull_request:45487", + "pull_request:45817", + "pull_request:45843" + ], + "soft_pairs": [ + "pull_request:45487|pull_request:45843", + "pull_request:45817|pull_request:45843" + ], + "prepared_review_unit_hash": "fe99c2df606b79dd9b67c817566b7cbdbca3a0b1a48f1a1ccdbabf30f3bbcec2", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 7561, + "estimated_input_tokens": 1891, + "estimated_eval_tokens": 4038 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 7561, + "estimated_input_tokens": 1891, + "estimated_eval_tokens": 4038 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are all pull requests about model-parallel/device-placement fixes, but they target different model families and different code paths, so they do not look like duplicates. The Gemma4 PR is the strongest single representative of the cluster theme.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45817 is the best cluster representative because it has the most concrete model-parallel fix set in one model family, with clear code changes and tests, and it is the most self-contained of the three PRs.", + "best_issue_reason": null, + "best_pr_reason": "PR #45817 is the most suitable standalone PR in this cluster: it fixes a specific device-placement bug in Gemma4, includes the relevant model code and test coverage, and reads as a cohesive change rather than a broad umbrella patch.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45487", + "right": "pull_request:45843", + "accept": false, + "reason": "Both are model-parallel fixes, but they target different architectures (AltCLIP/ChineseCLIP vs Deimv2) and different failure points, so they are not the same underlying change." + }, + { + "left": "pull_request:45817", + "right": "pull_request:45843", + "accept": false, + "reason": "Gemma4 device-placement/no-split-module changes are unrelated to Deimv2 backbone propagation of _no_split_modules; same theme, different bug and code path." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 28, + "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": "8e99e1e66043711887846c3de594f513230f7f917f57a195018dfe8aeeebe3b1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4505, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are both EP-related distributed-loading PRs, but they target different failure modes and code paths: one is about serializing/restoring `distributed_config` for Accelerate/ZeRO-3 loading, the other is about preventing expert weights from being overwritten during FSDP2/rank-0 broadcast. They should not be merged as duplicates.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45662 is the stronger canonical PR for this cluster because it fixes a specific, concrete runtime corruption bug in the loading path (experts overwritten by rank-0 broadcast) and includes coordinated changes across the relevant distributed-loading modules.", + "best_issue_reason": null, + "best_pr_reason": "PR 45662 is the best representative because it addresses a well-defined user-visible correctness issue in EP/FSDP2 loading rather than a narrower serialization tweak.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Related subsystem, but not the same underlying bug. 45548 focuses on preserving `distributed_config` / EP state for Accelerate + ZeRO-3 loading; 45662 fixes expert tensors being overwritten during FSDP2/broadcast handling. Different concrete code paths and not plausibly one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 24, + "component_count": 28, + "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": "40b4e7a35bc44b52f7af101093435ee0c5729230590f70bb1b4155887ed9bd22", + "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 pull requests address the same xdist-related captured_info collision in testing utilities; PR 45645 is the broader, more complete fix and subsumes the narrower file-writing change in 45639.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the better canonical PR because it contains the core testing_utils xdist-safety fix plus the downstream CI/workflow update needed to consume multiple captured_info files, making it the more complete resolution of the bug.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 best represents the cluster because it addresses the same underlying captured_info xdist collision and also fixes the report aggregation path, while 45639 is only the local writer-side change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Same underlying bug: xdist workers colliding on captured_info output. 45645 expands the same fix with CI/report handling, so the two PRs are plausibly mergeable into one change set." + } + ] + }, + "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": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45683-2", + "nodes": [ + "pull_request:45683", + "pull_request:45734" + ], + "soft_pairs": [ + "pull_request:45683|pull_request:45734" + ], + "prepared_review_unit_hash": "eba4ca0f26b2d3be0c00e316270a9341d31af2208b44dbab31b1d3a8e81e7538", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4469, + "estimated_input_tokens": 1118, + "estimated_eval_tokens": 2492 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs touch the same quantization helper, but they fix different bugs: one special-cases audio submodules, the other changes how default skip lists are combined with user-supplied skips. They should not be clustered as duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "45734 is the better representative PR because it fixes the core skip-module composition logic in `get_modules_to_not_convert`, which is broader and more central than the narrow audio-module special case in 45683.", + "best_issue_reason": null, + "best_pr_reason": "45734 is the strongest standalone PR in the set: it addresses a concrete quantization failure mode in the main code path and its fix is directly about the helper\u2019s behavior rather than a model-specific workaround.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45683", + "right": "pull_request:45734", + "accept": false, + "reason": "Both touch quantization skip logic, but 45683 adds audio-tower/embed_audio exclusions while 45734 changes additive handling of `skip_modules`; these are different underlying bugs and would not naturally merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 28, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 27, + "component_count": 28, + "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-45858-2", + "nodes": [ + "pull_request:45858", + "pull_request:45890" + ], + "soft_pairs": [ + "pull_request:45858|pull_request:45890" + ], + "prepared_review_unit_hash": "3963afa2b995fa941eaa3442f8d91a5b11ab8118ef24c14d9ad00bb70ba72aa9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4139, + "estimated_input_tokens": 1035, + "estimated_eval_tokens": 2326 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4139, + "estimated_input_tokens": 1035, + "estimated_eval_tokens": 2326 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs add XPU-specific test expectations for different model test suites (hy_v3 and exaone4_5). They are both test-only changes, but they target different model families and different failure surfaces, so they do not look like duplicates.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "No duplicate PR canonical exists here; if one must be chosen as the cluster representative, PR 45890 is slightly more informative because it also adds an XPU determinism guard in addition to expectations, but it is still model-specific and not the same change as 45858.", + "best_issue_reason": null, + "best_pr_reason": "PR 45890 is the better standalone representative because it makes a fuller test harness adjustment for exaone4_5 on XPU. PR 45858 is similarly scoped but only updates expectations for a different model suite.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45858", + "right": "pull_request:45890", + "accept": false, + "reason": "Both are XPU expectation updates in tests, but they apply to different model suites (hy_v3 vs exaone4_5) and different concrete outputs. They do not appear to fix the same underlying bug or be mergeable into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 28, + "component_count": 28, + "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-45861-2", + "nodes": [ + "pull_request:45861", + "pull_request:45903" + ], + "soft_pairs": [ + "pull_request:45861|pull_request:45903" + ], + "prepared_review_unit_hash": "cb6f945a9544bf6bd24a6a24280d4d07fde49086ce541613a6c8808e1a39b6b1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5529, + "estimated_input_tokens": 1383, + "estimated_eval_tokens": 3022 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5529, + "estimated_input_tokens": 1383, + "estimated_eval_tokens": 3022 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are closely related, with 45903 appearing to subsume the device-mismatch fix from 45861 and add an additional meta/to_empty re-init fix in the same Qwen3-VL M-RoPE code path.", + "confidence": 0.84, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45903 is the better canonical PR because it covers the same M-RoPE device fix as 45861 and also includes an extra related initialization fix, making it the more complete change set.", + "best_issue_reason": null, + "best_pr_reason": "PR 45903 is the strongest representative: it is newer, broader, and appears to incorporate the core fix from 45861 while addressing an additional failure mode in the same family.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45861", + "right": "pull_request:45903", + "accept": true, + "reason": "Accept: 45903 looks like a superset of 45861 on the same concrete Qwen3-VL M-RoPE device-path bug, with an added but related meta/to_empty re-init fix. These could plausibly be combined into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/manifest.json b/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..7d3ba3385d3d6f2d9958545c5e1478b1b0d57db5 --- /dev/null +++ b/snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260512t060024z", + "artifacts": { + "hybrid": "snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-12T06:09:27Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260512T060024Z", + "variant": "hybrid" +} diff --git a/snapshots/20260512T060024Z/manifest.json b/snapshots/20260512T060024Z/manifest.json index f58351338dbe741dba0d941dc41df0f1b65589a1..7e334d1411cb6bce097683864baebef085961e43 100644 --- a/snapshots/20260512T060024Z/manifest.json +++ b/snapshots/20260512T060024Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 509 }, "extracted_at": "2026-05-12T06:00:24Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260512t060024z", + "runs": { + "hybrid-model-20260512t060024z": { + "analysis_id": "hybrid-model-20260512t060024z", + "artifacts": { + "hybrid": "snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260512T060024Z/analysis-runs/hybrid-model-20260512t060024z/manifest.json", + "model": null, + "published_at": "2026-05-12T06:09:27Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260512T060024Z", "watermark": {