diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index af55baf8b0e4b10561532b7cba3840a46e574181..88f73deb902e568149cf4f668650548bddd5d08e 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": "20260420T120036Z", - "generated_at": "2026-04-20T12:17:48Z", + "snapshot_id": "20260420T180040Z", + "generated_at": "2026-04-20T18:14:35Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1252,11 +1252,11 @@ { "left_pr_number": 43757, "right_pr_number": 45506, - "code_similarity": 0.096, - "size_similarity": 0.15, - "file_overlap": 0.2, + "code_similarity": 0.116, + "size_similarity": 0.17, + "file_overlap": 0.25, "area_overlap": 0.005, - "patch_similarity": 0.031, + "patch_similarity": 0.034, "shared_filenames": [ "src/transformers/modeling_gguf_pytorch_utils.py" ], @@ -1297,33 +1297,17 @@ { "left_pr_number": 45500, "right_pr_number": 45506, - "code_similarity": 0.997, - "size_similarity": 0.996, - "file_overlap": 1.0, + "code_similarity": 0.886, + "size_similarity": 0.877, + "file_overlap": 0.75, "area_overlap": 0.996, - "patch_similarity": 0.996, + "patch_similarity": 0.912, "shared_filenames": [ - "docs/source/en/model_doc/gpt_oss.md", "src/transformers/integrations/ggml.py", "src/transformers/modeling_gguf_pytorch_utils.py", "tests/quantization/ggml/test_ggml.py" ], "shared_file_areas": [ - { - "filename": "docs/source/en/model_doc/gpt_oss.md", - "left_ranges": [ - [ - 70, - 93 - ] - ], - "right_ranges": [ - [ - 70, - 93 - ] - ] - }, { "filename": "src/transformers/integrations/ggml.py", "left_ranges": [ @@ -1413,116 +1397,6 @@ } ] }, - { - "cluster_id": "cluster-45341-4", - "summary": "Cluster of 1 issues and 3 PRs centered on issue #45341.", - "status": "open", - "confidence": 0.8, - "canonical_issue_number": 45341, - "canonical_pr_number": 45351, - "issue_numbers": [ - 45341 - ], - "pr_numbers": [ - 45351, - 45509, - 45515 - ], - "evidence_types": [ - "closing_reference", - "shared_issue_target", - "soft_similarity" - ], - "pr_comparisons": [ - { - "left_pr_number": 45351, - "right_pr_number": 45509, - "code_similarity": 0.427, - "size_similarity": 0.308, - "file_overlap": 1.0, - "area_overlap": 0.148, - "patch_similarity": 0.093, - "shared_filenames": [ - "src/transformers/testing_utils.py" - ], - "shared_file_areas": [ - { - "filename": "src/transformers/testing_utils.py", - "left_ranges": [ - [ - 3207, - 3230 - ] - ], - "right_ranges": [ - [ - 3204, - 3210 - ] - ] - } - ] - }, - { - "left_pr_number": 45351, - "right_pr_number": 45515, - "code_similarity": 0.437, - "size_similarity": 0.359, - "file_overlap": 1.0, - "area_overlap": 0.148, - "patch_similarity": 0.091, - "shared_filenames": [ - "src/transformers/testing_utils.py" - ], - "shared_file_areas": [ - { - "filename": "src/transformers/testing_utils.py", - "left_ranges": [ - [ - 3207, - 3230 - ] - ], - "right_ranges": [ - [ - 3204, - 3210 - ] - ] - } - ] - }, - { - "left_pr_number": 45509, - "right_pr_number": 45515, - "code_similarity": 0.946, - "size_similarity": 0.857, - "file_overlap": 1.0, - "area_overlap": 1.0, - "patch_similarity": 0.833, - "shared_filenames": [ - "src/transformers/testing_utils.py" - ], - "shared_file_areas": [ - { - "filename": "src/transformers/testing_utils.py", - "left_ranges": [ - [ - 3204, - 3210 - ] - ], - "right_ranges": [ - [ - 3204, - 3210 - ] - ] - } - ] - } - ] - }, { "cluster_id": "cluster-43240-3", "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", @@ -2034,241 +1908,6 @@ ] } ] - }, - { - "cluster_id": "cluster-42975-2", - "summary": "Cluster of 2 related pull requests linked by soft_similarity.", - "status": "open", - "confidence": 0.5, - "canonical_issue_number": null, - "canonical_pr_number": 42976, - "issue_numbers": [], - "pr_numbers": [ - 42975, - 42976 - ], - "evidence_types": [ - "soft_similarity" - ], - "pr_comparisons": [ - { - "left_pr_number": 42975, - "right_pr_number": 42976, - "code_similarity": 0.131, - "size_similarity": 0.148, - "file_overlap": 0.212, - "area_overlap": 0.095, - "patch_similarity": 0.033, - "shared_filenames": [ - ".github/workflows/build-ci-docker-images.yml", - ".github/workflows/build-docker-images.yml", - ".github/workflows/build-nightly-ci-docker-images.yml", - ".github/workflows/build-past-ci-docker-images.yml", - ".github/workflows/check_failed_tests.yml", - ".github/workflows/new_model_pr_merged_notification.yml", - ".github/workflows/release-conda.yml" - ], - "shared_file_areas": [ - { - "filename": ".github/workflows/build-ci-docker-images.yml", - "left_ranges": [ - [ - 45, - 51 - ] - ], - "right_ranges": [ - [ - 54, - 60 - ] - ] - }, - { - "filename": ".github/workflows/build-docker-images.yml", - "left_ranges": [ - [ - 29, - 35 - ], - [ - 65, - 71 - ], - [ - 104, - 110 - ], - [ - 140, - 146 - ], - [ - 174, - 180 - ], - [ - 241, - 247 - ], - [ - 277, - 283 - ] - ], - "right_ranges": [ - [ - 38, - 44 - ], - [ - 74, - 80 - ], - [ - 113, - 119 - ], - [ - 149, - 155 - ], - [ - 183, - 189 - ], - [ - 250, - 256 - ], - [ - 286, - 292 - ] - ] - }, - { - "filename": ".github/workflows/build-nightly-ci-docker-images.yml", - "left_ranges": [ - [ - 26, - 32 - ], - [ - 55, - 61 - ] - ], - "right_ranges": [ - [ - 23, - 41 - ], - [ - 52, - 70 - ] - ] - }, - { - "filename": ".github/workflows/build-past-ci-docker-images.yml", - "left_ranges": [ - [ - 24, - 30 - ], - [ - 69, - 75 - ] - ], - "right_ranges": [ - [ - 21, - 27 - ], - [ - 38, - 50 - ], - [ - 66, - 72 - ], - [ - 83, - 95 - ] - ] - }, - { - "filename": ".github/workflows/check_failed_tests.yml", - "left_ranges": [ - [ - 56, - 62 - ], - [ - 77, - 83 - ], - [ - 113, - 119 - ], - [ - 194, - 200 - ], - [ - 211, - 222 - ], - [ - 280, - 286 - ] - ], - "right_ranges": [ - [ - 296, - 302 - ] - ] - }, - { - "filename": ".github/workflows/new_model_pr_merged_notification.yml", - "left_ranges": [ - [ - 13, - 19 - ] - ], - "right_ranges": [ - [ - 38, - 44 - ] - ] - }, - { - "filename": ".github/workflows/release-conda.yml", - "left_ranges": [ - [ - 19, - 25 - ] - ], - "right_ranges": [ - [ - 22, - 28 - ] - ] - } - ] - } - ] } ], "duplicate_issues": [ @@ -2292,15 +1931,6 @@ "target_issue_number": 41211, "reason": "PRs in cluster-41211-3 are treated as duplicates because they converge on issue #41211 with closing_reference, shared_issue_target evidence." }, - { - "cluster_id": "cluster-42975-2", - "canonical_pr_number": 42976, - "duplicate_pr_numbers": [ - 42975 - ], - "target_issue_number": null, - "reason": "PRs in cluster-42975-2 are treated as duplicates because they share soft_similarity evidence." - }, { "cluster_id": "cluster-43240-3", "canonical_pr_number": 43251, @@ -2381,16 +2011,6 @@ ], "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-45341-4", - "canonical_pr_number": 45351, - "duplicate_pr_numbers": [ - 45509, - 45515 - ], - "target_issue_number": 45341, - "reason": "PRs in cluster-45341-4 are treated as duplicates because they converge on issue #45341 with closing_reference, shared_issue_target, 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 b5d21764af30840cbf9080b48c1f16e2d15e21f1..190acdb27d94e7152632746241b4a92944d694a3 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": "20260420T120036Z", - "generated_at": "2026-04-20T12:17:48Z", + "snapshot_id": "20260420T180040Z", + "generated_at": "2026-04-20T18:14:35Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -13,8 +13,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-13244-3", "nodes": [ @@ -84,8 +84,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -208,7 +208,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -546,8 +546,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -641,7 +641,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -889,8 +889,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -986,7 +986,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -1228,8 +1228,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -1319,7 +1319,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -1513,8 +1513,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -1615,7 +1615,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -1905,8 +1905,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -2002,7 +2002,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -2241,8 +2241,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -2335,7 +2335,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -2686,12 +2686,12 @@ "issue:43881|issue:44488", "issue:43828|issue:44683" ], - "prepared_review_unit_hash": "a91bc455419db08a0ef11110500a39ecef0f6d29f4a2206d8d912e02d5e11561", + "prepared_review_unit_hash": "a74d6d537c4768d94e492a642dccf89c1a42aee9aa5d23444189330094d8622f", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -2708,222 +2708,222 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab-bag of distinct Transformers regressions and model-specific bugs (Qwen, tokenizer loading, dtype/init issues, etc.). A few pairs are semantically related, but none look like clear duplicates of the same concrete fix.", - "confidence": 0.34, - "canonical_issue_reason": "issue:45020 is the broadest umbrella in the set: it frames a recent-versions regression affecting model loading/remote_code, which makes it the best anchor for a mixed cluster of Transformers v5 breakages.", + "summary": "These are mostly unrelated issue reports with only superficial overlap in model family or Transformers version. I found no strong duplicate cluster; the broadest regression tracker is `issue:45020`.", + "confidence": 0.87, + "canonical_issue_reason": "No single issue is a clear duplicate hub; the set spans many distinct bugs. If one issue must anchor the cluster, `issue:45020` is the broadest open regression report about recent Transformers versions breaking `remote_code` models.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the most general and active issue here, so it is the best single representative even though the cluster contains many separate sub-bugs.", + "best_issue_reason": "`issue:45020` is the best representative issue because it is broad, open, and describes a real cross-model regression theme rather than a model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:40990", "right": "issue:44811", "accept": false, - "reason": "Different models and failure modes: perplexity regression vs Whisper batch_decode token skipping." + "reason": "Completely different problems: GPT-OSS perplexity vs Whisper batch_decode special-token handling." }, { "left": "issue:43611", "right": "issue:44534", "accept": false, - "reason": "Both are Transformers v5 regressions, but one is about base_model_prefix loading and the other about non-persistent buffers; different root causes." + "reason": "Both are Transformers v5 regressions, but one is `base_model_prefix` loading and the other is non-persistent buffer initialization; different code paths." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "Tokenizer AttributeError for T5 is unrelated to MobileLLM loading key errors." + "reason": "T5 tokenizer method-name conflict vs MobileLLM-125M key error are unrelated failures." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "One is device_map/offload loading failure, the other is Qwen3 MoE training memory usage; not the same bug." + "reason": "Dequantized model offload loading issue vs Qwen3 MoE training memory usage; not the same bug." }, { "left": "issue:42915", "right": "issue:44589", "accept": false, - "reason": "Both mention FP8, but one is FineGrainedFP8Config failure and the other is a Float8 storage loading error; distinct issues." + "reason": "Both mention FP8/float8, but one is Qwen3Moe FineGrainedFP8Config failure and the other is a storage-object lookup error; different underlying issues." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "Both are Qwen2.5-VL, but one is multi-image training with IterableDataset and the other is still-image rope/position-id scaling." + "reason": "Qwen2.5-VL multi-image finetuning failure vs still-image temporal position-id scaling bug; different symptoms and paths." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "Both are v5 regressions, but _is_hf_initialized handling is not the same as junk non-persistent buffer loading." + "reason": "`_is_hf_initialized` flag regression is separate from junk-filled non-persistent buffers." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Qwen3-MoE sliding_window bug is unrelated to granite_speech strict config loading." + "reason": "Qwen3-MoE sliding window issue and granite_speech strict-config loading are unrelated." }, { "left": "issue:44683", "right": "issue:45020", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 is a backend compatibility bug, not the remote_code loading regression in 45020." + "reason": "Compiled flex_attention on torch>=2.9 is unrelated to remote_code loading regressions." }, { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Special-token runtime updates in TokenizersBackend are different from the mdeberta add_special_tokens behavior change." + "reason": "Runtime special-token post-processor refresh vs missing BOS/EOS insertion are related to tokenizers broadly but not the same concrete bug." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Video-LLaVA architecture/weight-sharing bug is unrelated to Qwen3.5 save_pretrained key regression." + "reason": "Video-LLaVA weight/temporal-attention bug vs Qwen3.5 save_pretrained key regression are unrelated." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer construction error and Qwen3 cudaErrorAssert are different code paths." + "reason": "Tokenizer class-name conflict vs Qwen3 auto device-map cuda assert are unrelated." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch 2.10 incompatibility is unrelated to loading noise/logging." + "reason": "Torch 2.10 compatibility problem vs loading noise/verbosity issue." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "Whisper runtime failure and Float8 storage lookup error are unrelated." + "reason": "Whisper runtime failure vs float8 storage lookup error; different failure modes." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "Both affect classification training, but flash_attention_3 degeneracy and num_labels=1 zero-loss are different underlying problems." + "reason": "FlashAttention-3 training degeneration and zero-loss single-label classification are both training issues but have different causes." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "Unnecessary loading noise is not the same as tokenizer loading failure for EMBEDDIA/est-roberta." + "reason": "Loading noise vs tokenizer loading failure for a specific model are unrelated." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Both are Qwen-VL training-related, but multi-GPU training and multi-image iterable dataset failures are not the same bug." + "reason": "Qwen2-VL multi-GPU training and Qwen2.5-VL multi-image dataset failure are separate problems." }, { "left": "issue:44079", "right": "issue:44534", "accept": false, - "reason": "ModelOutput key assignment and non-persistent buffer loading are unrelated." + "reason": "ModelOutput key assignment bug is unrelated to buffer initialization regression." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "Both involve batching/padding effects, but MIMI encoder padding-mask support and Gemma3 NaN embeddings are not the same concrete defect." + "reason": "Both involve batching, but MIMI padding-mask outputs and Gemma3 NaN embeddings are different model-specific bugs." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen2.5-VL multi-image finetuning." + "reason": "Progressive generation with `inputs_embeds`/`past_key_values` is unrelated to Qwen2.5-VL multi-image finetuning." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "Qwen2.5-GGUF v5 loading and Llama4Config missing pad_token_id are separate model-specific compatibility issues." + "reason": "Qwen2.5-GGUF loading failure and missing `pad_token_id` on Llama4Config are different loader issues." }, { "left": "issue:44291", "right": "issue:44589", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized argument handling is unrelated to Float8 storage lookup." + "reason": "Unexpected `_is_hf_initialized` argument during init_empty_weights is a different regression from float8 storage lookup failure." }, { "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are different subsystems." + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are unrelated." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "Non-persistent buffer junk and ModelOutput key assignment are unrelated bugs." + "reason": "Non-persistent buffer junk regression is unrelated to ModelOutput key handling." }, { "left": "issue:44079", "right": "issue:45072", "accept": false, - "reason": "ModelOutput key assignment is unrelated to bfloat16 dtype mismatches in CI." + "reason": "ModelOutput key assignment bug is unrelated to bfloat16 dtype mismatch in inference." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "_is_hf_initialized regression is not the same as bfloat16 inference dtype mismatch." + "reason": "`_is_hf_initialized` regression is unrelated to dtype mismatch in bfloat16 inference." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "torch.export with torch_compilable_check is a different failure mode than bfloat16 dtype mismatch." + "reason": "torch.export / `torch_compilable_check` failure is unrelated to bfloat16 dtype mismatch." }, { "left": "issue:43531", "right": "issue:44291", "accept": false, - "reason": "Qwen3-MoE sliding_window and init_empty_weights argument handling are unrelated." + "reason": "Qwen3-MoE sliding_window issue and `_is_hf_initialized` init_empty_weights error are unrelated." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen2.5-VL, but multi-image training and video vision_position_ids are different code paths." + "reason": "Multi-image prompt finetuning failure vs video `vision_position_ids` bug are different Qwen2.5-VL issues." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "Packaging/backend dependency issue is unrelated to PaddleOCR-VL loading in vLLM." + "reason": "Packaging/backend dependency issue vs PaddleOCR-VL load failure are unrelated." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "Qwen3 device_map cuda assert and Mistral tokenizer regex patch crash are unrelated." + "reason": "Qwen3 auto device-map assert and Mistral tokenizer regex patch crash are different subsystems." }, { "left": "issue:45325", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen2.5-VL position-id bugs, but one is still-image temporal scaling and the other is video vision_position_ids; not clearly the same defect." + "reason": "Both are Qwen2.5-VL position-id complaints, but one is still-image temporal scaling and the other is video `vision_position_ids`; not clearly the same bug." }, { "left": "issue:43611", "right": "issue:43646", "accept": false, - "reason": "Both are v5 model-init/load regressions, but the reported failures differ enough that they do not look like one concrete duplicate." + "reason": "Both are Transformers v5 loading regressions, but `base_model_prefix` handling and custom model initialization are different concrete failures." }, { "left": "issue:43881", "right": "issue:44488", "accept": false, - "reason": "glm-4v-9b loading and sleng-bert tokenizer loading are unrelated." + "reason": "glm-4v-9b loading failure and `cjvt/sleng-bert` tokenizer loading failure are unrelated." }, { "left": "issue:43828", "right": "issue:44683", "accept": false, - "reason": "Autocast dtype mismatch and compiled flex_attention on torch>=2.9 are different problems." + "reason": "Autocast dtype mismatch for Phi-tiny-MoE is unrelated to compiled flex_attention on torch>=2.9." } ] }, @@ -2942,8 +2942,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -3037,7 +3037,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -3282,8 +3282,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -3375,7 +3375,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -3611,8 +3611,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -3702,7 +3702,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -3923,8 +3923,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -4013,7 +4013,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -4234,8 +4234,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -4322,7 +4322,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -4531,8 +4531,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -4623,7 +4623,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -4853,8 +4853,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -4945,7 +4945,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -5172,8 +5172,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -5263,7 +5263,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -5490,8 +5490,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -5582,7 +5582,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -5809,8 +5809,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -5897,7 +5897,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -6100,8 +6100,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -6191,7 +6191,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -6409,8 +6409,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -6503,7 +6503,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -6834,12 +6834,12 @@ "issue:43065|issue:45412", "issue:43065|issue:43994" ], - "prepared_review_unit_hash": "5a08f86786f43d54cc567fcdc047998501fc3266f20ba6245afe2b6ef228fb7b", + "prepared_review_unit_hash": "23e6a4f950eda39a212ca7fc933cb901b5caa98e53a6e5aba5d1387307e34462", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -6847,225 +6847,225 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 34, - "serialized_chars": 37515, - "estimated_input_tokens": 9379, - "estimated_eval_tokens": 19014 + "serialized_chars": 37517, + "estimated_input_tokens": 9380, + "estimated_eval_tokens": 19016 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is not a single duplicate cluster: the soft pairs span many unrelated bugs across tokenizers, multimodal processors, attention, device mapping, and CI regressions. None of the candidate edges look like the same underlying change or bug.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "This cluster is a heterogeneous mix of unrelated Transformers bugs; the soft matches are mostly title-level lexical similarity rather than the same underlying defect. I would not merge any of the suggested pairs.", + "confidence": 0.95, + "canonical_issue_reason": "issue:43335 is the closest thing to a hub by soft-match fan-out, but the surrounding links are superficial and the cluster is too heterogeneous to justify a true canonical duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a strong canonical target because the pairings are mostly false positives across unrelated reports. If forced, issue:43335 is only the most connected node, not the most representative bug.", + "best_issue_reason": "issue:43335 is the least-bad representative only because it has the most soft-similarity links; it is not a strong semantic cluster center.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "Different subsystems and failures: LayoutLMv3 error messaging vs Trainer/_gpu_broadcast_one NoneType broadcast error." + "reason": "Different models and failures: layoutlmv3 box validation messaging vs Trainer NoneType GPU broadcast." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "Unrelated bugs: SwitchTransformers sparse-layer config vs BigBirdTokenizer special-token decoding." + "reason": "SwitchTransformers sparse-layer config bug is unrelated to BigBirdTokenizer special-token registration." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Different models and failure modes: Qwen3.5 flash-attention generation bug vs Gemma4 multi-GPU OOM." + "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU OOM are different code paths and symptoms." }, { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "Different issues: SigLIP2 zero probabilities vs widespread unexpected position-id keys." + "reason": "siglip2 zero-probabilities vs position-id unexpected-key loading are unrelated." }, { "left": "issue:43335", "right": "issue:45083", "accept": false, - "reason": "SwitchTransformers config bug is unrelated to qwen3_omni_moe feature-length helper behavior." + "reason": "SwitchTransformers config creation issue does not match qwen3_omni_moe feature-length helper behavior." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "Different model families and code paths: SwitchTransformers config vs BEiT semantic-segmentation load preset legacy field." + "reason": "Sparse-layer construction in SwitchTransformers is unrelated to BEiT legacy-field loading." }, { "left": "issue:43550", "right": "issue:44112", "accept": false, - "reason": "Bamba torch.compile/SDPA issue is unrelated to GraniteSpeech stale device-override CI failure." + "reason": "Bamba torch.compile/SDPA failure and GraniteSpeech CI stale override test are different problems." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "Sparse-layer creation in SwitchTransformers is not the same bug as bfloat16 dtype mismatches in inference." + "reason": "SwitchTransformers sparse-layer bug is not the same as dtype mismatch in bfloat16 inference." }, { "left": "issue:44568", "right": "issue:45491", "accept": false, - "reason": "Tokenizer special-token behavior and Gemma3 mixed-length NaNs are distinct bugs." + "reason": "Tokenizer add_special_tokens behavior and Gemma3 NaN embeddings from sliding-window attention are different bugs." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "BitNet packed-weight loading bug is unrelated to GraniteSpeech CI device override state." + "reason": "BitNet packed-weight loading under accelerate is unrelated to a GraniteSpeech CI test failure." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Different regressions: Pegasus v4/v5 output drift vs Qwen3.5 flash-attention generation failure." + "reason": "Pegasus v4/v5 output regression and Qwen3.5 flash-attention generation failure are not the same issue." }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "Qwen2.5-VL iterable-dataset/multi-image failure is unrelated to BEiT fast processor label reduction." + "reason": "Qwen2.5-VL iterable-dataset multi-image finetuning and BEiT fast processor label reduction are unrelated." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "AutoTokenizer loading in v5 and MPS attention correctness are unrelated code paths." + "reason": "AutoTokenizer loading in v5 and an MPS attention correctness bug are different code paths." }, { "left": "issue:43335", "right": "issue:44112", "accept": false, - "reason": "SwitchTransformers sparse-layer config and GraniteSpeech device-override CI failure are unrelated." + "reason": "SwitchTransformers config bug does not match a GraniteSpeech stale-device CI test." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Llama 3.2 Vision model loading regression is unrelated to output-embedding reinit after resizing token embeddings." + "reason": "Llama 3.2 vision model loading breakage is not the same as output embeddings being reinitialized on resize." }, { "left": "issue:45372", "right": "issue:45406", "accept": false, - "reason": "Gemma4 processor import dependency issue is separate from transformers serve missing _tokenizer attribute." + "reason": "Both involve Gemma4, but one is an import-dependency failure and the other is a missing _tokenizer attribute in serve; not the same code-path bug." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "CPU-offload device mismatch for bark-small is unrelated to LwDetrImageLoss float16 CUDA crashes." + "reason": "CPU-offload device mismatch in bark-small is unrelated to an AMP/CUDA crash in LwDetrImageLoss." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "Both mention dtype/precision, but they are different models and concrete failures: AMP crash vs bfloat16 inference mismatch." + "reason": "These are both dtype-related, but they affect different models and different failure mechanisms." }, { "left": "issue:43873", "right": "issue:44493", "accept": false, - "reason": "Quantization offloading behavior is unrelated to unexpected position-id key warnings/errors." + "reason": "Quantization/offloading behavior and unexpected position-id keys are unrelated." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Tokenizer decoder type regression and tokenizer.json being ignored are different loading issues." + "reason": "Tokenizer decoder type selection and ignoring tokenizer.json are different tokenizer-loading bugs." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "Quantized offloading bug and Gemma4 multi-GPU OOM are not the same underlying problem." + "reason": "Quantized offloading problems and Gemma4 multi-GPU OOM are not the same underlying defect." }, { "left": "issue:37428", "right": "issue:44987", "accept": false, - "reason": "Flash-attention import error and loading physical-intelligence/fast on v5.1.0 are not clearly the same defect." + "reason": "Flash-attention import error and Qwen3.5 flash-attention generation failure share a subsystem but not a concrete bug." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Embedding dtype drift in eval is unrelated to multimodal token counting using undefined video helpers." + "reason": "Embedding dtype drift in eval and an undefined-variable multimodal token helper are unrelated." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint key mismatch and qwen3_omni_moe length helper behavior are different issues." + "reason": "resume_from_checkpoint key mismatch does not match qwen3_omni_moe feature-length logic." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Failing Flash Attention 2 tests do not match token-embedding reinitialization after resize." + "reason": "Failing Flash Attention 2 tests and embedding reinit after resize are different issues." }, { "left": "issue:41720", "right": "issue:45229", "accept": false, - "reason": "Qwen3 auto device-mapping assert and Gemma4 inference OOM are different failure modes." + "reason": "cudaErrorAssert under auto device mapping is not the same as multi-GPU inference OOM." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to qwen3_omni_moe feature extraction lengths." + "reason": "Bamba torch.compile/SDPA failure is unrelated to qwen3_omni_moe feature-length calculation." }, { "left": "issue:44451", "right": "issue:45520", "accept": false, - "reason": "ScandiBERT load failure and Python 3.13 flash_attn KeyError are different compatibility problems." + "reason": "Model-loading failure for ScandiBERT and flash_attn import KeyError on Python 3.13 are different problems." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "Python-version incompatibility in Transformers 5.1.0 is unrelated to DeepseekV3MoE implementation divergence." + "reason": "Python version compatibility breakage and DeepSeekV3 implementation divergence are unrelated." }, { "left": "issue:32090", "right": "issue:33357", "accept": false, - "reason": "Trainer NoneType broadcast error and MacOS bus error with community CLIP are unrelated." + "reason": "Trainer broadcast NoneType error and MacOS bus error loading a CLIP model are not the same bug." }, { "left": "issue:45372", "right": "issue:45459", "accept": false, - "reason": "Gemma4 ReasoningEffort import breakage and protobuf-related tokenizer error masking are different bugs." + "reason": "Gemma4 ReasoningEffort import failure and protobuf-related tokenizer error masking are different failure modes." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Pegasus output drift and lm_head.weight serialization inconsistency may both be v5 regressions, but they are not the same concrete bug." + "reason": "Both are v4/v5 regressions, but one is generation output difference and the other is lm_head serialization inconsistency; different code paths." }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to RT-DETR memory not being freed." + "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory release on delete are unrelated." }, { "left": "issue:43065", "right": "issue:43994", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d and SigLIP2 nonsensical outputs are different model bugs." + "reason": "Sam3PixelDecoder dummy layer and ScandiBERT loading failure have no shared underlying bug." } ] }, @@ -7171,12 +7171,12 @@ "issue:29942|issue:36010", "issue:29127|issue:33357" ], - "prepared_review_unit_hash": "e635f5ce5d597c27339dc0c29362244fd3c326857d6e8fcecabd9f4c0bc64ae2", + "prepared_review_unit_hash": "f79e4db9c237686722495b953149c4d18146928c910b9fb0a67ca9f9759a9308", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -7193,198 +7193,198 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the soft links mostly reflect broad lexical overlap (errors, tokenizers, processors, vision models, training/runtime issues) rather than the same underlying bug. I would not merge any of the proposed pairs.", - "confidence": 0.94, - "canonical_issue_reason": null, + "summary": "This cluster is a loose grab-bag of mostly unrelated Hugging Face issues that were only weakly linked by text similarity. None of the suggested soft pairs look like true duplicates or the same underlying fix, and there are no PRs in the set.", + "confidence": 0.96, + "canonical_issue_reason": "If a representative issue is needed, issue 45198 is one of the clearest standalone bug reports with a concrete failure mode and reproducible symptoms, but the cluster is not cohesive enough to have a strong canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Issue 45198 is the most concrete and actionable report among these unrelated items; it has a specific model, specific failure, and a likely reproducible path.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "Different components and failure modes: LayoutLMv2 NER/batching crash vs Wav2Vec2 save_pretrained/tokenization failure." + "reason": "Both are tokenizer-related, but they describe different models and different failures: NER/batching crashes vs save_pretrained/tokenization failure." }, { "left": "issue:25251", "right": "issue:32090", "accept": false, - "reason": "Unrelated behavior: pipeline top_k nesting bug vs Trainer/_gpu_broadcast_one NoneType error." + "reason": "Pipeline output nesting and Trainer broadcast TypeError are unrelated code paths and symptoms." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "BigBirdTokenizer special-token decode issue is unrelated to Qwen3.5 recurrent-state reset in modular_qwen3_5.py." + "reason": "BigBirdTokenizer special-token decode behavior and Qwen3-MoE recurrent-state reset are different bugs in different components." }, { "left": "issue:43278", "right": "issue:43381", "accept": false, - "reason": "BF16\u2192FP32 dtype drift in eval is not the same as gradient checkpointing being disallowed in eval mode." + "reason": "Embedding dtype drift in eval and gradient-checkpointing disallowed in eval mode are separate training/evaluation issues." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "torch.export with torch_compilable_check is a different code path from Wav2Vec2 save/tokenization failures." + "reason": "torch.export failures with torch_compilable_check are unrelated to Wav2Vec2 save_pretrained/tokenization problems." }, { "left": "issue:44361", "right": "issue:45198", "accept": false, - "reason": "MLukeTokenizer task AttributeError is unrelated to Wav2Vec2 save_pretrained/tokenization failure." + "reason": "MLukeTokenizer task AttributeError and Wav2Vec2 tokenization/save failures are different tokenizer bugs with different triggers." }, { "left": "issue:43257", "right": "issue:43278", "accept": false, - "reason": "Qwen3 MoE weight conversion issue is unrelated to embedding dtype changes during evaluation." + "reason": "Qwen3 MoE weight conversion/loading under accelerate+deepspeed is not the same bug as BF16-to-FP32 embedding dtype drift." }, { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "Qwen3Moe FP8 config failure and quantized model saving failure are distinct quantization bugs." + "reason": "Qwen3Moe FineGrainedFP8Config failure and quantized model saving failure are separate quantization-related problems." }, { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime special-token post-processor update bug is unrelated to Gemma3 NaN embeddings with sliding-window attention." + "reason": "Runtime post-processor updates for special tokens and Gemma3 NaN embeddings are unrelated features/bugs." }, { "left": "issue:44871", "right": "issue:44977", "accept": false, - "reason": "Gemma eos_token_id mismatch is not the same as Qwen3.5 flash-attention generation corruption." + "reason": "Gemma eos_token_id mismatch and Qwen3.5 flash-attention generation issues affect different models and different mechanisms." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 model/pipeline mismatch is unrelated to RT-DETR memory not being released on delete." + "reason": "SigLIP2 nonsense outputs and RT-DETR memory leaks are distinct model behavior vs lifecycle bugs." }, { "left": "issue:44206", "right": "issue:44479", "accept": false, - "reason": "Unsupported center arg in LasrFeatureExtractor is a different regression from Qwen2.5/3 video input handling." + "reason": "Unsupported center argument in LasrFeatureExtractor is unrelated to the qwen2_5_vl/qwen3_vl video regression." }, { "left": "issue:43756", "right": "issue:45440", "accept": false, - "reason": "Smollm3 RoPE-layer configuration issue is unrelated to DeepseekV3MoE divergence from remote implementation." + "reason": "Smollm3 RoPE-layer discrepancy and DeepseekV3MoE divergence are different model-implementation issues." }, { "left": "issue:43504", "right": "issue:44857", "accept": false, - "reason": "BEiT legacy-field load bug is unrelated to LwDetrImageLoss AMP/CUDA crash." + "reason": "Beit pretrained-load legacy-field handling and LwDetr float16 CUDA loss crashes are unrelated bugs." }, { "left": "issue:44610", "right": "issue:45412", "accept": false, - "reason": "OmDet-Turbo processor size mismatch is unrelated to RT-DETR model memory retention." + "reason": "Processor image-size mismatch and RT-DETR memory release behavior do not share the same underlying defect." }, { "left": "issue:29942", "right": "issue:30064", "accept": false, - "reason": "Failing Flash Attention 2 tests and void segmentation-map processing are different subsystems and symptoms." + "reason": "Flash Attention 2 CI failures and void segmentation-map processing are different subsystems and failure modes." }, { "left": "issue:45103", "right": "issue:45372", "accept": false, - "reason": "auto_docstring annotations crash is unrelated to Gemma 4 processor loading failing on missing ReasoningEffort import." + "reason": "auto_docstring annotation parsing and Gemma 4 processor import failure come from unrelated tooling paths." }, { "left": "issue:33357", "right": "issue:39692", "accept": false, - "reason": "MacOS bus error on CLIP model and SigLIP2 documentation errors are different problems." + "reason": "Both mention CLIP/SigLIP-like models, but the MacOS bus error and documentation example errors are different issues." }, { "left": "issue:29127", "right": "issue:34567", "accept": false, - "reason": "LayoutLMv3 error-message clarity issue is unrelated to TrainerState token counter not updating." + "reason": "LayoutLMv3 error-message clarity and TrainerState token-count tracking are unrelated concerns." }, { "left": "issue:32090", "right": "issue:33290", "accept": false, - "reason": "Trainer NoneType broadcast error is unrelated to Adafactor OOM in DeepSpeed." + "reason": "Trainer NoneType broadcast errors and DeepSpeed Adafactor OOM are distinct training failures." }, { "left": "issue:45072", "right": "issue:45229", "accept": false, - "reason": "dtype mismatches in bfloat16 inference are unrelated to Gemma4 multi-GPU CUDA OOM." + "reason": "Bfloat16 dtype mismatches in inference and Gemma4 multi-GPU OOM are different classes of problems." }, { "left": "issue:43824", "right": "issue:44279", "accept": false, - "reason": "Qwen2.5-VL import error is unrelated to a generic dependency issue with transformers." + "reason": "Specific Qwen2.5-VL import failure and a generic dependency issue are not the same bug." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug is unrelated to AutoTokenizer failing to load FastSpeech2ConformerTokenizer." + "reason": "BigBirdTokenizer special-token registration and AutoTokenizer loading FastSpeech2ConformerTokenizer are unrelated tokenizer/loading bugs." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch are different training-loop issues." + "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch do not describe the same code path." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Qwen3-VL pad_token_id AttributeError is unrelated to Qwen3-MoE sliding_window behavior." + "reason": "Qwen3-VL pad_token_id missing and Qwen3-MoE sliding_window issues are different model-family regressions." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "BeitImageProcessorFast reduce_labels bug is unrelated to LayoutLMv2Tokenizer crashes on NER/padding." + "reason": "BeitImageProcessorFast reduce_labels behavior and LayoutLMv2Tokenizer batching crashes are different components and failures." }, { "left": "issue:44464", "right": "issue:45491", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency is unrelated to Gemma3 NaN embeddings from mixed-length batching." + "reason": "Compiled-forward chunked generation inconsistency and Gemma3 NaN embeddings are not the same underlying bug." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Audio processor chat-template sample-rate default bug is unrelated to LasrFeatureExtractor center-arg crash." + "reason": "Audio chat-template sampling-rate defaulting and unsupported center arg in an image extractor are unrelated." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Flash-attention generation bug is unrelated to the category-count limit runtime error." + "reason": "Qwen3.5 flash-attention generation problems and category-count limits are entirely different issues." }, { "left": "issue:29942", "right": "issue:36010", "accept": false, - "reason": "Flash Attention 2 test failures do not match a GenerationMixin import error." + "reason": "Failing Flash Attention 2 tests and GenerationMixin import errors are unrelated." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 error-message clarity and CLIP MacOS bus error are not the same bug." + "reason": "LayoutLMv3 error messaging and CLIP bus errors on MacOS are not the same bug." } ] }, @@ -7488,12 +7488,12 @@ "issue:33290|issue:34689", "issue:33290|issue:35141" ], - "prepared_review_unit_hash": "1e218f6b0bf79ffa24861049a4a3b3daf8f374067ae4a3691b0269d82fd64eee", + "prepared_review_unit_hash": "094d24fc85d6f3110c473e4815fc0427b99cc0503adea5f833e76c1df19c1055", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -7510,192 +7510,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous: the soft pairs are mostly lexical similarities across different models, regressions, and subsystems, not the same underlying bug/change. I would not merge any of the proposed pairs as duplicates.", + "summary": "This set is not a duplicate cluster; it mixes many unrelated issues across different models, processors, generation, quantization, and docs. I rejected all soft edges because none appear to describe the same concrete bug.", "confidence": 0.97, - "canonical_issue_reason": "No single canonical issue fits this cluster; the items describe unrelated bugs across different models and code paths, with no soft pair clearly sharing the same root cause.", - "canonical_pr_reason": null, - "best_issue_reason": "issue:45440 is the strongest representative: it is an open, concrete model-implementation divergence report with broader technical impact than the other narrowly scoped issues.", - "best_pr_reason": null, + "canonical_issue_reason": "No single canonical issue fits the cluster: the items span unrelated regressions and API mismatches, so none cleanly subsumes the rest.", + "canonical_pr_reason": "No PRs are present in the provided items.", + "best_issue_reason": "If forced to choose a representative, issue 43873 is the broadest open regression with active discussion, but it still does not represent the rest of the set.", + "best_pr_reason": "No PRs are present in the provided items.", "soft_edge_verdicts": [ { "left": "issue:29127", "right": "issue:35141", "accept": false, - "reason": "Different bugs: one is an error-message clarity issue in LayoutLMv3, the other is token embedding reinitialization in post_init." + "reason": "Different bugs: LayoutLMv3 error-message clarity vs token-embedding reinitialization in post_init." }, { "left": "issue:43761", "right": "issue:44079", "accept": false, - "reason": "CLIPVision hidden_states regression and ModelOutput key assignment are distinct code paths and failure modes." + "reason": "One is a CLIPVisionModel hidden_states regression; the other is ModelOutput key handling for None values." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "Tokenizer loading failure vs dtype mismatch in inference; no shared concrete bug." + "reason": "Unrelated failures: tokenizer loading for FastSpeech2ConformerTokenizer vs dtype mismatches in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:42915", "right": "issue:43931", "accept": false, - "reason": "Both involve model loading/regression language, but they are different models and different failures (FP8 config vs weight shape mismatch)." + "reason": "Different model-load paths and symptoms: FineGrainedFP8Config failure vs Qwen3-VL weight-shape mismatch." }, { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Generation kwargs update after sync_gpus is unrelated to metric gathering dropping tuple labels." + "reason": "Generation kwargs sync bug vs metric-gathering dropping tuple labels; unrelated code paths." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug is unrelated to LwDetrImageLoss AMP/CUDA crashing." + "reason": "BeitImageProcessorFast label reduction bug vs LwDetrImageLoss AMP/CUDA crash." }, { "left": "issue:43526", "right": "issue:44610", "accept": false, - "reason": "Different processor/model mismatch issues affecting different pipelines and outputs." + "reason": "Both touch processors, but one is label reduction in BeitImageProcessorFast and the other is input-size mismatch in OmDet-Turbo." }, { "left": "issue:44479", "right": "issue:45290", "accept": false, - "reason": "Video input regression in Qwen variants is unrelated to chat template tool-call handling." + "reason": "Different regressions: video-input handling for Qwen variants vs chat-template tool-call tokenization crash." }, { "left": "issue:43723", "right": "issue:45479", "accept": false, - "reason": "Tokenizer auto-loading regression and single-label classification zero-loss are separate problems." + "reason": "Tokenizer loading in v5 is unrelated to the zero-loss classification bug with num_labels=1." }, { "left": "issue:44743", "right": "issue:44811", "accept": false, - "reason": "Recurrent state reset in cached generation is unrelated to Whisper batch_decode skip_special_tokens handling." + "reason": "Qwen recurrent-state caching bug vs Whisper batch_decode skip_special_tokens handling." }, { "left": "issue:45003", "right": "issue:45440", "accept": false, - "reason": "sys.modules access in modeling_utils is a different bug from DeepseekV3MoE implementation divergence." + "reason": "Unsafe sys.modules access in modeling_utils vs DeepseekV3MoE implementation divergence." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "Tensor-parallel OOM on loading is unrelated to resume_from_checkpoint key mismatch." + "reason": "Tensor-parallel OOM when loading Qwen2-57B-A14B-Instruct is unrelated to resume_from_checkpoint key mismatch." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Both are Qwen-related regressions, but one is a weight-shape load error and the other is incorrect save_pretrained checkpoint contents." + "reason": "Both are Qwen3-family regressions, but one is a weight-shape load error and the other is a bad save_pretrained checkpoint." }, { "left": "issue:43316", "right": "issue:43525", "accept": false, - "reason": "Different config API inconsistencies on different models; same theme, not same bug." + "reason": "Both are API discrepancies, but Gemma3TextConfig missing parity is different from Llama4Config lacking pad_token_id." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "Custom model init breakage and patchtsmixer post_init policy are not the same underlying issue." + "reason": "General custom model initialization breakage is not the same bug as patchtsmixer's post_init policy change." }, { "left": "issue:43761", "right": "issue:44188", "accept": false, - "reason": "Hidden_states omission and attention-kernel divergence under torch.compile are unrelated." + "reason": "CLIPVision hidden_states regression and allow_is_bidirectional_skip branching under torch.compile are distinct issues." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "OOM during tensor-parallel loading and increased reserved memory under int4 quantization are different memory issues." + "reason": "Both mention OOM, but one is TP loading OOM and the other is increased reserved memory under int4 quantization." }, { "left": "issue:44964", "right": "issue:45440", "accept": false, - "reason": "Phi-4 multimodal loading failure is unrelated to DeepseekV3MoE remote-implementation divergence." + "reason": "Phi-4 multimodal loading failure is unrelated to DeepseekV3MoE divergence from remote implementation." }, { "left": "issue:43994", "right": "issue:44206", "accept": false, - "reason": "SigLIP2 wrong outputs and LasrFeatureExtractor center-arg regression are different bugs." + "reason": "SigLIP2 nonsensical outputs with AutoModel/pipeline do not match the LasrFeatureExtractor center-arg crash." }, { "left": "issue:29942", "right": "issue:33666", "accept": false, - "reason": "Flash Attention 2 CI failures and Qwen2-VL multi-GPU training are unrelated." + "reason": "Failing Flash Attention 2 tests and Qwen2-VL multi-GPU training are different subsystems and failures." }, { "left": "issue:39692", "right": "issue:45491", "accept": false, - "reason": "SigLIP2 docs example mistakes are not the same as Gemma3 NaN embeddings on GPU." + "reason": "Documentation example errors for SigLIP2 are unrelated to Gemma3 NaN embeddings on mixed-length batches." }, { "left": "issue:43673", "right": "issue:44743", "accept": false, - "reason": "Both involve generation/cache behavior, but they affect different mechanisms and code paths." + "reason": "Chunked-prefill cache missing in GenerationMixin is a different cache bug than Qwen recurrent states resetting." }, { "left": "issue:44442", "right": "issue:44898", "accept": false, - "reason": "Tokenizer loading failure and Perceiver non-default resolution failure are unrelated." + "reason": "Tokenizer loading failure vs Perceiver image-classification resolution/interpolation failure are unrelated." }, { "left": "issue:33290", "right": "issue:34567", "accept": false, - "reason": "AdaFactor/deepspeed OOM and TrainerState token counter not updating are separate trainer issues." + "reason": "AdaFactor OOM in DeepSpeed is unrelated to TrainerState.num_input_tokens_seen not updating." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are model-loading regressions, but they stem from different version changes and different loader failures." + "reason": "Both are loading regressions, but they concern different releases, model families, and failure modes." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Gradient checkpointing in eval mode and offloading with quantization are distinct behaviors." + "reason": "Gradient checkpointing in eval mode and quantization offloading behavior are separate bugs." }, { "left": "issue:43493", "right": "issue:43827", "accept": false, - "reason": "SigLIP2 HF-vs-JAX divergence is unrelated to stale pipeline docs after v5 removals." + "reason": "SigLIP2 implementation drift is unrelated to docs still referencing pipeline() after v5 removals." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "patchtsmixer post_init policy and Qwen video-input regression are unrelated." + "reason": "PatchTSMixer post_init policy change is unrelated to the Qwen video-input regression." }, { "left": "issue:33290", "right": "issue:34689", "accept": false, - "reason": "OOM in deepspeed adafactor training and Llama 3.2 model-loading breakage are different failures." + "reason": "AdaFactor/DeepSpeed OOM and Llama 3.2 Vision model-loading breakage are different problems." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "Training OOM and output embedding reinitialization are unrelated bugs." + "reason": "Optimizer OOM in DeepSpeed is unrelated to token-embedding reinitialization during post_init." } ] }, @@ -7714,8 +7714,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -7800,7 +7800,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -7991,8 +7991,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -8080,7 +8080,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -8289,8 +8289,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -8381,7 +8381,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -8608,8 +8608,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -8702,7 +8702,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -8941,8 +8941,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -9030,7 +9030,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -9325,12 +9325,12 @@ "issue:43232|issue:44336", "issue:44496|issue:45003" ], - "prepared_review_unit_hash": "b747085123d727f9463a75202b8dea16e37b5b1b63f1cb05594ea62b27920532", + "prepared_review_unit_hash": "8a1f91b82b8f7b7ea956c1d3a52474175c9003765ddd7282846f20c49e645938", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -9338,7 +9338,7 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36465, + "serialized_chars": 36467, "estimated_input_tokens": 9117, "estimated_eval_tokens": 18490 }, @@ -9347,192 +9347,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are mostly unrelated Transformers bugs/regressions across different model families and subsystems (imports, tokenizers, generation, config, distributed loading, pipelines). I did not find any soft-edge pair that looks like the same underlying bug/change.", - "confidence": 0.93, - "canonical_issue_reason": "No single canonical issue stands out; the items are heterogeneous and do not cluster around one concrete bug.", + "summary": "This cluster is mostly heterogeneous: many items are version/regression or model-loading reports, but the soft pairs do not look like true duplicates. I treated the cluster as having no strong duplicate hub and chose the most generic import-regression issue as the best loose anchor.", + "confidence": 0.67, + "canonical_issue_reason": "issue:36246 is the broadest and most generic import/export regression in the set, so it is the closest loose anchor for the cluster; however, there is no strong evidence that the items are true duplicates of it.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a good global representative because the set spans many distinct failure modes rather than one duplicate thread.", + "best_issue_reason": "issue:36246 is the best representative only in a weak sense: it matches the common theme of broken imports/public API exports better than the more model-specific reports, but the cluster is not a coherent duplicate set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44295", "right": "issue:45397", "accept": false, - "reason": "Different problems and model paths: position_ids buffer access vs Gemma-4 ZeRO3 loading." + "reason": "Different failures: position_ids buffer access vs Gemma-4 ZeRO3 from_pretrained loading." }, { "left": "issue:42491", "right": "issue:43299", "accept": false, - "reason": "Both involve Qwen3/MoE loading regressions, but the concrete failures and model types differ; not the same bug." + "reason": "Both involve Qwen3 MoE loading regressions, but they target different model variants and failure modes." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import-time slowdown vs unrecognized model/config loading failure; unrelated." + "reason": "Unrelated: slow import vs unrecognized model/config loading failure." }, { "left": "issue:44336", "right": "issue:44373", "accept": false, - "reason": "ANSI output in loading_report vs a docstring issue for position_ids; unrelated." + "reason": "ANSI escape output bug and a wrong docstring are unrelated." }, { "left": "issue:44462", "right": "issue:45356", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different code paths and symptoms." + "reason": "Different tokenizer problems: repository tokenizer selection vs Kimi codec/regression handling." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug vs unsafe sys.modules access in modeling_utils." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to unsafe sys.modules access." }, { "left": "issue:43994", "right": "issue:45276", "accept": false, - "reason": "Siglip2 inference/pipeline issue vs resize_token_embeddings not updating embeddings; different bug classes." + "reason": "Siglip2 inference corruption and resize_token_embeddings not updating embeddings are different code paths." }, { "left": "issue:43531", "right": "issue:45362", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior vs Qwen3.5-35B chat crash; not the same failure." + "reason": "Both mention Qwen, but one is sliding_window/MoE behavior and the other is chat crash; not the same bug." }, { "left": "issue:36246", "right": "issue:42757", "accept": false, - "reason": "Missing transformers symbol vs missing huggingface_hub symbol; separate import errors." + "reason": "Both are import errors, but for different symbols and unrelated modules." }, { "left": "issue:36246", "right": "issue:44351", "accept": false, - "reason": "Different missing exports: Qwen2_5_VLImageProcessor vs HybridCache." + "reason": "ImportError for Qwen2.5 VL image processor is not the same as missing HybridCache export." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Generation cache issue vs removal of is_torch_fx_available breaking trust_remote_code models." + "reason": "Generation cache/chunked prefill issue is unrelated to removal of is_torch_fx_available." }, { "left": "issue:44336", "right": "issue:44485", "accept": false, - "reason": "Terminal ANSI output bug vs GLM-5 RoPE implementation discussion; unrelated." + "reason": "Loading report ANSI codes and GLM-5 RoPE implementation are unrelated." }, { "left": "issue:36246", "right": "issue:43596", "accept": false, - "reason": "ImportError for a vision processor vs DeepSpeed ZeRO3/BertModel index error." + "reason": "Qwen2.5 VL import error and DeepSpeed/BertModel IndexError are unrelated." }, { "left": "issue:44242", "right": "issue:44857", "accept": false, - "reason": "MoE router loss bug vs CUDA/AMP crash in LwDetrImageLoss; different subsystems." + "reason": "Load-balancing loss logic and LwDetrImageLoss AMP crash are different bugs." }, { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "ESM2 model breakage vs Gemma 4 token-type ID requirement; unrelated models and symptoms." + "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids handling are unrelated." }, { "left": "issue:44246", "right": "issue:44871", "accept": false, - "reason": "Import performance vs Gemma-3 eos_token_id inconsistency; unrelated." + "reason": "Slow import and eos_token_id configuration inconsistency are unrelated." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "DeepSeek tokenizer regression vs resize_token_embeddings not propagating; different problems." + "reason": "Deepseek tokenizer regression is unrelated to resize_token_embeddings not updating output embeddings." }, { "left": "issue:44987", "right": "issue:45459", "accept": false, - "reason": "Model loading failure vs tokenizer exception masking when protobuf is absent; unrelated." + "reason": "Model loading failure and tokenizer protobuf error masking are different problems." }, { "left": "issue:44295", "right": "issue:44749", "accept": false, - "reason": "Buffer/read error vs Chinese report about post-upgrade data filtering slowdown; unrelated." + "reason": "Position_ids buffer bug is unrelated to the Chinese report about data filtering slowdown." }, { "left": "issue:43441", "right": "issue:43540", "accept": false, - "reason": "FlashAttention failure for Ministral-3 vs video-input processing error in Qwen3OmniMoe." + "reason": "FlashAttention failure for Ministral-3 and Qwen3OmniMoe video-input ValueError are unrelated." }, { "left": "issue:44877", "right": "issue:45375", "accept": false, - "reason": "Both mention strict config handling, but they are different models and different missing-field issues." + "reason": "Both involve strict config handling, but they are different model configs and not clearly the same concrete bug." }, { "left": "issue:41950", "right": "issue:43596", "accept": false, - "reason": "Pipeline processor lookup bug vs DeepSpeed/BertModel init failure; unrelated." + "reason": "Video-classification pipeline image-processor lookup is unrelated to the ZeRO3/BertModel IndexError." }, { "left": "issue:43066", "right": "issue:44779", "accept": false, - "reason": "Tokenizer decoder type mismatch vs DeepSeek tokenizer incorrect results; both v5 tokenizer regressions but not the same concrete defect." + "reason": "Wrong tokenizer decoder type and Deepseek tokenizer corruption are different tokenizer regressions." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "Docs mismatch in text classification pipeline vs unsafe sys.modules access; unrelated." + "reason": "Docs mention of return_all_scores and unsafe sys.modules access are unrelated." }, { "left": "issue:42886", "right": "issue:45229", "accept": false, - "reason": "Offline cache load failure vs Gemma4 multi-GPU OOM; unrelated." + "reason": "Offline cache loading failure and Gemma4 multi-GPU OOM are unrelated." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "Stale indexer cache crash on second forward vs Gemma 4 mm_token_type_ids defaulting; unrelated." + "reason": "Stale indexer cache crash and mm_token_type_ids defaulting are different bugs." }, { "left": "issue:43257", "right": "issue:45137", "accept": false, - "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed vs generic ZeRO3 deque pop error; different failures." + "reason": "Qwen3 MoE weight conversion and DeepSpeed ZeRO3 deque error are unrelated." }, { "left": "issue:43065", "right": "issue:43408", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder vs model-type mismatch warning for sam3_video/sam3_tracker." + "reason": "Dummy Conv2d in Sam3PixelDecoder and sam3_video vs sam3_tracker warning are related only by model family, not the same bug." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs/update bug vs ANSI codes in loading_report; unrelated." + "reason": "Generation kwargs handling and ANSI code rendering are unrelated." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Unrecognized model/config loading failure vs unsafe sys.modules access; unrelated." + "reason": "Unrecognized model loading and sys.modules access are unrelated." } ] }, @@ -9636,12 +9636,12 @@ "issue:45081|issue:45103", "issue:42371|issue:45092" ], - "prepared_review_unit_hash": "6629718bbf7d49e9ea8075345183bb652a98eb40ba5a424714522fbf4f33c5b4", + "prepared_review_unit_hash": "6c5c97538c27fd62b4a323119318d6ed72662deb6204dfaacf3199a443abe445", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -9649,7 +9649,7 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36149, + "serialized_chars": 36151, "estimated_input_tokens": 9038, "estimated_eval_tokens": 18332 }, @@ -9658,198 +9658,198 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a semantic spillover of many unrelated Transformers bug reports. Only one soft pair looks like a true duplicate; the rest share broad themes like tokenization, generation, or v5 regressions but describe different concrete code paths or symptoms.", - "confidence": 0.69, - "canonical_issue_reason": "Issue 45278 is the broadest umbrella here, describing widespread import failures after upgrading to 5.5.0. It is still not a true canonical for the whole cluster, but it best matches the cluster\u2019s general upgrade/regression theme.", + "summary": "This cluster is mostly a grab-bag of Transformers v5-era regressions across tokenizers, generation, multimodal inputs, and model-loading paths. Only one pair is a clear duplicate; the rest are related at a broad theme level but not the same underlying bug.", + "confidence": 0.88, + "canonical_issue_reason": "issue:43646 is the broadest representative of the cluster\u2019s main theme: general Transformers v5 breakage around model initialization and compatibility, while most other items are narrower, model-specific regressions.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45278 is the best single issue to represent the cluster because it is the most general and user-facing regression report among the set. It is not a precise duplicate target, just the least-specific representative.", + "best_issue_reason": "issue:43646 is the best single issue to anchor this cluster because it is a generic upgrade-breakage report and captures the overarching v5 regression theme better than the more niche model-specific reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43262", "right": "issue:44246", "accept": false, - "reason": "Both involve loading/processing behavior, but one is audio chat-template sampling-rate handling and the other is slow imports. Different bugs and code paths." + "reason": "Different failures: audio processor chat-template sample-rate handling vs slow import performance." }, { "left": "issue:43295", "right": "issue:45292", "accept": false, - "reason": "Different regressions: processor/tokenizer access breakage versus resize_token_embeddings not updating output embeddings." + "reason": "Different code paths: processor/tokenizer image handling regression vs token-embedding resize not propagating to output embeddings." }, { "left": "issue:44060", "right": "issue:44077", "accept": false, - "reason": "One is a tied-weights warning bug in Qwen3-Next; the other is a post_init/patchtsmixer policy issue. Not the same change." + "reason": "Both mention config/model semantics, but one is a tied-weights warning bug and the other is a post_init allowance issue for a different model class." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "Both are video/multimodal failures, but they affect different models and different failure points." + "reason": "Different multimodal bugs: missing vision encoder attribute vs video-input validation error in another model." }, { "left": "issue:44466", "right": "issue:45335", "accept": false, - "reason": "Both concern tied embeddings/resizing, but one is inconsistent serialization by device while the other is resize_token_embeddings not propagating to decoder embeddings." + "reason": "Both involve embeddings/tied weights, but one is serialization-dependent and the other is resize_token_embeddings not updating decoder embeddings." }, { "left": "issue:43653", "right": "issue:44162", "accept": false, - "reason": "Tokenizer special-token registration bug versus a broken ESM2 model. No shared underlying defect." + "reason": "Different tokenizer/model failures: BigBird tokenizer special-token handling vs ESM2 being broadly broken." }, { "left": "issue:44368", "right": "issue:44977", "accept": false, - "reason": "A tied-weights warning is unrelated to flash-attention generation failure." + "reason": "A warning about tie_word_embeddings is unrelated to Qwen3.5 flash-attention generation breakage." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Both mention cache/generation, but one is missing GenerationMixin cache in chunked prefill while the other is a server KV-cache continuation indexing crash." + "reason": "Both are generation/cache-related, but the concrete bugs differ: missing GenerationMixin cache vs wrong tensor indexing in serve continuation." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "Import-related, but one is a missing image_utils import and the other is exception handling hiding protobuf tokenizer errors." + "reason": "Different import/tokenizer issues: missing image_utils import vs protobuf decode error masking real tokenizer exceptions." }, { "left": "issue:43441", "right": "issue:43606", "accept": false, - "reason": "Different model-specific failures: FlashAttention incompatibility versus CPU offload device mismatch." + "reason": "Different model-specific regressions: FlashAttention failure for Ministral vs CPU offload device mismatch for bark-small." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Both are tokenizer/decoder issues, but one is whisper timestamp decoding and the other is Kimi-K2.5 codec/regex regression." + "reason": "Different tokenizer/audio edge cases: Whisper timestamp decode crash vs Kimi-K2.5 codec/fix_mistral_regex regression." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "Different generation bugs: sync_gpus/update_model_kwargs ordering versus missing cache during chunked prefill." + "reason": "Both touch generation internals, but one is sync_gpus/model_kwargs handling and the other is chunked_prefill cache availability." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "Weight-shape mismatch loading a VL model is not the same as a tied-embeddings warning in LoRA fine-tuning." + "reason": "Weight-shape mismatch on a specific VL model is not the same bug as a tied-weights warning in a Qwen3.5 LoRA workflow." }, { "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "Both are save_pretrained-related, but tokenizer_class metadata mismatch and processor file omission are distinct bugs." + "reason": "Both are save_pretrained-related, but one is tokenizer_config metadata mismatch while the other is processor file omissions." }, { "left": "issue:43673", "right": "issue:45278", "accept": false, - "reason": "One is generation cache behavior; the other is import failures after upgrade. Different subsystems and symptoms." + "reason": "A generation cache regression is not the same as broad import errors after upgrading Transformers." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Custom model initialization breakage is not the same as ESM2 being broken; too broad to merge." + "reason": "Both are broad breakages, but they affect different areas: custom model initialization vs an ESM2-specific regression." }, { "left": "issue:43381", "right": "issue:45292", "accept": false, - "reason": "Gradient checkpointing in eval mode and token embedding resize behavior are unrelated." + "reason": "Gradient-checkpointing eval-mode behavior is unrelated to token embedding resizing." }, { "left": "issue:43381", "right": "issue:45335", "accept": false, - "reason": "Different functionality and failure modes; no shared underlying bug." + "reason": "These are separate bugs: eval-mode gradient checkpointing vs resize_token_embeddings not updating decoder embeddings." }, { "left": "issue:42673", "right": "issue:43704", "accept": true, - "reason": "Same title and same Qwen3ForCausalLM VRAM leak symptom; these are duplicates of the same bug." + "reason": "Same model, same symptom, same title: Qwen3ForCausalLM leaking VRAM across multiple dataloader threads." }, { "left": "issue:28282", "right": "issue:30990", "accept": false, - "reason": "An AutoModel missing-PyTorch ImportError is unrelated to Sentence Transformers getting stuck loading." + "reason": "ImportError about missing PyTorch is unrelated to a Sentence Transformers loading hang." }, { "left": "issue:44361", "right": "issue:44749", "accept": false, - "reason": "Tokenizer AttributeError on tasks versus a performance regression in filtering data after upgrade; not the same issue." + "reason": "Different issues: a tokenizer AttributeError on tasks vs a general slowdown after upgrading Transformers." }, { "left": "issue:44077", "right": "issue:45003", "accept": false, - "reason": "A patchtsmixer post_init policy issue is unrelated to unsafe sys.modules access in modeling_utils." + "reason": "Optional post_init policy for patchtsmixer is unrelated to unsafe sys.modules access in modeling_utils." }, { "left": "issue:44749", "right": "issue:45310", "accept": false, - "reason": "One is a slowdown in filtering data; the other is a Qwen3.5 MoE from_pretrained error. Different code paths." + "reason": "General preprocessing slowdown is not the same underlying bug as a Qwen3.5 MoE from_pretrained error." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "Generic bug report versus a specific gemma-4 zero3 initialization problem." + "reason": "The first is a vague, underspecified report; the second is a specific gemma-4 zero3 from_pretrained failure." }, { "left": "issue:44038", "right": "issue:44623", "accept": false, - "reason": "Qwen3-VL-Moe loading bug and processor.save_pretrained missing files are unrelated." + "reason": "A Qwen3-VL-Moe transformers-5 compatibility bug is unrelated to missing files on processor save_pretrained." }, { "left": "issue:43475", "right": "issue:45381", "accept": false, - "reason": "Both involve video inputs, but they concern different models and different bugs." + "reason": "Both are vision/video-related, but they target different models and different failure modes." }, { "left": "issue:43475", "right": "issue:43643", "accept": false, - "reason": "Missing attribute in SAM 3 Video output is unrelated to trust_remote_code AutoConfig field loss." + "reason": "A missing vision-encoder output attribute is not the same bug as trust_remote_code dropping fields from AutoConfig." }, { "left": "issue:43701", "right": "issue:44749", "accept": false, - "reason": "Checkpoint key mismatch and data filtering slowdown are unrelated." + "reason": "Checkpoint resume key mismatch is unrelated to slow filtering after upgrade." }, { "left": "issue:45081", "right": "issue:45103", "accept": false, - "reason": "Both raise AttributeError, but one is Mistral regex patching and the other is auto_docstring handling future annotations." + "reason": "Both are AttributeErrors, but they arise in unrelated subsystems: tokenizer regex patching vs auto-docstring processing." }, { "left": "issue:42371", "right": "issue:45092", "accept": false, - "reason": "TF32 setting guidance and InternVL2 meta-initialization incompatibility are different issues with no shared code path." + "reason": "TF32 settings guidance is unrelated to remote-code checkpoint incompatibility with v5 meta initialization." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary stays conservative and is supported by the packet: it characterizes the cluster as mostly unrelated regression reports, and the single accepted duplicate pair is plainly grounded by identical titles/symptoms. The soft-edge rejections are also cautious and tied to distinct titles/code paths rather than overstating duplicate evidence. One small caveat: calling issue 45278 a 'canonical' representative is still a bit strong, but the analyst already hedges that appropriately." + "feedback": "The cluster summary is grounded in the packet: the items are mostly separate Transformers v5-era regressions, and the only clearly duplicate pair marked true is the Qwen3ForCausalLM VRAM leak issues (42673/43704). The false soft-edge calls are conservative and generally distinguish different subsystems or failure modes without overclaiming." }, "evaluator_used": true, "retried": false, @@ -9865,8 +9865,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -9959,7 +9959,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -10288,12 +10288,12 @@ "issue:41628|issue:43824", "issue:42831|issue:45310" ], - "prepared_review_unit_hash": "2b1b40d7cc59c10d43e9ec7243abd141a8f4bf4fefad174565146fdf37be9e95", + "prepared_review_unit_hash": "01eb065c064023df022a1b2aa9c1a51620fc9ea362440a9a1c4f385826476729", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -10301,7 +10301,7 @@ "node_count": 47, "item_count": 47, "soft_pair_count": 35, - "serialized_chars": 37410, + "serialized_chars": 37412, "estimated_input_tokens": 9353, "estimated_eval_tokens": 18962 }, @@ -10310,204 +10310,204 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are a heterogeneous mix of unrelated tokenizer, import, multimodal, save/load, and model-regression reports. No soft pair looks like the same underlying bug/change, so all candidates are rejected as duplicate matches.", - "confidence": 0.96, - "canonical_issue_reason": "No single canonical issue; the set spans many unrelated bugs and regressions rather than one underlying defect.", + "summary": "This cluster is mostly a loose collection of Transformers v5 regression reports, especially around tokenizer/processor loading and save/load behavior, plus several unrelated model-specific bugs. There are no PRs, and none of the soft pairs look like true duplicates of the same concrete fix.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43723 is the clearest umbrella report for the cluster\u2019s tokenizer-loading regressions in v5. It is broad enough to represent the shared load-path theme while still being a concrete user-facing failure.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a strong global representative because there is no shared code-path or symptom across the cluster.", + "best_issue_reason": "issue:43723 is the best representative issue because it targets the core AutoTokenizer.from_pretrained regression and overlaps conceptually with several nearby tokenizer-related reports without being tied to a single model family.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "Both are tokenizer-related, but one is a generic AutoTokenizer load failure and the other is a model-specific special-token regression; different bugs." + "reason": "Both are tokenizer regressions in v5, but one is loading failure and the other is BOS/EOS handling; different code paths and symptoms." }, { "left": "issue:42898", "right": "issue:44779", "accept": false, - "reason": "Both mention v5 tokenizer behavior, but one is about clean_up_tokenization_spaces and the other about DeepSeek output correctness; not the same defect." + "reason": "One is about clean_up_tokenization_spaces behavior, the other about Deepseek tokenizer outputs; same broad area, different bug." }, { "left": "issue:45137", "right": "issue:45276", "accept": false, - "reason": "DeepSpeed ZeRO3 deque failure is unrelated to resize_token_embeddings not updating Gemma4 embeddings." + "reason": "ZeRO3 deque IndexError and gemma4 resize_token_embeddings behavior are unrelated failures." }, { "left": "issue:43874", "right": "issue:45092", "accept": false, - "reason": "Both touch multimodal models, but one is a missing image-patch method and the other is a meta-init incompatibility for old InternVL2 checkpoints." + "reason": "Different model families and different problems: missing image-processor method vs remote-code checkpoint/meta-init incompatibility." }, { "left": "issue:44077", "right": "issue:44242", "accept": false, - "reason": "PatchTSMixer post_init allowance and MoE load-balancing loss gating are different model/config bugs." + "reason": "PatchTSMixer post_init validation and MoE load-balancing loss are distinct implementation issues." }, { "left": "issue:42898", "right": "issue:44448", "accept": false, - "reason": "Tokenizer cleanup-space behavior and Pegasus output differences are separate regressions." + "reason": "Tokenizer cleanup behavior and Pegasus output differences are not the same concrete bug." }, { "left": "issue:41628", "right": "issue:45459", "accept": false, - "reason": "Importing AutoImageProcessor and masked tokenizer exceptions are different failure modes in different code paths." + "reason": "AutoImageProcessor import failure and tokenizer protobuf error masking are separate import/error-handling issues." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "FP8 MoE save_pretrained and tokenizer_class mismatch in tokenizer_config.json are unrelated save-path bugs." + "reason": "FP8 MoE save_pretrained failure is unrelated to tokenizer_class metadata mismatch on save." }, { "left": "issue:44442", "right": "issue:45459", "accept": false, - "reason": "AutoTokenizer failing for a specific tokenizer class is not the same bug as hiding protobuf-related tokenizer errors." + "reason": "A specific tokenizer load failure is not the same as generic exception masking when protobuf is missing." }, { "left": "issue:42898", "right": "issue:43295", "accept": false, - "reason": "Clean-up-tokenization-space behavior changes are unrelated to processor.tokenizer/image-passing regression." + "reason": "clean_up_tokenization_spaces behavior and processor.tokenizer/image passing regression are different features." }, { "left": "issue:43479", "right": "issue:43644", "accept": false, - "reason": "Phi4Multimodal default config initialization and junk-filled non-persistent buffers are unrelated." + "reason": "Phi4MultimodalConfig default-init bug and junk non-persistent buffers are unrelated." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "FP8 MoE save_pretrained failure and processor.save_pretrained missing files are different serialization bugs." + "reason": "Saving FP8 MoE checkpoints and processor.save_pretrained missing files are different save-path bugs." }, { "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Unsupported center argument in a feature extractor is unrelated to the auto_docstring annotations crash." + "reason": "Feature extractor center-arg crash and auto-docstring annotation crash are unrelated." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "FP8 accuracy issues and missing processor save files are different problems." + "reason": "FineGrainedFP8 accuracy loss is not the same as processor serialization missing files." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "ONNX module import failure and missing PyTorch dependency are distinct import errors." + "reason": "Both are import errors, but one is a missing module path and the other is a missing PyTorch dependency; not the same bug." }, { "left": "issue:41628", "right": "issue:42757", "accept": false, - "reason": "Missing AutoImageProcessor export and missing is_offline_mode export from huggingface_hub are separate import regressions." + "reason": "Different missing imports from different packages and symbols." }, { "left": "issue:44297", "right": "issue:45310", "accept": false, - "reason": "Tokenizer save metadata mismatch is unrelated to Qwen3.5 MoE from_pretrained loading failure." + "reason": "Tokenizer save metadata mismatch and Qwen3.5 from_pretrained failure are different regressions." }, { "left": "issue:44483", "right": "issue:45406", "accept": false, - "reason": "Chat-completions API failure and Gemma4Processor missing _tokenizer are different regressions." + "reason": "Chat-completions request handling and Gemma4Processor _tokenizer attribute errors are unrelated." }, { "left": "issue:44222", "right": "issue:44484", "accept": false, - "reason": "FP8 MoE save_pretrained behavior is unrelated to the default max_shard_size question." + "reason": "FP8 checkpoint saving and max_shard_size defaults are not the same issue." }, { "left": "issue:44263", "right": "issue:44360", "accept": false, - "reason": "Both involve DSA indexer wording, but one is a torch.split return-value bug and the other is a missing ReLU; not the same issue." + "reason": "Both mention DSA indexer, but the concrete operations and failures differ (torch.split vs missing ReLU)." }, { "left": "issue:43723", "right": "issue:44977", "accept": false, - "reason": "Tokenizer loading regression and Qwen3.5 flash-attention generation failure are unrelated." + "reason": "Tokenizer loading regression and flash-attention generation bug are different code paths." }, { "left": "issue:44263", "right": "issue:45092", "accept": false, - "reason": "GlmMoeDsaIndexer torch.split behavior is unrelated to InternVL2 meta-initialization incompatibility." + "reason": "GlmMoeDsaIndexer torch.split issue is unrelated to InternVL2 remote-code/meta-init incompatibility." }, { "left": "issue:44514", "right": "issue:45103", "accept": false, - "reason": "Qwen2_5_VL batched chat-template crash and auto_docstring annotations crash are separate bugs." + "reason": "Batched processor chat-template crash and auto-docstring annotation crash are unrelated." }, { "left": "issue:43479", "right": "issue:44913", "accept": false, - "reason": "Phi4Multimodal config defaults and GPTNeoX rotary_pct reload bug affect different components." + "reason": "Config default initialization and GPTNeoX rotary_pct reload bug are different problems." }, { "left": "issue:44295", "right": "issue:44623", "accept": false, - "reason": "Position_ids buffer readback error is unrelated to missing files from processor.save_pretrained." + "reason": "position_ids buffer read error and processor.save_pretrained missing files are not the same failure." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "Generic tokenizer loading failure and Gemma-3 eos_token_id mismatch are different regressions." + "reason": "Tokenizer loading failure and eos_token_id config mismatch are distinct." }, { "left": "issue:44261", "right": "issue:45092", "accept": false, - "reason": "MLA layernorm epsilon precision issue is unrelated to InternVL2 meta-init compatibility." + "reason": "MLA precision/config epsilon issue and remote-code meta-init incompatibility do not match." }, { "left": "issue:43723", "right": "issue:44991", "accept": false, - "reason": "These are both tokenizer-related, but they describe different models and different failure modes." + "reason": "Both are tokenizer load regressions in v5, but one is a general AutoTokenizer failure and the other is a model-specific tokenizer load error; not enough evidence of one underlying bug." }, { "left": "issue:30990", "right": "issue:38175", "accept": false, - "reason": "Sentence Transformers loading hang and siglip2 zero-probability outputs are unrelated." + "reason": "Sentence-Transformers loading hang and SigLIP2 zero probabilities are different model issues." }, { "left": "issue:44373", "right": "issue:44485", "accept": false, - "reason": "Wrong docstring for position_ids is documentation-only; GLM-5 RoPE is an implementation bug." + "reason": "Docstring wording for position_ids and GLM-5 RoPE implementation are unrelated." }, { "left": "issue:43723", "right": "issue:44442", "accept": false, - "reason": "AutoTokenizer load failure for one tokenizer class is distinct from FastSpeech2ConformerTokenizer load failure." + "reason": "General AutoTokenizer loading regression and FastSpeech2ConformerTokenizer-specific load failure are related only at a broad level, not clearly the same bug." }, { "left": "issue:45092", "right": "issue:45357", "accept": false, - "reason": "InternVL2 meta-init incompatibility and Qwen3.5 visual-encoder save_pretrained key errors are different code paths." + "reason": "Remote-code checkpoint incompatibility and incorrect visual encoder keys on save are different Qwen3.5 issues." }, { "left": "issue:42886", @@ -10519,13 +10519,13 @@ "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Missing AutoImageProcessor export and missing Qwen2_5_VLForConditionalGeneration export are separate import issues." + "reason": "Missing AutoImageProcessor import and missing Qwen2_5_VLForConditionalGeneration import are separate symbol-resolution problems." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "FineGrainedFP8 accuracy regression and Qwen3.5 MoE from_pretrained failure are unrelated." + "reason": "FineGrainedFP8 accuracy issue and Qwen3.5 MoE from_pretrained error are unrelated bugs." } ] }, @@ -10544,8 +10544,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -10640,7 +10640,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -10891,8 +10891,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -10984,7 +10984,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -11307,12 +11307,12 @@ "issue:44117|issue:44987", "issue:43931|issue:44410" ], - "prepared_review_unit_hash": "17617c714e78407083df12c6dbfbc0bca210d168aa5c526ca9294244c543267b", + "prepared_review_unit_hash": "06eeae27479a57baa601cb2f68554d46003037d71a6d4a4eca4edc7ac1bb048c", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -11320,225 +11320,225 @@ "node_count": 48, "item_count": 48, "soft_pair_count": 34, - "serialized_chars": 37596, - "estimated_input_tokens": 9399, - "estimated_eval_tokens": 19054 + "serialized_chars": 37598, + "estimated_input_tokens": 9400, + "estimated_eval_tokens": 19056 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly heterogeneous regression and import/tokenizer reports; I do not see enough evidence to merge any soft edge as a true duplicate. The closest theme is tokenizer behavior in v5, but the symptoms still look too different to consolidate confidently.", - "confidence": 0.57, - "canonical_issue_reason": "issue:43066 is the most concrete root-cause-oriented tokenizer regression in the set (wrong decoder type in v5) and is the best representative of the small tokenizer-behavior subcluster.", + "summary": "This cluster is mostly a loose collection of Transformers v5 regressions and API/import/tokenizer bugs, not a set of true duplicates. The strongest common thread is broad import/API breakage around the v5 transition, but the individual reports target different code paths and symptoms.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 45278 is the best umbrella representative: it is broad, explicitly about multiple import errors after upgrading to 5.5.0, and matches the cluster\u2019s general v5 API-breakage theme better than the narrower model-specific reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43066 is the clearest single bug report among the issues and is more specific and actionable than the symptom-level tokenizer reports.", + "best_issue_reason": "Issue 45278 is the most suitable global representative because it is the broadest, most general regression report in the set and can stand in for the cluster\u2019s common import/API compatibility problem.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44484", "right": "issue:45310", "accept": false, - "reason": "Unrelated topics: shard-size/save_pretrained behavior vs a Qwen3.5 from_pretrained loading error." + "reason": "Both mention Qwen3.5/v5.x regressions, but one is about `max_shard_size` behavior and the other is a `from_pretrained` model-loading error; different failure modes." }, { "left": "issue:44829", "right": "issue:45216", "accept": false, - "reason": "FlashAttention-3 training collapse and a checkpoint save regression are different code paths." + "reason": "Both involve training/checkpoint behavior on v5, but one is flash-attention-induced degenerate training and the other is incorrect `save_pretrained` output for Qwen3.5; not the same bug." }, { "left": "issue:39401", "right": "issue:43421", "accept": false, - "reason": "Offset-mapping bug and runtime special-token/post-processor sync bug are related only at a high level." + "reason": "Both are tokenizer-related, but one is a wrong `offset_mapping` bug and the other is runtime post-processor updates when special tokens change; different code paths." }, { "left": "issue:38617", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different APIs." + "reason": "Both are import errors, but they concern different symbols (`layer_type_validation` vs `AutoImageProcessor`) and likely separate broken exports." }, { "left": "issue:44117", "right": "issue:45081", "accept": false, - "reason": "Tokenizer mapping fallback failure and Mistral regex patch crash are distinct tokenizer-loading bugs." + "reason": "Both affect tokenizer loading, but one is a mapping-name/`from_pretrained` assumption and the other is a Mistral regex patch crash on a specific tokenizer object; not the same issue." }, { "left": "issue:42673", "right": "issue:43582", "accept": false, - "reason": "VRAM leak in multi-threaded dataloader use vs Apple Silicon TypeError; no shared concrete bug." + "reason": "One is a VRAM leak in multi-threaded dataloaders, the other is a TypeError in Apple Silicon warmup; unrelated runtime problems." }, { "left": "issue:42673", "right": "issue:43577", "accept": false, - "reason": "Memory leak and dtype propagation bug are different failure modes." + "reason": "Both mention model loading/runtime, but one is a VRAM leak and the other is dtype propagation for BLIP2 components; distinct bugs." }, { "left": "issue:44410", "right": "issue:45310", "accept": false, - "reason": "Missing projections in qwen3next layer 0 is unrelated to a Qwen3.5 MoE loading error." + "reason": "Both involve Qwen3.5/Qwen3-next style model loading, but one is missing projections in a layer and the other is a `from_pretrained` MoE loading error; not the same fix." }, { "left": "issue:43408", "right": "issue:43742", "accept": false, - "reason": "Model-type warning and key error loading a different model are not the same issue." + "reason": "Both are model-loading errors, but one is a sam3_video/sam3_tracker type mismatch warning and the other is a MobileLLM key error; different causes." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "ImportError for a config symbol and audio feature extraction failure are unrelated." + "reason": "Both touch low-level preprocessing/import internals, but one is an import failure and the other is an fbank feature extraction issue; not duplicate." }, { "left": "issue:43937", "right": "issue:44496", "accept": false, - "reason": "Invalid GenerationConfig and missing model_type in config.json are different root causes." + "reason": "Both are model/config loading errors, but one is invalid GenerationConfig for GLM-5 and the other is an unrecognized model/config.json issue for Olmo-Hybrid; unrelated." }, { "left": "issue:42371", "right": "issue:44261", "accept": false, - "reason": "TF32 API guidance issue and MLA epsilon precision bug do not share the same code path." + "reason": "Both mention TF32/precision, but one is about new API settings for TF32 behavior and the other is missing `rms_norm_eps` in MLA q_a_layernorm; different problems." }, { "left": "issue:42175", "right": "issue:42222", "accept": false, - "reason": "Packaging/backend dependency omission vs VitPose model breakage are different problems." + "reason": "One is about TensorFlow not being installed with a torch extra, the other is broken VitPose models; no shared underlying bug." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "Chat/completions contract regression and streaming inference failure are not the same concrete bug." + "reason": "Both mention chat/completions API behavior, but one is a v5.3 request acceptance issue and the other is streaming inference failure on Qwen3.5-0.8B; different endpoints/symptoms." }, { "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "3d_parallel.py execution failure and a testing_utils bug are unrelated." + "reason": "One cannot run `3d_parallel.py`, the other is a testing_utils bug; no shared code-path." }, { "left": "issue:44933", "right": "issue:45278", "accept": false, - "reason": "Specific missing import from image_utils is broader only in theme, not the same bug as general import failures." + "reason": "Both are import-related, but 44933 is a missing image_utils export while 45278 is a broad upgrade-related import-failure report; not the same concrete bug." }, { "left": "issue:44484", "right": "issue:45478", "accept": false, - "reason": "max_shard_size behavior question is unrelated to the Qwen3.5 MoE from_pretrained regression." + "reason": "Both concern Qwen3.5/v5.4 regressions, but one is about shard-size defaults and the other is a MoE `from_pretrained` error; separate issues." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Both concern tokenizer behavior in v5, but the titles point to different concrete failures and the evidence is too weak to merge." + "reason": "Both are tokenizer behavior regressions across v5, but one is decoder type selection and the other is changed tokenization output; related theme, not same bug." }, { "left": "issue:43673", "right": "issue:45341", "accept": false, - "reason": "Generation cache missing in chunked_prefill and a testing_utils bug are unrelated." + "reason": "One is a GenerationMixin cache regression in chunked prefill, the other is a testing utility bug; unrelated." }, { "left": "issue:43097", "right": "issue:44493", "accept": false, - "reason": "Removed config API and unexpected position-id keys are different regressions." + "reason": "Both mention v5 regressions and position-related behavior, but one is a removed config option and the other is unexpected position-id keys; not the same concrete change." }, { "left": "issue:42222", "right": "issue:45459", "accept": false, - "reason": "VitPose breakage and protobuf-related tokenizer error handling are unrelated." + "reason": "One is broken VitPose models, the other is tokenizer error masking when protobuf is missing; different subsystems and fixes." }, { "left": "issue:44410", "right": "issue:45478", "accept": false, - "reason": "Missing qwen3next projections and Qwen3.5 MoE load failure are different model bugs." + "reason": "Both are Qwen3.5/Qwen3-next loading regressions, but one is missing layer projections and the other is a Qwen3.5 MoE `from_pretrained` failure; separate bugs." }, { "left": "issue:43986", "right": "issue:44484", "accept": false, - "reason": "AutoProcessor crash without torchvision and a save_pretrained shard-size question are unrelated." + "reason": "One is a missing torchvision dependency causing a confusing AutoProcessor crash, the other is a checkpoint shard-size question; unrelated." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "FlashAttention failure in Ministral and degenerate training with flash_attention_3 are different issues." + "reason": "One is FlashAttention failure for Ministral-3, the other is degenerate training with flash_attention_3 in sequence classification; similar buzzwords but different concrete code paths." }, { "left": "issue:43874", "right": "issue:44261", "accept": false, - "reason": "Missing image-patch method and missing rms_norm_eps are separate multimodal-model bugs." + "reason": "One is a missing method on GLM46VImageProcessorFast, the other is an MLA layernorm epsilon precision issue; distinct model bugs." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "BF16 compile warning and model-type mismatch warning are unrelated." + "reason": "One is a PyTorch warning when compiling bf16 models, the other is a sam3_video/sam3_tracker type warning; unrelated warnings." }, { "left": "issue:42222", "right": "issue:42994", "accept": false, - "reason": "VitPose breakage and quantized model saving failure are different code paths." + "reason": "One is broken VitPose models, the other is quantized model saving failure; different functionality." }, { "left": "issue:44263", "right": "issue:44485", "accept": false, - "reason": "torch.split return-value handling and GLM RoPE implementation are not the same bug." + "reason": "One is about `torch.split()` return values in a specific indexer, the other is GLM-5 RoPE implementation; not the same bug." }, { "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Missing AutoImageProcessor import and PreTrainedConfig type-checking regression are unrelated." + "reason": "Both are API/import compatibility issues in v5, but one is a missing `AutoImageProcessor` import and the other is `PreTrainedConfig` type checking; distinct symptoms and fixes." }, { "left": "issue:45003", "right": "issue:45341", "accept": false, - "reason": "Unsafe sys.modules access and a testing_utils bug are different changes." + "reason": "One is unsafe `sys.modules[]` access in modeling_utils, the other is a small testing_utils bug; no shared underlying problem." }, { "left": "issue:43097", "right": "issue:43452", "accept": false, - "reason": "Config API removal and gguf_file loading breakage are not the same failure." + "reason": "One is a removed config attribute warning, the other is a gguf_file path causing `from_pretrained` failures for tokenizer/model loading; separate regressions." }, { "left": "issue:43986", "right": "issue:45341", "accept": false, - "reason": "AutoProcessor/torchvision crash and testing_utils bug do not share a concrete cause." + "reason": "One is a video-model crash without torchvision, the other is a testing_utils issue; unrelated." }, { "left": "issue:44117", "right": "issue:44987", "accept": false, - "reason": "Tokenizer mapping None and a specific model loading failure are too far apart to treat as duplicates." + "reason": "Both involve tokenizer/model loading assumptions, but 44117 is a generic mapping-name None case while 44987 is a specific failure on `physical-intelligence/fast`; not clearly the same bug." }, { "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and qwen3next missing projections are distinct model-loading problems." + "reason": "Both are Qwen-related model-loading issues, but one is weight-shape mismatch in Qwen3-VL and the other is missing projections in qwen3next; different model families and failures." } ] }, @@ -11645,12 +11645,12 @@ "issue:42886|issue:43381", "issue:43208|issue:43550" ], - "prepared_review_unit_hash": "746c51e101e6414d5461c4a578fcec9d540fc1bb193e53395b42eae2a5154dfc", + "prepared_review_unit_hash": "9a17454e8a2c2bad6455a46dc029d4ea5cb936f9750927ebc7f473caa016505c", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -11667,60 +11667,60 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated Transformers bug reports that happen to share superficial keywords (imports, loading, config, attention/backends, tokenizer/model variants). None of the suggested soft pairs look like the same underlying bug or change, so no duplicate cluster should be merged.", - "confidence": 0.96, - "canonical_issue_reason": "No canonical issue: the set does not form a true duplicate cluster, and the soft pairs span distinct code paths and failure modes.", + "summary": "These items are mostly unrelated Transformers regressions and API breakages rather than duplicates. I reject every soft edge because the paired issues affect different symbols, code paths, models, or failure modes. The best representative issue is 43873 because it is the broadest, most active runtime bug report in the set.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43873 is the broadest and most actively discussed bug report here, with multiple inbound refs and a clear runtime failure, so it is the best representative issue for the set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the most substantial and still-open report with broad discussion, but it is not a duplicate anchor for the rest of the set.", + "best_issue_reason": "issue:43873 has the strongest combination of scope, activity, and actionable bug detail; it is more representative than the narrow import/config regressions elsewhere in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43335", "right": "issue:45071", "accept": false, - "reason": "Different problems: a SwitchTransformers single-layer config bug vs a v5 PreTrainedConfig type-checking regression." + "reason": "Different bugs: one is SwitchTransformers sparse-layer construction, the other is PretrainedConfig type-checking in v5.4.0." }, { "left": "issue:43408", "right": "issue:44368", "accept": false, - "reason": "One is a sam3_video/sam3_tracker type mismatch warning; the other is a tie_word_embeddings warning during Qwen LoRA fine-tuning." + "reason": "Both mention warnings, but they concern unrelated model/config mismatches in different models and code paths." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Both involve Qwen VL models, but the failures are different: weight-shape mismatch vs a separate Qwen3-VL-MoE issue." + "reason": "Separate failures: Qwen3-VL-30B-A3B-Instruct weight-shape mismatch vs a Qwen3-VL-Moe issue; not the same concrete bug." }, { "left": "issue:43986", "right": "issue:45372", "accept": false, - "reason": "Both are processor-loading crashes, but one is missing torchvision and the other is a missing ReasoningEffort import from mistral_common." + "reason": "Both are processor-loading crashes, but one is about missing torchvision for video models and the other is a mistral_common import error for Gemma 4." }, { "left": "issue:44829", "right": "issue:45245", "accept": false, - "reason": "Degenerate training with flash_attention_3 is unrelated to the categories > 2^24 runtime limit." + "reason": "Unrelated problems: flash_attention_3 training degeneration vs category-count overflow at 2^24." }, { "left": "issue:43874", "right": "issue:44263", "accept": false, - "reason": "Different GLM components: image-processor token counting vs a torch.split indexing bug in GlmMoeDsaIndexer." + "reason": "Different components and symptoms: a missing image-processor method vs a torch.split return-value issue in GlmMoeDsaIndexer." }, { "left": "issue:43976", "right": "issue:45071", "accept": false, - "reason": "Python-version compatibility breakage is not the same as a PretrainedConfig type-checking failure." + "reason": "These are different compatibility regressions: Python version support vs type-checking breakage in PretrainedConfig." }, { "left": "issue:44464", "right": "issue:45071", "accept": false, - "reason": "Chunked-generation inconsistency under compile is a different code path from config type checking." + "reason": "Chunked generation with compiled forward is unrelated to PretrainedConfig type checking." }, { "left": "issue:43531", @@ -11732,139 +11732,139 @@ "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "FSDP2/PEFT optimizer-state corruption is a different bug from Liger Kernel not being applied with model_init." + "reason": "Different training issues: FSDP2/PEFT optimizer-state corruption vs Liger Kernel not being applied with model_init." }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but for different symbols and modules: layer_type_validation vs is_offline_mode." + "reason": "Both are import errors, but for different missing names from different modules and likely different root causes." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "Missing rms_norm_eps causing precision drift is not the same as a GLM-5 RoPE implementation discussion." + "reason": "Different model bugs: missing rms_norm_eps precision issue vs GLM-5 RoPE implementation discussion." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "Different model config bugs: missing attn_qkv/attn_gate projections vs a missing deepstack_visual_indexes field." + "reason": "One is missing attention projections in qwen3next; the other is a missing config field in Qwen3_5MoeVisionConfig." }, { "left": "issue:44704", "right": "issue:45103", "accept": false, - "reason": "AutoProcessor kwargs forwarding and an auto_docstring annotation crash are unrelated issues." + "reason": "Both involve kwargs processing, but one is AutoProcessor forwarding args to cached_file and the other is an auto_docstring annotation crash." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "local_files_only still making API requests is unrelated to UMT5Encoder missing embed_tokens.weight." + "reason": "Different loading problems: unwanted API requests despite local_files_only vs missing embed_tokens.weight in UMT5Encoder.from_pretrained." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "AddedToken() kwarg duplication and TOKENIZER_MAPPING_NAMES returning None are different tokenizer bugs." + "reason": "Tokenizers.AddedToken keyword duplication is unrelated to TOKENIZER_MAPPING_NAMES returning None." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Missing torchvision during AutoProcessor loading is unrelated to tokenizer mapping name assumptions." + "reason": "Processor loading without torchvision is a different failure mode from tokenizer mapping assumptions in from_pretrained." }, { "left": "issue:38617", "right": "issue:44351", "accept": false, - "reason": "Different import failures: configuration_utils.layer_type_validation vs transformers.HybridCache." + "reason": "Both are import-name failures, but they concern different symbols (layer_type_validation vs HybridCache) and different release breaks." }, { "left": "issue:43582", "right": "issue:45341", "accept": false, - "reason": "AppleSilicon caching_allocator_warmup TypeError is unrelated to the testing_utils bug." + "reason": "Apple Silicon caching_allocator_warmup TypeError is unrelated to the testing_utils bug." }, { "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Both mention Qwen variants, but they affect different architectures and failure modes." + "reason": "Different Qwen-family issues: Qwen3-VL-Moe regression vs missing projections in qwen3next." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "A missing tie_embeddings_and_encoder_decoder warning is not the same as quantization offloading behavior." + "reason": "tie_embeddings removal is a config/API change, while offloading with quantization is a runtime memory-management bug." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Missing embed_tokens.weight and max_shard_size default behavior are unrelated." + "reason": "Missing embed_tokens.weight on load is unrelated to save_pretrained shard-size defaults." }, { "left": "issue:43986", "right": "issue:45290", "accept": false, - "reason": "Missing torchvision on video-model loading is unrelated to apply_chat_template crashing on tool-call assistant messages." + "reason": "Video-model processor dependency crash and chat-template tool-call crash are separate code paths." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Insufficient evidence of the same bug; a tokenizer decoder-type issue and a reproduction of another issue are not the same concrete failure." + "reason": "The isolated reproduction is too vague to treat as the same concrete tokenizer-decoder bug as 43066." }, { "left": "issue:38617", "right": "issue:43097", "accept": false, - "reason": "ImportError for layer_type_validation is unrelated to tie_embeddings_and_encoder_decoder removal." + "reason": "ImportError for layer_type_validation is unrelated to the tie_embeddings_and_encoder_decoder removal." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Pipeline translation-task messaging and saving Pipeline objects are different behaviors." + "reason": "Pipeline translation-task messaging is unrelated to save_pretrained pipeline serialization." }, { "left": "issue:43352", "right": "issue:44380", "accept": false, - "reason": "Both involve attention backends, but one is unsupported Flash Attention 2.0 for NemotronH and the other is GPT2 attention scaling being ignored." + "reason": "Nemotron Flash Attention 2.0 support and GPT2 attention scaling under SDPA/FlashAttention are different backend/model issues." }, { "left": "issue:43097", "right": "issue:43901", "accept": false, - "reason": "A removed config field is not the same as stale docs mentioning return_all_scores." + "reason": "tie_embeddings removal and TextClassificationPipeline return_all_scores docs mismatch are unrelated." }, { "left": "issue:43012", "right": "issue:43550", "accept": false, - "reason": "A bfloat16 precision warning is unrelated to Bamba-9B-v2 failing under torch.compile with SDPA." + "reason": "A bfloat16 precision warning and a Bamba SDPA compile failure are different problems." }, { "left": "issue:43012", "right": "issue:44368", "accept": false, - "reason": "These are different warnings with different causes: PyTorch precision warning vs tie_word_embeddings config advice." + "reason": "The bfloat16 PyTorch warning is not the same as the tie_word_embeddings warning in Qwen3.5 LoRA fine-tuning." }, { "left": "issue:42886", "right": "issue:43381", "accept": false, - "reason": "Offline-cache loading failure and gradient-checkpointing-in-eval are unrelated." + "reason": "Offline cache loading failure and eval-mode gradient checkpointing are unrelated." }, { "left": "issue:43208", "right": "issue:43550", "accept": false, - "reason": "xLSTM training bugs and a Bamba compile/SDPA failure are distinct model-specific issues." + "reason": "xLSTM training blockers and Bamba compile/SDPA failure are distinct model-specific bugs." } ] }, @@ -11883,8 +11883,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -11980,7 +11980,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -12315,12 +12315,12 @@ "issue:44355|issue:44749", "issue:45125|issue:45375" ], - "prepared_review_unit_hash": "b39e3098c4da62b259e1c3b474c0d8a46ac54abb9b42f44b11f451c68f94ab0f", + "prepared_review_unit_hash": "acedf5bb454355d7c7e7b2cecbdb20b3594c4b165acbcafc2eb2e708f5f60810", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -12337,217 +12337,226 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of distinct Transformer regressions and environment-specific failures that only overlap at a broad 'loading/import' theme. I do not see any soft pair that clearly describes the same concrete bug or change, so all soft edges are rejected. The best cluster representative is the broad upgrade/import umbrella issue.", - "confidence": 0.74, - "canonical_issue_reason": "issue:45278 is the broadest and most representative report in the cluster: many import errors after upgrading from 4.57.0 to 5.5.0. It reads like an umbrella for the nearby loading/import regression reports.", + "summary": "This cluster is mostly a noisy mix of Transformers v5 regression reports around importing, loading, and model-specific failures. Most soft pairs are only superficially similar; the only plausible duplicate-like pair is the Qwen3.5 MoE from_pretrained/_tp_plan reports.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45278 is the broadest and most representative issue in the set for the recurring post-upgrade import/load regressions, even though it is still fairly generic.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 best fits the cluster because it captures the common upgrade-related import failure theme without being tied to one narrow model or code path.", + "best_issue_reason": "issue:45278 best matches the cluster\u2019s dominant theme and can serve as the umbrella issue, but it is not a precise root-cause ticket.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36683", "right": "issue:44242", "accept": false, - "reason": "Different bugs: Gemma3Config missing vocab_size vs load balancing loss not added." + "reason": "Different bugs: Gemma3Config vocab_size missing vs load balancing loss for MoE routing." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "Cache/layer no_grad update bug vs broad import errors after upgrade; unrelated." + "reason": "Different areas: cache/layer update no_grad behavior vs broad import failures after upgrade." }, { "left": "issue:36683", "right": "issue:43352", "accept": false, - "reason": "Config attribute error vs Flash Attention 2.0 support gating; not the same bug." + "reason": "Unrelated model issues: Gemma3Config attribute error vs NemotronH flash-attention support guard." }, { "left": "issue:41669", "right": "issue:44246", "accept": false, - "reason": "Import * performance issue vs slow import sometimes; similar area, different underlying problem." + "reason": "One is import-star performance, the other is slow import behavior; related topic but not the same concrete bug." }, { "left": "issue:43352", "right": "issue:43931", "accept": false, - "reason": "Flash-attn unsupported model check vs weight shape mismatch on Qwen3-VL; unrelated." + "reason": "Different model loading failures with different symptoms and likely different code paths." }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "State_dict sorting load error vs missing config field silently dropped; different code paths." + "reason": "Both are config/loading related, but one is state_dict sort/load failure and the other is a missing config field being dropped." }, { "left": "issue:36683", "right": "issue:43064", "accept": false, - "reason": "Gemma3Config vocab_size error vs FSDP2/PEFT optimizer state corruption; unrelated." + "reason": "Different problems: config attribute error vs FSDP2/PEFT optimizer-state mismatch." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "Missing embed_tokens.weight vs Qwen3.5 MoE from_pretrained failure; different load bugs." + "reason": "Different model families and failure modes: missing embed_tokens.weight vs Qwen3.5 MoE from_pretrained error." }, { "left": "issue:44938", "right": "issue:45071", "accept": false, - "reason": "Python 3.14 load failure vs PretrainedConfig type-checking regression; not the same defect." + "reason": "Version-related, but Python 3.14 import failure is not the same as PretrainedConfig type-checking regression." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Load error for sorted state_dict vs save_pretrained writing wrong visual keys; different directions and causes." + "reason": "Both involve loading/saving regressions, but the reported broken behavior and model specifics differ." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "Generation cache update bug vs Python 3.9/3.10 compatibility issue; unrelated." + "reason": "Different issues: cache/layer update semantics vs Python/version compatibility." }, { "left": "issue:44938", "right": "issue:45381", "accept": false, - "reason": "Interpreter load failure vs Qwen2.5-VL vision_position_ids bug; different failures." + "reason": "Different bugs: Python 3.14 load failure vs Qwen2.5-VL video position-id regression." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "DSA indexer ReLU discussion vs DeepSeekV3 implementation divergence; unrelated." + "reason": "Completely different topics: DSA indexer/ReLU discussion vs DeepseekV3MoE remote implementation divergence." }, { "left": "issue:43618", "right": "issue:44077", "accept": false, - "reason": "Missing attentions in CLIPOutput vs patchtsmixer post_init policy; different issues." + "reason": "Different subjects: CLIPOutput attentions regression vs patchtsmixer post_init API restriction." }, { "left": "issue:43644", "right": "issue:44938", "accept": false, - "reason": "Non-persistent buffer junk vs Python 3.14 load failure; unrelated." + "reason": "Non-persistent buffer junk in v5 is unrelated to Python 3.14 load failure." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Both touch tensor parallelism, but one is a training bug and the other is an OOM loading Qwen2-57B; not the same concrete issue." + "reason": "Both mention tensor parallelism/OOM, but one is a training bug and the other is model loading OOM for Qwen2-57B." }, { "left": "issue:43867", "right": "issue:44484", "accept": false, - "reason": "Load error on state_dict sorting vs save_pretrained shard-size question; unrelated." + "reason": "State_dict loading error and max_shard_size default question are not the same underlying bug." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIPOutput attentions regression vs LwDetrImageLoss AMP crash; unrelated." + "reason": "Different model/output regression vs AMP/CUDA crash in a loss module." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "Test seed flakiness vs Phi-4 multimodal load failure; unrelated." + "reason": "Seed-related flaky tests and a model load failure are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "Both are import/loading complaints, but AutoModel missing PyTorch and tokenizer loading regression are different failures." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Missing set_seed in tests vs stale device override CI failure; both test-related, but not the same bug." + "reason": "Two separate test failures with different causes: missing seed setup vs stale device override." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "CLIPOutput attentions missing vs Qwen3.5 flash-attention generation bug; unrelated." + "reason": "Different Qwen/CLIP generation and flash-attention issues; no shared concrete code-path." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "local_files_only still hits network vs AddedToken special-arg TypeError; different subsystems." + "reason": "Local-files-only network leakage is unrelated to AddedToken argument handling." }, { "left": "issue:43010", "right": "issue:44075", "accept": false, - "reason": "Cache update no_grad bug vs SGD args ignored; unrelated." + "reason": "Different functionality: cache/layer update vs optimizer SGD args not being used." }, { "left": "issue:42890", "right": "issue:45341", "accept": false, - "reason": "Both mention testing, but one is SamHQ seed flakiness and the other is a bug in testing_utils.py; not clearly the same bug." + "reason": "Both are test-related, but one is seeding flakes and the other is a different testing_utils bug." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Both are loading regressions after upgrade, but one is tokenizer loading and the other is checkpoint reload compatibility; too broad to merge." + "reason": "Both involve loading after v5 upgrades, but tokenizer.from_pretrained regression and checkpoint reload compatibility are different problems." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 quantization OOM vs checkpoint reload failure after upgrade; different concrete problems." + "reason": "Int4 quantization memory growth is unrelated to checkpoint reload compatibility." }, { "left": "issue:43010", "right": "issue:43232", "accept": false, - "reason": "Both involve generation internals, but cache update decoration and sync_gpus kwargs update are different code paths." + "reason": "Both involve generation/cached kwargs semantics, but not the same bug or code path." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "FP8 save_pretrained issue vs missing _tp_plan for tensor parallelism; unrelated." + "reason": "FP8 save_pretrained for MoE is different from missing _tp_plan for tensor parallelism." }, { "left": "issue:43010", "right": "issue:43065", "accept": false, - "reason": "Cache no_grad update bug vs dummy Conv2d in Sam3PixelDecoder; unrelated." + "reason": "Cache update semantics and Sam3PixelDecoder dummy Conv2d are unrelated." }, { "left": "issue:42548", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but one is missing PreTrainedModel export and the other is missing HybridCache export; different symbols and likely causes." + "reason": "Both are import errors, but PreTrainedModel missing and HybridCache missing are different export/regression problems." }, { "left": "issue:45125", "right": "issue:45478", - "accept": false, - "reason": "Same model family, but one is missing tensor-parallel plan and the other is a from_pretrained error; not enough evidence of one bug." + "accept": true, + "reason": "Same model family and same from_pretrained failure theme; the missing _tp_plan for tensor parallelism plausibly explains the Qwen3.5 MoE load error after 5.4.0." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Compiled Python file errors vs performance regression after upgrade; unrelated." + "reason": "Compiled Python file errors are unrelated to the reported slowdown after upgrading from 4.57.3 to 5.3.0." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Missing _tp_plan vs missing deepstack_visual_indexes field; both Qwen3.5 MoE-related, but different config/load issues." + "reason": "Both are Qwen3.5 MoE-related, but one is a tensor-parallelism loading error and the other is a config field being dropped by strict parsing." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft pair, issue:45125 vs issue:45478, is reasonably supported by the titles and looks mergeable as a single Qwen3.5 MoE from_pretrained / tensor-parallelism fix. The remaining pair verdicts are appropriately cautious given the limited evidence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -12559,8 +12568,8 @@ "review_unit_count": 41, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-15354-362", "nodes": [ @@ -12657,7 +12666,7 @@ "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -13024,12 +13033,12 @@ "issue:43606|issue:45468", "issue:42890|issue:43704" ], - "prepared_review_unit_hash": "2eb71c61684522af6ecf4c38015e14d1d0c19d141056730fe8e7649bfe46a6ea", + "prepared_review_unit_hash": "b13dc79d6f6d4b66782171a5760bc2a9704c1163d9b26bd9e462fe7a26bf81f8", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -13046,306 +13055,306 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly heterogeneous bugs/regressions across loading, caching, docs, and model-specific behavior. Several pairs share broad themes like v5 loading regressions or model-init issues, but none are safely the same concrete bug/change.", - "confidence": 0.84, - "canonical_issue_reason": "Use issue:44556 as the closest anchor: it is a concrete, broad v5 checkpoint-loading regression and best matches the repeated compatibility/load-failure theme across the cluster.", + "summary": "This cluster is mostly heterogeneous: several unrelated v5 loading/compatibility regressions are mixed together, with only a couple of clear near-duplicate-looking cases elsewhere in the full set. For the listed soft edges, none are the same concrete bug/change, so they should all be rejected.", + "confidence": 0.61, + "canonical_issue_reason": "issue:45310 is the best anchor for the cluster because it is a specific, actionable regression report and has a later exact-title duplicate (issue:45478) with the same Qwen3.5 MoE from_pretrained failure.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44556 is the strongest representative issue because it is specific, user-visible, and broad enough to cover the recurring v5 reload/incompatibility reports without being as narrowly model-specific as many others.", + "best_issue_reason": "issue:45310 is the strongest overall issue candidate: clear title, concrete versioned regression, and direct duplicate evidence make it the most useful representative of the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Different bugs: import-time slowdown from `import *` vs a cache-related GenerationMixin failure during chunked prefill." + "reason": "Different bugs: import-star performance/regression vs missing GenerationMixin cache in chunked_prefill." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Unrelated failures: Qwen3-VL bbox hallucination/error vs `PretrainedConfig` type-checking breakage in v5.4.0." + "reason": "Unrelated failures: Qwen3-VL 2D bbox output issue vs PretrainedConfig type-checking regression." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Same family, but different bug: one is a Qwen3-VL-Moe loading/runtime issue, the other is missing `_tp_plan` for tensor parallelism." + "reason": "Both are Qwen/MoE-related, but one is a general v5 model bug and the other is specifically missing tensor-parallel planning." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both concern v5 model-loading regressions, but the concrete triggers differ: generic reload failure after upgrade vs old remote-code checkpoints failing under meta init." + "reason": "Both concern loading after upgrading to v5, but the reported failure modes and affected checkpoints differ; not enough to treat as the same bug." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "Different topics: TF32 behavior API guidance vs a typo in cache strategy names." + "reason": "TF32 behavior settings and a cache-strategy typo are unrelated." }, { "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "No overlap beyond being test/runtime issues: missing `set_seed()` in SAM HQ tests vs `inverse_sqrt` scheduler kwargs not being passed." + "reason": "A flaky integration test due to missing set_seed is unrelated to scheduler kwargs being ignored." }, { "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "Different code paths: `AutoProcessor.from_pretrained` kwargs forwarding vs scheduler kwargs handling." + "reason": "Different code paths: AutoProcessor kwargs forwarding vs inverse_sqrt scheduler kwargs handling." }, { "left": "issue:44246", "right": "issue:44273", "accept": false, - "reason": "Both mention loading/performance, but one is intermittent import slowness and the other is a lazy-loading malfunction." + "reason": "Import-time slowness and lazy-loading malfunction are related at a high level, but not the same concrete defect." }, { "left": "issue:43408", "right": "issue:44315", "accept": false, - "reason": "Different issues in different subsystems: SAM3 model-type warning vs Liger Kernel not being applied with `model_init`." + "reason": "Wrong model-type warning vs Liger Kernel not applied under model_init are different issues." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "A specific tokenizer save bug vs a generic, under-specified bug report; not the same underlying problem." + "reason": "Tokenizer save mismatch is unrelated to an empty generic bug report." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "`transformers env` CLI breakage is unrelated to scheduler keyword handling." + "reason": "Broken env command and scheduler kwarg handling are different bugs." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Different model-specific failures: Flash Attention 2 unsupported for Nemotron vs Qwen3-VL 2D bbox output errors." + "reason": "Flash Attention 2 support for Nemotron is unrelated to Qwen3-VL bounding-box output errors." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs omission and `PretrainedConfig` type-checking regression are unrelated." + "reason": "Scheduler kwarg plumbing and PretrainedConfig type checking are unrelated regressions." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python version compatibility failure vs Qwen3-VL bounding-box output bug; no shared code path." + "reason": "Python version compatibility issue does not match a Qwen3-VL output bug." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "Specific `position_ids` buffer access error vs a vague bug report; not the same issue." + "reason": "Position_ids buffer access error is unrelated to a generic bug report." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Both involve import behavior, but one is import-time slowdown and the other is a missing `HybridCache` symbol." + "reason": "Import-star cleanup/performance and HybridCache import failure are different problems." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Import-performance issue vs a testing utility bug; no concrete overlap." + "reason": "Unrelated: model import performance vs a testing_utils bug." }, { "left": "issue:44492", "right": "issue:44945", "accept": false, - "reason": "A cache-strategy typo is not the same as incorrect LLM output under pipeline parallelism." + "reason": "Cache-strategy typo and pipeline-parallelism wrong output are unrelated." }, { "left": "issue:41669", "right": "issue:44492", "accept": false, - "reason": "Import-performance regression and cache-strategy typo are distinct problems." + "reason": "Import-star performance regression is not the same as a typo in cache strategy docs/code." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Both touch training/model setup, but one is about `model_init` not applying Liger Kernel and the other about degenerate training with Flash Attention 3." + "reason": "Liger Kernel application under model_init and flash_attention_3 degenerate training are different failures." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Different Qwen issues: bbox output failures vs a Qwen3.5 Moe `from_pretrained` regression." + "reason": "Different issues: Qwen3-VL 2D bbox output vs Qwen3.5 MoE from_pretrained failure." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Different bugs in different utilities: `patchtsmixer` post-init validation vs `_get_tied_weight_keys` crashing on list input." + "reason": "PatchTSMixer post_init policy and tied-weights key handling are unrelated." }, { "left": "issue:31795", "right": "issue:33453", "accept": false, - "reason": "Documentation confusion about `input_ids`/`past_key_values` is unrelated to a tokenizer loading regression." + "reason": "Documentation confusion about forward args is unrelated to tokenizer loading regression." }, { "left": "issue:43827", "right": "issue:44908", "accept": false, - "reason": "Docs still referencing `pipeline()` after removals vs scheduler kwargs handling; unrelated." + "reason": "Docs still referencing pipeline() and inverse_sqrt scheduler kwargs are unrelated." }, { "left": "issue:41669", "right": "issue:44908", "accept": false, - "reason": "Import slowdown from `import *` is unrelated to scheduler kwargs propagation." + "reason": "Import performance regression and scheduler kwargs handling are unrelated." }, { "left": "issue:43723", "right": "issue:44393", "accept": false, - "reason": "Tokenizer loading in v5 and Qwen3-VL bbox errors are different failure modes." + "reason": "Tokenizer loading in v5 is unrelated to Qwen3-VL bounding-box output errors." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Saving `Pipeline` objects and tied-weight key extraction are separate code paths." + "reason": "Saving Pipeline objects and _tied_weights_keys attribute errors are different code paths." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Broken `transformers env` command is not the same as lazy loading failing." + "reason": "Broken env command and lazy-loading malfunction are different bugs, even if both touch v5 behavior." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "Different model/component bugs: DSA indexer ReLU discussion vs Gemma-4 audio positional encoding." + "reason": "DSA indexer ReLU omission is unrelated to Gemma-4 audio positional encoding." }, { "left": "issue:45230", "right": "issue:45310", "accept": false, - "reason": "Generic bug report vs a concrete Qwen3.5 Moe `from_pretrained` error; no shared underlying bug." + "reason": "A generic bug report is not evidence of the same Qwen3.5 MoE from_pretrained regression." }, { "left": "issue:44273", "right": "issue:44908", "accept": false, - "reason": "Lazy loading malfunction and inverse-sqrt scheduler kwargs omission are unrelated." + "reason": "Lazy loading failure and scheduler kwargs omission are unrelated." }, { "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Import-time slowdown vs VRAM leak in multi-threaded Qwen3ForCausalLM use." + "reason": "Import-star performance issue and VRAM leak across dataloader threads are unrelated." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Incorrect timestamp calculation in Qwen3VL Processor and GLM-5 RoPE implementation are distinct model-specific bugs." + "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are different bugs." }, { "left": "issue:43519", "right": "issue:44908", "accept": false, - "reason": "Timestamp math in a processor and scheduler kwargs propagation are unrelated." + "reason": "Timestamp math in Qwen3VL is unrelated to inverse_sqrt scheduler kwargs." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Docs confusion for `forward` arguments vs a Llama 3.2 model-loading regression." + "reason": "Forward-arg documentation confusion is unrelated to a model-loading breakage for Llama 3.2 Vision Instruct." }, { "left": "issue:31795", "right": "issue:37428", "accept": false, - "reason": "Documentation issue vs import error for `_flash_supports_window_size`; not the same problem." + "reason": "Documentation confusion is unrelated to the flash-support import error." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Both involve model initialization/loading, but one is Liger Kernel not applied with `model_init` and the other is remote-code checkpoint incompatibility under meta init." + "reason": "Liger Kernel application and remote-code checkpoint incompatibility are different bugs." }, { "left": "issue:44273", "right": "issue:45071", "accept": false, - "reason": "Lazy loading failure and `PretrainedConfig` type-checking regression are unrelated." + "reason": "Lazy loading not working and PretrainedConfig type checking are unrelated." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leak in multi-threaded loading is not the same as a RoPE implementation issue." + "reason": "VRAM leak in dataloader threads and GLM-5 RoPE implementation are unrelated." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "Different architectures and bugs: GLM-5 RoPE vs Gemma-4 audio relative positional encoding." + "reason": "Different model-specific implementation issues." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 API change guidance is unrelated to a Qwen3ForCausalLM VRAM leak." + "reason": "TF32 control settings and VRAM leak are unrelated." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "Local-files-only network access bug and Qwen3VL timestamp calculation are unrelated." + "reason": "local_files_only API requests and Qwen3VL timestamp calculation are different bugs." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Repeated docs-vs-loading mismatch: the issues describe different problems and code paths." + "reason": "Documentation issue vs model-loading regression." }, { "left": "issue:31795", "right": "issue:37428", "accept": false, - "reason": "Docs confusion and flash-attention import failure are unrelated." + "reason": "Documentation issue vs import error." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Both involve initialization, but they target different bugs and could not be merged into one fix cleanly." + "reason": "Liger Kernel integration and meta-init checkpoint incompatibility do not share the same fix." }, { "left": "issue:44273", "right": "issue:45071", "accept": false, - "reason": "Lazy loading bug vs `PretrainedConfig` typing regression; no shared root cause." + "reason": "Lazy loading regression and PretrainedConfig type checking are unrelated." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "Distinct issues in different models/code paths; no duplicate evidence." + "reason": "VRAM leak and RoPE implementation bug are unrelated." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "RoPE implementation bug and audio positional encoding bug are separate." + "reason": "RoPE implementation discussion and Gemma-4 audio positional encoding are different model bugs." }, { - "left": "issue:42890", + "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "Flaky integration tests due to missing seed and VRAM leak in threaded inference are unrelated." + "reason": "TF32 behavior control and VRAM leak are unrelated." } ] }, @@ -13411,12 +13420,12 @@ "issue:31515|issue:36683", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "9300c562a404f4e5d1003b17d7038d50aa5cc632921d4a79cbc8251a1d877eb2", + "prepared_review_unit_hash": "d92b333e4d5b02c0d9bda377ed052741c259dba41c2944c5b37310c9f59096ff", "component_budget": { "node_count": 362, "item_count": 362, "soft_pair_count": 1351, - "serialized_chars": 697245, + "serialized_chars": 697247, "estimated_input_tokens": 174312, "estimated_eval_tokens": 348880 }, @@ -13433,121 +13442,124 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items span several unrelated issue families; the soft pairs are mostly lexical/topic similarity rather than true duplicates. The only strong shared theme is checkpoint/tokenizer loading and v5 migration regressions, but none of the candidate pairs are safe duplicate merges from the available evidence.", - "confidence": 0.84, - "canonical_issue_reason": "issue:44556 is the clearest, most concrete loading/reload regression in the set (v4.57 checkpoint no longer reloads after v5.2/v5.3), so it best represents the dominant load-related theme.", + "summary": "Only one soft match looks like the same underlying bug: the two tokenizer-v5 issues. The other pairs are either clearly unrelated or too broadly similar to safely merge.", + "confidence": 0.87, + "canonical_issue_reason": "issue #43066 is the more concrete duplicate candidate: it names the specific tokenizer-v5 decoder-type regression, while #42913 is broader and more generic.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44556 is the best single anchor among the issues because it names a specific, user-facing compatibility break rather than a vague symptom or orthogonal bug.", + "best_issue_reason": "issue #43066 is the best representative issue because it states the failure mode more precisely and is easier to map to a fix.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42913", "right": "issue:43066", - "accept": false, - "reason": "Both are tokenizer-v5 complaints, but one is broad behavior drift and the other is a specific decoder-type bug; not enough evidence they are the same underlying defect." + "accept": true, + "reason": "Both describe tokenizer behavior regressions after the v4\u2192v5 transition; the decoder-type mismatch is a concrete instance of the broader behavior difference." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Completely unrelated topics: scheduler kwargs vs a nonsensical/unemployment title." + "reason": "Scheduler kwarg handling and an unrelated joke title are not the same bug." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Different code paths and symptoms: tied-weight-key handling vs chat-template crashes with tool-call messages." + "reason": "One is a tied-weights attribute error; the other is a chat-template crash with tool calls. Different code paths." }, { "left": "issue:44998", "right": "issue:45341", "accept": false, - "reason": "No substantive overlap; one is unrelated, the other is a small testing_utils bug." + "reason": "No meaningful technical overlap; the second is a testing_utils bug, not related to the first." }, { "left": "issue:44492", "right": "issue:44998", "accept": false, - "reason": "A cache-strategy typo is not the same bug as the unrelated item." + "reason": "A cache-strategy typo is unrelated to the other issue." }, { "left": "issue:43618", "right": "issue:44998", "accept": false, - "reason": "CLIP attentions assignment regression is unrelated to the other item." + "reason": "CLIP attentions assignment and the other issue are unrelated." }, { "left": "issue:44556", "right": "issue:44998", "accept": false, - "reason": "Checkpoint reload regression after v5 upgrade is unrelated to the other item." + "reason": "Checkpoint reload breakage after v4\u2192v5 upgrade is unrelated to the other item." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_id in Llama4Config and tied-weight-key AttributeError are distinct failures." + "reason": "Missing pad_token_id in Llama4Config and tied-weight-key crashing are different bugs." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is a different config-attribute issue than tied-weight-key handling." + "reason": "Missing pad_token_idx in StableLmConfig is not the same as the tied-weights list crash." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Slow from_pretrained checkpoint loading and an ImportError for layer_type_validation are different problems." + "reason": "Checkpoint loading slowness and an import error for layer_type_validation are unrelated." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 inference support for Qwen models is not the same bug as processor.save_pretrained missing files." + "reason": "FP8 Qwen inference support and processor.save_pretrained missing files are different problems." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Checkpoint loading performance and tensor-parallel training bugs do not match." + "reason": "Loading slowdown and tensor-parallel training bug do not describe the same failure." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Checkpoint loading performance is unrelated to model.forward documentation confusion." + "reason": "Model loading performance and forward() documentation confusion are unrelated." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "Both mention Qwen3.5/MoE and from_pretrained, but one is FP8 inference support and the other is a specific loading error; too broad to merge." + "reason": "Both mention Qwen/from_pretrained, but one is FP8 support and the other is a specific loading error; not enough evidence of the same bug." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Slow checkpoint loading and tokenizer loading regression are different failure modes." + "reason": "Checkpoint loading slowness and tokenizer loading regression are different issues." }, { "left": "issue:31515", "right": "issue:36683", "accept": false, - "reason": "from_pretrained loading slowness is unrelated to Gemma3Config missing vocab_size." + "reason": "From_pretrained slowness and Gemma3Config missing vocab_size are not the same code-path bug." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching not supporting audio models is a different feature gap than FP8 Qwen inference support." + "reason": "Continuous batching audio-model support and FP8 Qwen inference support are different feature gaps." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The result is grounded in the packet and stays conservative overall. The one accepted pair (42913/43066) is plausibly the same tokenizer-v5 regression area, and the other pairs are rejected with sufficiently distinct titles/code paths." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -13559,8 +13571,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-26350-2", "nodes": [ @@ -13622,8 +13634,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-27088-4", "nodes": [ @@ -13722,8 +13734,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-36817-13", "nodes": [ @@ -13964,8 +13976,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-37934-6", "nodes": [ @@ -14080,8 +14092,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-41084-2", "nodes": [ @@ -14143,8 +14155,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43598-2", "nodes": [ @@ -14206,8 +14218,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43684-2", "nodes": [ @@ -14269,8 +14281,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43835-4", "nodes": [ @@ -14372,8 +14384,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-44371-5", "nodes": [ @@ -14494,8 +14506,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45145-2", "nodes": [ @@ -14609,7 +14621,7 @@ { "label": "pull_request", "component_index": 1, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -14658,166 +14670,178 @@ "pull_request:43823|pull_request:45489", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "694f821a4c7fe21308232a0dc54351b70fba22d5dcd09a4c1cb70100be4b945d", + "prepared_review_unit_hash": "a0ff1721763883c73033f88928d07cfabab71abd617a051d7f6b67ecc47d6e46", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 23, - "serialized_chars": 37544, - "estimated_input_tokens": 9386, - "estimated_eval_tokens": 19028 + "serialized_chars": 37549, + "estimated_input_tokens": 9388, + "estimated_eval_tokens": 19032 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 23, - "serialized_chars": 37544, - "estimated_input_tokens": 9386, - "estimated_eval_tokens": 19028 + "serialized_chars": 37549, + "estimated_input_tokens": 9388, + "estimated_eval_tokens": 19032 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Almost all PRs are unrelated despite superficial overlap in Transformers subsystems; the only clear duplicate pair is the two `fixed_cross_entropy` fixes for issue #43240.", - "confidence": 0.94, + "summary": "This cluster is mostly a set of unrelated PRs across model additions, docs, tests, and small fixes. The only clear duplicate pair is the two `fixed_cross_entropy` patches (#43251 and #43254), which both implement the same `nn.functional.cross_entropy` kwargs support in the same file/function.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the stronger representative of the duplicate fix: it is explicitly issue-linked, has more discussion, and directly updates `fixed_cross_entropy` to forward the missing kwargs.", + "canonical_pr_reason": "PR #43251 is the clearest canonical representative of the duplicate loss fix: it targets the explicit issue, edits the same `fixed_cross_entropy` path, and has the fuller patch/discussion. PR #43254 is a near-identical alternate implementation of the same change.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the best cluster representative because it is the clearest, most complete version of the one true duplicate change in this set.", + "best_pr_reason": "PR #43251 is the best overall representative of the cluster because it is the only strong duplicate anchor and the most complete version of that concrete fix.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Unrelated PRs: a new VideoPrism model/docs addition vs an Executorch dynamic-shape export test." + "reason": "Different changes: VideoPrism model/docs addition vs an executorch dynamic-shape export test." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Different work: processor robustness plumbing vs adding MobileLLM model support." + "reason": "Different artifacts and goals: processor robustness fixes vs adding MobileLLM model support." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "`fixed_cross_entropy` kwargs fix is unrelated to MobileLLM model implementation." + "reason": "Unrelated: cross-entropy kwargs fix vs new MobileLLM model code." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Different changes and codepaths: loss utility kwargs vs Mistral4 test/model adjustments." + "reason": "Different code paths: loss utility kwargs support vs Mistral4 test/model fixes." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch export testing is not the same bug as Mistral4 test fixes." + "reason": "Different areas: executorch export test vs Mistral4 model/test changes." }, { "left": "pull_request:43424", "right": "pull_request:45435", "accept": false, - "reason": "Different subsystems and bugs: Executorch export dynamic shapes vs Whisper tokenizer indexing." + "reason": "Different bugs: executorch dynamic-shape export testing vs Whisper tokenizer boundary fix." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "No shared underlying change; one is export testing, the other is a new model addition." + "reason": "Different scope: exportability test vs MobileLLM model addition." }, { "left": "pull_request:43823", "right": "pull_request:45454", "accept": false, - "reason": "MobileLLM model addition is unrelated to Gemma4 text-only training behavior." + "reason": "Different model families and issues: MobileLLM addition vs Gemma4 text-only training behavior." }, { "left": "pull_request:43823", "right": "pull_request:45435", "accept": false, - "reason": "No overlap beyond being Transformers PRs; model addition vs Whisper tokenizer bug fix." + "reason": "No shared underlying change; model addition vs Whisper tokenization bug." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "Different model and purpose: MobileLLM addition vs Falcon output-interface refactor." + "reason": "Different changes: MobileLLM model addition vs Falcon output-interface refactor." }, { "left": "pull_request:43995", "right": "pull_request:45435", "accept": false, - "reason": "Falcon refactor is unrelated to Whisper special-token decoding fix." + "reason": "Different code paths: Falcon refactor vs Whisper tokenizer boundary fix." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "A model refactor is not the same as the model-creation skill/meta PR." + "reason": "Falcon model refactor is unrelated to the model-creation skill/meta PR." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon standardized-output refactor and Mistral4 test fixes are different codepaths and problems." + "reason": "Different model work: Falcon refactor vs Mistral4 test/model fixes." }, { "left": "pull_request:44827", "right": "pull_request:45489", "accept": false, - "reason": "Both touch Gemma/Mistral-family areas only broadly; they fix different concrete issues in different models." + "reason": "Related by theme but not the same change: Mistral4 test/model fixes vs Gemma3n/Gemma4 cache-sharing alignment." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 tests are unrelated to the `layrnorm` -> `layernorm` renaming/conversion fix." + "reason": "Different underlying changes: Mistral4 fixes vs CLIP-like layrnorm\u2192layernorm renaming." }, { "left": "pull_request:43823", "right": "pull_request:44827", "accept": false, - "reason": "New MobileLLM model support is not the same underlying change as Mistral4 test fixes." + "reason": "Different model implementations and bugs; not mergeable as one PR." }, { "left": "pull_request:45213", "right": "pull_request:45435", "accept": false, - "reason": "Meta model-creation skill PR is unrelated to Whisper tokenizer bug fixing." + "reason": "Meta model-creation skill PR is unrelated to Whisper tokenizer bug fix." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 test fixes and the model-creation skill PR are not the same change." + "reason": "Mistral4 fixes are unrelated to the model-creation skill/meta PR." }, { "left": "pull_request:43823", - "right": "pull_request:45489", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model addition is unrelated to the model-creation skill/meta PR." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45435", "accept": false, - "reason": "MobileLLM addition and Gemma3n/Gemma4 cache-sharing alignment are unrelated." + "reason": "Mistral4 fixes and Whisper tokenizer fix are different code paths and symptoms." }, { "left": "pull_request:45454", "right": "pull_request:45489", "accept": false, - "reason": "Both are Gemma-related, but one fixes text-only training inputs while the other aligns cache sharing; different concrete bugs and patches." + "reason": "Both touch Gemma-related code, but one is a text-only training fix and the other is cache-sharing alignment; different concrete changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45489", + "accept": false, + "reason": "Different models and bugs: MobileLLM addition vs Gemma3n/Gemma4 cache-sharing refactor." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Same file, same issue (#43240), and both patch `fixed_cross_entropy` to forward missing `nn.functional.cross_entropy` kwargs; these are the same underlying fix." + "reason": "Same underlying fix in the same function/file: both add supported kwargs to `fixed_cross_entropy` so they can be merged into one PR." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only supported duplicate pair is PR 43251 / 43254: same file, same issue target (#43240), and both implement the same `fixed_cross_entropy` kwargs-forwarding fix. The other soft-edge rejections are reasonable and do not overclaim mergeability or shared bug origin." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft-edge pair, #43251 and #43254, is supported by shared issue target, same file/function, and the same concrete cross-entropy kwargs fix. The remaining pairs are reasonably rejected as distinct model additions, tests, refactors, or unrelated bug fixes." }, "evaluator_used": true, "retried": false, @@ -14828,7 +14852,7 @@ { "label": "pull_request", "component_index": 2, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -14844,7 +14868,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "bf8e71ea0259acd18937ec89c4b2a7109d6059e1528157790484ee1e24285864", + "prepared_review_unit_hash": "1cd090f34516eec6dbd87701699b850d9038ade82307e3e8c2c96a810910e3ec", "component_budget": { "node_count": 2, "item_count": 2, @@ -14866,18 +14890,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related VibeVoice pull requests, but they are not duplicates: one is the base VibeVoice implementation, the other adds a separate realtime/acoustic-tokenizer extension. Shared files reflect the same model family, not the same concrete change.", - "confidence": 0.92, + "summary": "Both PRs are about VibeVoice, but they target different deliverables: one is the base VibeVoice integration, while the other adds a separate realtime/acoustic-tokenizer path. They overlap on shared model plumbing, but they are not the same change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the better canonical PR for the cluster because it is the earlier, non-draft, broad base implementation of VibeVoice and establishes the core files that the later work builds on.", + "canonical_pr_reason": "PR 40546 is the cleaner canonical VibeVoice implementation: it introduces the core model/docs/auto-class wiring without the extra realtime-specific tokenizer and generation changes.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the best representative because it is the main initial implementation, while PR #42781 is a follow-on realtime-specific draft that extends the model rather than fixing or completing the same change.", + "best_pr_reason": "PR 40546 is the best representative artifact because it defines the foundational VibeVoice integration that the later realtime PR builds on.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Reject: the overlap is mostly the VibeVoice package and docs, but #42781 adds realtime/acoustic-tokenizer functionality and touches generation/runtime code beyond the base implementation in #40546. They are related, not the same underlying change." + "reason": "Not a duplicate: 40546 implements core VibeVoice support, while 42781 adds VibeVoice Realtime plus acoustic tokenizer and generation changes. They share filenames because they touch the same subsystem, but they are different features and would not plausibly be merged into one PR." } ] }, @@ -14891,7 +14915,7 @@ { "label": "pull_request", "component_index": 3, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -14907,12 +14931,12 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "8bcc97fcc59f8ebc687436baba5c07ea0108b56ab7b691e60b832d662068bd88", + "prepared_review_unit_hash": "1c6b9da50922886a862667a2c8ff58e8fd7e1a5351127037699a33d21950c03a", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4674, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -14920,7 +14944,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4674, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -14929,18 +14953,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two pull requests are unrelated: one adds covariate forecasting support for TimesFM, the other adds image-classification support for DINOv3ViT. They do not fix the same code-path problem and should not be merged as duplicates.", - "confidence": 0.99, + "summary": "These two PRs are unrelated feature additions in different model families: TimesFM covariate forecasting vs. DINOv3 image classification support. They do not fix the same code-path problem and should not be clustered as duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: the changes target different models and different features (TimesFM covariate forecasting vs. DINOv3 image classification), with no shared concrete bug or merged code path.", + "canonical_pr_reason": "PR #41224 is the more self-contained and concrete change: it adds image-classification support for DINOv3 with accompanying docs/tests. PR #40755 is a separate, broader feature for TimesFM forecasting with covariates.", "best_issue_reason": null, - "best_pr_reason": "No single best PR for this cluster because the PRs are not duplicates or substitutes; each stands alone for a different subsystem and use case.", + "best_pr_reason": "PR #41224 is the best representative of the cluster only because it is the clearest single feature PR; however, the cluster itself is not a duplicate set and the two PRs should remain separate.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Reject: these PRs address different model capabilities in different files and code paths, so they are not the same underlying change." + "reason": "Different models and different functionality: TimesFM covariate forecasting vs DINOv3 image classification support. No shared bug or mergeable code-path overlap." } ] }, @@ -14954,13 +14978,13 @@ { "label": "pull_request", "component_index": 4, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-41356-2", "nodes": [ @@ -14970,46 +14994,46 @@ "soft_pairs": [ "pull_request:41356|pull_request:44339" ], - "prepared_review_unit_hash": "bf853edcac36b9d46727ab7091e6d4edc2525d28b28d3cc612346441fafe02a8", + "prepared_review_unit_hash": "88e60f926a84fb13a881f1700f827def51f6a2034775286ab5e8f054384e362c", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, - "estimated_input_tokens": 1484, - "estimated_eval_tokens": 3224 + "serialized_chars": 5929, + "estimated_input_tokens": 1483, + "estimated_eval_tokens": 3222 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5934, - "estimated_input_tokens": 1484, - "estimated_eval_tokens": 3224 + "serialized_chars": 5929, + "estimated_input_tokens": 1483, + "estimated_eval_tokens": 3222 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are for adding DEIMv2 to Transformers. PR #44339 is a broader, more complete implementation that subsumes the earlier partial add in #41356, so they look like the same underlying feature work rather than separate changes.", - "confidence": 0.92, + "summary": "Both pull requests are about adding DEIMv2 support to Transformers. PR #44339 is the more complete, later implementation and appears to supersede the smaller initial addition in #41356.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44339 is the more complete DEIMv2 implementation: it adds the model plus loss utilities, auto-class registration, conversion script, modular file, and config updates. It clearly subsumes the narrower earlier PR #41356.", + "canonical_pr_reason": "PR #44339 is the stronger canonical PR because it is the later, more complete DEIMv2 integration: it adds the model, loss, auto-mapping, conversion script, and related docs/tests, while #41356 is an earlier partial model/image-processor addition.", "best_issue_reason": null, - "best_pr_reason": "PR #44339 is the best representative because it covers the full DEIMv2 integration and is the more complete, maintainable landing point for this feature.", + "best_pr_reason": "PR #44339 is the best representative of the cluster because it most fully implements the DEIMv2 feature and includes the broader set of integration changes expected for a merged model addition.", "soft_edge_verdicts": [ { "left": "pull_request:41356", "right": "pull_request:44339", "accept": true, - "reason": "Same underlying change: both add DEIMv2 support. #44339 expands on the same model/files and looks like a superset of #41356 rather than a different fix." + "reason": "Same underlying feature addition for DEIMv2 support, with substantial overlap in model files, docs, and tests; #44339 looks like the expanded successor to the earlier partial PR." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: both PRs target the same issue (#41211), share several DEIMv2 files, and the later PR clearly adds more DEIMv2-related pieces. The soft-edge accept is conservative enough here, and the characterization as related feature work rather than separate changes is supported by the evidence." + "feedback": "The summary is grounded in the packet: both PRs target the same DEIMv2 issue, share several core files, and #44339 clearly adds broader integration pieces beyond #41356. The soft-edge verdict is conservative because it says the later PR 'looks like' an expanded successor rather than asserting a definitive relationship." }, "evaluator_used": true, "retried": false, @@ -15020,7 +15044,7 @@ { "label": "pull_request", "component_index": 5, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15036,7 +15060,7 @@ "soft_pairs": [ "pull_request:41797|pull_request:45186" ], - "prepared_review_unit_hash": "cd3efc7ec4256a342065c8179ac790974e7d68ca66be62eee5663658665f2254", + "prepared_review_unit_hash": "587a88d1cde82753c3f1087a8edf5173c49e0f2afee9eab6bcd82177c06252cd", "component_budget": { "node_count": 2, "item_count": 2, @@ -15058,8 +15082,8 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate model-addition PRs: one for DeepSeek OCR and one for Isaac. They share generic Transformers boilerplate and docs/auto-registration work, but they do not appear to fix or implement the same underlying feature or bug.", - "confidence": 0.97, + "summary": "These are two unrelated model-integration PRs (DeepSeek OCR vs Isaac). They share standard Transformers boilerplate and generated scaffolding, but not the same underlying bug or feature change.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -15069,7 +15093,7 @@ "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Reject: the PRs add different models with distinct codepaths, configs, processors, and tests. Shared filenames are only expected integration surfaces for model onboarding, not evidence of a duplicate change." + "reason": "Different models and different codepaths; overlap is only generic new-model integration files and docs, not a single mergeable change." } ] }, @@ -15083,7 +15107,7 @@ { "label": "pull_request", "component_index": 6, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15099,12 +15123,12 @@ "soft_pairs": [ "pull_request:42166|pull_request:45426" ], - "prepared_review_unit_hash": "f43c98475991713139598405bccf884463f853c9a01419baa4f8aa7248cf9b13", + "prepared_review_unit_hash": "c1dbd24520c660e240eec75dcd0520c46f84ef529d7e529ee5362239c6786dc5", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5408, + "serialized_chars": 5407, "estimated_input_tokens": 1352, "estimated_eval_tokens": 2960 }, @@ -15112,7 +15136,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5408, + "serialized_chars": 5407, "estimated_input_tokens": 1352, "estimated_eval_tokens": 2960 }, @@ -15121,18 +15145,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two unrelated model-addition PRs that only overlap in shared Transformers registration files; they do not appear to fix the same underlying bug/change.", + "summary": "These are unrelated feature PRs adding different models: InternVLFlash vs AXK1. They share some Transformers registry boilerplate, but not the same underlying bug or change.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #42166 is the stronger cluster representative: it is a full model addition with docs, tests, and broader integration, whereas the other PR is a separate model addition.", + "canonical_pr_reason": "No canonical PR: #42166 and #45426 implement separate model integrations with different packages, configs, modeling files, and tests; shared auto-registration edits are incidental.", "best_issue_reason": null, - "best_pr_reason": "PR #42166 is a good standalone exemplar of this cluster because it includes the most complete end-to-end model scaffolding and validation, but it should not be treated as a duplicate of the other PR.", + "best_pr_reason": "If a single representative is needed, #42166 is the stronger model-addition PR because it includes a broader InternVLFlash integration surface (docs, auto mappings, model code, and tests), but it is still not a duplicate of #45426.", "soft_edge_verdicts": [ { "left": "pull_request:42166", "right": "pull_request:45426", "accept": false, - "reason": "Different model families and different implementation targets (InternVLFlash vs AXK1). Shared edits to __init__.py and auto config/model registries are incidental boilerplate, not the same concrete code change, and the PRs would not be merged as one." + "reason": "Reject: they add different models and different codepaths; shared registry files alone are not enough to treat them as the same change." } ] }, @@ -15146,7 +15170,7 @@ { "label": "pull_request", "component_index": 7, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15154,14 +15178,12 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-42227-6", + "cluster_id": "cluster-42227-4", "nodes": [ "pull_request:42227", "pull_request:43291", - "pull_request:43498", "pull_request:43665", - "pull_request:44815", - "pull_request:45528" + "pull_request:44815" ], "soft_pairs": [ "pull_request:42227|pull_request:43291", @@ -15169,86 +15191,72 @@ "pull_request:42227|pull_request:44815", "pull_request:43291|pull_request:43665", "pull_request:43291|pull_request:44815", - "pull_request:43498|pull_request:45528", - "pull_request:43665|pull_request:44815", - "pull_request:43665|pull_request:45528" + "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "f81d57d3aeee7cc6509e170b6960c0b3fd84272e5f0763e3b9b7d0c507938015", + "prepared_review_unit_hash": "1d63bd0a59ec46a4458c32edfef9aaf5fc4db188ce330ec3e2ef77a1d8cb4b26", "component_budget": { - "node_count": 6, - "item_count": 6, - "soft_pair_count": 8, - "serialized_chars": 15568, - "estimated_input_tokens": 3892, - "estimated_eval_tokens": 8040 + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 }, "budget": { - "node_count": 6, - "item_count": 6, - "soft_pair_count": 8, - "serialized_chars": 15568, - "estimated_input_tokens": 3892, - "estimated_eval_tokens": 8040 + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are not duplicates: they span unrelated areas (Whisper ASR, Whisper tokenizer/tests, model-weight tying deprecation, CLIP/ViT test noise, FP8/dequantization, and image-processor doc consistency). The only substantive fix is the Whisper return_language pipeline change; the others are separate changes or test/doc churn.", - "confidence": 0.95, + "summary": "These PRs are not duplicates overall: one fixes Whisper return-language plumbing, one changes Whisper tokenizer tests/timestamp decoding, one is a CLIP/ViT test-only edit, and one is an FP8 dequant/loading fix. The only superficially related pair is the two Whisper PRs, but they address different code paths and should not be merged as the same change.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42227 is the clearest standalone bug fix: it directly addresses Whisper return_language handling, has an explicit issue target, and includes a focused code-path change plus tests.", + "canonical_pr_reason": "PR 42227 is the strongest anchor: it has an explicit issue link, a focused user-facing Whisper pipeline fix, and a clear implementation change with tests. The others are either test-only or unrelated model/quantization work.", "best_issue_reason": null, - "best_pr_reason": "PR 42227 is the best representative of the cluster because it is the only concrete, user-facing bug fix with a clear scope; the others are either unrelated subsystems, test-only changes, or broad refactors/docs.", + "best_pr_reason": "PR 42227 is the best representative of the cluster because it is the most concrete standalone bug fix and the only one tied to a tracked issue; the rest are not the same underlying change.", "soft_edge_verdicts": [ { "left": "pull_request:42227", "right": "pull_request:43291", "accept": false, - "reason": "Both mention Whisper, but they fix different problems: 42227 forwards return_language through the ASR pipeline, while 43291 refactors Whisper decode/batch handling and tests. Not the same underlying bug." + "reason": "Both mention Whisper, but 42227 fixes ASR pipeline return-language propagation while 43291 changes tokenizer decode/timestamp test behavior; different code paths and not one mergeable fix." }, { "left": "pull_request:42227", "right": "pull_request:43665", "accept": false, - "reason": "42227 is a Whisper pipeline bug fix; 43665 is just test-file edits with failing asserts and no related code-path change. Unrelated." + "reason": "42227 is a Whisper runtime fix; 43665 only adds/edit tests for CLIP and ViT. Same broad repo area, not the same bug or change." }, { "left": "pull_request:42227", "right": "pull_request:44815", "accept": false, - "reason": "Different domains and fixes: Whisper ASR parameter forwarding versus FP8/model-loading/dequantization changes. No shared underlying bug." + "reason": "42227 touches Whisper ASR; 44815 is a quantization/dequant/loading fix across model-loading and FP8 integration. Unrelated changes." }, { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "43291 changes Whisper tokenizer decode behavior; 43665 is test noise in CLIP/ViT. Not the same issue." + "reason": "Whisper tokenizer decoding vs. CLIP/ViT test edits are unrelated; no shared concrete bug or code path." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper tokenizer/test changes are unrelated to FP8 dequantization and loading logic." - }, - { - "left": "pull_request:43498", - "right": "pull_request:45528", - "accept": false, - "reason": "43498 is a backward-compatibility/deprecation wrapper for tie_weights; 45528 is a consistency/doc comment sweep across image processors. No shared code-path problem." + "reason": "Whisper decoding/test work and FP8 dequant/loading work solve different problems in different subsystems." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "43665 only touches tests; 44815 changes quantization/model-loading code. They do not fix the same bug and would not be merged together as one PR." - }, - { - "left": "pull_request:43665", - "right": "pull_request:45528", - "accept": false, - "reason": "43665 is test-only churn, while 45528 is a documentation/consistency update across image processors. Unrelated." + "reason": "A test-only CLIP/ViT change is not the same underlying bug/change as the FP8 dequant fix." } ] }, @@ -15262,7 +15270,7 @@ { "label": "pull_request", "component_index": 8, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15278,7 +15286,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "ab55841bcd788b4d175c834ec90ea22d1fe9d97b0daaf8edd7997c55d042e46c", + "prepared_review_unit_hash": "dd4160f5e4869084f26bdd0761b6e20b55b5195b46890d1b39d5af9c93681895", "component_budget": { "node_count": 2, "item_count": 2, @@ -15300,18 +15308,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests are broad GitHub Actions version bumps, but they target different action families and different upgrade goals. They overlap in workflow files, yet they are not the same concrete change.", - "confidence": 0.92, + "summary": "Two workflow-dependency upgrade PRs overlap on some GitHub Actions files, but they target different upgrade goals and do not look like the same change set.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: #42975 upgrades checkout/cache/upload-artifact to satisfy Node 24 compatibility, while #42976 separately bumps docker/build-push-action and other workflow actions to newer versions.", + "canonical_pr_reason": "No clear duplicate PR here: PR #42975 is specifically about Node 24 compatibility for GitHub Actions, while PR #42976 is a broader 'latest versions' upgrade centered on docker/build-push-action and related workflow actions.", "best_issue_reason": null, - "best_pr_reason": "#42975 is the more central representative because it has the explicit Node 24 compatibility goal and a wider workflow footprint.", + "best_pr_reason": "PR #42975 is the better representative PR if one must be chosen because it has the clearest, more specific purpose and broader workflow-wide compatibility framing; PR #42976 looks like a separate dependency refresh.", "soft_edge_verdicts": [ { - "left": "PR #42975", - "right": "PR #42976", + "left": "pull_request:42975", + "right": "pull_request:42976", "accept": false, - "reason": "Related maintenance work, but not the same bug/change: one is Node 24 compatibility for core GitHub actions, the other is a separate docker-action/version refresh. They could live in separate PRs." + "reason": "Different underlying changes: one upgrades actions for Node 24 compatibility, the other updates actions to newer versions (notably docker/build-push-action). Shared workflow filenames alone are not enough to treat these as the same fix/change." } ] }, @@ -15325,7 +15333,7 @@ { "label": "pull_request", "component_index": 9, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15333,12 +15341,18 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-42978-4", + "cluster_id": "cluster-42978-10", "nodes": [ "pull_request:42978", "pull_request:43448", "pull_request:43451", - "pull_request:45490" + "pull_request:43838", + "pull_request:43973", + "pull_request:44601", + "pull_request:45157", + "pull_request:45283", + "pull_request:45490", + "pull_request:45532" ], "soft_pairs": [ "pull_request:42978|pull_request:43448", @@ -15346,72 +15360,128 @@ "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:43448|pull_request:45532", + "pull_request:43451|pull_request:45490", + "pull_request:43451|pull_request:45532", + "pull_request:43838|pull_request:45283", + "pull_request:43973|pull_request:45283", + "pull_request:44601|pull_request:45532", + "pull_request:45157|pull_request:45532", + "pull_request:45283|pull_request:45532", + "pull_request:45490|pull_request:45532" ], - "prepared_review_unit_hash": "036457cb07e5ab8e504d203bd32c1fe2629d5cedab775b53c3e4760656e030d8", + "prepared_review_unit_hash": "e3a4576fc0e397eb2fadf1fb118853a2db34567eb308f2ab22c8bb21920550b1", "component_budget": { - "node_count": 4, - "item_count": 4, - "soft_pair_count": 6, - "serialized_chars": 14136, - "estimated_input_tokens": 3534, - "estimated_eval_tokens": 7324 + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 32077, + "estimated_input_tokens": 8020, + "estimated_eval_tokens": 16296 }, "budget": { - "node_count": 4, - "item_count": 4, - "soft_pair_count": 6, - "serialized_chars": 14136, - "estimated_input_tokens": 3534, - "estimated_eval_tokens": 7324 + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 32077, + "estimated_input_tokens": 8020, + "estimated_eval_tokens": 16296 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are four separate model-addition PRs (ViT NEPA, Molmo, Molmo2, and CTSM). They share boilerplate registration/docs paths, but they do not describe the same underlying model or code-path change, so they should not be deduplicated.", + "summary": "False-positive cluster: the PRs are mostly unrelated model additions or infrastructure work that only overlap in boilerplate docs/auto-registry files. There is no single underlying bug or change here.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "No true canonical duplicate exists here; the PRs target different models and different implementation stacks, so none should be treated as the same change.", + "canonical_pr_reason": "No canonical PR: the set mixes distinct model additions (ViT NEPA, Molmo, Molmo2, Qwen3-ASR, Lfm2 Audio, CTSM, SLANet) plus unrelated distributed/quantization/GGUF changes; shared files are incidental boilerplate.", "best_issue_reason": null, - "best_pr_reason": "PR 43451 is the strongest single representative only because it has the broadest model-addition scope and the most review activity, but it is still distinct from the other PRs.", + "best_pr_reason": "No PR is a suitable global representative; these are separate feature PRs touching overlapping registry/docs files but fixing/adding different things.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different models and different implementations; shared docs/auto-registration files are just boilerplate for adding a new model." + "reason": "ViT NEPA vs Molmo are different model additions; overlap is only in docs/auto registration boilerplate." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "ViT NEPA vs Molmo2 are unrelated model additions; same support files do not imply the same underlying change." + "reason": "ViT NEPA and Molmo2 are distinct model integrations, not the same code change." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "Completely different model families and code paths; only generic model-registration files overlap." + "reason": "ViT NEPA and CTSM are unrelated model-addition PRs sharing only registry/docs files." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are separate model releases with distinct configs, modeling, and processing code, so they are not the same change." + "reason": "Molmo and Molmo2 are different model families with different files and logic; not one change." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM are unrelated additions; overlap is limited to shared Transformers scaffolding." + "reason": "Molmo vs CTSM are unrelated model support PRs; same broad subsystem is not enough." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45532", + "accept": false, + "reason": "Molmo and SLANet are separate model additions; shared docs/auto files are incidental." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM fix/add different model packages and code paths, so they should remain separate." + "reason": "Molmo2 and CTSM are different model integrations, not the same concrete bug or feature." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45532", + "accept": false, + "reason": "Molmo2 and SLANet are unrelated model support PRs; overlap is only registry scaffolding." + }, + { + "left": "pull_request:43838", + "right": "pull_request:45283", + "accept": false, + "reason": "Qwen3-ASR support and Qwen3.5 GGUF loading are different features in different code paths." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45283", + "accept": false, + "reason": "Lfm2 Audio model support is unrelated to Qwen3.5 GGUF loading; only broad audio/LLM tooling overlap." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45532", + "accept": false, + "reason": "Native pipeline-parallel support is infrastructure work, not the same change as SLANet model support." + }, + { + "left": "pull_request:45157", + "right": "pull_request:45532", + "accept": false, + "reason": "PrismML Bonsai GGUF quantization support and SLANet model support are unrelated changes." + }, + { + "left": "pull_request:45283", + "right": "pull_request:45532", + "accept": false, + "reason": "Qwen3.5 GGUF loading and SLANet model support do not fix the same concrete code-path problem." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45532", + "accept": false, + "reason": "CTSM and SLANet are different model-addition PRs; they share only generic docs/registry updates." } ] }, @@ -15425,7 +15495,7 @@ { "label": "pull_request", "component_index": 10, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15444,52 +15514,52 @@ "pull_request:43488|pull_request:45476", "pull_request:43532|pull_request:45476" ], - "prepared_review_unit_hash": "02232159f4100e6fbd268f172e7bc61c2aa8510ff089b098323dac7a55be609e", + "prepared_review_unit_hash": "91c37c0ad45a1f46a680f8f323a0a6ca98ea550e434cdb54e01949a00fe8ecf6", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7469, - "estimated_input_tokens": 1868, - "estimated_eval_tokens": 3992 + "serialized_chars": 7464, + "estimated_input_tokens": 1866, + "estimated_eval_tokens": 3988 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7469, - "estimated_input_tokens": 1868, - "estimated_eval_tokens": 3992 + "serialized_chars": 7464, + "estimated_input_tokens": 1866, + "estimated_eval_tokens": 3988 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Three unrelated open PRs were clustered only by weak soft similarity on a shared Vit test file; they target different synthetic repo-bot/CI behaviors and are not duplicates.", - "confidence": 0.98, + "summary": "Three unrelated open PRs that look like test/bot-infrastructure experiments rather than duplicates of the same fix. They share some filenames only because they all poke at repo testing/CI files, but the titles and diffs point to different purposes.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No clear canonical PR: the three PRs are about different changes (setup/deps formatting, comment-CI workflow plumbing, and CI workflow calling), so none is a strong representative duplicate target.", + "canonical_pr_reason": "PR #43532 is the broadest and most representative of the cluster: it touches multiple workflow and test files and has the most discussion activity, so it best captures the shared 'bot/CI test PR' theme.", "best_issue_reason": null, - "best_pr_reason": "PR #43532 is the broadest CI/workflow-oriented change, but it is still not a duplicate of the others; it is only the least isolated example among the three.", + "best_pr_reason": "PR #43532 is the strongest cluster exemplar because it has the widest scope across CI/test infrastructure and is more informative than the tiny, highly synthetic changes in #43488 and #45476.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Shared filename is only a test file, but the PRs modify different code paths and concerns: setup/dependency/version formatting vs workflow/comment-CI plumbing." + "reason": "Different intents: #43488 is a repo-bot format check, while #43532 rewrites a self-comment CI workflow and related test utilities. Shared Vit test filename is incidental and not the same underlying change." }, { "left": "pull_request:43488", "right": "pull_request:45476", "accept": false, - "reason": "These are different synthetic changes: one touches packaging/dependencies, the other adds a workflow caller and unrelated tokenizer/test edits; no same underlying bug or change." + "reason": "#43488 changes setup/versioning and a test file for a bot-format check; #45476 adds a PR CI caller workflow and unrelated placeholder edits. They do not fix the same code-path problem." }, { "left": "pull_request:43532", "right": "pull_request:45476", "accept": false, - "reason": "Both touch CI-related areas, but they fix different behaviors and files; the overlap is only superficial and they would not plausibly merge as one PR." + "reason": "Both are CI-related, but they target different workflows and behaviors: #43532 modifies self-comment/scheduled/slack reporting logic, while #45476 adds a PR CI workflow caller and unrelated tokenization/test noise. Not mergeable as one PR." } ] }, @@ -15503,7 +15573,7 @@ { "label": "pull_request", "component_index": 11, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15519,7 +15589,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "dd3cec546ebce74c4d941109823cab7e1a0d0aff1ed1280adc0d7c44c1443fc2", + "prepared_review_unit_hash": "46d53a5a505a20a476d557fa8d07d5b8cad0fbf79e57e86e14652007a57ec86c", "component_budget": { "node_count": 2, "item_count": 2, @@ -15541,18 +15611,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are related only at the framework/docs level; they add different pipelines for different tasks (concept segmentation vs visual segmentation) with different model coverage and tests, so they should not be treated as duplicates.", - "confidence": 0.96, + "summary": "Two open PRs add different segmentation pipelines and their associated docs/tests. They share scaffolding files, but they target different code paths and model families, so they are related but not duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical duplicate: these PRs implement different segmentation features and touch different concrete pipeline/model code paths.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the better representative only because it is the broader, more fully fleshed-out segmentation feature, but it is not a duplicate of 43612.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Different underlying changes: promptable concept segmentation vs promptable visual segmentation are separate pipelines with distinct filenames, model integrations, and test targets. Shared docs/infrastructure files are not enough to merge them as one change." + "reason": "Reject: these are separate feature PRs for different pipelines ('Promptable Concept Segmentation' vs 'Promptable Visual Segmentation'). They touch overlapping documentation and registration files, but the added pipeline modules, tests, and model integrations are different, so they do not look like one mergeable change." } ] }, @@ -15566,7 +15636,7 @@ { "label": "pull_request", "component_index": 12, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15582,12 +15652,12 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "c05359acea158ef062dbbd2a64bb64507d9afffa93f6c6ec4cea065571854efb", + "prepared_review_unit_hash": "4400efa376c7dcbc6858f01c76aa7e101ef0f006777a7d1bb3274167fccaaa65", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4291, + "serialized_chars": 4292, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -15595,7 +15665,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4291, + "serialized_chars": 4292, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -15604,18 +15674,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch the same trainer file but address different behavior: gradient-accumulation loss scaling vs. PEFT/signature-column inspection. They are not duplicates and should not be merged into one triage item.", - "confidence": 0.96, + "summary": "These are two separate trainer refactor/extension PRs in the same file, but they change different code paths: gradient-accumulation loss scaling vs. signature-column filtering for custom trainers. Shared filename alone is not enough to treat them as duplicates.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No single canonical PR for a duplicate cluster; the two PRs solve different trainer concerns. If one must be chosen as the closest representative, #43651 is more concrete because it changes the training-step loss scaling path directly.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "#43651 is the better standalone representative of this cluster because it introduces a focused training behavior change with an explicit helper and a concrete loss-scaling path. #43663 is a separate API/refactor for signature-column handling and is not the same change.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different concrete code paths and user-visible fixes: 43651 changes loss normalization in training_step for gradient accumulation, while 43663 extracts signature column inspection for column filtering and PEFT models. Shared file alone is not enough to treat them as the same change." + "reason": "Different underlying changes in `trainer.py`: #43651 alters gradient accumulation loss normalization in `training_step`, while #43663 extracts `_get_signature_columns` for model input filtering. They do not fix the same bug or implement the same feature, and would not plausibly be merged as one PR." } ] }, @@ -15629,7 +15699,7 @@ { "label": "pull_request", "component_index": 13, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15647,55 +15717,55 @@ "pull_request:43656|pull_request:43842", "pull_request:43836|pull_request:43842" ], - "prepared_review_unit_hash": "133d9eeed96d948e9b6929db551639bc031d3e9a7615015bb760e3955aee78fa", + "prepared_review_unit_hash": "c86cba35672572405f16aaae4b13227adea85732fa9f7ec589cb6bd44a0c13e5", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5993, - "estimated_input_tokens": 1499, - "estimated_eval_tokens": 3254 + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 5993, - "estimated_input_tokens": 1499, - "estimated_eval_tokens": 3254 + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster centers on `src/transformers/cli/serve.py` annotation/runtime fixes, but only 43836 and 43842 look like the same underlying `TypeAdapter` NameError bug. 43656 is a related annotation cleanup in the same file, but the evidence does not show it fixing the same `TypeAdapter` import/typing failure.", - "confidence": 0.79, + "summary": "All three PRs are small fixes in `src/transformers/cli/serve.py` around runtime type-annotation handling for `TypeAdapter` / CLI startup NameErrors. `43842` is the cleanest, most targeted fix; `43836` looks like a close variant of the same fix; `43656` appears related but broader and less clearly the same concrete change.", + "confidence": 0.82, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43842 is the cleanest, most concrete fix for the `TypeAdapter` NameError in `cli/serve.py`; it directly addresses the missing runtime import/typing reference with the narrowest scope.", + "canonical_pr_reason": "PR 43842 is the most focused and direct fix: it avoids importing `TypeAdapter` at runtime and quotes the annotation under `TYPE_CHECKING`, which cleanly addresses the reported NameError when pydantic is absent.", "best_issue_reason": null, - "best_pr_reason": "PR 43842 is the best representative because it targets the specific runtime failure described in the title and diff, without the extra scope of the broader refactor-style change in 43836.", + "best_pr_reason": "PR 43842 is the best representative of the cluster because it is narrowly scoped, directly tied to the runtime error, and less entangled with unrelated typing cleanups than 43656 or the broader refactor-like 43836.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Both touch `serve.py`, but 43656 only shows annotation/name-resolution cleanup around `TimedModel`; it does not show the `TypeAdapter` import/annotation fix that 43842 makes. Shared file alone is not enough." + "reason": "Both mention `TypeAdapter` NameError in the same file, but the visible fixes differ enough that they do not clearly look like the same concrete change; 43656 also includes broader annotation cleanup, so I would not merge them as one PR." }, { "left": "pull_request:43836", "right": "pull_request:43842", "accept": true, - "reason": "Both target the same `TypeAdapter` NameError in `cli/serve.py` and the same issue target, so they appear to be alternative fixes for the same concrete bug, even though 43836 is broader." + "reason": "These appear to be overlapping fixes for the same `TypeAdapter` annotation/runtime-NameError issue in `serve.py`, and the changes look plausibly mergeable into a single PR." } ] }, "evaluator_result": { - "accept": false, - "feedback": "Reject: the output overstates the evidence for the 43656 pair. The packet only shows 43656 fixing runtime annotation/name-resolution issues in `TimedModel` via `from __future__ import annotations` and unquoted model/processor types; it does not show the `TypeAdapter` import/annotation fix that 43842 addresses. Shared file + soft similarity is not enough to call it the same bugfix. The 43836\u219443842 pairing is more plausible because both target issue 43824, but the summary should stay more conservative about mergeability and scope." + "accept": true, + "feedback": "The summary is grounded in the packet: all three PRs touch `src/transformers/cli/serve.py` and are about the same `TypeAdapter`/startup NameError area. The softer edge decisions are also conservative enough: `43656` is plausibly broader and not clearly the same concrete change as `43842`, while `43836` and `43842` look mergeable as closely related fixes for the same bug in the same file." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -15703,7 +15773,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15722,52 +15792,52 @@ "pull_request:43757|pull_request:45500", "pull_request:43757|pull_request:45506" ], - "prepared_review_unit_hash": "4a8ca5d156ca4a6f689a49f6caa5fb5c16cdeca0fed52939bee7407bb15542d3", + "prepared_review_unit_hash": "7f6ef0b38d2a676600b5f113a3637f9f95d78e3df0afa91373be98f1fa40f423", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7783, - "estimated_input_tokens": 1946, - "estimated_eval_tokens": 4148 + "serialized_chars": 7755, + "estimated_input_tokens": 1939, + "estimated_eval_tokens": 4134 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7783, - "estimated_input_tokens": 1946, - "estimated_eval_tokens": 4148 + "serialized_chars": 7755, + "estimated_input_tokens": 1939, + "estimated_eval_tokens": 4134 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "PRs 45500 and 45506 are effectively the same GPT-OSS GGUF support change; 45506 is the better canonical PR because it is the non-draft latest version. PR 43757 is an earlier partial fallback fix in the same area, but it is not the same concrete change as the fuller support PRs.", - "confidence": 0.93, + "summary": "These are closely related GPT-OSS GGUF-loading PRs, but only the two later PRs are true duplicates; the earliest one is a narrower partial fix with extra unrelated changes. The strongest representative is PR #45506.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "45506 is the latest non-draft PR with the same title, same tracking issue, and the same file set as 45500; it appears to be the final version of that change.", + "canonical_pr_reason": "PR #45506 is the best canonical PR: it has the broadest and most complete GPT-OSS GGUF support, includes the relevant ggml mapping, loader changes, and tests, and it is a non-draft reviewed PR that effectively supersedes the earlier draft.", "best_issue_reason": null, - "best_pr_reason": "45506 is the best cluster representative because it is non-draft, later than 45500, and contains the complete GPT-OSS GGUF loading support rather than the earlier fallback-only approach in 43757.", + "best_pr_reason": "PR #45506 is the best global representative because it appears to implement the intended full fix for GPT-OSS GGUF loading rather than just a fallback, and it aligns with the shared target issue and the later duplicate PR.", "soft_edge_verdicts": [ { "left": "pull_request:45500", "right": "pull_request:45506", "accept": true, - "reason": "Same underlying GPT-OSS GGUF loading support change, same files and issue target, with 45506 looking like the updated final revision of 45500." + "reason": "Same underlying GPT-OSS GGUF loading change: same issue target, same title, overlapping files, and the later PR looks like a fuller iteration of the same fix that could plausibly be merged into one PR." }, { "left": "pull_request:43757", "right": "pull_request:45500", "accept": false, - "reason": "43757 is only an early fallback-to-gpt-neox workaround in the GGUF loader, while 45500 is a broader full-support PR; related, but not the same concrete change." + "reason": "Both touch GPT-OSS GGUF loading, but #43757 is a narrower fallback-based partial fix and also includes unrelated Grounding DINO changes, while #45500 is a broader full-support PR; they are related but not the same concrete change." }, { "left": "pull_request:43757", "right": "pull_request:45506", "accept": false, - "reason": "Same as above: 43757 is a partial predecessor workaround, not a duplicate of the later full GPT-OSS GGUF support implementation." + "reason": "#43757 only adds a fallback for an unsupported architecture and mixes in unrelated edits, while #45506 implements full GGUF support with mapping/test changes; they address the same bug family but are not the same mergeable code change." } ] }, @@ -15781,7 +15851,7 @@ { "label": "pull_request", "component_index": 15, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -15847,78 +15917,7 @@ { "label": "pull_request", "component_index": 16, - "component_count": 25, - "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-43838-3", - "nodes": [ - "pull_request:43838", - "pull_request:43973", - "pull_request:45283" - ], - "soft_pairs": [ - "pull_request:43838|pull_request:45283", - "pull_request:43973|pull_request:45283" - ], - "prepared_review_unit_hash": "35eb92639c5cdbf37fae6498b00d1ecf6e553669fb74fbe5e2d69a69fd709f8f", - "component_budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 2, - "serialized_chars": 8701, - "estimated_input_tokens": 2176, - "estimated_eval_tokens": 4608 - }, - "budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 2, - "serialized_chars": 8701, - "estimated_input_tokens": 2176, - "estimated_eval_tokens": 4608 - }, - "overflow_policy": "truncate_then_skip", - "trimmed": false, - "aggressively_trimmed": false, - "split": false, - "analyst_result": { - "summary": "These are three separate pull requests for different features: Qwen3-ASR model support, Lfm2Audio model support, and Qwen3.5 GGUF loading support. They share only broad audio/model-integration context and are not duplicates of the same underlying change.", - "confidence": 0.95, - "canonical_issue_reason": null, - "canonical_pr_reason": "No single PR represents the same underlying change as the others; the items cover distinct models and a separate GGUF-loading integration.", - "best_issue_reason": null, - "best_pr_reason": "43838 is the strongest standalone PR in the set because it is the most mature and explicit model-support addition, but it is not a canonical duplicate target for the other PRs.", - "soft_edge_verdicts": [ - { - "left": "pull_request:43838", - "right": "pull_request:45283", - "accept": false, - "reason": "Qwen3-ASR support and Qwen3.5 GGUF loading are different changes: one adds a new ASR model implementation/docs/tests, the other adds metadata mappings for GGUF loading. They do not fix the same code-path problem." - }, - { - "left": "pull_request:43973", - "right": "pull_request:45283", - "accept": false, - "reason": "Lfm2Audio model support and Qwen3.5 GGUF loading are unrelated features. They touch different model families and solve different integration problems." - } - ] - }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, - "error_kind": null, - "error_message": null - }, - { - "label": "pull_request", - "component_index": 17, - "component_count": 25, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 2, "status": "reviewed", @@ -15965,8 +15964,8 @@ "pull_request:44066|pull_request:44072", "pull_request:44013|pull_request:44044", "pull_request:44066|pull_request:44086", - "pull_request:44018|pull_request:44068", "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", @@ -15976,15 +15975,15 @@ "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:44116", "pull_request:44018|pull_request:44086", "pull_request:44018|pull_request:44085", "pull_request:44068|pull_request:44086", "pull_request:44071|pull_request:44085", "pull_request:44059|pull_request:44086", - "pull_request:44085|pull_request:44086", "pull_request:44059|pull_request:44722", + "pull_request:44085|pull_request:44086", "pull_request:44098|pull_request:44101", "pull_request:44018|pull_request:44071", "pull_request:44017|pull_request:44722", @@ -16030,12 +16029,12 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "a7df589688b5fd82c4de96519def960407f584706596230b449649d9c0e70114", + "prepared_review_unit_hash": "0126593005e81b5e9f15af1ba1ebddbb46aacb2bdea8e9a9d32aba0126e2ab5d", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, + "serialized_chars": 84895, "estimated_input_tokens": 21224, "estimated_eval_tokens": 42704 }, @@ -16043,327 +16042,309 @@ "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75091, - "estimated_input_tokens": 18773, - "estimated_eval_tokens": 37802 + "serialized_chars": 75096, + "estimated_input_tokens": 18774, + "estimated_eval_tokens": 37804 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly independent model-specific refactors for the broader output-tracing initiative, not a single duplicate bug. Only a few PRs clearly overlap on the same concrete code path: GPTJ/CodeGen variants and the GPT-Neo variants.", - "confidence": 0.86, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the best canonical PR here: it targets the same GPTJ/CodeGen output-tracing refactor as the other GPTJ variants, has explicit issue linkage, and appears to be the most complete/latest version of that concrete change.", - "best_issue_reason": null, - "best_pr_reason": "PR 44722 is the strongest representative of the duplicate subgroup because it covers the same GPTJ/CodeGen forward/output-capture path and subsumes narrower GPTJ-only variants.", + "summary": "This cluster is mostly a family of model-specific refactors toward standardized output tracing. Most PRs target different architectures and should stay separate; only a few pairs within the same model family look like true duplicates/overlaps.", + "confidence": 0.84, + "canonical_issue_reason": "Issue #43979 is the shared umbrella tracker for the standardized output-tracing refactor across these PRs.", + "canonical_pr_reason": "PR #44722 is the strongest representative for the GPT-J/CodeGen slice: it explicitly targets #43979, touches the same concrete code paths, and is the broadest later iteration in that subfamily.", + "best_issue_reason": "#43979 is the best global issue anchor because all of these PRs are variations of that same tracking effort.", + "best_pr_reason": "#44722 is the best global PR representative because it covers the same decorator-based output-tracing change on the core GPT-J/CodeGen path and is the most comprehensive example in the overlapping set.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model families and code paths; same meta-initiative only." + "reason": "Different models and code paths (CVT/FNet vs GPT-J); sharing the umbrella issue is not enough to make them duplicates." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different model families and code paths; not the same concrete fix." + "reason": "Different model families and different implementations of the tracing refactor." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both refactor the same GPTJ block output-tracing path; 44066 also updates the copied CodeGen block." + "reason": "Both are GPT-J output-tracing refactors on the same underlying code path, and could plausibly be merged into one PR." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "Different models and implementations; only share the standardized tracing theme." + "reason": "RegNet and EfficientNet are separate model implementations; same issue target only indicates a shared migration theme." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "Different model families; same broad refactor theme is not enough." + "reason": "Different models (EfficientNet vs GPT-J/CodeGen); not the same concrete bug or change." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "Different model families/code paths despite the same issue target." + "reason": "GPT-J/CodeGen vs EfficientNet are unrelated code paths despite the same tracking issue." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "Different models and code paths; only related by the output-tracing program." + "reason": "MobileNetV2 and DeBERTa are separate refactors with no shared code path." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPTJ/CodeGen vs MGP-STR are unrelated code paths." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44068", - "accept": true, - "reason": "Same model family and same GPT-Neo output-tracing refactor; these look like duplicate variants of the same change." + "reason": "Different model families (GPT-J/CodeGen vs MGP-STR); same umbrella refactor but not the same fix." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "Different models/code paths; not mergeable as one concrete fix." + "reason": "GPT-J/CodeGen and MPT are different implementations; no evidence of a single shared bug." }, { - "left": "pull_request:44066", + "left": "pull_request:44018", "right": "pull_request:44068", - "accept": false, - "reason": "GPTJ/CodeGen and GPT-Neo are distinct code paths." + "accept": true, + "reason": "Both PRs are GPT-Neo output-tracing refactors on the same model/file set, so they look like overlapping versions of the same change." }, { - "left": "pull_request:44018", - "right": "pull_request:44066", + "left": "pull_request:44066", + "right": "pull_request:44068", "accept": false, - "reason": "GPT-Neo vs GPTJ/CodeGen are different model implementations." + "reason": "GPT-J/CodeGen and GPT-Neo are different model paths, so these are separate PRs." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet and GPTJ/CodeGen are unrelated code paths." + "reason": "ResNet and GPT-J/CodeGen are unrelated model refactors." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPTJ/CodeGen are different model paths." + "reason": "MGP-STR and GPT-J/CodeGen are different code paths; same theme only." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPTJ are different code paths." + "reason": "ResNet vs GPT-J are different model implementations and not duplicates." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are unrelated implementations." + "reason": "GPT-Neo and ResNet are separate model-specific output-tracing changes." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are unrelated model paths." + "reason": "ResNet and MPT are different code paths." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert/XLM are different model code paths." + "reason": "GPT-Neo and Flaubert/XLM are different models; no shared concrete change." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo vs GPTJ/CodeGen are different fixes." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44116", - "accept": false, - "reason": "Different models and different concrete changes." + "reason": "GPT-Neo and GPT-J/CodeGen are separate implementations." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPTJ/CodeGen are unrelated code paths." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44086", - "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated implementations." + "reason": "MPT and GPT-J/CodeGen are different model paths." }, { - "left": "pull_request:44018", - "right": "pull_request:44085", - "accept": false, - "reason": "GPT-Neo and GPTJ are different model paths." - }, - { - "left": "pull_request:44068", + "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated changes." + "reason": "GPT2 and MGP-STR are unrelated model refactors." }, { "left": "pull_request:44059", - "right": "pull_request:44086", + "right": "pull_request:44722", "accept": false, - "reason": "GPT-2 and MGP-STR are different concrete code paths." + "reason": "GPT2 output tracing is a separate code path from GPT-J/CodeGen." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPTJ and MGP-STR are unrelated implementations." - }, - { - "left": "pull_request:44059", - "right": "pull_request:44722", - "accept": false, - "reason": "GPT-2 and GPTJ/CodeGen are different fixes." + "reason": "GPT-J and MGP-STR are different models; the similarity is only thematic." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert/XLM are distinct model paths." + "reason": "ViLT and Flaubert/XLM are distinct model implementations." }, { "left": "pull_request:44017", "right": "pull_request:44722", "accept": false, - "reason": "SegFormer and GPTJ/CodeGen are unrelated code paths." + "reason": "SegFormer and GPT-J/CodeGen are unrelated code paths." }, { "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "SegFormer and LongT5 are different implementations." + "reason": "SegFormer and LongT5 are different model-specific refactors." }, { "left": "pull_request:44017", "right": "pull_request:44073", "accept": false, - "reason": "SegFormer and VisualBert are different code paths." + "reason": "SegFormer and VisualBERT are separate implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different models, so this is not the same concrete change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBERT and Flaubert/XLM are distinct code paths." }, { "left": "pull_request:43997", "right": "pull_request:44056", "accept": false, - "reason": "RegNet and MPNet are unrelated model implementations." + "reason": "RegNet and MPNet are separate model refactors." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are unrelated model implementations." }, { "left": "pull_request:44074", "right": "pull_request:44101", "accept": false, - "reason": "TextNet and Flaubert/XLM are different code paths." + "reason": "TextNet and Flaubert/XLM are different models; same migration pattern only." }, { "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "MPNet and LongT5 are unrelated fixes." + "reason": "MPNet and LongT5 are separate code paths." }, { "left": "pull_request:43997", "right": "pull_request:44018", "accept": false, - "reason": "RegNet and GPT-Neo are different model paths." + "reason": "RegNet and GPT-Neo are different model families." }, { "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "RegNet and LongT5 are unrelated implementations." + "reason": "RegNet and LongT5 are unrelated model refactors." }, { "left": "pull_request:44074", - "right": "pull_request:44161", - "accept": false, - "reason": "TextNet and LongT5 are different code paths." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44071", + "right": "pull_request:44129", "accept": false, - "reason": "RegNet and MPT are unrelated model changes." + "reason": "TextNet and SpeechT5 are different code paths." }, { - "left": "pull_request:44010", - "right": "pull_request:44071", + "left": "pull_request:43996", + "right": "pull_request:44161", "accept": false, - "reason": "SqueezeBert and MPT are different concrete fixes." + "reason": "CVT/FNet and LongT5 are separate model implementations." }, { - "left": "pull_request:44010", - "right": "pull_request:44073", + "left": "pull_request:43996", + "right": "pull_request:44017", "accept": false, - "reason": "SqueezeBert and VisualBert are unrelated code paths." + "reason": "CVT/FNet and SegFormer are unrelated code paths." }, { "left": "pull_request:44010", - "right": "pull_request:44018", + "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBert and GPT-Neo are different implementations." + "reason": "SqueezeBERT and MPT are different model families." }, { "left": "pull_request:44010", - "right": "pull_request:44044", + "right": "pull_request:44073", "accept": false, - "reason": "SqueezeBert and DeBERTaV2 are unrelated fixes." + "reason": "SqueezeBERT and VisualBERT are separate refactors." }, { "left": "pull_request:44044", - "right": "pull_request:44074", + "right": "44074", "accept": false, - "reason": "DeBERTaV2 and TextNet are different model paths." + "reason": "DeBERTa and TextNet are different model implementations." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPTJ/CodeGen output-tracing refactor; 44722 is another iteration of the same concrete change." + "reason": "Both touch the same GPT-J/CodeGen output-tracing change family and could be combined into one PR." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both target the same GPTJ output-tracing code path and are plausibly mergeable into one PR." + "reason": "Both are GPT-J output-tracing refactors on the same file, so they look like overlapping versions of the same fix." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPTJ and SpeechT5 are unrelated code paths." + "reason": "GPT-J and SpeechT5 are unrelated model paths." }, { "left": "pull_request:43996", "right": "pull_request:44007", "accept": false, - "reason": "Different model families and different concrete refactors." + "reason": "CVT/FNet and RegNet are different models." }, { "left": "pull_request:43996", - "right": "44129", + "right": "pull_request:44129", "accept": false, - "reason": "CVT/FNet and SpeechT5 are unrelated implementations." + "reason": "CVT/FNet and SpeechT5 are unrelated code paths." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTaV2 and SpeechT5 are different model paths." + "reason": "DeBERTa and SpeechT5 are separate model refactors." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTaV2 and ViT/S are unrelated concrete changes." + "reason": "DeBERTa and VITS are different implementations; only the tracing pattern is shared." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays mostly conservative. The main duplicate candidates called out by the analyst \u2014 GPTJ/CodeGen variants and GPT-Neo variants \u2014 are supported by shared filenames, issue targets, and high similarity. The broader conclusion that most PRs are independent model-specific refactors is also consistent with the evidence. No obvious overstatement stands out." + "feedback": "The summary stays grounded in the packet: issue #43979 is the clear umbrella tracker for many of these output-tracing refactors, and #44722 is a reasonable representative for the GPT-J/CodeGen subgroup. The soft-edge calls are conservative overall: the accepted pairs share the same model/file family and look mergeable into a single bugfix PR, while the rejected pairs mostly involve different model architectures/code paths and are not strong duplicate candidates." }, "evaluator_used": true, "retried": false, @@ -16373,8 +16354,8 @@ }, { "label": "pull_request", - "component_index": 17, - "component_count": 25, + "component_index": 16, + "component_count": 23, "review_unit_index": 2, "review_unit_count": 2, "status": "reviewed", @@ -16401,12 +16382,12 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "c7013cddb5dc432ccc6343e583bbf6412c0e5cbf1ab01c6ba77bc91b401a55a2", + "prepared_review_unit_hash": "bf24c3b5dd052e905bf132d3a6bb0a219e86a5bed6415e6a0a0b481f6a4c1e3d", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84896, + "serialized_chars": 84895, "estimated_input_tokens": 21224, "estimated_eval_tokens": 42704 }, @@ -16414,57 +16395,57 @@ "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17126, - "estimated_input_tokens": 4282, - "estimated_eval_tokens": 8820 + "serialized_chars": 17120, + "estimated_input_tokens": 4280, + "estimated_eval_tokens": 8816 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs are thematically similar (model-by-model migration to standardized output capture), but they are separate per-model refactors rather than duplicates of one concrete fix/change.", - "confidence": 0.89, + "summary": "This cluster is a set of model-specific PRs all moving individual architectures toward standardized output tracing/capture_outputs. They share a broad refactor theme, but they are not the same concrete change and should not be merged as duplicates.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44129 is the strongest representative: it has an explicit issue link, a clear standardized output-capture refactor, and concrete code-path changes in SpeechT5.", + "canonical_pr_reason": "No issue artifacts are present. If one PR must represent the cluster, 44129 is the strongest standalone candidate because it has an explicit issue target and a clearly scoped standardized output tracing refactor.", "best_issue_reason": null, - "best_pr_reason": "PR #44129 is the best cluster representative because it is the most explicit about the intended refactor and ties to a tracking issue; the others are similarly scoped but model-specific.", + "best_pr_reason": "44129 is the best single PR to keep as canonical representative: it is a focused refactor with an explicit linked issue, while the others are separate model-by-model implementations of the same general migration pattern.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are standardized output-tracing refactors, but they touch different model implementations (FocalNet vs ImageGPT) and are not the same concrete code-path change." + "reason": "Both are output-tracing migrations, but for different models and code paths (FocalNet vs ImageGPT). This is the same refactor pattern, not the same change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Same refactor pattern, but different models (VisualBert vs TextNet) and different forward/output plumbing, so not mergeable as one duplicate change." + "reason": "VisualBert and TextNet are unrelated model implementations; the PRs share only the standardized output capture theme and do not fix the same concrete bug or change." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "Both migrate output recording, but MPNet and VisualBert are separate architectures with distinct tracing hooks and model code paths." + "reason": "These target different architectures (MPNet vs VisualBert). Similar decorator/capture_outputs work is too broad to treat as a duplicate PR." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "These are model-specific refactors for MPNet and TextNet, not the same underlying bug or patch." + "reason": "MPNet and TextNet are separate model refactors. The overlap is only the output-tracing migration pattern, not a mergeable single change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBERT are unrelated model implementations; despite similar decorator migration, they are distinct changes." + "reason": "RegNet and SqueezeBert changes affect different model files and code paths. Shared standardized-output plumbing is not enough to call them duplicates." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "Both are output-tracing refactors, but they target different models and code paths (SqueezeBERT vs SpeechT5), so they are not the same PR-worthy fix." + "reason": "SqueezeBert and SpeechT5 are unrelated model-specific PRs. They both touch output handling, but they are distinct refactors with different implementations and targets." } ] }, @@ -16477,8 +16458,8 @@ }, { "label": "pull_request", - "component_index": 18, - "component_count": 25, + "component_index": 17, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16543,262 +16524,274 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "41f057294154f7f7644d1a2937c5da52c6ed950eb4ad6b2c2c4f717bb25f9ff1", + "prepared_review_unit_hash": "1810dc89024bb4736c8db67097155b9cdb6729b9c26c379d4e778b08a7f16663", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 39, - "serialized_chars": 39778, - "estimated_input_tokens": 9945, - "estimated_eval_tokens": 20146 + "serialized_chars": 39787, + "estimated_input_tokens": 9947, + "estimated_eval_tokens": 20150 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 39, - "serialized_chars": 39778, - "estimated_input_tokens": 9945, - "estimated_eval_tokens": 20146 + "serialized_chars": 39787, + "estimated_input_tokens": 9947, + "estimated_eval_tokens": 20150 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs share a broad 'refactor output tracing' theme, but they are model-specific changes across different code paths and files, so they are not duplicates of the same underlying fix/change.", - "confidence": 0.94, + "summary": "These are many separate model-specific refactors that share the same output-tracing theme, but they do not fix the same concrete bug or change the same code path. I would not merge any of them as duplicates across model families.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No single PR is the obvious canonical duplicate because each patch targets a different model implementation; if one representative is needed, PR #44025 is a reasonable anchor since it touches two closely related model files and is a clear example of the refactor pattern.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR #44025 is the best representative of the cluster: it is a substantial instance of the output-tracing refactor, spans two related files, and its change scope is clearer than many of the single-file variants. It is not a duplicate of the others, just the most canonical example.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model families (`timm_backbone` vs `upernet`); same refactor motif, but not the same underlying code change." + "reason": "Different models and files (`timm_backbone` vs `upernet`); same refactor pattern, not the same code-path change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different implementations (`timm_backbone` vs `vision_text_dual_encoder`) with separate forward/output logic; not mergeable as one PR." + "reason": "Different subsystems (`timm_backbone` vs `vision_text_dual_encoder`); only the output-tracing refactor is shared." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different model code paths (`timm_backbone` vs `univnet`); only the refactor pattern matches." + "reason": "Different model families (`timm_backbone` vs `univnet`); no shared underlying bug/change." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Different subsystems (`timm_backbone` vs `falcon_mamba`/`mamba`); not the same bug or change." + "reason": "`timm_backbone` and `falcon_mamba/mamba` are unrelated code paths; similarity is only in the refactor style." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "`timm_backbone` and `codegen` touch unrelated architectures and files; not the same concrete change." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different model code paths (`timm_backbone` vs `rwkv`); shared output-tracing theme is too broad to count as duplicate." + "reason": "Different models (`timm_backbone` vs `rwkv`); shared output-capturing cleanup only." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "`mobilenet_v1` and `univnet` are unrelated model implementations; same refactor style, different changes." + "reason": "`mobilenet_v1` and `univnet` are unrelated implementations; not a duplicate bug fix." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "`mobilenet_v1` vs `upernet`; separate forward signatures and output handling." + "reason": "Different model families (`mobilenet_v1` vs `upernet`); no shared code-path problem." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "`mobilenet_v1` and `depth_anything` are distinct model files and code paths; not the same underlying fix." + "reason": "`mobilenet_v1` and `depth_anything` are separate model code paths; same refactor theme only." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "Different model families (`mobilenet_v1` vs `vision_encoder_decoder`); only superficially similar refactor work." + "reason": "`mobilenet_v1` and `vision_encoder_decoder` are unrelated; not the same underlying change." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "`mobilenet_v1` and `speech_encoder_decoder` change different encoder/decoder stacks; not duplicate PRs." + "reason": "Different models (`mobilenet_v1` vs `speech_encoder_decoder`); no mergeable duplicate relationship." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "`vision_text_dual_encoder` and `univnet` are unrelated models; same output-tracing cleanup, but not the same concrete change." + "reason": "`vision_text_dual_encoder` and `univnet` are different model families; only the refactor pattern matches." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different model code paths (`vision_text_dual_encoder` vs `upernet`); not the same fix." + "reason": "Different files and model architectures (`vision_text_dual_encoder` vs `upernet`); not the same concrete fix." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "`vision_text_dual_encoder` vs `falcon_mamba`/`mamba`; distinct model internals and outputs." + "reason": "`vision_text_dual_encoder` and `falcon_mamba/mamba` are unrelated code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model families (`vision_text_dual_encoder` vs `codegen`); shared output-tracing refactor is too broad to be a duplicate." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different models and files (`vision_text_dual_encoder` vs `depth_anything`); not mergeable as one PR." + "reason": "`vision_text_dual_encoder` and `depth_anything` modify different model stacks; not the same change." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "`univnet` and `upernet` are separate architectures with independent forward/output refactors." + "reason": "`univnet` and `upernet` are unrelated; same style of refactor, not same bug or PR." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "`univnet` vs `falcon_mamba`/`mamba`; same theme, different code paths." + "reason": "Different model families (`univnet` vs `falcon_mamba/mamba`); no shared concrete code path." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "`univnet` and `depth_anything` target different model families and output APIs." + "reason": "`univnet` and `depth_anything` are separate changes despite similar output-tracing cleanup." }, { "left": "pull_request:44002", - "right": "pull_request:44029", + "right": "pull_request:44003", "accept": false, - "reason": "`upernet` and `rwkv` are unrelated implementations; no shared concrete bug." + "reason": "`upernet` and `falcon_mamba/mamba` are different subsystems; not mergeable as one fix." }, { "left": "pull_request:44002", - "right": "pull_request:44003", + "right": "pull_request:44029", "accept": false, - "reason": "`upernet` vs `falcon_mamba`/`mamba`; not the same underlying code change." + "reason": "`upernet` and `rwkv` are unrelated model implementations; only the refactor theme overlaps." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "`falcon_mamba`/`mamba` and `codegen` are distinct model stacks; only the tracing refactor motif overlaps." + "reason": "`falcon_mamba/mamba` and `codegen` fix different model code paths; similarity is superficial." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "`timm_backbone` and `codegen` are unrelated model implementations; not the same change." + "reason": "Different models (`timm_backbone` vs `codegen`) and different files; not the same underlying bug/change." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "`univnet` and `codegen` differ in architecture and output semantics; not duplicates." + "reason": "`univnet` and `codegen` are unrelated; same output-tracing cleanup only." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "`upernet` and `codegen` are separate model code paths with different output handling." + "reason": "`upernet` and `codegen` are different code paths; not a duplicate change." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "`depth_anything` vs `vision_encoder_decoder`; similar refactor theme but different model families and files." + "reason": "Different model families (`depth_anything` vs `vision_encoder_decoder`); same refactor motif only." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "`depth_anything` and `speech_encoder_decoder` are unrelated changes." + "reason": "`depth_anything` and `speech_encoder_decoder` are separate code paths; not the same bug or feature." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "`depth_anything` vs `superpoint`; different model internals and output capture changes." + "reason": "`depth_anything` and `superpoint` are unrelated model implementations." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "`depth_anything` and `rwkv` are separate model implementations; not the same fix." + "reason": "`depth_anything` and `rwkv` are distinct model families; no duplicate fix." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "`depth_anything` vs `dpr`; different model code paths and output signatures." + "reason": "`depth_anything` and `dpr` touch different model code paths; not mergeable as one PR." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "`vision_encoder_decoder` and `speech_encoder_decoder` are related by pattern only; the concrete changes live in different files and model stacks." + "reason": "`vision_encoder_decoder` and `speech_encoder_decoder` are different wrappers and code paths; only the refactor pattern is shared." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "`vision_encoder_decoder` vs `superpoint`; unrelated models, not one underlying bug." + "reason": "`vision_encoder_decoder` and `superpoint` are unrelated; not the same underlying change." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "`vision_encoder_decoder` and `rwkv` are distinct code paths; no duplicate evidence beyond the refactor theme." + "reason": "`vision_encoder_decoder` and `rwkv` are different model families; not duplicates." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "`vision_encoder_decoder` and `dpr` are different models with separate output-tracing implementations." + "reason": "`vision_encoder_decoder` and `dpr` modify different code paths; similarity is only thematic." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "`speech_encoder_decoder` and `superpoint` are unrelated model changes." + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated model code paths." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "`speech_encoder_decoder` vs `rwkv`; different architectures and code paths." + "reason": "`speech_encoder_decoder` and `rwkv` are separate models; not the same concrete fix." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "`speech_encoder_decoder` and `dpr` are separate model implementations; not the same fix." + "reason": "`speech_encoder_decoder` and `dpr` are different subsystems; no duplicate relationship." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "`superpoint` and `rwkv` are unrelated; same output-tracing motif is too broad." + "reason": "`superpoint` and `rwkv` are unrelated implementations; same refactor pattern only." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "`superpoint` vs `dpr`; different models and forward behavior." + "reason": "`superpoint` and `dpr` touch different code paths; not the same bug/change." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "`rwkv` and `dpr` are different model stacks; not a duplicate change." + "reason": "`rwkv` and `dpr` are different model families; do not collapse into one PR." } ] }, @@ -16811,8 +16804,8 @@ }, { "label": "pull_request", - "component_index": 19, - "component_count": 25, + "component_index": 18, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16831,12 +16824,12 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "29641cd607dc31b6677ea4406f5ec4f9160265d97e3b8f57a181d798528a08dd", + "prepared_review_unit_hash": "87479abdaf2a74f154d5b71d23bb4b43e11ac6a4ad5617e44a6d80e24385af86", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 11070, + "serialized_chars": 11071, "estimated_input_tokens": 2768, "estimated_eval_tokens": 5792 }, @@ -16844,7 +16837,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 11070, + "serialized_chars": 11071, "estimated_input_tokens": 2768, "estimated_eval_tokens": 5792 }, @@ -16853,30 +16846,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition PRs for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They share the standard Transformers integration pattern, but they are not the same underlying change and should not be deduplicated.", - "confidence": 0.97, + "summary": "Three open PRs that each add a different model integration (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They overlap only in shared Transformers boilerplate and auto-registry/doc files, not in the underlying model or code path, so they are not duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "No single PR is a canonical duplicate target here; if forced to pick a representative, PR 45075 is the most complete model-addition implementation, but it addresses a different model than the others.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different models and codepaths: PenguinVL vs Voxtral TTS. Shared auto-registration/docs boilerplate is expected for model additions, not evidence of the same fix." + "reason": "Different model additions with different model directories, configs, modeling code, and tests (PenguinVL vs Voxtral TTS). Shared registry/docs updates are expected for any new model and do not indicate the same change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different models and implementations: PenguinVL vision-language support vs DeepSeek-OCR-2 OCR model. Same subsystem, but not the same underlying change." + "reason": "These implement unrelated model integrations (PenguinVL vs DeepSeek-OCR-2). The overlap is limited to generic auto-registration and docs plumbing, which is not enough to treat them as the same PR." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "Different model families and functionality: DeepSeek-OCR-2 vs Voxtral TTS. They only overlap on generic Transformers plumbing, so they should remain separate." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model implementations with separate codepaths and tests. Similar framework scaffolding is incidental, so they should not be merged as duplicates." } ] }, @@ -16889,8 +16882,8 @@ }, { "label": "pull_request", - "component_index": 20, - "component_count": 25, + "component_index": 19, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16906,7 +16899,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "e629c4851a5fc137ff92cd114b70f6efc821b7a79e635d501bd0356383afae0c", + "prepared_review_unit_hash": "3e6e27aa6a448edd5ef3ca66693e90ec03d598c522ff7f2bd67e3680357b7177", "component_budget": { "node_count": 2, "item_count": 2, @@ -16928,18 +16921,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are conceptually related around model/module fusion, but they are not duplicates: one introduces a general Module Fusion API scaffold, while the other implements KernelConfig-driven n-to-1 kernel fusion in model loading and integrations.", - "confidence": 0.92, + "summary": "These are related by theme (kernel/module fusion) but they do not look like duplicate PRs. One introduces a new low-level Module Fusion API, while the other adds n-to-1 kernel fusion through KernelConfig and integration points in modeling/integrations code.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45363 is the stronger representative of the cluster because it delivers a concrete end-to-end user feature with integration changes in modeling_utils, hub_kernels, and KernelConfig, plus an example. PR 44979 is a more generic API foundation.", + "canonical_pr_reason": "PR 45363 is the more representative cluster item because it implements the more concrete end-user feature set: KernelConfig-driven fusion wired into core loading/integration paths, plus an example. PR 44979 is a lower-level API scaffold for module fusion.", "best_issue_reason": null, - "best_pr_reason": "PR 45363 is the best overall PR to keep in view because it is more complete and actionable; it shows the actual fusion workflow rather than only the underlying abstraction layer.", + "best_pr_reason": "PR 45363 is the best overall representative because it has the broader, more product-facing change set and clearer integration surface, whereas PR 44979 is primarily the foundational API layer.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Related topic, but different underlying change: 44979 adds a new generic Module Fusion API in src/transformers/module_fusion.py, while 45363 wires KernelConfig-based n-to-1 fusion into loading/integrations and adds an example. They target different code paths and would not plausibly be merged as one duplicate PR." + "reason": "Reject as duplicate: the PRs target different change scopes and code paths. 44979 adds a standalone Module Fusion API in a new file, while 45363 wires KernelConfig-based n-to-1 kernel fusion through modeling/integration code and an example. They may be complementary, but they are not the same concrete fix or mergeable duplicate." } ] }, @@ -16952,8 +16945,8 @@ }, { "label": "pull_request", - "component_index": 21, - "component_count": 25, + "component_index": 20, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -16969,12 +16962,12 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "93f9ceeab1c9677afbc34c1d1588d409eb04506c3fffc3ffd26991ceeca665d3", + "prepared_review_unit_hash": "81a24774a51ba7b7ec74b2973a96490008e979b339ef8b5534b93f3f98409142", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4414, + "serialized_chars": 4413, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -16982,7 +16975,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4414, + "serialized_chars": 4413, "estimated_input_tokens": 1104, "estimated_eval_tokens": 2464 }, @@ -16991,18 +16984,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests target the same Mistral regex AttributeError fix in the same code path; 45317 appears to be the fuller follow-up with tests, while 45086 is the minimal code-only version.", - "confidence": 0.96, + "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 tests, so it is the more complete duplicate-candidate.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the better canonical representative because it implements the same fix as 45086 and also adds test coverage, making it the more complete change set.", + "canonical_pr_reason": "PR #45317 is the stronger canonical PR: it fixes the same bug as #45086 but also includes test coverage and appears to be the more complete version of the fix.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the strongest overall candidate: same underlying bug, same file, same explicit issue target, and it includes validation via tests.", + "best_pr_reason": "PR #45317 is the best overall representative because it addresses the same concrete bug with additional validation, while #45086 is a smaller earlier variant.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Accept: both PRs make the same concrete fix to _patch_mistral_regex / Mistral pre-tokenizer handling, with 45317 effectively superseding the smaller 45086 by adding tests." + "reason": "Same code path, same AttributeError fix, same target issue, and the second PR is just a more complete version with tests." } ] }, @@ -17015,8 +17008,8 @@ }, { "label": "pull_request", - "component_index": 22, - "component_count": 25, + "component_index": 21, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17032,12 +17025,12 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "9a01a3d257dd05f5730065704380d51bb74b81d542036a2e735dafe54249eb4c", + "prepared_review_unit_hash": "80316ef99041a814bb9552144ad0340fc485e79ef771d697f52377ec2c915992", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5397, + "serialized_chars": 5398, "estimated_input_tokens": 1350, "estimated_eval_tokens": 2956 }, @@ -17045,7 +17038,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5397, + "serialized_chars": 5398, "estimated_input_tokens": 1350, "estimated_eval_tokens": 2956 }, @@ -17054,18 +17047,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related but distinct PRs: one adds heterogeneous per-layer config support, the other builds broader heterogeneous model/runtime support on top of it. They overlap in shared heterogeneity plumbing, but they are not the same concrete change.", - "confidence": 0.89, + "summary": "The two open PRs are related but not duplicates: one adds heterogeneous per-layer config support, while the other adds broader heterogeneous model/runtime support that builds on that foundation. They overlap in infrastructure, but they address different scopes and code paths.", + "confidence": 0.86, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45332 is the broader end-to-end change: it includes config-aware cache/modeling updates plus heterogeneous model support, so it is the best single representative of the cluster.", + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes cache/modeling/masking updates plus GPT OSS integration and tests, making it the clearest representative of the overall heterogeneous-model feature set.", "best_issue_reason": null, - "best_pr_reason": "PR #45332 is the strongest representative because it spans the actual runtime/model-path changes, not just config plumbing.", + "best_pr_reason": "PR #45332 is the most complete and representative PR in this cluster, since it covers the end-to-end modeling/runtime support rather than just the config layer.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Shared heterogeneity framework and files, but #45333 is config-only while #45332 adds modeling/cache/runtime changes. They are related groundwork and follow-up, not the same bug or a single mergeable PR." + "reason": "Related feature work, but not the same concrete change. #45333 is config-only per-layer configuration support, while #45332 adds model/runtime handling on top of that. They should remain separate PRs and would not plausibly be merged into one duplicate fix." } ] }, @@ -17078,89 +17071,8 @@ }, { "label": "pull_request", - "component_index": 23, - "component_count": 25, - "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-45351-3", - "nodes": [ - "pull_request:45351", - "pull_request:45509", - "pull_request:45515" - ], - "soft_pairs": [ - "pull_request:45351|pull_request:45509", - "pull_request:45351|pull_request:45515", - "pull_request:45509|pull_request:45515" - ], - "prepared_review_unit_hash": "6008f1acf7788fba1a6632d554c45ad90ba846233f20853acab194f0eb97c389", - "component_budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 3, - "serialized_chars": 5819, - "estimated_input_tokens": 1455, - "estimated_eval_tokens": 3166 - }, - "budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 3, - "serialized_chars": 5819, - "estimated_input_tokens": 1455, - "estimated_eval_tokens": 3166 - }, - "overflow_policy": "truncate_then_skip", - "trimmed": false, - "aggressively_trimmed": false, - "split": false, - "analyst_result": { - "summary": "All three PRs target the same underlying bug in `get_device_properties()` on CUDA-capable systems without an available GPU: calling `torch.cuda.get_device_capability()` without first checking `torch.cuda.is_available()`. The patches differ mainly in scope and cleanup, not in the core fix.", - "confidence": 0.93, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45515 is the cleanest and most focused fix for the shared crash: it directly adds the CUDA availability guard in `get_device_properties()` with minimal extra changes.", - "best_issue_reason": null, - "best_pr_reason": "PR 45515 best represents the cluster because it addresses the exact failure mode with the smallest, most direct code change.", - "soft_edge_verdicts": [ - { - "left": "pull_request:45351", - "right": "pull_request:45509", - "accept": true, - "reason": "Same concrete bug in `get_device_properties()`: both prevent `get_device_capability()` from running when CUDA is unavailable. The extra XPU-related cleanup in 45351 does not change the underlying fix." - }, - { - "left": "pull_request:45351", - "right": "pull_request:45515", - "accept": true, - "reason": "Both PRs fix the same crash path by guarding CUDA capability access with `torch.cuda.is_available()`. They are the same underlying change, with 45351 just carrying additional nearby edits." - }, - { - "left": "pull_request:45509", - "right": "pull_request:45515", - "accept": true, - "reason": "Both are straightforward fixes for the same `get_device_properties()` CUDA/no-GPU crash and could plausibly be merged into one PR." - } - ] - }, - "evaluator_result": { - "accept": true, - "feedback": "The cluster summary is grounded in the packet: all three PRs edit the same `get_device_properties()` path and add a CUDA availability guard to avoid the no-GPU crash. The soft-edge verdicts are conservative enough, and the pairwise merges look like plausible same-bugfix alternatives rather than unrelated changes. PR 45515 is a reasonable canonical choice because it is the most focused of the three." - }, - "evaluator_used": true, - "retried": false, - "accepted_nontrivial_soft_edge": true, - "error_kind": null, - "error_message": null - }, - { - "label": "pull_request", - "component_index": 24, - "component_count": 25, + "component_index": 22, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17176,12 +17088,12 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "e9480638c07cdb9b3bff778ef0c20d22c800a324ab9036ea50cc3bc3168fc8b6", + "prepared_review_unit_hash": "ee755e34959b05cc003c30ff28d3bc1159ee2c45e62a08e22bb0b8a1720a6b99", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5305, + "serialized_chars": 5306, "estimated_input_tokens": 1327, "estimated_eval_tokens": 2910 }, @@ -17189,7 +17101,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5305, + "serialized_chars": 5306, "estimated_input_tokens": 1327, "estimated_eval_tokens": 2910 }, @@ -17198,18 +17110,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs both touch typing-related code, but they address different scopes: one is a broad type-checking sweep across many files, the other is a focused set of typing aliases and PEFT/modeling_utils adjustments. They are not the same underlying change.", - "confidence": 0.86, + "summary": "These are both typing-related PRs in transformers, but they address different scopes: one is a broad repo-wide type-checking sweep, the other is a focused typing cleanup around modeling_utils/PEFT. They are not the same underlying change.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45415 is the broader, more central typing cleanup change and is the better cluster representative if a PR must be chosen.", + "canonical_pr_reason": "PR 45425 is the more self-contained change set: it adds typing protocols/aliases for modeling_utils and related PEFT integration, with a clear single purpose.", "best_issue_reason": null, - "best_pr_reason": "PR #45415 is the most representative of the cluster\u2019s overall typing-theme and spans the widest set of affected files.", + "best_pr_reason": "PR 45425 is the best representative for the cluster because it has a narrower, coherent typing objective and is less of a sweeping repository-wide cleanup.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Both are typing-related, but #45415 is a broad type-checking sweep while #45425 is a narrower typing-compatibility patch in _typing/modeling_utils/PEFT. They do not appear to fix the same concrete code-path problem and would not naturally merge into one PR." + "reason": "Both are typing-focused, but 45415 is a broad multi-file type-checking pass while 45425 is a targeted modeling_utils/PEFT typing refactor; they do not appear to fix the same concrete code-path problem and would not plausibly merge as one PR." } ] }, @@ -17222,8 +17134,8 @@ }, { "label": "pull_request", - "component_index": 25, - "component_count": 25, + "component_index": 23, + "component_count": 23, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17239,40 +17151,40 @@ "soft_pairs": [ "pull_request:45470|pull_request:45487" ], - "prepared_review_unit_hash": "46ee694ab4f30d54ac2972a441b88c43bbc05516be60e1e96b484bec6b24cb46", + "prepared_review_unit_hash": "483cef7dedc5d0ddad970e5774ae026987915b01ccf43260587ac71f587d83b9", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4769, - "estimated_input_tokens": 1193, - "estimated_eval_tokens": 2642 + "serialized_chars": 4777, + "estimated_input_tokens": 1195, + "estimated_eval_tokens": 2646 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4769, - "estimated_input_tokens": 1193, - "estimated_eval_tokens": 2642 + "serialized_chars": 4777, + "estimated_input_tokens": 1195, + "estimated_eval_tokens": 2646 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are unrelated in substance: one adjusts a test expectation for SAM3 Lite Text, while the other fixes a model-parallel/device handling bug across AltCLIP/ChineseCLIP and related models. They should not be clustered as duplicates.", - "confidence": 0.97, + "summary": "These PRs are not duplicates: one is a narrow test skip for SAM3 Lite Text flash-attn dispatch behavior, while the other is a multi-file model-parallel fix for AltCLIP/ChineseCLIP and related models. They touch different code paths and would not plausibly merge into one PR.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45487 is the stronger canonical PR because it makes a concrete code-path fix in model forward logic and touches the actual bug source, whereas PR 45470 only skips a failing test.", + "canonical_pr_reason": "PR 45487 is the stronger canonical PR because it contains the actual functional fix across model code, whereas PR 45470 only adjusts a test expectation/skip for a specific SAM3 Lite Text case.", "best_issue_reason": null, - "best_pr_reason": "PR 45487 is the best representative of the cluster\u2019s substantive work; PR 45470 is just a test skip workaround and does not cover the same underlying problem.", + "best_pr_reason": "PR 45487 is the best representative artifact for the cluster since it addresses a concrete runtime bug and spans the substantive code changes; PR 45470 is only a test-level workaround.", "soft_edge_verdicts": [ { "left": "pull_request:45470", "right": "pull_request:45487", "accept": false, - "reason": "Different underlying problems: 45470 only skips a SAM3 Lite Text flash-attn test due to a composite-model test mismatch, while 45487 fixes device/model-parallel handling in AltCLIP/ChineseCLIP code paths. They are not the same change and would not plausibly merge into one PR." + "reason": "Different problems and code paths: 45470 skips a flash-attn composite-model test in sam3_lite_text, while 45487 fixes model-parallel token_type_ids/device handling and related modules in AltCLIP/ChineseCLIP. Not the same underlying change." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index d7a152faac127b195c096bc91fa355945fe2f6d7..55b6139d014b96c1a963587127d03c930b3902be 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260420t120036z", + "analysis_id": "hybrid-model-20260420t180040z", "archived_artifacts": { - "hybrid": "snapshots/20260420T120036Z/analysis-runs/hybrid-model-20260420t120036z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260420T120036Z/analysis-runs/hybrid-model-20260420t120036z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-04-20T12:17:50Z", + "published_at": "2026-04-20T18:14:36Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260420T120036Z", + "snapshot_id": "20260420T180040Z", "variant": "hybrid" } diff --git a/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.json b/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..88f73deb902e568149cf4f668650548bddd5d08e --- /dev/null +++ b/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.json @@ -0,0 +1,2028 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260420T180040Z", + "generated_at": "2026-04-20T18:14:35Z", + "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": 0.75, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.164, + "size_similarity": 0.096, + "file_overlap": 0.3, + "area_overlap": 0.078, + "patch_similarity": 0.182, + "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, + 1753 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44514-5", + "summary": "Cluster of 3 issues and 2 PRs centered on issue #44521.", + "status": "open", + "confidence": 0.6, + "canonical_issue_number": 44521, + "canonical_pr_number": 44535, + "issue_numbers": [ + 44514, + 44521, + 44545 + ], + "pr_numbers": [ + 44535, + 44543 + ], + "evidence_types": [ + "closing_reference", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44535, + "right_pr_number": 44543, + "code_similarity": 0.121, + "size_similarity": 0.477, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.169, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-43366-4", + "summary": "Cluster of 1 issues and 3 PRs centered on issue #43366.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43366, + "canonical_pr_number": 45506, + "issue_numbers": [ + 43366 + ], + "pr_numbers": [ + 43757, + 45500, + 45506 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43757, + "right_pr_number": 45500, + "code_similarity": 0.096, + "size_similarity": 0.149, + "file_overlap": 0.2, + "area_overlap": 0.005, + "patch_similarity": 0.031, + "shared_filenames": [ + "src/transformers/modeling_gguf_pytorch_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/modeling_gguf_pytorch_utils.py", + "left_ranges": [ + [ + 462, + 474 + ] + ], + "right_ranges": [ + [ + 171, + 277 + ], + [ + 456, + 462 + ], + [ + 518, + 525 + ], + [ + 620, + 627 + ], + [ + 709, + 753 + ] + ] + } + ] + }, + { + "left_pr_number": 43757, + "right_pr_number": 45506, + "code_similarity": 0.116, + "size_similarity": 0.17, + "file_overlap": 0.25, + "area_overlap": 0.005, + "patch_similarity": 0.034, + "shared_filenames": [ + "src/transformers/modeling_gguf_pytorch_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/modeling_gguf_pytorch_utils.py", + "left_ranges": [ + [ + 462, + 474 + ] + ], + "right_ranges": [ + [ + 171, + 277 + ], + [ + 456, + 462 + ], + [ + 518, + 525 + ], + [ + 620, + 627 + ], + [ + 709, + 753 + ] + ] + } + ] + }, + { + "left_pr_number": 45500, + "right_pr_number": 45506, + "code_similarity": 0.886, + "size_similarity": 0.877, + "file_overlap": 0.75, + "area_overlap": 0.996, + "patch_similarity": 0.912, + "shared_filenames": [ + "src/transformers/integrations/ggml.py", + "src/transformers/modeling_gguf_pytorch_utils.py", + "tests/quantization/ggml/test_ggml.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/ggml.py", + "left_ranges": [ + [ + 89, + 109 + ] + ], + "right_ranges": [ + [ + 89, + 109 + ] + ] + }, + { + "filename": "src/transformers/modeling_gguf_pytorch_utils.py", + "left_ranges": [ + [ + 171, + 277 + ], + [ + 456, + 462 + ], + [ + 518, + 525 + ], + [ + 620, + 627 + ], + [ + 709, + 753 + ] + ], + "right_ranges": [ + [ + 171, + 277 + ], + [ + 456, + 462 + ], + [ + 518, + 525 + ], + [ + 620, + 627 + ], + [ + 709, + 753 + ] + ] + }, + { + "filename": "tests/quantization/ggml/test_ggml.py", + "left_ranges": [ + [ + 351, + 358 + ], + [ + 386, + 406 + ] + ], + "right_ranges": [ + [ + 351, + 358 + ], + [ + 386, + 405 + ] + ] + } + ] + } + ] + }, + { + "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-43824-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43824.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43824, + "canonical_pr_number": 43836, + "issue_numbers": [ + 43824 + ], + "pr_numbers": [ + 43836, + 43842 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43836, + "right_pr_number": 43842, + "code_similarity": 0.332, + "size_similarity": 0.088, + "file_overlap": 1.0, + "area_overlap": 0.033, + "patch_similarity": 0.017, + "shared_filenames": [ + "src/transformers/cli/serve.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/cli/serve.py", + "left_ranges": [ + [ + 11, + 18 + ], + [ + 359, + 429 + ], + [ + 584, + 590 + ], + [ + 1892, + 1910 + ], + [ + 1917, + 1923 + ] + ], + "right_ranges": [ + [ + 54, + 61 + ], + [ + 587, + 593 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-44018-2", + "summary": "Cluster of 2 related pull requests linked by soft_similarity.", + "status": "open", + "confidence": 0.5, + "canonical_issue_number": null, + "canonical_pr_number": 44068, + "issue_numbers": [], + "pr_numbers": [ + 44018, + 44068 + ], + "evidence_types": [ + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 44018, + "right_pr_number": 44068, + "code_similarity": 0.766, + "size_similarity": 0.939, + "file_overlap": 1.0, + "area_overlap": 0.425, + "patch_similarity": 0.866, + "shared_filenames": [ + "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "tests/models/gpt_neo/test_modeling_gpt_neo.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gpt_neo/modeling_gpt_neo.py", + "left_ranges": [ + [ + 26, + 46 + ], + [ + 138, + 143 + ], + [ + 182, + 187 + ], + [ + 283, + 295 + ], + [ + 327, + 341 + ], + [ + 348, + 354 + ], + [ + 360, + 369 + ], + [ + 399, + 406 + ], + [ + 411, + 419 + ], + [ + 428, + 433 + ], + [ + 472, + 492 + ], + [ + 507, + 513 + ], + [ + 519, + 528 + ], + [ + 541, + 559 + ], + [ + 562, + 567 + ], + [ + 595, + 601 + ], + [ + 607, + 614 + ], + [ + 627, + 643 + ], + [ + 685, + 690 + ], + [ + 708, + 714 + ], + [ + 720, + 727 + ], + [ + 740, + 757 + ], + [ + 761, + 766 + ], + [ + 780, + 786 + ], + [ + 791, + 798 + ], + [ + 807, + 822 + ], + [ + 840, + 845 + ] + ], + "right_ranges": [ + [ + 26, + 31 + ], + [ + 34, + 44 + ], + [ + 136, + 141 + ], + [ + 180, + 185 + ], + [ + 281, + 293 + ], + [ + 325, + 339 + ], + [ + 346, + 352 + ], + [ + 358, + 367 + ], + [ + 397, + 404 + ], + [ + 409, + 417 + ], + [ + 426, + 434 + ], + [ + 463, + 483 + ], + [ + 498, + 504 + ], + [ + 510, + 519 + ], + [ + 532, + 550 + ], + [ + 553, + 564 + ], + [ + 586, + 592 + ], + [ + 598, + 605 + ], + [ + 618, + 634 + ], + [ + 676, + 688 + ], + [ + 699, + 705 + ], + [ + 711, + 718 + ], + [ + 731, + 748 + ], + [ + 752, + 762 + ], + [ + 771, + 777 + ], + [ + 782, + 789 + ], + [ + 798, + 813 + ], + [ + 831, + 836 + ] + ] + }, + { + "filename": "tests/models/gpt_neo/test_modeling_gpt_neo.py", + "left_ranges": [ + [ + 458, + 464 + ] + ], + "right_ranges": [ + [ + 458, + 464 + ] + ] + } + ] + } + ] + } + ], + "duplicate_issues": [ + { + "cluster_id": "cluster-44514-5", + "canonical_issue_number": 44521, + "duplicate_issue_numbers": [ + 44514, + 44545 + ], + "reason": "Issues in cluster-44514-5 are treated as duplicates because they share closing_reference, soft_similarity evidence." + } + ], + "duplicate_prs": [ + { + "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, shared_issue_target 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-43366-4", + "canonical_pr_number": 45506, + "duplicate_pr_numbers": [ + 43757, + 45500 + ], + "target_issue_number": 43366, + "reason": "PRs in cluster-43366-4 are treated as duplicates because they converge on issue #43366 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43824-3", + "canonical_pr_number": 43836, + "duplicate_pr_numbers": [ + 43842 + ], + "target_issue_number": 43824, + "reason": "PRs in cluster-43824-3 are treated as duplicates because they converge on issue #43824 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43979-11", + "canonical_pr_number": 44007, + "duplicate_pr_numbers": [ + 43996, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "target_issue_number": 43979, + "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-44514-5", + "canonical_pr_number": 44535, + "duplicate_pr_numbers": [ + 44543 + ], + "target_issue_number": 44521, + "reason": "PRs in cluster-44514-5 are treated as duplicates because they converge on issue #44521 with closing_reference, 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." + } + ], + "best_issue": { + "cluster_id": "cluster-44514-5", + "issue_number": 44521, + "reason": "Issue #44521 is the strongest global issue candidate because it is open, belongs to a cluster with 5 artifacts, and carries 8 discussion comments plus 5 inbound references.", + "score": 171.0 + }, + "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/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..190acdb27d94e7152632746241b4a92944d694a3 --- /dev/null +++ b/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,17199 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260420T180040Z", + "generated_at": "2026-04-20T18:14:35Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 13, + "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-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "98df1802115efb1a69b7d7bdc06a79effc3bec4a2484ef1b0714822889240aaa", + "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 do not look like one duplicate set. #13244 is about TAPAS tokenization mismatching TensorFlow, while #15980 and #16618 are both model-loading/download failures but appear to describe different failure modes: private-model authentication versus a generic \"can't load bert-base-uncased\" error.", + "confidence": 0.78, + "canonical_issue_reason": "#16618 is the broadest model-loading issue in the set and the most plausible umbrella candidate; #15980 is narrower and specifically about private-model login/auth messaging, and #13244 is unrelated.", + "canonical_pr_reason": null, + "best_issue_reason": "#16618 is the best single issue to represent the cluster because it is the most generic model-load failure title, but it still does not clearly subsume the other two issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Different problem domains: TAPAS tokenization vs. bert model loading. No indication they share the same underlying bug." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Both concern model download/load failures, but one is explicitly about private-model auth and bad messaging while the other is a generic bert-base-uncased load failure; not enough evidence they are the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 1, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "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:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44661", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45070", + "issue:45081", + "issue:45084", + "issue:45161", + "issue:45237", + "issue:45362", + "issue:45464", + "issue:45507" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "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:43638|issue:44805", + "issue:35545|issue:36010", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:44661|issue:44805", + "issue:30277|issue:43638", + "issue:34634|issue:35545", + "issue:43596|issue:43638", + "issue:43975|issue:44457", + "issue:43039|issue:45161", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:43975|issue:45237", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:43828|issue:45161", + "issue:43425|issue:44292", + "issue:34928|issue:41720", + "issue:44918|issue:45161", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "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:43716|issue:44918", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:43039|issue:44805", + "issue:34928|issue:36010", + "issue:41762|issue:43596", + "issue:43901|issue:44512", + "issue:39290|issue:41720", + "issue:43039|issue:44560", + "issue:43866|issue:44863", + "issue:43854|issue:43866", + "issue:43425|issue:45070", + "issue:39290|issue:43531", + "issue:41093|issue:43638", + "issue:45362|issue:45464", + "issue:43404|issue:43866", + "issue:43792|issue:45070", + "issue:43541|issue:43828", + "issue:36010|issue:39290", + "issue:44841|issue:45084", + "issue:41093|issue:41762", + "issue:43296|issue:43366" + ], + "prepared_review_unit_hash": "601f58403abd9fc607c6a01a7ea93110494079e728734ee014951a37a939e532", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 63, + "serialized_chars": 46473, + "estimated_input_tokens": 11619, + "estimated_eval_tokens": 23494 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issues with a few thematic clusters. The only clear duplicate-like pair is the DeepSpeed ZeRO-3 zero-sized index error on Bert; the rest are too loosely related to merge.", + "confidence": 0.87, + "canonical_issue_reason": "issue:43596 is the best representative of the only strong duplicate cluster: the same DeepSpeed ZeRO-3 'index 0 is out of bounds for dimension 0 with size 0' loading failure, with issue:43638 as a near-exact duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43596 is the clearest canonical issue to keep because it is specific, well-scoped, and has the strongest near-duplicate match in the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different problems: config attribute missing vs streaming chat/completions failure." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Both mention model execution, but one is an image-preprocessor dtype mismatch and the other is AMD GPU support." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Autocast dtype mismatch is not the same failure as GPT-OSS not working on AMD GPUs." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Unrelated failures: AMD GPU runtime issue vs invalid method call in GraniteMoEHybrid." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different model/runtime failures with no clear shared code path." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "DeepSpeed collective mismatch is unrelated to ModernBERT ONNX export." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "ModernBERT ONNX export and Qwen3MoE FP8 loading are different code paths." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "Export error vs auto device-mapping CUDA assert; not the same bug." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs issues for v5, but they target different stale references and are not clearly one fix." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both are index/error-themed, but one is ZeRO-3 zero-sized tensor loading and the other is a mask-shape mismatch." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export and GenerationMixin import failure are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different symptom and likely different underlying bug: ZeRO-3 loading vs mask indexing." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Mask-shape index error is unrelated to GPT-OSS tensor-parallel failure." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer-mapping generator bug vs tensor mask mismatch; not the same issue." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both involve DeepSpeed, but collective mismatch and zero-sized index-out-of-bounds are different failures." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice_preset and ModernBERT ONNX export are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Near-exact duplicate: same DeepSpeed ZeRO-3 'index 0 is out of bounds for dimension 0 with size 0' loading failure on Bert." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Detokenization regression and LoRA merge/reload mismatch are different bugs." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger cross-entropy call and GPT-OSS tensor-parallel failure do not share a concrete fix." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Qwen NVFP4 runtime error and LoRA save/reload inconsistency are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation-checkpointing/FSDP tensor recomputation issue is distinct from the mask-shape index error." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both involve DeepSpeed, but the runtime weight-dimension error and collective mismatch are different code paths." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Detokenization bug and AMD GPU runtime failure are unrelated." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 Bert loading failure and GPT-OSS tensor-parallel issue are different bugs." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Activation checkpointing mismatch is unrelated to CustomTrainer.compute_loss signature breakage." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "DeepSpeed ZeRO-3 loading failure does not match the GPT-OSS tensor-parallel problem." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Dtype mismatch in Mistral-3 is not the same as an invalid-method call in GraniteMoEHybrid." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3 config attribute error and Mistral regex patch crash are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch is unrelated to GPT-OSS MoE tensor-parallel failure." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and CustomTrainer API break are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger kernel cross-entropy call is unrelated to mask/tensor indexing." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "Checkpointing tensor-size mismatch and GenerationMixin import failure are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Both are ZeRO-3 loading errors, but Gemma3 and Bert titles do not show the same concrete bug." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs topics and different stale references." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different model families and different runtime failures." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Liger kernel cross-entropy issue is unrelated to Qwen3-vl video StopIteration." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Corrupted checkpoint vs model implementation cannot load checkpoints are not the same issue." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unit-test load failure and checkpoint corruption are different root causes." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch version incompatibility and pydantic PretrainedConfig breakage are unrelated." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Gemma3 vLLM config attribute error and Qwen3-MoE sliding_window issue are different." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are index errors, but the mask-length mismatch is not the same as ZeRO-3 zero-sized loading." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Qwen3.5 chat crash and streaming inference API failure are related only by model family, not concrete bug." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Untied lm_head weights and corrupted checkpoint are unrelated." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper runtime failure and pydantic field breakage are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Grouped_mm tracing failure and autocast dtype mismatch are different MoE/runtime issues." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "GenerationMixin import error and Gemma3 sliding_window_pattern error are unrelated." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Processor failure and template-node compilation error are different problems." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are index-style runtime errors, but the specific mask mismatch and ZeRO-3 zero-size access are not the same bug." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "PaddleOCR-VL loading failure and GGUF gpt-oss support request are not duplicates." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted duplicate pair, issue:43596 with issue:43638, is well-supported by the titles. The other soft-edge rejections are cautious and do not overclaim duplicates. Minor note: issue:41762 is somewhat thematically close to the ZeRO-3 loading cluster, but the analyst did not overstate it as a duplicate, which is acceptable." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 2, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:36331", + "issue:39186", + "issue:39290", + "issue:39692", + "issue:40990", + "issue:41093", + "issue:41553", + "issue:41762", + "issue:42915", + "issue:43054", + "issue:43366", + "issue:43404", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43644", + "issue:43645", + "issue:43742", + "issue:43828", + "issue:43866", + "issue:43873", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44492", + "issue:44512", + "issue:44530", + "issue:44534", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44863", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45070", + "issue:45161", + "issue:45399", + "issue:45464", + "issue:45507" + ], + "soft_pairs": [ + "issue:43572|issue:45070", + "issue:44387|issue:45005", + "issue:43541|issue:45161", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:43531|issue:45070", + "issue:44661|issue:45464", + "issue:43541|issue:44589", + "issue:39290|issue:43742", + "issue:43054|issue:43994", + "issue:41093|issue:43596", + "issue:42915|issue:43541", + "issue:40990|issue:44960", + "issue:39186|issue:44918", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:44530|issue:45005", + "issue:44863|issue:45005", + "issue:43873|issue:45005", + "issue:42915|issue:45399", + "issue:44360|issue:44512", + "issue:44918|issue:45507", + "issue:43975|issue:44292", + "issue:43950|issue:44534", + "issue:44492|issue:44512", + "issue:44292|issue:45507", + "issue:43644|issue:43950", + "issue:43828|issue:44928", + "issue:39692|issue:43054", + "issue:43866|issue:44403", + "issue:41553|issue:43883", + "issue:44560|issue:45507", + "issue:36331|issue:41762" + ], + "prepared_review_unit_hash": "87183a493ef53abdc59cd05c18403765eb66d77b0f5919a44b8725fdae06d890", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37565, + "estimated_input_tokens": 9392, + "estimated_eval_tokens": 19040 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The non-persistent-buffer regression cluster is the only strong duplicate family here. The SigLIP2 pair is related in topic but not strong enough to merge on the evidence provided, so it should remain rejected/tentative. The rest of the cluster is heterogeneous and best kept separate.", + "confidence": 0.82, + "canonical_issue_reason": "issue:43950 is the clearest root-cause report for the duplicate family: it explicitly describes the Transformers 5.x non-persistent-buffer corruption regression and matches the follow-up report in issue:44534.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 is the best representative issue because it states the regression most concretely and broadly, and the linked follow-up issue shows the same underlying non-persistent-buffer bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Both are v5 config regressions, but the failure modes differ: missing `pad_token_idx` versus a pydantic `PretrainedConfig` field breakage." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "One is an int4 quantization/OOM regression; the other is tied-weights behavior in translation models." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Both mention MoE models, but the concrete bugs differ: Mixtral torch-dynamo grouped_mm tracing versus GPT-OSS tensor-parallel-only behavior." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Different models and failure surfaces: Phi-tiny-MoE autocast dtype mismatch versus Qwen3.5 streaming chat/completions failure." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "`init_empty_weights` with unexpected `_is_hf_initialized` is a different loader/config bug from the pydantic `PretrainedConfig` issue." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF gpt-oss support and Qwen3.5 streaming inference are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE `sliding_window` handling is a model-specific bug, not the same as the pydantic config regression." + }, + { + "left": "issue:44661", + "right": "issue:45464", + "accept": false, + "reason": "Tokenizer-mapping/add-new-model-like failure is unrelated to Qwen3.5 streaming inference." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Mixtral tracing/grouped_mm and missing Float8 storage are different failures." + }, + { + "left": "issue:39290", + "right": "issue:43742", + "accept": false, + "reason": "Gemma3 sliding-window attribute error and MobileLLM key error are separate model-loading bugs." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Both are SigLIP2-related, but the packet only shows title-level similarity; it does not establish the same underlying bug or a shared code path." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are index/mask errors, but one is a mask-length mismatch and the other is a ZeRO-3/BertModel empty-weight indexing failure." + }, + { + "left": "issue:42915", + "right": "issue:43541", + "accept": false, + "reason": "FineGrainedFP8Config on Qwen3Moe and grouped_mm tracing on Mixtral are unrelated MoE problems." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "GPT-OSS perplexity regression and a GLM5 issue are unrelated model reports." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP `'weight' must be 2-D` and TRL SFT unpacking on Qwen3.5 are different training-time failures." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both involve tied weights, but the concrete model families and symptoms differ enough that they should not be merged." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Custom-model-in-notebook initialization and flash-attn2 fallback gating are unrelated." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache invalid group type on Qwen3.5 is not the same as tied-weight handling in translation models." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading and tied-weight regression are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is a different issue from tied weights." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "FP8 Qwen3Moe and flash-attn2 fallback checks are unrelated." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "A missing ReLU in a DSA indexer and outdated docs for the run command are not the same bug." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Qwen3.5 embedding unpacking in TRL and GraniteMoEHybrid invalid method calls are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "DeepSeek detokenization and Qwen-3-8B-NVFP4 runtime failure are different model-specific problems." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "These both describe the same Transformers 5.x bug where non-persistent buffers are mishandled/corrupted on load." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "A cache-strategy typo and stale CLI docs are unrelated documentation issues." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime error and GraniteMoEHybrid invalid method are unrelated." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Both report the same Transformers 5.x regression affecting non-persistent buffers on load." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch on Phi-tiny-MoE and RLHF gradient explosion on Qwen3.5 are different failure modes." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "SigLIP2 docs-example errors/quantization mismatch is not the same as a report that SigLIP2 embeddings are worse than SigLIP." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "A corrupted checkpoint and a noisy load-message complaint are unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "Voxtral AutoTokenizer error message and missing `all_tied_weights_keys` on Molmo are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:45507", + "accept": false, + "reason": "Qwen3-vl StopIteration during video embedding and GraniteMoEHybrid invalid method calls are unrelated." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "CustomTrainer `compute_loss()` kwarg mismatch and Gemma3 ZeRO-3 indexing failure are unrelated." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary is mostly grounded, but one soft-edge verdict is too strong for the evidence in the packet: accepting issue:43054 with issue:43994 overstates similarity based on titles alone. They are both SigLIP2-related, but the packet does not clearly establish the same underlying bug, so this should stay tentative/rejected. The non-persistent-buffer cluster around issue:43644 / issue:43950 / issue:44534 looks solid; the rest of the rejections are conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 3, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:41093", + "issue:41553", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43257", + "issue:43278", + "issue:43404", + "issue:43493", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43854", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43940", + "issue:43950", + "issue:43975", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44509", + "issue:44589", + "issue:44661", + "issue:44863", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45305", + "issue:45313", + "issue:45356", + "issue:45399", + "issue:45520" + ], + "soft_pairs": [ + "issue:43872|issue:44589", + "issue:41553|issue:43881", + "issue:38175|issue:43054", + "issue:42947|issue:44387", + "issue:43054|issue:43493", + "issue:43881|issue:43883", + "issue:44403|issue:44451", + "issue:42947|issue:43856", + "issue:43975|issue:45520", + "issue:43643|issue:45020", + "issue:44403|issue:44488", + "issue:43782|issue:44960", + "issue:42491|issue:44368", + "issue:41762|issue:42915", + "issue:43975|issue:44451", + "issue:45020|issue:45356", + "issue:44661|issue:45020", + "issue:43824|issue:43872", + "issue:43054|issue:43278", + "issue:44991|issue:45399", + "issue:43792|issue:44220", + "issue:43827|issue:44509", + "issue:45081|issue:45399", + "issue:43404|issue:43950", + "issue:42915|issue:45020", + "issue:43257|issue:43866", + "issue:43742|issue:45399", + "issue:43742|issue:45020", + "issue:41553|issue:44991", + "issue:43940|issue:45313", + "issue:43872|issue:44291", + "issue:43854|issue:44863", + "issue:42915|issue:43872", + "issue:41553|issue:44488", + "issue:43257|issue:45305", + "issue:36331|issue:41093" + ], + "prepared_review_unit_hash": "c2453587dfa5cd45377d1c3757a017eabed2201cc8778f9915a54ae73384b243", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38578, + "estimated_input_tokens": 9645, + "estimated_eval_tokens": 19546 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a set of unrelated issues with a few clear duplicate-like clusters: docs/pipeline removals, SigLIP2 implementation discrepancy, and the `_is_hf_initialized` loading incompatibility. Most other pairings are too broad or model-specific to merge.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43872 is the clearest concrete bug report here: a specific, reproducible loading incompatibility around `_is_hf_initialized`, and it has a strong duplicate candidate in issue:44291.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43872 is the best representative issue overall because it is narrowly scoped, actionable, and tied to a specific runtime failure rather than a broad or vague symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Both are loading-related TypeErrors, but they point to different failure modes (`_is_hf_initialized` vs missing `Float8_e4m3fnStorage`) and do not look like the same bug." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different failures: Voxtral tokenizer error messaging vs GLM-4V load failure." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both mention SigLIP2, but one is zero probabilities and the other is lower embedding quality; not enough to treat as the same concrete defect." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing/LoRA inefficiency is a different problem from int4 quantization CUDA reserved-memory/OOM behavior." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": true, + "reason": "Both describe the same SigLIP2 implementation discrepancy/quality regression, centered on the text embedding behavior relative to the expected/original implementation." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Different model-specific loading failures with unrelated symptoms (`glm-4v-9b` load failure vs missing `all_tied_weights_keys`)." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "One is about noisy loading logs, the other about failing to load a specific model; these are not the same bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "Both involve training/memory, but one is checkpointing ineffectiveness and the other is memory usage during Qwen3 MoE training; not the same code-path issue." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Different areas entirely: tokenizer detokenization regression vs Python 3.13 `flash_attn` import utility failure." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "`trust_remote_code` missing fields in AutoConfig is more specific; `remote_code` breakage in general is broader and not clearly the same defect." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading complaints, but one is about noise and the other is a hard load failure for a specific checkpoint." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Different models and different failure descriptions; not enough evidence of a shared underlying bug." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Both mention Qwen3 LoRA/tie-word-embeddings, but one is about HF5.x compatibility for a trained LoRA model and the other is a warning during fine-tuning; not the same concrete failure." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Both are DeepSpeed-related, but Gemma3 ZeRO-3 loading and Qwen3 MoE weight conversion are different bugs." + }, + { + "left": "issue:43975", + "right": "issue:44451", + "accept": false, + "reason": "Tokenizer detokenization regression and a model load failure for ScandiBERT are unrelated." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "`remote_code` breakage is too broad; Kimi-K2.5 tokenizer codec handling and the misleading Mistral warning are a separate tokenizer regression." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "`add-new-model-like` failing inside `TOKENIZER_MAPPING_NAMES` is a registry edge case, not the same as broader `remote_code` breakage." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Importing `Qwen2_5_VLForConditionalGeneration` and the `_is_hf_initialized` parameter error are unrelated failures." + }, + { + "left": "issue:43054", + "right": "issue:43278", + "accept": false, + "reason": "SigLIP2 text embedding quality vs dtype drift between training and evaluate are different issues." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading for EMBEDDIA/est-roberta and flash-attn fallback checks are unrelated." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper runtime failure and `_torch_extract_fbank_features()` may be adjacent, but the evidence is too weak to call them the same concrete bug." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both are the same docs regression: pipeline task docs still reference removed v5 pipeline tasks." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex patch crash and flash-attn fallback gating are different subsystems and failure modes." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Weight tying in Mistral3 and non-persistent buffer corruption are unrelated state/model-loading issues." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Qwen3 MoE weight loading with accelerate+deepspeed is a specific loading bug, not the broader remote_code regression." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate+deepspeed and an Ovis2 corrupted checkpoint are different problems." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM load failure and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Both are model-loading failures, but for different model families and likely different root causes." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "DeepSpeed Qwen3 weight conversion and the `_is_hf_initialized`/bitsandbytes loading incompatibility are not the same bug." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Different models and different symptoms: bad tokenizer error message vs a direct load failure." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed and GAS gradient averaging with DeepSpeed are different training/load bugs." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Trainer API kwarg mismatch and a mask-shape IndexError are unrelated failures." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Same underlying `_is_hf_initialized` loading incompatibility; both reports describe the same constructor-argument breakage during model initialization/loading." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the accepted soft pairs look mergeable for the same bugfixes: the docs/pipeline removal pair, the SigLIP2 implementation discrepancy pair, and the `_is_hf_initialized` loading incompatibility pair. The rejected pairs are generally conservative and do not overclaim duplicates from the available evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 4, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:38175", + "issue:39692", + "issue:41093", + "issue:42491", + "issue:42617", + "issue:42915", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43720", + "issue:43824", + "issue:43828", + "issue:43872", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44534", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44960", + "issue:44977", + "issue:45030", + "issue:45084", + "issue:45313", + "issue:45325", + "issue:45357" + ], + "soft_pairs": [ + "issue:41093|issue:44805", + "issue:44479|issue:44560", + "issue:44530|issue:44863", + "issue:43872|issue:45084", + "issue:43366|issue:43828", + "issue:24643|issue:30064", + "issue:43366|issue:43531", + "issue:43550|issue:44910", + "issue:43645|issue:43646", + "issue:43950|issue:45325", + "issue:43366|issue:44589", + "issue:44560|issue:44918", + "issue:43824|issue:43957", + "issue:42915|issue:43957", + "issue:42617|issue:43366", + "issue:38175|issue:43994", + "issue:43646|issue:43950", + "issue:44560|issue:44805", + "issue:36010|issue:42915", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44877|issue:45030", + "issue:43317|issue:44756", + "issue:43644|issue:44534", + "issue:38175|issue:39692", + "issue:45313|issue:45357", + "issue:42491|issue:43720", + "issue:44451|issue:44488", + "issue:44960|issue:44977", + "issue:43708|issue:44075" + ], + "prepared_review_unit_hash": "41fd9e59e690151a980be88f81530841aaf44481dcced7d452879bf203a6bf7d", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36647, + "estimated_input_tokens": 9162, + "estimated_eval_tokens": 18580 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue set with a few small duplicate-style pairs. The clearest true duplicates are the non-persistent-buffer regression reports and the custom-model-initialization reports; most other pairs are only superficially similar and should stay separate.", + "confidence": 0.86, + "canonical_issue_reason": "issue:43950 is the clearest and most general description of the non-persistent-buffer regression, and it best represents the 43644/44534 mini-cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43950 is the strongest issue candidate overall because it is specific, reproducible, and broader than the earlier rephrasings.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same exact IndexError class and mask/tensor shape mismatch; these look like duplicate reports of the same indexing bug." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-related, but the failures differ materially: a regression across Qwen video models vs a StopIteration in Qwen3-VL embedding handling." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "Different models and different failure modes; one is a PagedAttentionCache/linear_attention crash, the other is a NemotronH checkpoint loading issue." + }, + { + "left": "issue:43872", + "right": "issue:45084", + "accept": false, + "reason": "Unrelated problems: bitsandbytes Int8Params init incompatibility vs a compiler/template-node TypeError." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "These do not describe the same bug; one is GGUF support for gpt-oss, the other is an autocast dtype mismatch on Phi-tiny-MoE." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Completely different domains: DeepSpeed training weight-shape error vs image processor handling of void segmentation maps." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Different Qwen/GGUF topics; one is general GGUF support, the other is a sliding_window issue in Qwen3-MoE." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Both involve attention/compile problems, but on different models and different concrete bugs; not mergeable as one PR." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These are the same custom-model initialization regression, with 43645 just adding the Jupyter notebook context." + }, + { + "left": "issue:43950", + "right": "issue:45325", + "accept": false, + "reason": "Non-persistent-buffer corruption is unrelated to the Qwen2.5-VL rope-index scaling bug." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF support for gpt-oss and Float8 storage lookup failure are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Different bugs: a video StopIteration regression vs unpacking Qwen3.5 embeddings in TRL SFT trainer." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Importing a missing class and meta-device model loading are separate issues with different code paths." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Qwen3Moe FP8 config failure is unrelated to meta-device loading regressions." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "DeepSpeed ZeRO-3 Bert index errors and TOKENIZER_MAPPING_NAMES add-new-model-like validation are different bugs." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Same reasoning as above: one is a ZeRO-3 empty-tensor initialization crash, the other is model-registration validation." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both mention config validation, but they affect different model families and different validation failures." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Device-map dequantized loading/offload and Strix Halo mmap OOM are distinct loading/resource issues." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Same underlying regression: from_pretrained / Transformers v5 fills non-persistent buffers with junk." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Both mention SigLIP2, but one is about zero probabilities in the model output while the other is a docs example with model/processor mismatch and quantization failures." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Same model family, but different concrete problems: ZeRO-3 loading of language_model weights vs save_pretrained writing incorrect visual encoder keys." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "LoRA/Qwen3-MoE cross-version incompatibility and BitNet packed-weight loading are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading failures for different checkpoints, but there is not enough evidence they share the same code-path bug." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "These are different GLM/Qwen issues with different symptoms; not the same underlying change." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Trainer resume/max_steps accounting and SGD argument handling are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the soft-edge calls are conservative. The accepted pairs are well-supported by near-identical titles/regression descriptions (41093/44805, 43645/43646, 43644/44534), while the rejected pairs mostly differ in model, failure mode, or subsystem enough to stay separate." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 5, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43381", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43828", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44661", + "issue:44683", + "issue:44743", + "issue:44756", + "issue:44863", + "issue:44877", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:44991", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406" + ], + "soft_pairs": [ + "issue:43854|issue:43931", + "issue:43856|issue:43873", + "issue:41720|issue:42915", + "issue:45362|issue:45406", + "issue:42491|issue:45276", + "issue:44488|issue:44991", + "issue:39692|issue:43994", + "issue:43257|issue:43854", + "issue:44661|issue:44683", + "issue:43856|issue:44387", + "issue:42915|issue:44756", + "issue:43644|issue:43645", + "issue:42491|issue:43931", + "issue:42491|issue:43856", + "issue:45276|issue:45335", + "issue:43404|issue:43454", + "issue:36010|issue:39404", + "issue:44164|issue:44291", + "issue:41720|issue:44155", + "issue:44402|issue:44488", + "issue:43873|issue:44387", + "issue:39692|issue:44960", + "issue:44387|issue:44756", + "issue:43425|issue:43957", + "issue:44292|issue:44912", + "issue:43854|issue:45216", + "issue:42947|issue:43381", + "issue:44291|issue:44756", + "issue:45276|issue:45292", + "issue:44743|issue:44960", + "issue:43381|issue:44928", + "issue:43957|issue:44756", + "issue:44164|issue:44756", + "issue:43646|issue:43708", + "issue:44479|issue:44877", + "issue:45292|issue:45335", + "issue:44402|issue:44451", + "issue:43645|issue:44164", + "issue:43257|issue:44863", + "issue:43425|issue:43828", + "issue:43828|issue:43957" + ], + "prepared_review_unit_hash": "c855c176b7dbed2536294ffd369ff29579cd11abab8e6f64d5d9636a908a1ff7", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 41, + "serialized_chars": 39812, + "estimated_input_tokens": 9953, + "estimated_eval_tokens": 20162 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous, with only a small duplicate-like subcluster around `resize_token_embeddings` behavior (and a possible custom-model-init pair). Most other pairs are same-subsystem but different bugs or model-specific regressions.", + "confidence": 0.66, + "canonical_issue_reason": "`issue:45292` is the broadest representative of the resize-token-embedding regression and best captures the shared root problem behind the closest matches.", + "canonical_pr_reason": null, + "best_issue_reason": "`issue:45292` has the most generic wording and is the clearest umbrella issue for the resize-token-embedding failures; the nearby model-specific reports look like manifestations of the same bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Both are model-loading failures, but they involve different models and different failure modes, so they do not look like the same underlying bug." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both mention memory/quantization, but one is Qwen3 MoE training memory usage and the other is offloading behavior; likely different code paths." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Both are Qwen3-related, but one is a cuda assert under auto device mapping and the other is a LoRA compatibility issue across versions; not the same bug." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different models and different failure types (chat crash vs processor attribute error), so these are not the same issue." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Both concern Qwen3/gemma-style model behavior across versions, but the reported problems are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer/load failures, but on different models with no clear shared code-path or identical root cause." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Both are SigLIP2-related, but one is documentation/example errors while the other is nonsensical inference output; not clearly the same bug." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Different model families and different symptoms (accelerate/deepspeed weight conversion vs unit-test loading failure)." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Unrelated issues: tokenizer mapping behavior versus compiled flex_attention on newer torch." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both are memory-related, but one is Qwen3 MoE training efficiency and the other is int4 quantization OOM regression; too different to merge." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Different problem domains: Qwen3 MoE FP8 loading versus disabling mmap on Strix Halo." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "One is about non-persistent buffers being initialized with junk; the other is custom model initialization in notebooks." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Distinct model/version compatibility problems with no clear common bug." + }, + { + "left": "issue:42491", + "right": "issue:43856", + "accept": false, + "reason": "Different Qwen3-related regressions; the symptoms and likely fixes do not match." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": true, + "reason": "Same underlying regression: `resize_token_embeddings` fails to propagate to downstream embeddings; these are model-specific repros of the same bug." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both mention untied `lm_head` weights, but they affect different model implementations and are not clearly the same code-path fix." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Import error for `GenerationMixin` is unrelated to Whisper pipeline `return_language` behavior." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Both are save/load or init-related, but one is `extra_state` handling and the other is `_is_hf_initialized` argument handling; different root causes." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Both involve model inference correctness, but one is a device-mapping CUDA assert and the other is a batched embedding/token leak." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Both are tokenizer-related, but the specific failures and affected models are different." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both touch quantization memory, but one is offloading not working as expected and the other is a reserved-memory/OOM regression; not the same concrete bug." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "SigLIP2 doc/example issues are unrelated to the GLM5 issue." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "OOM under int4 quantization is unrelated to disabling mmap on Strix Halo." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version incompatibility and meta-device loading failures are separate issues." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Different quantization/load failures with different models and no shared fix signal." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Model-loading test failure for GLM-4.7 versus a save_pretrained regression for Qwen3.5; different bugs." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Gradient checkpointing inefficiency in PEFT LoRA is not the same as checkpointing being disallowed in eval mode." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "Different loading mechanisms and failure modes; not the same underlying issue." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Same resize-token-embedding regression; `45292` is the broader version and `45276` is a model-specific manifestation." + }, + { + "left": "issue:44743", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3.5 recurrent-state caching bug and GLM5 issue are unrelated." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Checkpointing in eval mode and RLHF gradient explosion via position IDs are different problems." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading failures are unrelated to mmap/OOM behavior." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "Save/load `extra_state` handling and mmap/OOM are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization breakage and Trainer checkpoint-resume `max_steps` math are different bugs." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video-input regression and strict config loading are unrelated." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same family of `resize_token_embeddings` propagation failures; both point to the same underlying embedding-update bug." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Different tokenizer/vocab loading problems for different models." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Notebook/custom-model init regression is unrelated to `extra_state` save/load handling." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Different Qwen3 MOE-related issues with different failure modes." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility is unrelated to the autocast dtype mismatch." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Dtype mismatch under autocast and meta-device loading are distinct bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: issue:45292 is the most generic resize_token_embeddings report, and the high-similarity model-specific issues (45276, 45335) are a reasonable narrow duplicate-like subcluster. The other soft-edge calls are conservative rejects rather than overclaims, and the one accepted pair appears mergeable as the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 6, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42947", + "issue:43299", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43856", + "issue:43883", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44265", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44671", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45161" + ], + "soft_pairs": [ + "issue:44589|issue:44756", + "issue:43906|issue:44530", + "issue:43931|issue:44863", + "issue:39404|issue:44912", + "issue:43611|issue:43645", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:44265|issue:44898", + "issue:43299|issue:43931", + "issue:43901|issue:44509", + "issue:44479|issue:44805", + "issue:43596|issue:44683", + "issue:43994|issue:44079", + "issue:44589|issue:45084", + "issue:43856|issue:44756", + "issue:44671|issue:44991", + "issue:40990|issue:42947", + "issue:43425|issue:44918", + "issue:39404|issue:44671", + "issue:36032|issue:43452", + "issue:44991|issue:45081", + "issue:32090|issue:39404", + "issue:43582|issue:43632", + "issue:43957|issue:44164", + "issue:44488|issue:45081", + "issue:44164|issue:44479", + "issue:40990|issue:43421", + "issue:43425|issue:45161", + "issue:43883|issue:44488", + "issue:43611|issue:43644", + "issue:44206|issue:44220", + "issue:44488|issue:44987", + "issue:42947|issue:44756", + "issue:43716|issue:45084", + "issue:34567|issue:40444", + "issue:43883|issue:44991" + ], + "prepared_review_unit_hash": "258ffcdb95ce7e8211eeb01d1eee372476db5f3682c870d28d3a3010236578bf", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38483, + "estimated_input_tokens": 9621, + "estimated_eval_tokens": 19498 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is not a single duplicate cluster; it\u2019s a heterogeneous mix of unrelated bugs/regressions across tokenizers, model loading, training, audio, vision, and docs. None of the soft pairs look like the same underlying issue closely enough to merge.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue stands out because the items span many unrelated failure modes and subsystems rather than one shared bug.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue is appropriate; the cluster is too mixed to represent with one issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Different problems: float8 storage lookup error vs mmap/OOM workaround on Strix Halo." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "Both are regressions, but they affect different code paths and model families; no clear shared bug." + }, + { + "left": "issue:43931", + "right": "issue:44863", + "accept": false, + "reason": "Both concern model loading, but one is a Qwen3-VL weight-shape mismatch and the other is NemotronH checkpoint loading." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Unrelated: Whisper pipeline language return vs GPT-OSS quantization fallback." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both involve v5 model loading behavior, but one is base_model_prefix handling and the other is Jupyter/custom-model initialization." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Completely different issues: Torch version incompatibility vs image preprocessor/model dtype mismatch." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "Different failures in different areas; no evidence they share the same concrete code path." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export/torch_compilable_check failure is unrelated to Perceiver interpolation at inference time." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both are Qwen-related loading bugs, but the affected models and failure modes differ too much to merge." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs issues, but they refer to different documentation mismatches and task sets." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Different regressions: Qwen video-input handling vs a mask/tensor shape indexing error." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Deepspeed ZeRO-3 init error is unrelated to compiled flex_attention on newer torch." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "A bad SigLIP2 output symptom does not clearly match the ModelOutput key-assignment bug." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage resolution and template-node compilation are unrelated errors." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory, but one is Qwen3 MoE training inefficiency and the other is a platform-specific mmap OOM fix." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "Different v5 regressions: CamemBERT masked-LM behavior vs tokenizer loading for est-roberta." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Perplexity regression and gradient-checkpointing/LoRA behavior are not the same bug." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch compatibility is unrelated to Qwen3.5 embedding unpacking in TRL SFT training." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline language output and CamemBERT masked-LM predictions are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "Both are loading/tokenizer-related, but T5 special-token method conflict is not the same as gguf_file loading breakage." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer-loading failures, but for different models and different mechanisms; not one concrete bug." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast TypeError is unrelated to Whisper pipeline return_language behavior." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon warmup TypeError and _is_hf_initialized flag regression are separate issues." + }, + { + "left": "issue:43957", + "right": "issue:44164", + "accept": false, + "reason": "Model loading on meta device and save/from_pretrained extra_state handling are different code paths." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Both touch tokenizer loading, but sleng-bert loading failure and Mistral regex patch crash are not the same bug." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "save/from_pretrained extra_state handling is unrelated to Qwen video-input regression." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity regression and runtime post-processor update for special tokens are not the same issue." + }, + { + "left": "issue:43425", + "right": "issue:45161", + "accept": false, + "reason": "Torch version incompatibility is unrelated to GPT-OSS MoE tensor-parallel loading behavior." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing all_tied_weights_keys for Molmo is unrelated to sleng-bert model loading." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 loading/init regressions, but one is base_model_prefix and the other is non-persistent buffer initialization." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Likely same audio area, but the titles do not show the same concrete bug or code path strongly enough." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Different tokenizer/model-loading regressions for different models." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Molmo tied-weights metadata issue is unrelated to est-roberta tokenizer loading." + } + ] + }, + "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": 13, + "review_unit_index": 7, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:36032", + "issue:39404", + "issue:41553", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43452", + "issue:43482", + "issue:43531", + "issue:43540", + "issue:43541", + "issue:43582", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43819", + "issue:43825", + "issue:43994", + "issue:44062", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44466", + "issue:44479", + "issue:44530", + "issue:44534", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45507" + ], + "soft_pairs": [ + "issue:43644|issue:43646", + "issue:43643|issue:44530", + "issue:44451|issue:44987", + "issue:43541|issue:45084", + "issue:43317|issue:43482", + "issue:36032|issue:42915", + "issue:43452|issue:43482", + "issue:43262|issue:43377", + "issue:42915|issue:44530", + "issue:44849|issue:45325", + "issue:39404|issue:43825", + "issue:36032|issue:43645", + "issue:45084|issue:45507", + "issue:43404|issue:44466", + "issue:44987|issue:44991", + "issue:43646|issue:44534", + "issue:43994|issue:44610", + "issue:43377|issue:43819", + "issue:43645|issue:44534", + "issue:44403|issue:45081", + "issue:43322|issue:43540", + "issue:45216|issue:45357", + "issue:44451|issue:45081", + "issue:44220|issue:44683", + "issue:44265|issue:44610", + "issue:43632|issue:44756", + "issue:42915|issue:45084", + "issue:41553|issue:43582", + "issue:44987|issue:45081", + "issue:43404|issue:45127", + "issue:43296|issue:43531", + "issue:44062|issue:44987", + "issue:44479|issue:45325", + "issue:42915|issue:44291" + ], + "prepared_review_unit_hash": "dda1340949a4c492643de151a1b544abdc1296aec732aa7eb5bec6561403ad62", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 37382, + "estimated_input_tokens": 9346, + "estimated_eval_tokens": 18948 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers bugs across different models/features; there is no broad duplicate family. The only strong near-duplicate pair is the Qwen3.5 save_pretrained regression report and its follow-up about incorrect visual encoder keys.", + "confidence": 0.86, + "canonical_issue_reason": "Issue #45216 is the best canonical issue: it describes the broader Qwen3.5 save_pretrained regression since 5.4.0, and #45357 reads like a narrower follow-up on the same checkpoint-serialization bug.", + "canonical_pr_reason": null, + "best_issue_reason": "#45216 is the strongest representative overall because it is a clear regression report with a concrete API and model family, and it likely subsumes the more specific #45357 report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 initialization-related, but one is about non-persistent buffers and the other about custom model init; different failure modes." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "Different subsystems and errors: AutoConfig/trust_remote_code field loss vs Qwen3.5 paged attention cache group-type failure." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Both are tokenizer/model load failures, but for different models and likely different root causes." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Unrelated code paths: torch dynamo grouped_mm tracing in Mixtral vs a template-node compilation error." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "Different loading paths: dequantized device_map auto-offload vs GGUF loading on Qwen2.5." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "Tokenizer special-token conflict and Qwen3-MoE FP8 config failure are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both involve GGUF, but one is a broad gguf_file API breakage and the other is a specific Qwen2.5-GGUF v5 failure." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio processor sampling-rate default bug vs MIMI batch-vs-single padding-mask mismatch are distinct issues." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Different Qwen3-family bugs: FP8 config loading vs paged-attention cache group-type handling." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Both are Qwen3/Qwen2.5-VL regressions, but one is about output_hidden_states and the other about rope/temporal position scaling." + }, + { + "left": "issue:39404", + "right": "issue:43825", + "accept": false, + "reason": "Whisper return_language pipeline behavior and a translation-task error message issue are not the same bug." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer method conflict vs notebook custom-model initialization regression; different failures." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "A template compilation error is not the same as GraniteMoEHybrid calling an invalid method." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both concern tied weights, but one is a model not tying lm_head at all and the other is inconsistent serialization by device." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer load failures, but they target different model repositories and likely different causes." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model init breakage and non-persistent buffer junk are separate v5 regressions." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different model/input mismatches: SigLIP2 nonsensical outputs vs OmDet-Turbo processor size mismatch." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI padding-mask batch inconsistency and DAC STE mismatch are different audio-model bugs." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook custom model initialization and non-persistent buffer serialization are not the same code-path issue." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Noise in transformer loading is unrelated to a Mistral regex patch crash." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Different multimodal model failures: Llava Next segfault vs Qwen3OmniMoe video processing ValueError." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same model family and same save_pretrained regression; #45357 is a narrower manifestation of the checkpoint serialization bug reported in #45216." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Unrelated model-loading failure and Mistral tokenizer regex patch crash." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Audio feature extraction issue and torch>=2.9 flex_attention compilation failure are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export with torch_compilable_check is unrelated to an image-size processor bug." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized regression and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3-MoE FP8 loading and template compilation errors are unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Tokenizer load error messaging and Apple Silicon allocator warmup TypeError are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer load failure for a specific model and Mistral regex patch crash are different bugs." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Tied-lm_head bug in Mistral3ForConditionalGeneration is distinct from LoRA merge collapse with extended vocab." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL load failure in vLLM and Qwen3-MoE sliding_window behavior are unrelated." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken special-argument duplication and tokenizer load failure for EMBEDDIA/est-roberta are different issues." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both touch Qwen vision/video positioning, but one is a broad video-input regression and the other is a specific still-image temporal position-id scaling bug; not clearly the same underlying defect." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3.5 PagedAttentionCache group-type failure is unrelated to a template-node compilation error." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Different model-load failures with no shared concrete code path." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Different tied-weight-related symptoms and different triggers; not safe to merge as duplicates." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted near-duplicate, #45216/#45357, is plausibly the same Qwen3.5 save_pretrained regression family. The rejected soft-edge pairs are mostly justified by clearly different models, APIs, or failure modes, and I don\u2019t see any 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": 13, + "review_unit_index": 8, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:33666", + "issue:35707", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43421", + "issue:43425", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43742", + "issue:43749", + "issue:43792", + "issue:43818", + "issue:43828", + "issue:43856", + "issue:43881", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44488", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44811", + "issue:44829", + "issue:44877", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45491" + ], + "soft_pairs": [ + "issue:40990|issue:44811", + "issue:43611|issue:44534", + "issue:36032|issue:43742", + "issue:43317|issue:43856", + "issue:42915|issue:44589", + "issue:40444|issue:45325", + "issue:43632|issue:44534", + "issue:43531|issue:44877", + "issue:44683|issue:45020", + "issue:43421|issue:44568", + "issue:43818|issue:45357", + "issue:36032|issue:41720", + "issue:43425|issue:44403", + "issue:43792|issue:44589", + "issue:44829|issue:45479", + "issue:44403|issue:44991", + "issue:33666|issue:40444", + "issue:44079|issue:44534", + "issue:43377|issue:45491", + "issue:35707|issue:40444", + "issue:43482|issue:43525", + "issue:44291|issue:44589", + "issue:43749|issue:44079", + "issue:43644|issue:44079", + "issue:44079|issue:45072", + "issue:43632|issue:45072", + "issue:44265|issue:45072", + "issue:43531|issue:44291", + "issue:40444|issue:45381", + "issue:42175|issue:43296", + "issue:41720|issue:45081", + "issue:45325|issue:45381", + "issue:43611|issue:43646", + "issue:43881|issue:44488", + "issue:43828|issue:44683" + ], + "prepared_review_unit_hash": "a74d6d537c4768d94e492a642dccf89c1a42aee9aa5d23444189330094d8622f", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38147, + "estimated_input_tokens": 9537, + "estimated_eval_tokens": 19330 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated issue reports with only superficial overlap in model family or Transformers version. I found no strong duplicate cluster; the broadest regression tracker is `issue:45020`.", + "confidence": 0.87, + "canonical_issue_reason": "No single issue is a clear duplicate hub; the set spans many distinct bugs. If one issue must anchor the cluster, `issue:45020` is the broadest open regression report about recent Transformers versions breaking `remote_code` models.", + "canonical_pr_reason": null, + "best_issue_reason": "`issue:45020` is the best representative issue because it is broad, open, and describes a real cross-model regression theme rather than a model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "Completely different problems: GPT-OSS perplexity vs Whisper batch_decode special-token handling." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Both are Transformers v5 regressions, but one is `base_model_prefix` loading and the other is non-persistent buffer initialization; different code paths." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "T5 tokenizer method-name conflict vs MobileLLM-125M key error are unrelated failures." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Dequantized model offload loading issue vs Qwen3 MoE training memory usage; not the same bug." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Both mention FP8/float8, but one is Qwen3Moe FineGrainedFP8Config failure and the other is a storage-object lookup error; different underlying issues." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Qwen2.5-VL multi-image finetuning failure vs still-image temporal position-id scaling bug; different symptoms and paths." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "`_is_hf_initialized` flag regression is separate from junk-filled non-persistent buffers." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding window issue and granite_speech strict-config loading are unrelated." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 is unrelated to remote_code loading regressions." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Runtime special-token post-processor refresh vs missing BOS/EOS insertion are related to tokenizers broadly but not the same concrete bug." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA weight/temporal-attention bug vs Qwen3.5 save_pretrained key regression are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer class-name conflict vs Qwen3 auto device-map cuda assert are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch 2.10 compatibility problem vs loading noise/verbosity issue." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure vs float8 storage lookup error; different failure modes." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "FlashAttention-3 training degeneration and zero-loss single-label classification are both training issues but have different causes." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Loading noise vs tokenizer loading failure for a specific model are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and Qwen2.5-VL multi-image dataset failure are separate problems." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment bug is unrelated to buffer initialization regression." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Both involve batching, but MIMI padding-mask outputs and Gemma3 NaN embeddings are different model-specific bugs." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with `inputs_embeds`/`past_key_values` is unrelated to Qwen2.5-VL multi-image finetuning." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Qwen2.5-GGUF loading failure and missing `pad_token_id` on Llama4Config are different loader issues." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Unexpected `_is_hf_initialized` argument during init_empty_weights is a different regression from float8 storage lookup failure." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk regression is unrelated to ModelOutput key handling." + }, + { + "left": "issue:44079", + "right": "issue:45072", + "accept": false, + "reason": "ModelOutput key assignment bug is unrelated to bfloat16 dtype mismatch in inference." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "`_is_hf_initialized` regression is unrelated to dtype mismatch in bfloat16 inference." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export / `torch_compilable_check` failure is unrelated to bfloat16 dtype mismatch." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue and `_is_hf_initialized` init_empty_weights error are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Multi-image prompt finetuning failure vs video `vision_position_ids` bug are different Qwen2.5-VL issues." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Packaging/backend dependency issue vs PaddleOCR-VL load failure are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 auto device-map assert and Mistral tokenizer regex patch crash are different subsystems." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL position-id complaints, but one is still-image temporal scaling and the other is video `vision_position_ids`; not clearly the same bug." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are Transformers v5 loading regressions, but `base_model_prefix` handling and custom model initialization are different concrete failures." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "glm-4v-9b loading failure and `cjvt/sleng-bert` tokenizer loading failure are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:44683", + "accept": false, + "reason": "Autocast dtype mismatch for Phi-tiny-MoE is unrelated to compiled flex_attention on torch>=2.9." + } + ] + }, + "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": 13, + "review_unit_index": 9, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:39692", + "issue:40444", + "issue:41720", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43454", + "issue:43482", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43632", + "issue:43701", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43792", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43957", + "issue:43994", + "issue:44164", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44423", + "issue:44466", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44683", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45325", + "issue:45357", + "issue:45406" + ], + "soft_pairs": [ + "issue:43994|issue:44898", + "issue:43454|issue:44466", + "issue:44387|issue:44617", + "issue:42915|issue:43482", + "issue:43792|issue:43957", + "issue:43526|issue:43883", + "issue:43701|issue:45325", + "issue:43262|issue:43746", + "issue:43317|issue:43873", + "issue:34634|issue:35707", + "issue:44291|issue:44877", + "issue:43881|issue:44991", + "issue:43606|issue:44265", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:43632|issue:44164", + "issue:35707|issue:41720", + "issue:43377|issue:44898", + "issue:44610|issue:45325", + "issue:43377|issue:44610", + "issue:43454|issue:45072", + "issue:43454|issue:43550", + "issue:39692|issue:40444", + "issue:43749|issue:44534", + "issue:43296|issue:44991", + "issue:44466|issue:45357", + "issue:43296|issue:44877", + "issue:43792|issue:44683", + "issue:43454|issue:43720", + "issue:41720|issue:43322", + "issue:41720|issue:44977", + "issue:43404|issue:45357", + "issue:44423|issue:45406", + "issue:44186|issue:45072" + ], + "prepared_review_unit_hash": "6f58512e03ff2b1dd73dc05e0ca664e3e5faa7eb47a64a8df2a8c5ad508ba9e9", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37954, + "estimated_input_tokens": 9489, + "estimated_eval_tokens": 19234 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose bundle of unrelated model-loading, serialization, processor, and quantization regressions; there is no clear duplicate core, so I treated it as a weak thematic cluster rather than a true same-bug set.", + "confidence": 0.64, + "canonical_issue_reason": "issue:43957 is the broadest representative: a general transformers 5.x meta-device loading regression affecting multiple models, which best matches the cluster\u2019s overall loading/offload theme.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43957 is the best global representative because it captures the widest cross-model loading failure pattern among the issues shown.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Both touch vision model usage, but one is a SigLIP2 docs/example mismatch and quantization failure while the other is a Perceiver resolution issue; different bugs." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied lm_head weights, but one is a model-specific failure to tie weights and the other is a device-dependent serialization inconsistency; not the same concrete bug." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both are memory/OOM reports, but they involve different models and different failure modes; too broad to merge." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Different model families and different root causes: FP8 config failure vs GGUF loading on v5." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper runtime failure is not the same concrete issue as the general meta-device loading regression, even if both concern loading." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "Unrelated bugs: BeitImageProcessorFast label reduction vs missing all_tied_weights_keys on Molmo." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint key mismatch and Qwen2.5-VL rope-index scaling are different code paths." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sample-rate handling and GraniteSpeech PEFT checkpoint loading are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both concern offload/quantization broadly, but one is dequantized model loading with device_map=auto and the other is generic offloading behavior; not the same bug." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset and progressive generation with inputs_embeds/past_key_values are different features and failures." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized and strict granite_speech config loading are distinct regressions." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different artifacts and failure modes: glm-4v-9b load failure vs tokenizer loading failure for est-roberta." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch and torch.export.export failing on torch_compilable_check are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer padding/truncation crash is not the same as export-time torch_compilable_check failure." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Bark offload device mismatch and DAC.from_latents vs forward mismatch are different bugs." + }, + { + "left": "issue:43632", + "right": "issue:44164", + "accept": false, + "reason": "Both are v5 loading/saving regressions, but one is the _is_hf_initialized flag and the other is extra_state handling; different code paths." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation with caches and Qwen3 auto device mapping cudaErrorAssert are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Missing padding-mask support in MIMI and SigLIP2 doc/example errors are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:45325", + "accept": false, + "reason": "Processor output-size bug and Qwen2.5-VL temporal rope scaling are different issues." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Both are multimodal preprocessing problems, but one is batched-vs-single encoder output mismatch and the other is an image-size mismatch; not the same bug." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Tied-weight serialization and bfloat16 dtype mismatch are different failure classes." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Weight tying bug and torch.compile SDPA failure are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Different models and different problems: SigLIP2 docs/example errors vs Qwen2.5-VL multi-image finetuning failure." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer junk are separate v5 regressions." + }, + { + "left": "issue:43296", + "right": "issue:44991", + "accept": false, + "reason": "PaddleOCR-VL load failure in vLLM and tokenizer loading failure for est-roberta are unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "lm_head serialization inconsistency and Qwen3.5 visual encoder key saving are different save_pretrained bugs." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "PaddleOCR-VL model loading and granite_speech strict config parsing are different problems." + }, + { + "left": "issue:43792", + "right": "issue:44683", + "accept": false, + "reason": "Whisper loading/runtime failure and compiled flex_attention on torch>=2.9 are unrelated." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "lm_head tying/serialization and BitNet packed-weight unpacking are different code paths." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3 auto device-mapping assert and Llava Next segfault are different model-loading failures." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Auto device mapping cudaErrorAssert and flash-attention generation failure are distinct bugs." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 lm_head tying and Qwen3.5 visual encoder key serialization are different model-specific issues." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Serve-time multimodal crash with a string .to() call and Gemma4Processor missing _tokenizer are not the same failure." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crash on padding/truncation and bfloat16 dtype 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": 13, + "review_unit_index": 10, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:33357", + "issue:34567", + "issue:35707", + "issue:36010", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:42994", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43388", + "issue:43482", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43873", + "issue:43881", + "issue:44186", + "issue:44292", + "issue:44361", + "issue:44479", + "issue:44514", + "issue:44545", + "issue:44610", + "issue:44671", + "issue:44743", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44991", + "issue:45059", + "issue:45161", + "issue:45406", + "issue:45464" + ], + "soft_pairs": [ + "issue:34567|issue:40990", + "issue:43873|issue:44756", + "issue:43526|issue:43881", + "issue:43577|issue:43708", + "issue:42617|issue:42915", + "issue:44877|issue:44991", + "issue:43550|issue:43720", + "issue:44610|issue:44898", + "issue:44479|issue:44918", + "issue:44186|issue:44610", + "issue:36331|issue:42915", + "issue:36331|issue:42617", + "issue:42994|issue:43482", + "issue:43316|issue:44913", + "issue:44671|issue:44743", + "issue:42915|issue:43317", + "issue:43550|issue:43606", + "issue:41720|issue:42617", + "issue:43531|issue:43572", + "issue:44292|issue:44479", + "issue:41720|issue:45161", + "issue:44186|issue:44361", + "issue:43388|issue:45059", + "issue:43540|issue:43782", + "issue:41720|issue:43873", + "issue:45406|issue:45464", + "issue:42915|issue:43322", + "issue:36010|issue:42617", + "issue:36331|issue:41720", + "issue:44514|issue:44545", + "issue:33357|issue:35707", + "issue:41720|issue:43746", + "issue:43606|issue:43720" + ], + "prepared_review_unit_hash": "7e7479c677752f9390a0819da3ef5b10ef9cacf3bb84b0ea420eed3383b5a920", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36769, + "estimated_input_tokens": 9193, + "estimated_eval_tokens": 18642 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformer bugs across different models and subsystems. Only one clear duplicate pair stands out: the Qwen2_5_VLProcessor batched-input crash with padding=False.", + "confidence": 0.96, + "canonical_issue_reason": "issue:44545 is the best canonical issue: it is the cleaner, more explicit report of the same Qwen2_5_VLProcessor batched-input/padding=False crash as 44514, and it has slightly more inbound discussion.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44545 is the strongest representative issue in this set because it is a clear duplicate target with the most complete wording and references.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Unrelated bugs: TrainerState token counting vs GPT-OSS perplexity regression." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory/offload, but one is quantization offloading behavior and the other is mmap/OOM on Strix Halo; different root causes." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "Different models and failures: BeitImageProcessorFast label reduction vs glm-4v-9b load failure." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "Blip2 dtype propagation bug vs Trainer checkpoint resume/max_steps calculation; unrelated." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel.py runtime issue vs Qwen3Moe FineGrainedFP8Config failure; not the same bug." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Config-loading strictness for granite_speech vs tokenizer loading failure for est-roberta on v5; different code paths." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "Different failures: Bamba torch.compile with SDPA vs BitNet packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both are image-size/preprocessing mismatches, but for different models and mechanisms; not the same concrete bug." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Both touch Qwen models, but one is a video-input regression and the other is TRL SFT unpacking of embeddings." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "LayoutLMv2Tokenizer NER/padding crash vs OmDet-Turbo image size mismatch; unrelated." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "CustomTrainer compute_loss signature mismatch vs Qwen3Moe FP8 load failure; unrelated." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "CustomTrainer keyword-arg regression vs 3d_parallel.py runtime issue; unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure vs Qwen2.5-GGUF loading failure; both are quantization-related but not the same bug." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Different config regressions in different models: Gemma3TextConfig API mismatch vs GPTNeoX rotary_pct reload issue." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked LM regression vs Qwen3.5 modular recurrent-state reset bug; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Qwen3Moe FP8 failure vs device_map=auto dequantized-model offload failure; different code paths." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Different load/compile problems on different models; no shared concrete bug." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 auto device mapping cudaErrorAssert vs 3d_parallel.py issue; unrelated." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior vs StableLmConfig missing pad_token_idx after v5 update; unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44479", + "accept": false, + "reason": "Different Qwen model families and failures: NVFP4 run error vs video input regression." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both involve parallelism on MoE models, but the affected model and failure mode are different; not a single underlying bug." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer issues in different models; no concrete shared code path." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Metric gathering label-truncation bug vs SAM3 text/box behavior; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Qwen3OmniMoe video-processing error vs Qwen3VL weight_only load error; different failure points." + }, + { + "left": "issue:41720", + "right": "issue:43873", + "accept": false, + "reason": "Both mention device/offload concerns, but one is auto device mapping CUDA assert and the other is quantization offloading; not the same bug." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer in serve vs Qwen3.5 streaming chat/completions failure; different issues." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3Moe FP8 issue vs Llava Next segmentation fault; unrelated." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "GenerationMixin import error vs 3d_parallel.py runtime failure; unrelated." + }, + { + "left": "issue:36331", + "right": "issue:41720", + "accept": false, + "reason": "Trainer compute_loss signature regression vs Qwen3 device-mapping CUDA assert; unrelated." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "These are the same batched-input crash in Qwen2_5_VLProcessor.apply_chat_template with padding=False, described with near-identical reproduction." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3 auto device mapping failure vs GraniteSpeech PEFT local-checkpoint loading problem; unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both are loading/offload-related, but the model/code paths differ and the bugs are not the same concrete failure." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall: the cluster is dominated by unrelated issue reports, and the lone duplicate pair (44514/44545) is well supported by the packet. The canonical choice is conservative and the soft-edge rejections do not overclaim shared causality." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 11, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:30064", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:39692", + "issue:41720", + "issue:42886", + "issue:43381", + "issue:43421", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43606", + "issue:43645", + "issue:43653", + "issue:43746", + "issue:43782", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:43994", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44843", + "issue:44898", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45357", + "issue:45381", + "issue:45479" + ], + "soft_pairs": [ + "issue:30064|issue:34634", + "issue:43550|issue:43653", + "issue:44368|issue:45357", + "issue:44492|issue:44509", + "issue:44625|issue:45479", + "issue:43606|issue:43653", + "issue:43421|issue:43927", + "issue:34634|issue:41720", + "issue:44898|issue:45072", + "issue:43782|issue:45381", + "issue:44451|issue:44991", + "issue:44062|issue:44451", + "issue:34567|issue:35707", + "issue:43381|issue:43844", + "issue:42886|issue:44843", + "issue:44077|issue:44625", + "issue:44918|issue:44936", + "issue:43421|issue:43653", + "issue:43531|issue:44589", + "issue:44987|issue:45042", + "issue:43994|issue:44671", + "issue:39692|issue:44610", + "issue:43421|issue:44186", + "issue:43596|issue:44220", + "issue:43531|issue:43645", + "issue:45081|issue:45356", + "issue:43746|issue:45381", + "issue:45183|issue:45479", + "issue:39692|issue:43873", + "issue:44220|issue:44661" + ], + "prepared_review_unit_hash": "2a8b8b47fa7fa1cf25bff901627818582021fc8d80e12c470fb7aadb2a556f25", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36958, + "estimated_input_tokens": 9240, + "estimated_eval_tokens": 18736 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a heterogeneous cluster of mostly unrelated Transformers bug reports; the title/body overlap is superficial in each soft pair, and none of the candidate pairs look like the same concrete bug or change.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out: the cluster spans many different subsystems (tokenizers, generation, image processors, training, quantization, docs), so the items are not one duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44843 is the best representative anchor if one is needed: it is open, clearly scoped, and has a concrete reproducible tokenizer/offline regression with a specific code path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Different products and failures: image processor void segmentation maps vs BarkProcessor voice_preset handling." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Unrelated bugs: torch.compile/SDPA on Bamba vs BigBirdTokenizer special-token decode output." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "One is a tied-embeddings warning during LoRA fine-tuning; the other is a save/load regression for visual encoder keys." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A typo in cache strategy docs is not the same issue as stale pipeline-task docs removed in v5." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Both involve classification config, but one is num_labels propagation in Qwen3.5 and the other is a zero-loss bug for num_labels=1 across models." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "CPU offload device-mismatch bug vs BigBirdTokenizer special-token registration/decode bug." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Both are tokenizer/config-related, but one is runtime special-token post-processing and the other is save/load loss of custom token IDs." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice preset vs Qwen3 auto device mapping cuda assert; different model paths and symptoms." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Perceiver resolution/interpolation failure is unrelated to dtype mismatches in SwitchTransformers/TimmWrapperModel bfloat16 inference." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Different multimodal bugs: Qwen3VL weight_only loading error vs Qwen2.5-VL video vision_position_ids regression." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are model-loading failures, but they affect different models and describe different tokenizer/load paths." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "AddedToken special-kwarg TypeError is not the same as failing to load a specific tokenizer/model." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counter not updating is unrelated to progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Gradient checkpointing eval-mode failure is not the same bug as gradient explosion under HfDeepSpeedConfig + ZeRO-3." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Both mention offline/tokenizer loading, but one is general cache loading on HF_HUB_OFFLINE and the other is a specific mistral-regex patch calling model_info()." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Optional post_init prohibition in patchtsmixer is unrelated to Qwen3.5 num_labels propagation." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer failures: SFT embedding unpacking vs evaluate-after-train behavior." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Runtime special-token/post-processor updates are not the same as BigBirdTokenizer mask-token registration." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to the Float8 storage lookup error." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "A model-loading regression for physical-intelligence/fast is unrelated to PIL backend image processors requiring torchvision." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Both are model-output correctness reports, but they concern different architectures and failure modes." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both are vision-related, but one is a SigLIP2 docs/model-processor mismatch and the other is OmDet-Turbo input-size mismatch." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Special-token post-processor updates are not the same as LayoutLMv2Tokenizer NER padding/truncation crashes." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Zero3/BertModel index error and fbank feature extraction issue are unrelated code paths." + }, + { + "left": "issue:43531", + "right": "issue:43645", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug does not match the Jupyter custom-model initialization regression." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both mention mistral regex/tokenizer handling, but one is an AttributeError in _patch_mistral_regex and the other is a Kimi-K2.5 codec-handling regression." + }, + { + "left": "issue:43746", + "right": "issue:45381", + "accept": false, + "reason": "PEFT/local-checkpoint loading for GraniteSpeech is unrelated to Qwen2.5-VL video position IDs." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Both involve sequence-classification validation, but one is bad input_ids/inputs_embeds error messaging and the other is a degenerate zero-loss training bug." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 docs/model mismatch is unrelated to offloading problems with quantization." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "fbank feature extraction and add-new-model-like handling of TOKENIZER_MAPPING_NAMES are different subsystems and 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": 13, + "review_unit_index": 12, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:40444", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43618", + "issue:43643", + "issue:43644", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43873", + "issue:43927", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44442", + "issue:44448", + "issue:44488", + "issue:44561", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45381" + ], + "soft_pairs": [ + "issue:43540|issue:44008", + "issue:43746|issue:43873", + "issue:40444|issue:43746", + "issue:43618|issue:43697", + "issue:43716|issue:44008", + "issue:44843|issue:45081", + "issue:43720|issue:43819", + "issue:43653|issue:43720", + "issue:43335|issue:43756", + "issue:44062|issue:44488", + "issue:30064|issue:36010", + "issue:44186|issue:44898", + "issue:43421|issue:44811", + "issue:43550|issue:45072", + "issue:43540|issue:45381", + "issue:43577|issue:43818", + "issue:43550|issue:43927", + "issue:43643|issue:44877", + "issue:43577|issue:43582", + "issue:43531|issue:43643", + "issue:43782|issue:44977", + "issue:43644|issue:43749", + "issue:44448|issue:44671", + "issue:44561|issue:45020", + "issue:43653|issue:43819", + "issue:44821|issue:45084", + "issue:43825|issue:43994", + "issue:43550|issue:43819", + "issue:44186|issue:44442", + "issue:43825|issue:43827" + ], + "prepared_review_unit_hash": "0fe87f5b7c151165ad1edb273945f3525d8a0eccd8641e74d231787e78894c0b", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36280, + "estimated_input_tokens": 9070, + "estimated_eval_tokens": 18396 + }, + "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. I do not see a strong duplicate cluster; the only near-match is the Mistral regex/helper area, but the paired reports describe different failure modes.", + "confidence": 0.71, + "canonical_issue_reason": "issue:45081 is the most concrete standalone report in the set: it names the exact exception, trigger, and code path (`_patch_mistral_regex` with `fix_mistral_regex=True`), making it the best representative issue here.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45081 is the clearest, most actionable issue in the cluster and the best single representative of the only closely related pair.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Different models and different bugs: Qwen3OmniMoe video-input processing vs Gemma3n variable-name collision." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "GraniteSpeech PEFT/local checkpoint loading is unrelated to quantization offloading behavior." + }, + { + "left": "issue:40444", + "right": "issue:43746", + "accept": false, + "reason": "IterableDataset multi-image fine-tuning failure is not the same as GraniteSpeech local checkpoint loading." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "CLIP attentions regression and RTDetrV2 output drift are different code paths and symptoms." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Mistral image-preprocessor dtype mismatch is unrelated to Gemma3n audio mask attribute collision." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve `_patch_mistral_regex`, but the reported failures differ: offline `model_info()` access vs missing `backend_tokenizer` attribute." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "BitNet packed-weight loading and DAC latent reconstruction are unrelated bugs." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "BigBirdTokenizer special-token decode failure is unrelated to BitNet accelerate-loading unpacking." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and Smollm3 RoPE-layer dropping are different model/config issues." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken special-argument error is not the same as failing to load `cjvt/sleng-bert`." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Image processor void-segmentation-map handling is unrelated to the GenerationMixin import error." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes on NER/padding are unrelated to Perceiver image-classification size handling." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token post-processor update bug is not the same as Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure and dtype mismatch in SwitchTransformers/TimmWrapperModel are different bugs." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Different multimodal models and different symptoms: Qwen3OmniMoe video processing vs Qwen2.5-VL vision_position_ids." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "BLIP2 dtype retention and Video-LLaVA temporal-attention/weight-sharing are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile/SDPA failure is unrelated to DiaConfig losing custom token IDs after save/load." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Generic trust_remote_code config field loss and granite_speech strict-config loading are not the same issue." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "BLIP2 dtype mismatch and Apple Silicon caching allocator warmup TypeError are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to trust_remote_code config field loss." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3VL weight_only loading error and Qwen3.5 flash-attention generation problem are different failures." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Non-persistent buffer junk in v5 is unrelated to FSDP CPU RAM efficient loading." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Pegasus output drift and CamemBERT masked-LM regression are different model regressions." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "`is_torch_fx_available` removal is a specific breakage; the other is a broad umbrella report about remote_code models, so they are not clearly the same concrete bug." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "BigBirdTokenizer special-token issue and DAC forward/from_latents mismatch are unrelated." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template-node compilation errors do not share the same code path." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "pipeline error-message regression and SigLIP2 nonsensical output are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Bamba SDPA/compile failure and DAC latent mismatch are different bugs." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "LayoutLMv2 tokenizer NER/padding crash is unrelated to AutoTokenizer failing to load FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "One is an error-message regression; the other is stale documentation after pipeline removals, so they are not the same bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 13, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:41720", + "issue:42175", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43452", + "issue:43454", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43638", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43906", + "issue:44060", + "issue:44291", + "issue:44368", + "issue:44485", + "issue:44509", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44811", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45406", + "issue:45488" + ], + "soft_pairs": [ + "issue:43650|issue:43906", + "issue:41720|issue:44991", + "issue:44805|issue:44936", + "issue:45081|issue:45406", + "issue:30064|issue:36331", + "issue:42175|issue:45081", + "issue:43606|issue:45072", + "issue:44610|issue:45072", + "issue:43782|issue:45325", + "issue:44485|issue:44509", + "issue:34634|issue:36010", + "issue:44060|issue:44368", + "issue:43720|issue:45072", + "issue:43262|issue:43819", + "issue:43582|issue:44857", + "issue:43749|issue:44291", + "issue:43653|issue:44671", + "issue:43526|issue:43697", + "issue:43526|issue:44554", + "issue:43653|issue:44912", + "issue:43454|issue:43577", + "issue:44568|issue:45488", + "issue:43452|issue:44991", + "issue:34634|issue:36331", + "issue:43638|issue:44936", + "issue:43257|issue:43329", + "issue:43746|issue:44811", + "issue:44589|issue:45042" + ], + "prepared_review_unit_hash": "1c6952c0eb1ca9402531ef7a5bcf58f1832eb309dd97917450075616393e087d", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 36089, + "estimated_input_tokens": 9023, + "estimated_eval_tokens": 18302 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the soft pairs mostly share broad themes like loading, tokenizers, processors, or dtype/device issues, but they point to different models, APIs, and failure modes. I do not see any pair that looks like the same underlying bug/change.", + "confidence": 0.94, + "canonical_issue_reason": "No single canonical issue stands out; the items span unrelated bugs across image processing, tokenizers, model loading, training, and device/dtype behavior.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a strong global representative because the cluster is not a true duplicate set; selecting one would mischaracterize the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Generic/placeholder issue vs isolated reproduction of issue #38071; no shared bug." + }, + { + "left": "issue:41720", + "right": "issue:44991", + "accept": false, + "reason": "CUDA assert in Qwen3 auto device mapping is unrelated to tokenizer loading for EMBEDDIA/est-roberta." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Different failure surfaces: mask/tensor shape index error vs trainer.evaluate() breaking after train()." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Mistral regex patch tokenizer crash and Gemma4Processor missing _tokenizer are different code paths/models." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "ImageProcessor segmentation-map handling is unrelated to CustomTrainer.compute_loss signature mismatch." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Packaging/backend dependency issue vs tokenizer regex crash; not the same underlying bug." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Bark CPU offload device mismatch is distinct from dtype mismatch in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Input-size mismatch in OmDet-Turbo processor is unrelated to bfloat16 inference dtype mismatches." + }, + { + "left": "issue:43782", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen VL bugs: from_pretrained weight_only error vs rope index scaling logic." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "RoPE implementation discussion is not the same as docs still mentioning removed pipeline tasks." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset bug and GenerationMixin import error are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tie warnings, but they concern different models and different warning causes." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight unpacking during loading is a different bug than dtype mismatch during inference." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio chat-template sampling-rate default and DAC latent/STE mismatch are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError is unrelated to LWDetr float16 AMP CUDA crash." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both involve loading, but one is FSDP CPU RAM efficient loading and the other is an unexpected init_empty_weights argument." + }, + { + "left": "issue:43653", + "right": "issue:44671", + "accept": false, + "reason": "BigBirdTokenizer special-token decoding issue is not the same as CamemBERT masked-LM prediction differences." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "BeitImageProcessorFast reduce_labels bug and RTDetrV2 output differences are separate issues." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "Image processor label reduction bug is unrelated to the MPS attention correctness issue." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer mask-token decode bug is unrelated to MXFP4 quantization falling back to bf16." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision weight-tying bug and BLIP2 dtype retention bug are different loading/model-initialization problems." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "mdeberta special-tokens behavior and LlamaTokenizer pre-tokenizer override are different tokenizer regressions." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "gguf_file loading breakage and est-roberta tokenizer loading failure are separate issues." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice_preset bug and trainer compute_loss keyword mismatch are unrelated." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Deepspeed ZeRO3 index error with non-pretrained Bert is unrelated to evaluate-after-train failure." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MOE conversion/loading issue and multimodal token counting video-branch bug are different paths." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "GraniteSpeech PEFT local checkpoint loading and Whisper batch_decode special-token handling are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Missing Float8 storage object and PIL backend torchvision dependency 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": 13, + "review_unit_index": 14, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:33357", + "issue:34567", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43582", + "issue:43645", + "issue:43696", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44560", + "issue:44568", + "issue:44610", + "issue:44756", + "issue:44811", + "issue:44821", + "issue:44912", + "issue:44938", + "issue:44977", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45356", + "issue:45357", + "issue:45381" + ], + "soft_pairs": [ + "issue:43854|issue:44977", + "issue:38175|issue:44610", + "issue:36010|issue:43645", + "issue:43257|issue:43696", + "issue:39692|issue:44912", + "issue:43819|issue:43927", + "issue:43262|issue:44811", + "issue:43720|issue:44610", + "issue:43550|issue:44912", + "issue:44568|issue:45356", + "issue:42175|issue:44938", + "issue:43749|issue:44756", + "issue:43531|issue:45042", + "issue:43329|issue:44479", + "issue:36010|issue:36331", + "issue:43257|issue:43931", + "issue:43257|issue:43756", + "issue:43329|issue:43450", + "issue:43577|issue:45072", + "issue:43452|issue:43582", + "issue:43697|issue:45357", + "issue:41720|issue:43540", + "issue:44479|issue:45381", + "issue:44291|issue:45042", + "issue:44062|issue:44991", + "issue:42915|issue:43742", + "issue:43540|issue:44560", + "issue:43927|issue:44912", + "issue:43540|issue:44479", + "issue:42915|issue:44821", + "issue:33357|issue:34567" + ], + "prepared_review_unit_hash": "e5544f86906b871aba37808834e3164c88a650816cb6e6604eb7fe40a2e8641f", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37096, + "estimated_input_tokens": 9274, + "estimated_eval_tokens": 18804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: many issues are only superficially similar (Qwen/video/loading/tokenizer/dtype regressions) but point to different code paths. The only clear duplicate-like subset is the Qwen 5.3.0 video-input regression pair.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44479 is the best anchor for the only apparent duplicate subset: it is the broadest Qwen 5.3.0 video-input regression report and can absorb the more specific qwen2.5-vl video symptom in issue:45381.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the most representative issue in the cluster for the accepted video-regression subset; the rest of the items are too diverse to share one canonical bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Different models and failure modes: GLM-4.7 load/test issue vs Qwen3.5 flash-attention generation." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "SigLIP2 probability bug vs OmDet-Turbo processor/model input-size mismatch; unrelated code paths." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import error is unrelated to Jupyter custom-model initialization." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Qwen3 MoE weight-conversion/loading bug vs GPT-oss CUDA OOM; not the same bug." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Documentation/example errors for SigLIP2 vs MXFP4 quantization fallback for gpt-oss." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC from_latents/STE mismatch is unrelated to DiaConfig save/load token-id corruption." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate default vs Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Accelerate loading/unpacking for BitNet vs OmDet image-size mismatch; different fixes." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "Bamba torch.compile+SDPA failure is unrelated to gpt-oss MXFP4 quantization fallback." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Tokenizer add_special_tokens regression vs Kimi codec/warning regression; different tokenizer paths." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Missing TensorFlow backend in torch install is unrelated to Python 3.14 import/load failure." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory/loading, but FSDP CPU RAM loading and Strix Halo mmap OOM are different bugs." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue vs PIL backend requiring torchvision; unrelated." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Both involve video/VLMs, but one is undefined helpers in token counting and the other is a broader video-input regression." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Importing GenerationMixin and CustomTrainer.compute_loss kwargs are unrelated failures." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE accelerate/deepspeed loading bug vs Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Qwen3 MoE weight conversion and Smollm3 RoPE-layer dropping are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Video-token counting helper bug vs batched video processor shape bug; similar area, different underlying issue." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Blip2 dtype staying float32 and SwitchTransformers/TimmWrapper dtype mismatches are model-specific loading bugs." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "gguf_file/from_pretrained breakage is unrelated to Apple Silicon caching_allocator_warmup TypeError." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "RTDetrV2 output drift and Qwen3.5 save_pretrained key corruption are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Qwen3 auto device mapping cudaErrorAssert and Qwen3OmniMoe video ValueError are different subsystems." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Same Qwen 5.3.0 video-input regression family; 45381 is a specific qwen2.5-vl symptom of the broader 44479 bug." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized bug is unrelated to PIL backend torchvision dependency regression." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "AddedToken special-argument conflict is unrelated to tokenizer loading failure for EMBEDDIA/est-roberta." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe fine-grained FP8 failure and MobileLLM key error are unrelated loading bugs." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Qwen3OmniMoe video-input ValueError and Qwen3-vl-embedding StopIteration are different model/code paths." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig token-ID persistence bug is unrelated to gpt-oss MXFP4 quantization fallback." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Qwen3OmniMoe video-processing failure is not the same regression as the Qwen 5.3.0 video-input issue." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3Moe FP8 loading failure is unrelated to AutoImageProcessor-from-URL loading." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "MacOS bus error with CLIP and TrainerState token counter not updating are unrelated issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The single accepted duplicate pair (44479/45381) is plausibly the broad Qwen 5.3.0 video-regression anchor with a more specific symptom, and the other soft-edge rejections are phrased cautiously as different bugs/code paths rather than over-claiming. No PR-mergeability issue applies here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 15, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:28282", + "issue:29127", + "issue:34567", + "issue:34689", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:42175", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43646", + "issue:43688", + "issue:43697", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43782", + "issue:43824", + "issue:43906", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44484", + "issue:44488", + "issue:44514", + "issue:44561", + "issue:44589", + "issue:44704", + "issue:44792", + "issue:44821", + "issue:44843", + "issue:44898", + "issue:44964", + "issue:45042", + "issue:45081", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45325", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479" + ], + "soft_pairs": [ + "issue:42175|issue:43824", + "issue:45137|issue:45405", + "issue:42175|issue:44488", + "issue:43906|issue:45381", + "issue:43526|issue:45479", + "issue:38175|issue:44898", + "issue:43582|issue:43782", + "issue:44484|issue:44704", + "issue:28282|issue:34689", + "issue:43646|issue:43749", + "issue:36010|issue:42175", + "issue:43742|issue:44291", + "issue:43493|issue:43994", + "issue:43643|issue:45375", + "issue:28282|issue:29127", + "issue:43756|issue:45325", + "issue:44062|issue:45081", + "issue:44291|issue:44821", + "issue:43452|issue:44488", + "issue:34567|issue:36331", + "issue:44792|issue:44964", + "issue:43688|issue:43749", + "issue:43742|issue:44589", + "issue:44514|issue:45290", + "issue:43452|issue:43577", + "issue:43643|issue:44561", + "issue:45042|issue:45081", + "issue:43531|issue:44821", + "issue:44514|issue:45381", + "issue:43697|issue:45216", + "issue:43452|issue:44843" + ], + "prepared_review_unit_hash": "f5e545888df399f2135cf3a46ba35f1552cc798ed5d66791e9a82953dabcb34a", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37292, + "estimated_input_tokens": 9323, + "estimated_eval_tokens": 18902 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All items are issue reports, not PRs. The soft edges mostly connect superficially similar loading/model bugs, but they span different models, APIs, and failure modes, so I don\u2019t see any clear duplicate pairs. I\u2019d treat issue:43452 as the most central representative only because it has the most soft links, not because it subsumes the others.", + "confidence": 0.71, + "canonical_issue_reason": "issue:43452 is the most connected node in this similarity set and is the broadest from_pretrained/load-path report, though the cluster is still heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "Best representative of the loose loading/auto-class subgroup; it is the most reusable summary point, but not a true duplicate hub.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Different problems: backend extra/install packaging vs missing model export/import." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "Unrelated failures: DeepSpeed ZeRO3 deque error vs PEFT version pin mismatch." + }, + { + "left": "issue:42175", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading-related, but one is torch extra backend packaging and the other is a specific model-load regression." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "Different code paths and symptoms: isolated reproduction of one bug vs Qwen2.5-VL video position-id regression." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Different training/classification bugs: BEiT fast processor label reduction vs degenerate zero loss." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different models and failures: SigLIP2 zero probabilities vs Perceiver non-default-resolution image classification." + }, + { + "left": "issue:43582", + "right": "issue:43782", + "accept": false, + "reason": "Different subsystems: AppleSilicon allocator warmup TypeError vs Qwen3VL weight_only load error." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "Save-pretrained shard-size question vs AutoProcessor kwargs forwarding bug; not the same defect." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Generic missing PyTorch import vs a Llama 3.2 Vision model-loading regression." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Different failures: custom model init breakage in v5 vs FSDP CPU RAM efficient loading." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "Importing GenerationMixin and missing TensorFlow backend are unrelated issues." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Different loading errors: MobileLLM key error vs init_empty_weights receiving an unexpected argument." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but one is HF-vs-JAX parity and the other is downstream inference/output quality; not clearly one fix." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Different config-loading bugs: missing fields in AutoConfig return object vs missing deepstack_visual_indexes in a model config." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Both mention error messages, but they are different failures on different models/code paths." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both involve RoPE/position handling, but they affect different models and different mechanics." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer AddedToken argument conflict vs Mistral regex patch backend_tokenizer attribute error." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "Different APIs: init_empty_weights model loading vs AutoImageProcessor URL loading." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading issues, but one is gguf-specific tokenizer/model loading and the other is a specific model compatibility failure." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "TrainerState token counting bug vs CustomTrainer compute_loss signature mismatch." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Different models and failures: janus image-generation test vs Phi-4 multimodal load regression." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Different areas: auxiliary-loss normalization vs FSDP CPU-efficient loading." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "Model key lookup failure vs missing Float8 storage type; unrelated defects." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both are apply_chat_template crashes, but under different inputs and edge cases; not clearly the same bug." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "Different dtype/loading behavior: gguf/model loading breakage vs Blip2 dtype propagation." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both touch trust_remote_code, but one is missing AutoConfig fields and the other is removal of a torch.fx helper breaking remote code." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "Unrelated: PIL image processor torchvision dependency vs Mistral regex patch crash." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Different components: Qwen3-MoE sliding_window behavior vs AutoImageProcessor URL loading." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen2.5-VL, but one is chat-template batching and the other is video vision_position_ids." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "RTDetrV2 output regression and Qwen3.5 save_pretrained checkpoint corruption are different bugs." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "Both are from_pretrained-path issues, but one is gguf handling and the other is offline model_info patching." + } + ] + }, + "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": 13, + "review_unit_index": 16, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:35141", + "issue:38175", + "issue:40444", + "issue:41720", + "issue:41762", + "issue:43122", + "issue:43295", + "issue:43329", + "issue:43525", + "issue:43531", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43819", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44625", + "issue:44743", + "issue:44811", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45005", + "issue:45325", + "issue:45356", + "issue:45440" + ], + "soft_pairs": [ + "issue:44625|issue:44877", + "issue:43688|issue:45440", + "issue:43720|issue:44898", + "issue:43819|issue:44811", + "issue:41762|issue:44936", + "issue:43653|issue:44568", + "issue:44464|issue:44743", + "issue:44466|issue:45005", + "issue:43295|issue:45356", + "issue:24643|issue:29127", + "issue:41720|issue:43906", + "issue:43525|issue:43643", + "issue:40444|issue:44811", + "issue:44361|issue:44442", + "issue:44843|issue:44991", + "issue:43577|issue:43697", + "issue:38175|issue:43295", + "issue:43653|issue:44361", + "issue:44479|issue:44936", + "issue:28282|issue:32090", + "issue:28282|issue:33357", + "issue:30064|issue:33666", + "issue:28282|issue:35141", + "issue:43122|issue:43906", + "issue:44977|issue:45356", + "issue:44464|issue:44977", + "issue:43531|issue:43742", + "issue:43577|issue:44554", + "issue:43653|issue:43927", + "issue:43329|issue:45325", + "issue:44479|issue:44625" + ], + "prepared_review_unit_hash": "e12aa1ba7fd05f146bb34745997fb0257fdf32d5fa4e1167da5ee944b3157944", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36792, + "estimated_input_tokens": 9198, + "estimated_eval_tokens": 18652 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: tokenizers, configs, multimodal processors, generation, training, and loading regressions. None of the soft pairs look like the same underlying bug/change, so no duplicate merges are justified.", + "confidence": 0.98, + "canonical_issue_reason": "No clear canonical issue: the items span unrelated failures, so selecting one issue as the representative would be arbitrary and misleading.", + "canonical_pr_reason": null, + "best_issue_reason": "No clear global best issue: the cluster is too mixed across subsystems for any single issue to represent it well.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Different problems: one is Qwen3.5 num_labels propagation, the other is strict config blocking granite_speech loading." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Different model families and failure modes: MoE auxiliary-loss normalization vs DeepSeekV3 implementation divergence." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "Unrelated bugs: BitNet packed-weight unpacking during load vs Perceiver image-classification resize/interpolation failure." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "Different code paths: DAC latent reconstruction vs Whisper batch_decode skipping special tokens." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Different stages of failure: Gemma3 DeepSpeed ZeRO-3 load-time index error vs trainer.evaluate() breaking after train()." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer-related, but the concrete bugs differ: BigBird special-token registration vs mdeberta add_special_tokens behavior." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both affect generation/caching, but one is compiled-forward chunked generation inconsistency and the other is recurrent state reset with cache." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Related theme of tied weights, but the reported failures are not the same concrete bug or mergeable fix scope." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Different regressions: processor.tokenizer/images API breakage vs Kimi-K2.5 codec handling and warning behavior." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "Different issues: a DeepSpeed training RuntimeError about weight shape vs LayoutLMv3 error-message clarity for insufficient boxes." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "No evidence of the same bug: Qwen3 auto device-mapping cuda assert vs an isolated reproduction of another issue." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Different config bugs: missing pad_token_id on Llama4Config vs missing fields from trust_remote_code AutoConfig." + }, + { + "left": "issue:40444", + "right": "issue:44811", + "accept": false, + "reason": "Different subsystems: multimodal iterable-dataset preprocessing vs Whisper batch_decode special-token handling." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Both are tokenizer/load failures, but they concern different tokenizers and different underlying error paths." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading regressions, but one is an offline model_info() call in a regex patch and the other is a specific tokenizer load failure." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Distinct model bugs: BLIP2 dtype propagation vs RTDetrV2 output differences in v5." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "No common bug: SigLIP2 zero probabilities vs processor.tokenizer regression in custom model code." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Both touch tokenization, but BigBird special-token registration and DiaConfig token-id loss are unrelated failures." + }, + { + "left": "issue:44479", + "right": "issue:44936", + "accept": false, + "reason": "Different bugs: Qwen video-input regression vs trainer.evaluate() failure after training." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "Unrelated: missing PyTorch import error vs NoneType broadcast error in Trainer." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Different failures: missing PyTorch dependency vs MacOS bus error with a CLIP model." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Different domains: void segmentation-map processing vs Qwen2-VL multi-GPU training." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "No duplicate relation: missing PyTorch import vs tied-embedding reinitialization on resize." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Different tokenizer concerns: version-dependent tokenization changes vs a reproduction of another issue." + }, + { + "left": "issue:44977", + "right": "issue:45356", + "accept": false, + "reason": "Distinct regressions: Qwen3.5 flash-attention generation vs Kimi-K2.5 tokenizer/codec handling." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both are generation bugs, but they hit different mechanisms: compiled forward chunking vs flash-attention generation." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Different failures: Qwen3-MoE sliding_window behavior vs MobileLLM-125M loading key error." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "Different code paths and symptoms: BLIP2 dtype mismatch vs an MPS attention correctness issue." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Same general area but different bugs: BigBird mask-token registration vs DiaConfig custom token IDs lost after save/load." + }, + { + "left": "issue:43329", + "right": "issue:45325", + "accept": false, + "reason": "Both involve multimodal/video handling, but one is an undefined-variable bug in token counting and the other is a rope-index scaling regression." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Unrelated: Qwen video-input regression vs Qwen3.5 num_labels propagation issue." + } + ] + }, + "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": 13, + "review_unit_index": 17, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:32090", + "issue:33666", + "issue:34567", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:43012", + "issue:43257", + "issue:43262", + "issue:43278", + "issue:43299", + "issue:43334", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43688", + "issue:43716", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43825", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44488", + "issue:44589", + "issue:44610", + "issue:44821", + "issue:44843", + "issue:44849", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45084", + "issue:45200", + "issue:45229", + "issue:45357", + "issue:45405", + "issue:45520" + ], + "soft_pairs": [ + "issue:43452|issue:44451", + "issue:43012|issue:43577", + "issue:41720|issue:44464", + "issue:43550|issue:44361", + "issue:43504|issue:43720", + "issue:43504|issue:43550", + "issue:32090|issue:33666", + "issue:32090|issue:34567", + "issue:43262|issue:45084", + "issue:43504|issue:44610", + "issue:43278|issue:43688", + "issue:44849|issue:45357", + "issue:43334|issue:43572", + "issue:45200|issue:45229", + "issue:43742|issue:44821", + "issue:43540|issue:43716", + "issue:43756|issue:44913", + "issue:43525|issue:43572", + "issue:43493|issue:43825", + "issue:33666|issue:36010", + "issue:43688|issue:43873", + "issue:43720|issue:43927", + "issue:43606|issue:43927", + "issue:43278|issue:43844", + "issue:44488|issue:44843", + "issue:44589|issue:45520", + "issue:43257|issue:43299", + "issue:43540|issue:44977", + "issue:43720|issue:44361", + "issue:39692|issue:43493", + "issue:44964|issue:45405" + ], + "prepared_review_unit_hash": "cc1da7e9d4f56e0f2ecb22e31ffd300d96624a86242ee55799090f52cf360da5", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36883, + "estimated_input_tokens": 9221, + "estimated_eval_tokens": 18698 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are mostly same-subsystem but not the same underlying bug/change; I would not merge any of them as duplicates based on the available titles and metadata.", + "confidence": 0.88, + "canonical_issue_reason": "issue:43525 is the clearest self-contained regression report in the set: a concrete config attribute failure with a direct load-time symptom. It is the best anchor among the near-matches, though it is not a duplicate of the other issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43525 is the strongest representative issue here because it is specific, reproducible, and narrowly scoped. None of the other candidates is a better global duplicate target from the available evidence.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both are load failures, but one is about gguf_file handling and the other is a specific model not loading; different bugs." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Both touch dtype behavior, but one is a compile-time warning and the other is load-time dtype propagation for BLIP2; not the same code-path issue." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Different models and different failures: auto device mapping CUDA assert versus chunked generation with compiled forward." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Unrelated subsystems and symptoms: torch.compile/SDPA versus tokenizer task attribute errors." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Different model families and failure modes: legacy field on Beit versus packed-weight unpacking in BitNet/accelerate." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "No shared underlying bug; one is a pretrained model load preset issue, the other is a compile/SDPA issue." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Both involve multi-GPU/trainer context, but the actual failure mechanisms are different and too broad to merge." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "One is a broadcast TypeError, the other is TrainerState token counting not updating; distinct bugs." + }, + { + "left": "issue:43262", + "right": "issue:45084", + "accept": false, + "reason": "Audio chat template sampling-rate default and template-node compilation errors are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Different models and different load/processor mismatches; not the same bug." + }, + { + "left": "issue:43278", + "right": "issue:43688", + "accept": false, + "reason": "Embedding dtype drift versus auxiliary-loss normalization; no concrete overlap." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Same model family but different bugs: hidden-states generation versus save_pretrained key serialization." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both are missing-pad-token style regressions, but they affect different config classes and fields; too different to treat as one bug." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Text-only mm_token_type_ids defaulting and multi-GPU CUDA OOM are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Different loading paths: one is a specific model key error, the other is AutoImageProcessor URL loading." + }, + { + "left": "issue:43540", + "right": "issue:43716", + "accept": false, + "reason": "Video-input processing in Qwen3OmniMoe and image dtype mismatch in Mistral-3 are different bugs." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Both mention RoPE/config behavior, but one is an architecture implementation bug and the other is config reload persistence." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Related regression theme, but different missing attribute names and model configs; not the same concrete issue." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and pipeline translation-task messaging are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU training and GenerationMixin import failure are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization and quantization offloading are different subsystems and symptoms." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "Packed-weight loading bug versus config token-ID persistence bug; no shared code-path." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch and save/load token-ID loss are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Different training-time numerical issues: dtype mismatch versus gradient growth under ZeRO-3." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "Both involve model loading, but one is a specific model load failure and the other is offline-mode breakage from an unconditional hub call." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage lookup failure and flash_attn import KeyError on Python 3.13 are different compatibility issues." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen3 MoE loading, but one is accelerate/deepspeed weight conversion and the other is a transformers dev-version load regression." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Video-input processing failure and flash-attention generation bug in Qwen3.5 are not the same code-path." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight loading and tokenizer attribute errors are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Both are SigLIP2-related, but one is a doc/example issue and the other is an HF-vs-JAX implementation discrepancy." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model loading failure versus an unreleased minimum dependency version bump; 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": 13, + "review_unit_index": 18, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:15354", + "issue:33357", + "issue:33666", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43329", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43572", + "issue:43575", + "issue:43582", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43701", + "issue:43746", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43927", + "issue:43994", + "issue:44060", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44466", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44589", + "issue:44734", + "issue:44792", + "issue:44977", + "issue:45072", + "issue:45084", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45405", + "issue:45446", + "issue:45520" + ], + "soft_pairs": [ + "issue:43329|issue:43606", + "issue:33666|issue:36331", + "issue:43493|issue:43844", + "issue:43756|issue:44060", + "issue:43646|issue:44466", + "issue:44423|issue:44734", + "issue:43688|issue:43746", + "issue:43824|issue:44589", + "issue:44521|issue:45290", + "issue:33357|issue:33666", + "issue:43572|issue:44291", + "issue:39692|issue:43295", + "issue:43994|issue:44493", + "issue:43504|issue:43606", + "issue:43575|issue:45405", + "issue:43504|issue:43653", + "issue:43927|issue:44361", + "issue:43257|issue:45405", + "issue:43278|issue:43701", + "issue:44792|issue:45405", + "issue:43606|issue:44112", + "issue:45084|issue:45520", + "issue:15354|issue:38175", + "issue:44554|issue:45446", + "issue:43540|issue:45200", + "issue:43582|issue:44977", + "issue:45072|issue:45198" + ], + "prepared_review_unit_hash": "a10f0f2c85fc9f8d47f9f32d5e88016b3fbba59beb193a8215db4b1a401a2d98", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36086, + "estimated_input_tokens": 9022, + "estimated_eval_tokens": 18300 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: the soft-linked pairs touch different models, regressions, and code paths, so none look like true duplicates or mergeable PR-equivalents.", + "confidence": 0.94, + "canonical_issue_reason": "No single issue is a clear canonical representative because the items span unrelated bugs across loading, training, multimodal processing, serialization, and CI.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue: the cluster does not form one coherent underlying bug, so any single issue would be arbitrary.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43329", + "right": "issue:43606", + "accept": false, + "reason": "Different failures: undefined multimodal video token helpers vs CPU offload device mismatch in Bark; no shared code path." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL is unrelated to CustomTrainer.compute_loss argument changes." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation discrepancy is not the same bug as a DeepSpeed/ZeRO gradient increase issue." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "RoPE layer dropping in Smollm3 and tied-weights warnings in Qwen3-Next are different model behaviors." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage is separate from device-dependent lm_head serialization." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve-related, but one is a multimodal '.to' crash and the other is KV-cache continuation indexing; different bugs." + }, + { + "left": "issue:43688", + "right": "issue:43746", + "accept": false, + "reason": "Aux-loss normalization issue and GraniteSpeech PEFT checkpoint loading are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Importing Qwen2.5-VL and missing Float8 storage are distinct runtime/import failures." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both mention chat templates, but one is assistant_masks for multimodal inputs and the other is tool-call content handling; not the same concrete bug." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS bus error in CLIP is unrelated to Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Different 5.0-related regressions: missing config field vs unexpected constructor arg during init_empty_weights." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Documentation example errors are not the same as a v4.57.5 processor/tokenizer regression." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "Nonsensical SigLIP2 outputs and unexpected position-id keys are different symptoms with different causes." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field model loading and device mismatch during CPU offload are unrelated." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "TP/OOM loading for Qwen2-57B is unrelated to an unreleased PEFT version bump." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Model preset loading failure and BigBirdTokenizer special-token registration are different areas." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "Config save/load token-ID loss is not the same as MLukeTokenizer task AttributeError." + }, + { + "left": "issue:43257", + "right": "issue:45405", + "accept": false, + "reason": "MOE weight conversion under accelerate+deepspeed is unrelated to the PEFT version pin issue." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "Embedding dtype drift during evaluate and resume_from_checkpoint key mismatch are separate problems." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "A failing Janus test case is unrelated to the PEFT release version bump." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "A real device mismatch bug and a stale CI test are not the same underlying issue." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Template-node compilation error and flash_attn import KeyError on Python 3.13 are unrelated." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure is unrelated to SigLIP2 zero-probability outputs." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness and a PyTorch version check for flex_attention import are different bugs." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-processing ValueError in Qwen3OmniMoe is unrelated to mm_token_type_ids defaults for text-only fine-tuning." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError and Qwen3.5 flash-attention generation issues do not share a concrete code path." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "Bfloat16 dtype mismatches in inference and Wav2Vec2 save/tokenization failures are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 19, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:39401", + "issue:40990", + "issue:42915", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43388", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43575", + "issue:43701", + "issue:43824", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43957", + "issue:43975", + "issue:43994", + "issue:44315", + "issue:44360", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44514", + "issue:44521", + "issue:44554", + "issue:44561", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44849", + "issue:44898", + "issue:44936", + "issue:44964", + "issue:44987", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45325", + "issue:45356", + "issue:45412" + ], + "soft_pairs": [ + "issue:43232|issue:44849", + "issue:43844|issue:44964", + "issue:39401|issue:44568", + "issue:37428|issue:43957", + "issue:44315|issue:44849", + "issue:44554|issue:45356", + "issue:43334|issue:43525", + "issue:43295|issue:44610", + "issue:45200|issue:45325", + "issue:43493|issue:43701", + "issue:44898|issue:45412", + "issue:43873|issue:44464", + "issue:44466|issue:45127", + "issue:40990|issue:44625", + "issue:37428|issue:43824", + "issue:43388|issue:43526", + "issue:43572|issue:44987", + "issue:44514|issue:44521", + "issue:43844|issue:44936", + "issue:43572|issue:44589", + "issue:43575|issue:44464", + "issue:43824|issue:43975", + "issue:43295|issue:43450", + "issue:44442|issue:45198", + "issue:43295|issue:43873", + "issue:38175|issue:45412", + "issue:43278|issue:43856", + "issue:43295|issue:43994", + "issue:44360|issue:44561", + "issue:42915|issue:43824" + ], + "prepared_review_unit_hash": "1806b43d6a75ab28a5f3c953782560d8303440eed4ae3db103ca6cea294b2233", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36844, + "estimated_input_tokens": 9211, + "estimated_eval_tokens": 18678 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is a heterogeneous mix of unrelated Transformers bugs; only one pair looks like a plausible duplicate around Qwen2.5-VL chat templating.", + "confidence": 0.76, + "canonical_issue_reason": "No single canonical issue cleanly spans the cluster; most items are unrelated regressions across different models and code paths.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue is truly suitable; issue:44521 is only the broadest representative of the one plausible duplicate pair, but it does not represent the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Different problems: generation kwargs update after sync_gpus vs Qwen3.5 hidden-state behavior." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "Unrelated: ZeRO-3 gradient growth vs model loading failure for Phi-4 multimodal." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer bugs, but different models and mechanisms: offset mapping vs add_special_tokens/BOS-EOS insertion." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Different loading failures: missing flash-attention import symbol vs meta-device loading breakage." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Unrelated: Liger Kernel application with model_init vs Qwen3.5 hidden-state bug." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "Different subsystems entirely: MPS attention correctness vs tokenizer codec regression." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Similar symptom (missing pad_token_id), but different model families and likely separate fixes rather than one concrete bug." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Both involve processors, but one is a regression in processor.tokenizer/image passing and the other is an OmDet input-size mismatch." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Different multimodal bugs: missing mm_token_type_ids defaults vs wrong rope temporal scaling." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "Discrepant SigLIP2 implementation vs resume_from_checkpoint key mismatch are unrelated." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Different issues: Perceiver resolution/interpolation failure vs RT-DETR memory not being released." + }, + { + "left": "issue:43873", + "right": "issue:44464", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to compiled-forward chunked generation outputs." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Both mention tied weights, but one is serialization behavior and the other is LoRA merge collapse; not the same bug." + }, + { + "left": "issue:40990", + "right": "issue:44625", + "accept": false, + "reason": "Unrelated: perplexity regression on GPT-OSS vs Qwen3.5 num_labels propagation." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different missing symbols and different model families." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Both touch labels, but one is trainer metric gathering and the other is BeitImageProcessorFast label reduction; different code paths." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Different regressions: missing pad_token_idx in StableLmConfig vs model loading failure in transformers>=5.1.0." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": true, + "reason": "Both concern Qwen2.5-VLProcessor.apply_chat_template on multimodal input; one crashes on batched padding=False, the other returns all-zero assistant masks, which points to the same chat-template/mask handling path." + }, + { + "left": "issue:43844", + "right": "issue:44936", + "accept": false, + "reason": "Unrelated training/runtime regressions: ZeRO-3 gradient issues vs trainer.evaluate() after trainer.train()." + }, + { + "left": "issue:43572", + "right": "issue:44589", + "accept": false, + "reason": "No concrete overlap beyond general v5 breakage; missing pad_token_idx is unrelated to the Float8 storage lookup error." + }, + { + "left": "issue:43575", + "right": "issue:44464", + "accept": false, + "reason": "OOM on tensor-parallel load and inconsistent compiled-forward generation are different problems." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "ImportError for a VL model class and a detokenization regression are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Both involve processor output shapes/batching, but for different processor families and different failure modes." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different speech-model issues: tokenizer loading vs save_pretrained/tokenization failure." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor regression and quantization offloading are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero probabilities and RT-DETR memory leak are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype drift in evaluation is unrelated to Qwen3 MoE memory usage." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer ReLU discussion is unrelated to removal of is_torch_fx_available breaking trust_remote_code." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3MoE FP8Config failure and Qwen2.5-VL import error are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is conservative and grounded in the packet: most pairwise rejections correctly note different model families or different failure modes. The only accepted pair, issue:44514 vs issue:44521, has a reasonable shared surface area around `apply_chat_template` and multimodal chat-mask handling, and the wording stays appropriately soft. No obvious overstatement." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 20, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:29942", + "issue:32090", + "issue:37428", + "issue:38175", + "issue:39692", + "issue:43262", + "issue:43278", + "issue:43335", + "issue:43404", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43901", + "issue:43931", + "issue:44112", + "issue:44292", + "issue:44351", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44568", + "issue:44610", + "issue:44743", + "issue:44779", + "issue:44849", + "issue:44855", + "issue:44857", + "issue:44991", + "issue:45003", + "issue:45083", + "issue:45127", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45478", + "issue:45520" + ], + "soft_pairs": [ + "issue:43827|issue:43901", + "issue:44849|issue:45003", + "issue:38175|issue:43493", + "issue:43653|issue:44112", + "issue:44568|issue:44991", + "issue:43450|issue:43493", + "issue:45127|issue:45245", + "issue:45290|issue:45381", + "issue:43819|issue:45083", + "issue:43450|issue:43575", + "issue:44462|issue:44561", + "issue:44561|issue:44779", + "issue:44610|issue:44857", + "issue:37428|issue:43425", + "issue:43819|issue:44112", + "issue:43262|issue:43450", + "issue:44448|issue:44743", + "issue:43606|issue:45083", + "issue:43278|issue:43825", + "issue:29942|issue:32090", + "issue:45310|issue:45478", + "issue:43611|issue:43931", + "issue:37428|issue:44351", + "issue:43819|issue:44493", + "issue:39692|issue:43526", + "issue:43335|issue:43550", + "issue:43450|issue:43526", + "issue:44855|issue:45083", + "issue:45200|issue:45381", + "issue:43404|issue:45200", + "issue:44292|issue:45520", + "issue:39692|issue:44493", + "issue:44448|issue:44779" + ], + "prepared_review_unit_hash": "38f2ad83fad4dbc196cd89db68f6fca6e32f0722fe9aebbe48cd7a0d043dec2b", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37613, + "estimated_input_tokens": 9404, + "estimated_eval_tokens": 19064 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a grab-bag of unrelated issue reports spanning many models, tokenizers, processors, and version-regression cases. The only clear duplicate pair is the two Qwen3.5 MoE from_pretrained reports (#45310 and #45478).", + "confidence": 0.87, + "canonical_issue_reason": "Issue #45478 is the strongest canonical choice: it is the same concrete Qwen3.5 MoE from_pretrained failure as #45310, with a later report and slightly more discussion, making it a good representative for the duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45478 is the best global representative because it is specific, actionable, and clearly tied to a reproducible model-loading regression; among the set, it is the cleanest duplicate anchor.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs/pipeline-related, but they describe different problems: one is stale pipeline references after v5 removals, the other is a TextClassificationPipeline docs/behavior mismatch about return_all_scores." + }, + { + "left": "issue:44849", + "right": "issue:45003", + "accept": false, + "reason": "Different subsystems and failure modes: Qwen3.5 hidden-states behavior vs an unsafe sys.modules access pattern in modeling_utils." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Both mention SigLIP2, but one is an output symptom (zero probabilities) and the other is a broader HF-vs-JAX implementation discrepancy; not clearly the same concrete bug." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "Unrelated issues: BigBirdTokenizer special-token registration vs a GraniteSpeech CI device-override test failure." + }, + { + "left": "issue:44568", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer regressions, but they concern different models and different behaviors (special-token insertion vs tokenizer loading)." + }, + { + "left": "issue:43450", + "right": "issue:43493", + "accept": false, + "reason": "Video batch-shape handling and SigLIP2 implementation discrepancy are different bugs in different code paths." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "These are unrelated: LoRA merging with tied embeddings vs a category-count runtime limit." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Different multimodal/chat-template problems affecting different inputs and models; not the same underlying bug." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent reconstruction mismatch is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batch video-processing shape bug and Qwen2-57B-A14B TP OOM are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "Both are loading-related, but one is AutoTokenizer ignoring tokenizer.json while the other is a trust_remote_code break from removing is_torch_fx_available." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Both are v5 regressions, but they affect different code paths: remote-code imports vs Deepseek tokenizer behavior." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor input-size mismatch and CUDA AMP loss crash are distinct bugs." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "Importing a removed flash-attention helper and Torch 2.10 incompatibility are different versioning issues." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "Different models and symptoms: DAC latent mismatch vs GraniteSpeech stale device override CI failure." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and video batch shape handling are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Different regressions in different models: Pegasus output drift vs Qwen3.5 recurrent-state reset behavior." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch in bark-small is unrelated to qwen3_omni_moe helper behavior." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift and pipeline error messaging are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and Trainer _gpu_broadcast_one NoneType errors are unrelated." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Exact same reported regression: transformers>=5.4.0 causes Qwen3.5 MoE from_pretrained failure. This is a clear duplicate pair." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "General base_model_prefix loading breakage and a specific Qwen3-VL weight-shape mismatch are different failures." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and different modules." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC latent/forward mismatch and unexpected position-id keys are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 docs/example issues and BeitImageProcessorFast label reduction are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and Bamba torch.compile SDPA failure do not share the same code-path bug." + }, + { + "left": "issue:43450", + "right": "issue:43526", + "accept": false, + "reason": "Video batching shape and BeitImageProcessorFast label reduction are unrelated." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 TorchScript indentation parsing error is unrelated to qwen3_omni_moe feature-length behavior." + }, + { + "left": "issue:45200", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal position/input-default issues, but they affect different models and different fields; not the same concrete bug." + }, + { + "left": "issue:43404", + "right": "issue:45200", + "accept": false, + "reason": "Mistral3 lm_head tying and Gemma 4 mm_token_type_ids defaults are unrelated model bugs." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime failure and a Python 3.13 flash_attn import KeyError are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 docs/model mismatch and unexpected position-id keys are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus v4/v5 output differences and Deepseek tokenizer regressions are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The only clearly supported duplicate pair is 45310/45478, which share the same Qwen3.5 MoE from_pretrained regression title and description. The other soft-edge rejections are cautious and do not overclaim equivalence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 21, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:37428", + "issue:38175", + "issue:40444", + "issue:41720", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43329", + "issue:43335", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43653", + "issue:43701", + "issue:43720", + "issue:43723", + "issue:43873", + "issue:43976", + "issue:43994", + "issue:44112", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44857", + "issue:44977", + "issue:44987", + "issue:45072", + "issue:45083", + "issue:45229", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520" + ], + "soft_pairs": [ + "issue:29127|issue:32090", + "issue:43335|issue:43653", + "issue:44977|issue:45229", + "issue:38175|issue:44493", + "issue:43335|issue:45083", + "issue:43335|issue:43504", + "issue:43550|issue:44112", + "issue:43335|issue:45072", + "issue:44568|issue:45491", + "issue:43720|issue:44112", + "issue:44448|issue:44977", + "issue:40444|issue:43526", + "issue:43723|issue:44554", + "issue:43335|issue:44112", + "issue:34689|issue:35141", + "issue:45372|issue:45406", + "issue:43606|issue:44857", + "issue:44857|issue:45072", + "issue:43873|issue:44493", + "issue:43066|issue:44462", + "issue:43873|issue:45229", + "issue:37428|issue:44987", + "issue:43278|issue:43329", + "issue:43701|issue:45083", + "issue:29942|issue:35141", + "issue:41720|issue:45229", + "issue:43550|issue:45083", + "issue:44451|issue:45520", + "issue:43976|issue:45440", + "issue:32090|issue:33357", + "issue:45372|issue:45459", + "issue:44448|issue:44466", + "issue:43065|issue:45412", + "issue:43065|issue:43994" + ], + "prepared_review_unit_hash": "23e6a4f950eda39a212ca7fc933cb901b5caa98e53a6e5aba5d1387307e34462", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 34, + "serialized_chars": 37517, + "estimated_input_tokens": 9380, + "estimated_eval_tokens": 19016 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a heterogeneous mix of unrelated Transformers bugs; the soft matches are mostly title-level lexical similarity rather than the same underlying defect. I would not merge any of the suggested pairs.", + "confidence": 0.95, + "canonical_issue_reason": "issue:43335 is the closest thing to a hub by soft-match fan-out, but the surrounding links are superficial and the cluster is too heterogeneous to justify a true canonical duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43335 is the least-bad representative only because it has the most soft-similarity links; it is not a strong semantic cluster center.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "Different models and failures: layoutlmv3 box validation messaging vs Trainer NoneType GPU broadcast." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to BigBirdTokenizer special-token registration." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU OOM are different code paths and symptoms." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "siglip2 zero-probabilities vs position-id unexpected-key loading are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers config creation issue does not match qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "Sparse-layer construction in SwitchTransformers is unrelated to BEiT legacy-field loading." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure and GraniteSpeech CI stale override test are different problems." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "SwitchTransformers sparse-layer bug is not the same as dtype mismatch in bfloat16 inference." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer add_special_tokens behavior and Gemma3 NaN embeddings from sliding-window attention are different bugs." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight loading under accelerate is unrelated to a GraniteSpeech CI test failure." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Pegasus v4/v5 output regression and Qwen3.5 flash-attention generation failure are not the same issue." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Qwen2.5-VL iterable-dataset multi-image finetuning and BEiT fast processor label reduction are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "AutoTokenizer loading in v5 and an MPS attention correctness bug are different code paths." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "SwitchTransformers config bug does not match a GraniteSpeech stale-device CI test." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Llama 3.2 vision model loading breakage is not the same as output embeddings being reinitialized on resize." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both involve Gemma4, but one is an import-dependency failure and the other is a missing _tokenizer attribute in serve; not the same code-path bug." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU-offload device mismatch in bark-small is unrelated to an AMP/CUDA crash in LwDetrImageLoss." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "These are both dtype-related, but they affect different models and different failure mechanisms." + }, + { + "left": "issue:43873", + "right": "issue:44493", + "accept": false, + "reason": "Quantization/offloading behavior and unexpected position-id keys are unrelated." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer decoder type selection and ignoring tokenizer.json are different tokenizer-loading bugs." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Quantized offloading problems and Gemma4 multi-GPU OOM are not the same underlying defect." + }, + { + "left": "issue:37428", + "right": "issue:44987", + "accept": false, + "reason": "Flash-attention import error and Qwen3.5 flash-attention generation failure share a subsystem but not a concrete bug." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype drift in eval and an undefined-variable multimodal token helper are unrelated." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "resume_from_checkpoint key mismatch does not match qwen3_omni_moe feature-length logic." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Failing Flash Attention 2 tests and embedding reinit after resize are different issues." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "cudaErrorAssert under auto device mapping is not the same as multi-GPU inference OOM." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure is unrelated to qwen3_omni_moe feature-length calculation." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model-loading failure for ScandiBERT and flash_attn import KeyError on Python 3.13 are different problems." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility breakage and DeepSeekV3 implementation divergence are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast NoneType error and MacOS bus error loading a CLIP model are not the same bug." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma4 ReasoningEffort import failure and protobuf-related tokenizer error masking are different failure modes." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Both are v4/v5 regressions, but one is generation output difference and the other is lm_head serialization inconsistency; different code paths." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory release on delete are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Sam3PixelDecoder dummy layer and ScandiBERT loading failure have no shared underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 22, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:25251", + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:36010", + "issue:39692", + "issue:42915", + "issue:42994", + "issue:43257", + "issue:43262", + "issue:43278", + "issue:43334", + "issue:43381", + "issue:43421", + "issue:43504", + "issue:43526", + "issue:43531", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43824", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44279", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45072", + "issue:45103", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45412", + "issue:45440", + "issue:45491" + ], + "soft_pairs": [ + "issue:44186|issue:45198", + "issue:25251|issue:32090", + "issue:43653|issue:44743", + "issue:43278|issue:43381", + "issue:44265|issue:45198", + "issue:44361|issue:45198", + "issue:43257|issue:43278", + "issue:42915|issue:42994", + "issue:43421|issue:45491", + "issue:44871|issue:44977", + "issue:43994|issue:45412", + "issue:44206|issue:44479", + "issue:43756|issue:45440", + "issue:43504|issue:44857", + "issue:44610|issue:45412", + "issue:29942|issue:30064", + "issue:45103|issue:45372", + "issue:33357|issue:39692", + "issue:29127|issue:34567", + "issue:32090|issue:33290", + "issue:45072|issue:45229", + "issue:43824|issue:44279", + "issue:43653|issue:44442", + "issue:43381|issue:43701", + "issue:43334|issue:43531", + "issue:43526|issue:44186", + "issue:44464|issue:45491", + "issue:43262|issue:44206", + "issue:44977|issue:45245", + "issue:29942|issue:36010", + "issue:29127|issue:33357" + ], + "prepared_review_unit_hash": "f79e4db9c237686722495b953149c4d18146928c910b9fb0a67ca9f9759a9308", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37017, + "estimated_input_tokens": 9255, + "estimated_eval_tokens": 18766 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose grab-bag of mostly unrelated Hugging Face issues that were only weakly linked by text similarity. None of the suggested soft pairs look like true duplicates or the same underlying fix, and there are no PRs in the set.", + "confidence": 0.96, + "canonical_issue_reason": "If a representative issue is needed, issue 45198 is one of the clearest standalone bug reports with a concrete failure mode and reproducible symptoms, but the cluster is not cohesive enough to have a strong canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45198 is the most concrete and actionable report among these unrelated items; it has a specific model, specific failure, and a likely reproducible path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "Both are tokenizer-related, but they describe different models and different failures: NER/batching crashes vs save_pretrained/tokenization failure." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline output nesting and Trainer broadcast TypeError are unrelated code paths and symptoms." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token decode behavior and Qwen3-MoE recurrent-state reset are different bugs in different components." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype drift in eval and gradient-checkpointing disallowed in eval mode are separate training/evaluation issues." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failures with torch_compilable_check are unrelated to Wav2Vec2 save_pretrained/tokenization problems." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and Wav2Vec2 tokenization/save failures are different tokenizer bugs with different triggers." + }, + { + "left": "issue:43257", + "right": "issue:43278", + "accept": false, + "reason": "Qwen3 MoE weight conversion/loading under accelerate+deepspeed is not the same bug as BF16-to-FP32 embedding dtype drift." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and quantized model saving failure are separate quantization-related problems." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime post-processor updates for special tokens and Gemma3 NaN embeddings are unrelated features/bugs." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma eos_token_id mismatch and Qwen3.5 flash-attention generation issues affect different models and different mechanisms." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 nonsense outputs and RT-DETR memory leaks are distinct model behavior vs lifecycle bugs." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported center argument in LasrFeatureExtractor is unrelated to the qwen2_5_vl/qwen3_vl video regression." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Smollm3 RoPE-layer discrepancy and DeepseekV3MoE divergence are different model-implementation issues." + }, + { + "left": "issue:43504", + "right": "issue:44857", + "accept": false, + "reason": "Beit pretrained-load legacy-field handling and LwDetr float16 CUDA loss crashes are unrelated bugs." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor image-size mismatch and RT-DETR memory release behavior do not share the same underlying defect." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 CI failures and void segmentation-map processing are different subsystems and failure modes." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation parsing and Gemma 4 processor import failure come from unrelated tooling paths." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "Both mention CLIP/SigLIP-like models, but the MacOS bus error and documentation example errors are different issues." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and TrainerState token-count tracking are unrelated concerns." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer NoneType broadcast errors and DeepSpeed Adafactor OOM are distinct training failures." + }, + { + "left": "issue:45072", + "right": "issue:45229", + "accept": false, + "reason": "Bfloat16 dtype mismatches in inference and Gemma4 multi-GPU OOM are different classes of problems." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Specific Qwen2.5-VL import failure and a generic dependency issue are not the same bug." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and AutoTokenizer loading FastSpeech2ConformerTokenizer are unrelated tokenizer/loading bugs." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch do not describe the same code path." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL pad_token_id missing and Qwen3-MoE sliding_window issues are different model-family regressions." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "BeitImageProcessorFast reduce_labels behavior and LayoutLMv2Tokenizer batching crashes are different components and failures." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency and Gemma3 NaN embeddings are not the same underlying bug." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and unsupported center arg in an image extractor are unrelated." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation problems and category-count limits are entirely different issues." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Failing Flash Attention 2 tests and GenerationMixin import errors are unrelated." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error messaging and CLIP bus errors on MacOS are not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 23, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:33290", + "issue:33666", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:39692", + "issue:42915", + "issue:43232", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43575", + "issue:43611", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43723", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:43994", + "issue:44077", + "issue:44079", + "issue:44188", + "issue:44206", + "issue:44387", + "issue:44442", + "issue:44479", + "issue:44610", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44898", + "issue:44964", + "issue:45003", + "issue:45072", + "issue:45216", + "issue:45290", + "issue:45440", + "issue:45479", + "issue:45491" + ], + "soft_pairs": [ + "issue:29127|issue:35141", + "issue:43761|issue:44079", + "issue:44442|issue:45072", + "issue:42915|issue:43931", + "issue:43232|issue:43388", + "issue:43526|issue:44857", + "issue:43526|issue:44610", + "issue:44479|issue:45290", + "issue:43723|issue:45479", + "issue:44743|issue:44811", + "issue:45003|issue:45440", + "issue:43575|issue:43701", + "issue:43931|issue:45216", + "issue:43316|issue:43525", + "issue:43646|issue:44077", + "issue:43761|issue:44188", + "issue:43575|issue:44387", + "issue:44964|issue:45440", + "issue:43994|issue:44206", + "issue:29942|issue:33666", + "issue:39692|issue:45491", + "issue:43673|issue:44743", + "issue:44442|issue:44898", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:43381|issue:43873", + "issue:43493|issue:43827", + "issue:44077|issue:44479", + "issue:33290|issue:34689", + "issue:33290|issue:35141" + ], + "prepared_review_unit_hash": "094d24fc85d6f3110c473e4815fc0427b99cc0503adea5f833e76c1df19c1055", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36126, + "estimated_input_tokens": 9032, + "estimated_eval_tokens": 18320 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is not a duplicate cluster; it mixes many unrelated issues across different models, processors, generation, quantization, and docs. I rejected all soft edges because none appear to describe the same concrete bug.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue fits the cluster: the items span unrelated regressions and API mismatches, so none cleanly subsumes the rest.", + "canonical_pr_reason": "No PRs are present in the provided items.", + "best_issue_reason": "If forced to choose a representative, issue 43873 is the broadest open regression with active discussion, but it still does not represent the rest of the set.", + "best_pr_reason": "No PRs are present in the provided items.", + "soft_edge_verdicts": [ + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "Different bugs: LayoutLMv3 error-message clarity vs token-embedding reinitialization in post_init." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "One is a CLIPVisionModel hidden_states regression; the other is ModelOutput key handling for None values." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Unrelated failures: tokenizer loading for FastSpeech2ConformerTokenizer vs dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Different model-load paths and symptoms: FineGrainedFP8Config failure vs Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwargs sync bug vs metric-gathering dropping tuple labels; unrelated code paths." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs LwDetrImageLoss AMP/CUDA crash." + }, + { + "left": "issue:43526", + "right": "issue:44610", + "accept": false, + "reason": "Both touch processors, but one is label reduction in BeitImageProcessorFast and the other is input-size mismatch in OmDet-Turbo." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Different regressions: video-input handling for Qwen variants vs chat-template tool-call tokenization crash." + }, + { + "left": "issue:43723", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer loading in v5 is unrelated to the zero-loss classification bug with num_labels=1." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen recurrent-state caching bug vs Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:45003", + "right": "issue:45440", + "accept": false, + "reason": "Unsafe sys.modules access in modeling_utils vs DeepseekV3MoE implementation divergence." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Tensor-parallel OOM when loading Qwen2-57B-A14B-Instruct is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Both are Qwen3-family regressions, but one is a weight-shape load error and the other is a bad save_pretrained checkpoint." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are API discrepancies, but Gemma3TextConfig missing parity is different from Llama4Config lacking pad_token_id." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "General custom model initialization breakage is not the same bug as patchtsmixer's post_init policy change." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIPVision hidden_states regression and allow_is_bidirectional_skip branching under torch.compile are distinct issues." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is TP loading OOM and the other is increased reserved memory under int4 quantization." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Phi-4 multimodal loading failure is unrelated to DeepseekV3MoE divergence from remote implementation." + }, + { + "left": "issue:43994", + "right": "issue:44206", + "accept": false, + "reason": "SigLIP2 nonsensical outputs with AutoModel/pipeline do not match the LasrFeatureExtractor center-arg crash." + }, + { + "left": "issue:29942", + "right": "issue:33666", + "accept": false, + "reason": "Failing Flash Attention 2 tests and Qwen2-VL multi-GPU training are different subsystems and failures." + }, + { + "left": "issue:39692", + "right": "issue:45491", + "accept": false, + "reason": "Documentation example errors for SigLIP2 are unrelated to Gemma3 NaN embeddings on mixed-length batches." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Chunked-prefill cache missing in GenerationMixin is a different cache bug than Qwen recurrent states resetting." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer loading failure vs Perceiver image-classification resolution/interpolation failure are unrelated." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "AdaFactor OOM in DeepSpeed is unrelated to TrainerState.num_input_tokens_seen not updating." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both are loading regressions, but they concern different releases, model families, and failure modes." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode and quantization offloading behavior are separate bugs." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation drift is unrelated to docs still referencing pipeline() after v5 removals." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTSMixer post_init policy change is unrelated to the Qwen video-input regression." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "AdaFactor/DeepSpeed OOM and Llama 3.2 Vision model-loading breakage are different problems." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "Optimizer OOM in DeepSpeed is unrelated to token-embedding reinitialization during post_init." + } + ] + }, + "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": 13, + "review_unit_index": 24, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:25251", + "issue:28282", + "issue:33290", + "issue:34689", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:43065", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43475", + "issue:43540", + "issue:43643", + "issue:43688", + "issue:43716", + "issue:43720", + "issue:43749", + "issue:43761", + "issue:43825", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:44162", + "issue:44190", + "issue:44206", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44617", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45137", + "issue:45200", + "issue:45372" + ], + "soft_pairs": [ + "issue:41628|issue:45372", + "issue:43720|issue:44442", + "issue:43749|issue:43931", + "issue:43643|issue:44913", + "issue:43873|issue:44871", + "issue:39692|issue:44206", + "issue:44190|issue:44496", + "issue:33290|issue:36331", + "issue:43381|issue:43856", + "issue:43316|issue:44877", + "issue:44855|issue:45137", + "issue:34689|issue:36010", + "issue:43540|issue:44514", + "issue:42175|issue:43316", + "issue:44162|issue:44792", + "issue:43388|issue:43688", + "issue:43404|issue:43441", + "issue:43316|issue:43716", + "issue:16998|issue:22355", + "issue:25251|issue:28282", + "issue:41950|issue:43475", + "issue:43065|issue:44617", + "issue:45127|issue:45200", + "issue:43295|issue:43825", + "issue:43761|issue:44479" + ], + "prepared_review_unit_hash": "0ee7053ab209298acf0c519cd756e386fc6f71a6398c1b872e4c3ede5b7b8acd", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 25, + "serialized_chars": 35229, + "estimated_input_tokens": 8808, + "estimated_eval_tokens": 17872 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated issue reports across different models, APIs, and regression types; none of the soft pairs look like the same underlying bug/change, so this is not a real duplicate cluster.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Different import failures in different places: AutoImageProcessor missing vs ReasoningEffort missing from mistral_common/Gemma 4 processor loading." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "One is a CI/accelerate packed-weights unloading bug; the other is AutoTokenizer failing to load a specific tokenizer class. Not the same code path." + }, + { + "left": "issue:43749", + "right": "issue:43931", + "accept": false, + "reason": "FSDP CPU RAM efficient loading vs Qwen3-VL shape mismatch during model load are distinct loading problems with different causes." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code missing config fields is a config deserialization issue; GPTNeoX rotary_pct reset on reload is a separate config persistence bug." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior vs Gemma-3 eos_token_id mismatch are unrelated model/runtime issues." + }, + { + "left": "issue:39692", + "right": "issue:44206", + "accept": false, + "reason": "SigLIP2 docs errors are about an example mismatch and quantization failure; LasrFeatureExtractor center-arg crash is a different preprocessing regression." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to unrecognized model/config.json loading for a different repository/model." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "AdaFactor/DeepSpeed OOM and CustomTrainer.compute_loss signature breakage are separate training bugs." + }, + { + "left": "issue:43381", + "right": "issue:43856", + "accept": false, + "reason": "Gradient checkpointing in eval mode is a mode-compatibility bug; Qwen3 MoE memory usage is a training efficiency issue." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy is not the same as strict config blocking granite_speech config loading." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 IndentationError from torch.jit parsing differs completely from DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama 3.2 model loading regression is unrelated to a missing GenerationMixin import path issue." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video input processing in Qwen3OmniMoe is different from batched apply_chat_template padding=False failure in Qwen2_5_VLProcessor." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Torch-only install missing TensorFlow backend is packaging/dependency-related, not the Gemma3TextConfig API issue." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 breakage for scientific workflows is unrelated to a janus test failure around image generation." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "One is gather_for_metrics dropping tuple labels in the last batch; the other is auxiliary loss normalization in MoE models." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Weight tying in Mistral3ForConditionalGeneration is a model consistency bug; FlashAttention failure for Ministral-3 is a separate attention backend issue." + }, + { + "left": "issue:43316", + "right": "issue:43716", + "accept": false, + "reason": "Gemma3TextConfig API mismatch and Mistral-3 image preprocessor dtype mismatch are unrelated model-specific regressions." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "DeBERTa-V3 model_max_length question and missing transformers.onnx module are unrelated and far apart in scope." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "top_k changing pipeline output shape is unrelated to AutoModel/PyTorch missing import error." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification pipeline using image processors and SAM3 video missing fpn_position_embeddings are different pipeline/model bugs." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is not the same as Sam3Video CUDA OOM; one is a code correctness issue, the other a resource issue." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge with extended vocabulary causing collapse is unrelated to Gemma 4 mm_token_type_ids defaulting for text-only fine-tuning." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "processor.tokenizer/images regression is distinct from the v5 translation-task error-message mismatch." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression is unrelated to Qwen video input regression across multiple model families." + } + ] + }, + "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": 13, + "review_unit_index": 25, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:41720", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43388", + "issue:43452", + "issue:43525", + "issue:43531", + "issue:43550", + "issue:43575", + "issue:43582", + "issue:43606", + "issue:43646", + "issue:43650", + "issue:43701", + "issue:43742", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44220", + "issue:44242", + "issue:44464", + "issue:44479", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44871", + "issue:44913", + "issue:44933", + "issue:44964", + "issue:44977", + "issue:45245", + "issue:45290", + "issue:45362", + "issue:45381", + "issue:45406" + ], + "soft_pairs": [ + "issue:44734|issue:45406", + "issue:44077|issue:44534", + "issue:43550|issue:43701", + "issue:43295|issue:44871", + "issue:43606|issue:43701", + "issue:43452|issue:44496", + "issue:43646|issue:44913", + "issue:43906|issue:45290", + "issue:43761|issue:44242", + "issue:42617|issue:43575", + "issue:43575|issue:43742", + "issue:43931|issue:44060", + "issue:44521|issue:45381", + "issue:43575|issue:43873", + "issue:43525|issue:43531", + "issue:44479|issue:44734", + "issue:44792|issue:44977", + "issue:32090|issue:35141", + "issue:44464|issue:44871", + "issue:44933|issue:45362", + "issue:43065|issue:44610", + "issue:43827|issue:43994", + "issue:44534|issue:44913", + "issue:41720|issue:45245", + "issue:44190|issue:44964", + "issue:43650|issue:44220", + "issue:43388|issue:43582", + "issue:43761|issue:44743" + ], + "prepared_review_unit_hash": "7805fff8c281d72f9c122499e4c12369ea7bcaf74d79a9104835081ee8b0ba04", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35939, + "estimated_input_tokens": 8985, + "estimated_eval_tokens": 18226 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: it mixes unrelated regressions, model-specific loading bugs, training/runtime issues, and docs/API breakages. None of the soft pairs look like safe duplicates.", + "confidence": 0.98, + "canonical_issue_reason": "No single canonical issue fits this cluster; the items are not the same underlying bug.", + "canonical_pr_reason": null, + "best_issue_reason": "If a representative issue is needed, issue:44521 is the most active/open and user-visible, but it is not a true canonical duplicate anchor.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "Different failures: KV-cache continuation tensor indexing in serve vs Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Unrelated bugs: post_init being optionally allowed for patchtsmixer vs junk-filled non-persistent buffers." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "Different code paths: Bamba SDPA/torch.compile failure vs resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Both touch model/config behavior, but one is processor.tokenizer/image handling and the other is Gemma eos_token_id mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch for bark-small is unrelated to checkpoint resume key handling." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Loading via gguf_file is a different problem from an unrecognized model/config.json issue." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Custom model initialization breakage is not the same as GPTNeoXConfig rotary_pct not persisting on reload." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "Isolated reproduction of an old issue is unrelated to apply_chat_template crashing on tool-call assistant messages." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "CLIPVisionModel hidden_states bug and missing load-balancing loss are separate model behaviors." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py runtime failure is unrelated to Qwen2-57B-A14B-Instruct loading OOM." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Both are loading-related, but one is tensor-parallel OOM and the other is a KeyError for MobileLLM config/loading." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Shape mismatch loading Qwen3-VL is not the same as a tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both involve multimodal chat/input handling, but assistant_masks being all zero is a different defect from wrong video vision_position_ids." + }, + { + "left": "issue:43575", + "right": "issue:43873", + "accept": false, + "reason": "Qwen2 tensor-parallel OOM and quantization offloading behavior are distinct issues." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config is unrelated to sliding_window behavior in Qwen3-MoE." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression in Qwen multimodal models is not the same as a serve KV-cache indexing crash." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to Qwen3.5 flash-attention generation issues." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer _gpu_broadcast_one NoneType error and embedding reinitialization after resize are different bugs." + }, + { + "left": "issue:44464", + "right": "issue:44871", + "accept": false, + "reason": "Chunked generation with compiled forward is unrelated to Gemma-3 eos_token_id configuration inconsistency." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Nonexistent image_utils import is unrelated to Qwen3.5 chat crashes." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and OmDet processor size mismatch are separate model/preprocessing issues." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() is not the same bug as nonsensical Siglip2 outputs with AutoModel/pipeline." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer junk in v5 is unrelated to GPTNeoX rotary_pct resetting on reload." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3 auto device-mapping cuda assert and the 2^24 category limit error are unrelated." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading failure in a no-trainer script is unrelated to Phi-4 multimodal model loading." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "The placeholder title and the fbank feature-extraction issue do not describe the same bug." + }, + { + "left": "issue:43388", + "right": "issue:43582", + "accept": false, + "reason": "gather_for_metrics last-batch label dropping is unrelated to Apple Silicon warmup TypeError." + }, + { + "left": "issue:43761", + "right": "issue:44743", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and Qwen3.5 recurrent-state reset are different failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 26, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:39692", + "issue:41628", + "issue:41950", + "issue:42175", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43299", + "issue:43335", + "issue:43404", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43643", + "issue:43644", + "issue:43854", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44077", + "issue:44079", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44279", + "issue:44355", + "issue:44466", + "issue:44496", + "issue:44683", + "issue:44734", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:45003", + "issue:45127", + "issue:45216", + "issue:45276", + "issue:45335", + "issue:45357", + "issue:45372", + "issue:45375", + "issue:45446" + ], + "soft_pairs": [ + "issue:45127|issue:45357", + "issue:44355|issue:44855", + "issue:43644|issue:44913", + "issue:44496|issue:45372", + "issue:43976|issue:44855", + "issue:43540|issue:44734", + "issue:44077|issue:44079", + "issue:43550|issue:44190", + "issue:43295|issue:45276", + "issue:43335|issue:44855", + "issue:43404|issue:45216", + "issue:43116|issue:44190", + "issue:41950|issue:44016", + "issue:36246|issue:41628", + "issue:39692|issue:44190", + "issue:43644|issue:44871", + "issue:44186|issue:44734", + "issue:43479|issue:45375", + "issue:36246|issue:38617", + "issue:44246|issue:45003", + "issue:44016|issue:44220", + "issue:38175|issue:43065", + "issue:44466|issue:44913", + "issue:44683|issue:45446", + "issue:42175|issue:44279", + "issue:44112|issue:44792", + "issue:43854|issue:44792", + "issue:43295|issue:45335", + "issue:43643|issue:44496", + "issue:43299|issue:45216", + "issue:44016|issue:44062" + ], + "prepared_review_unit_hash": "97416781cbbdd621cf7d5cbfc9231d1f67ee28f6de10fecffa1098d3cc9410ad", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37266, + "estimated_input_tokens": 9317, + "estimated_eval_tokens": 18890 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are distinct regressions across unrelated models, configs, imports, and scripts. I do not see any soft-edge pair that safely collapses into one duplicate/canonical bug.", + "confidence": 0.93, + "canonical_issue_reason": "No true canonical issue: the items span separate failure modes, so picking one as the cluster anchor would be arbitrary.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43295 is the best representative only in the loose sense that it is a broad, user-facing regression around multimodal processor/tokenizer behavior.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen save/tie-weight problems: LoRA+extended-vocab collapse vs incorrect visual-encoder keys in save_pretrained." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Both are import-time failures, but one is about compiled .py execution and the other is a Python 3.13 IndentationError from a torch.jit.script parsing edge case." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Different persistence bugs: junk non-persistent buffers vs rotary_pct resetting on reload." + }, + { + "left": "issue:44496", + "right": "issue:45372", + "accept": false, + "reason": "Unrecognized-model/config loading failure is unrelated to the mistral_common ReasoningEffort import breakage in Gemma 4 processor loading." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "A Python-version compatibility complaint is not the same as the DebertaV2 import parse error on Python 3.13." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Different code paths: Qwen3OmniMoe video-input validation vs serve KV-cache continuation tensor indexing." + }, + { + "left": "issue:44077", + "right": "issue:44079", + "accept": false, + "reason": "One is about optional post_init in patchtsmixer; the other is ModelOutput key assignment when a value was previously None." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "torch.compile/SDPA failure and a local-dataset loading failure in an example script are separate problems." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Both are regressions, but one is processor/tokenizer API breakage and the other is resize_token_embeddings not propagating to Gemma 4 embeddings." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "SwitchTransformersConfig sparse-layer creation and a Python 3.13 decorator/comment parsing issue are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Different multimodal weight/checkpoint bugs: untied lm_head in Mistral3 vs incorrect Qwen3.5 save_pretrained output." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Empty multi-label classification outputs and local dataset loading in the image-classification script are different failures." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Pipeline image-processor lookup for video is unrelated to a notebook syntax error." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but one is a missing Qwen2_5_VLImageProcessor symbol and the other is a top-level AutoImageProcessor import failure." + }, + { + "left": "issue:39692", + "right": "issue:44190", + "accept": false, + "reason": "Documentation example errors and local dataset loading in a training script are not the same bug." + }, + { + "left": "issue:43644", + "right": "issue:44871", + "accept": false, + "reason": "Non-persistent buffer junk and Gemma eos_token_id mismatch are different model-state/config issues." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "LayoutLMv2Tokenizer NER/padding crashes are unrelated to the serve KV-cache continuation indexing bug." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Default vision/audio config initialization and a missing deepstack_visual_indexes field are different config-handling problems." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Different missing imports in different modules; no shared underlying bug." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowdowns and unsafe sys.modules access may be related at a high level, but they are not the same concrete defect." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and fbank feature extraction failure are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "SigLIP2 zero-probability output and a dummy Conv2d in Sam3PixelDecoder are different model bugs." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "lm_head serialization inconsistency and rotary_pct reset-on-reload are separate persistence issues." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "These touch flex_attention, but one is a torch>=2.9 compilation failure and the other is a version-check/import bug for AuxRequest." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "An extras/backend dependency omission is not the same as a vague dependency issue report." + }, + { + "left": "issue:44112", + "right": "issue:44792", + "accept": false, + "reason": "GraniteSpeech CI stale test and Janus image-generation test failure are unrelated test failures." + }, + { + "left": "issue:43854", + "right": "issue:44792", + "accept": false, + "reason": "GLM-4.7-Flash loading in unit tests and Janus generate-images test failure are different model/test paths." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor/tokenizer regression and t5gemma embedding resize propagation are different bugs, despite both involving multimodal/model wiring." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading is not the same as an unrecognized-model/config.json failure." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both mention Qwen3.5 regressions, but one is model loading and the other is save_pretrained checkpoint correctness; they are different code paths." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "A notebook syntax error and AddedToken special-argument duplication 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": 13, + "review_unit_index": 27, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42907", + "issue:43295", + "issue:43299", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43550", + "issue:43577", + "issue:43650", + "issue:43673", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44075", + "issue:44112", + "issue:44242", + "issue:44279", + "issue:44297", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44462", + "issue:44464", + "issue:44496", + "issue:44521", + "issue:44617", + "issue:44779", + "issue:44871", + "issue:44877", + "issue:44933", + "issue:44964", + "issue:44987", + "issue:45020", + "issue:45042", + "issue:45081", + "issue:45200", + "issue:45216", + "issue:45245", + "issue:45278", + "issue:45290", + "issue:45325", + "issue:45357", + "issue:45405" + ], + "soft_pairs": [ + "issue:42907|issue:43441", + "issue:44112|issue:44964", + "issue:44871|issue:45245", + "issue:43673|issue:44336", + "issue:43976|issue:44987", + "issue:44496|issue:45042", + "issue:43526|issue:43901", + "issue:43824|issue:44933", + "issue:43299|issue:45357", + "issue:43976|issue:44279", + "issue:43577|issue:45216", + "issue:44075|issue:44368", + "issue:43901|issue:44496", + "issue:44521|issue:45325", + "issue:43854|issue:44964", + "issue:44242|issue:45200", + "issue:41950|issue:45020", + "issue:44464|issue:45245", + "issue:43976|issue:45405", + "issue:44351|issue:45278", + "issue:41950|issue:43650", + "issue:43479|issue:43525", + "issue:44462|issue:45081", + "issue:44496|issue:44877", + "issue:44297|issue:44462", + "issue:44279|issue:45405", + "issue:43550|issue:44964", + "issue:43299|issue:43854", + "issue:44462|issue:44779", + "issue:43295|issue:44779", + "issue:38175|issue:44617", + "issue:39692|issue:43901", + "issue:43650|issue:45290" + ], + "prepared_review_unit_hash": "c22bd1ac2d2d8491d3e6f17a7032c39fe4cf59730998a5267be3b3975bc79dc7", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37564, + "estimated_input_tokens": 9391, + "estimated_eval_tokens": 19038 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly separate Transformers bugs and docs issues, not true duplicates. The soft-similarity pairs share broad themes like tokenizer/loading regressions or multimodal handling, but the concrete failure modes differ.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the strongest standalone report: it has a concrete repro, active discussion, inbound references, and a clearly scoped bug in multimodal chat-template masking.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Different bugs: dequantized save failure vs FlashAttention load failure for Ministral; not the same code path." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI stale-device-test failure in GraniteSpeech is unrelated to Phi-4 multimodal model loading." + }, + { + "left": "issue:44871", + "right": "issue:45245", + "accept": false, + "reason": "Gemma eos_token_id inconsistency is unrelated to the category-count RuntimeError." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Chunked-prefill cache regression and ANSI logging output are unrelated subsystems." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python version support issue is not the same as failing to load a specific model repo." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Missing model_type/unrecognized model and torchvision requirement for PIL image processors are different problems." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to stale docs about return_all_scores." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import errors, but for different symbols and different failure causes." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Qwen3VL MoE loading failure and Qwen3.5 save_pretrained key corruption are distinct regressions." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "General dependency complaint does not match the Python compatibility bug." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype propagation bug is unrelated to Qwen3.5 checkpoint save regression." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "SGD argument handling and tie_word_embeddings warning are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs mismatch for pipeline output is unrelated to model_type/config loading failure." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Assistant mask generation bug is different from Qwen2.5-VL rope index scaling." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Different model-loading failures for different checkpoints." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "MoE load-balancing loss and Gemma 4 token-type defaults are different training issues." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup bug is not the same as remote_code loading regressions." + }, + { + "left": "issue:44464", + "right": "issue:45245", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is unrelated to the categories limit error." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python support regression is unrelated to the PEFT minimum-version bump." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "HybridCache import failure is only loosely related to broader import errors; not the same concrete bug." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "No meaningful duplicate relation; ADD THE DATA is not a technical bug report." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Different config/model classes and different attributes; not the same initialization bug." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer.json precedence bug and Mistral regex patch crash are different failure modes." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer class metadata mismatch on save is different from AutoTokenizer ignoring tokenizer.json." + }, + { + "left": "issue:44496", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config loading, but one is missing model_type and the other is strict granite_speech config validation; not the same bug." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "Generic dependency issue does not match the specific PEFT version bump problem." + }, + { + "left": "issue:43550", + "right": "issue:44964", + "accept": false, + "reason": "torch.compile+SDPA failure in Bamba is unrelated to Phi-4 multimodal loading." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3VL loading regression and Qwen2_5_VL import error are different model-family issues." + }, + { + "left": "issue:44462", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer.json precedence and Deepseek tokenizer correctness are different tokenizer regressions." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Processor.tokenizer regression in custom model code is unrelated to Deepseek tokenizer output changes." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero-probabilities bug is unrelated to Sam3Video CUDA OOM." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "SigLIP2 doc-example errors and text-classification docs mismatch are different documentation issues." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "Nonsense/meta issue is unrelated to the apply_chat_template tool-call crash." + } + ] + }, + "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": 13, + "review_unit_index": 28, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:41628", + "issue:41950", + "issue:42175", + "issue:42994", + "issue:43065", + "issue:43122", + "issue:43262", + "issue:43295", + "issue:43317", + "issue:43352", + "issue:43441", + "issue:43450", + "issue:43475", + "issue:43525", + "issue:43650", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43824", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44188", + "issue:44220", + "issue:44246", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44336", + "issue:44466", + "issue:44521", + "issue:44589", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:45250", + "issue:45276", + "issue:45362", + "issue:45397" + ], + "soft_pairs": [ + "issue:44016|issue:44291", + "issue:42994|issue:43317", + "issue:43441|issue:44683", + "issue:43450|issue:44279", + "issue:44466|issue:45276", + "issue:43065|issue:44898", + "issue:43723|issue:44162", + "issue:43262|issue:44521", + "issue:44261|issue:44263", + "issue:44623|issue:45397", + "issue:43122|issue:43650", + "issue:44623|issue:44749", + "issue:44671|issue:44779", + "issue:43673|issue:43761", + "issue:43901|issue:43994", + "issue:42175|issue:43976", + "issue:44297|issue:45397", + "issue:43475|issue:44016", + "issue:43824|issue:43976", + "issue:44589|issue:45362", + "issue:43295|issue:44617", + "issue:43901|issue:44246", + "issue:43352|issue:45250", + "issue:43525|issue:43881", + "issue:43450|issue:44617", + "issue:41950|issue:44220", + "issue:41628|issue:43976", + "issue:44188|issue:44336" + ], + "prepared_review_unit_hash": "2465ce0009ef635fdfca592c26430dffae2e904669cdc51293234427b20b6522", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35692, + "estimated_input_tokens": 8923, + "estimated_eval_tokens": 18102 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a heterogeneous grab-bag of unrelated Transformers issues, with only a loose overlap around v5 regressions, processors/tokenizers, and FlashAttention. I did not find any soft pair that is clearly the same underlying bug/change.", + "confidence": 0.36, + "canonical_issue_reason": "issue:43295 is the clearest broad user-facing regression in the set, centered on processor/tokenizer behavior breaking custom multimodal code paths in v4.57.5/v5.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43295 best represents the apparent v5 API-regression theme and is more generally phrased than the model-specific or environment-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error vs init_empty_weights unexpected argument; unrelated problems." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model saving failure vs dequantized model offload loading failure; related area, different code paths." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Both mention attention backends, but different models and different failures (model support check vs compiled flex_attention on newer torch)." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video batched-shape bug vs dependency issue; not the same bug." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Serialization of tied lm_head weights vs resize_token_embeddings not updating embeddings; different behavior." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs Perceiver non-default resolution failure; different models and code paths." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer loading regression vs ESM2 model breakage; no concrete overlap." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Audio chat_template sampling-rate default vs multimodal assistant_masks all zero; both touch chat templates but are different bugs." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "MLA q_a_layernorm precision/config issue vs torch.split return values in GlmMoeDsaIndexer; unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing files on processor.save_pretrained vs gemma-4 zero3 from_pretrained; not the same failure." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenization change regression vs unrelated generic 'ADD THE DATA' issue." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Processor save_pretrained/files bug vs data filtering slowdown after upgrade; different symptoms." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "CamemBERT masked LM prediction regression vs Deepseek tokenizer regression; distinct models and bugs." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Generation cache missing in v5 chunked_prefill vs CLIPVisionModel hidden_states regression; different subsystems." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores vs SigLIP2 model/pipeline results issue; unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43976", + "accept": false, + "reason": "TensorFlow extra-install packaging issue vs Python version compatibility issue; different environment problems." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch vs gemma-4 zero3 loading problem; not the same bug." + }, + { + "left": "issue:43475", + "right": "issue:44016", + "accept": false, + "reason": "Sam3Video encoder attribute error vs notebook syntax error; unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Missing model import vs Python version support; not the same issue." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Missing Float8 storage object vs Qwen3.5 chat crash; different code paths." + }, + { + "left": "issue:43295", + "right": "issue:44617", + "accept": false, + "reason": "Processor/tokenizer regression vs Sam3Video CUDA OOM; unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Pipeline docs mismatch vs slow import; no concrete overlap." + }, + { + "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 the same bug." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Llama4Config missing pad_token_id vs glm-4v-9b loading failure; distinct models and failure modes." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Incorrect batched video processor shape vs CUDA OOM in Sam3Video; not a duplicate." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification pipeline using image processors vs audio fbank extraction issue; different components." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "AutoImageProcessor import error vs Python 3.9/3.10 compatibility problem; unrelated." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "torch.compile attention-kernel divergence vs ANSI codes in loading_report; 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": 13, + "review_unit_index": 29, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:36246", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:42886", + "issue:43065", + "issue:43066", + "issue:43232", + "issue:43257", + "issue:43299", + "issue:43408", + "issue:43441", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43673", + "issue:43901", + "issue:43994", + "issue:44162", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44373", + "issue:44462", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45276", + "issue:45292", + "issue:45356", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45459" + ], + "soft_pairs": [ + "issue:44295|issue:45397", + "issue:42491|issue:43299", + "issue:44246|issue:44496", + "issue:44336|issue:44373", + "issue:44462|issue:45356", + "issue:43526|issue:45003", + "issue:43994|issue:45276", + "issue:43531|issue:45362", + "issue:36246|issue:42757", + "issue:36246|issue:44351", + "issue:43673|issue:44561", + "issue:44336|issue:44485", + "issue:36246|issue:43596", + "issue:44242|issue:44857", + "issue:44162|issue:45200", + "issue:44246|issue:44871", + "issue:44779|issue:45292", + "issue:44987|issue:45459", + "issue:44295|issue:44749", + "issue:43441|issue:43540", + "issue:44877|issue:45375", + "issue:41950|issue:43596", + "issue:43066|issue:44779", + "issue:43901|issue:45003", + "issue:42886|issue:45229", + "issue:44995|issue:45200", + "issue:43257|issue:45137", + "issue:43065|issue:43408", + "issue:43232|issue:44336", + "issue:44496|issue:45003" + ], + "prepared_review_unit_hash": "8a1f91b82b8f7b7ea956c1d3a52474175c9003765ddd7282846f20c49e645938", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36467, + "estimated_input_tokens": 9117, + "estimated_eval_tokens": 18490 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: many items are version/regression or model-loading reports, but the soft pairs do not look like true duplicates. I treated the cluster as having no strong duplicate hub and chose the most generic import-regression issue as the best loose anchor.", + "confidence": 0.67, + "canonical_issue_reason": "issue:36246 is the broadest and most generic import/export regression in the set, so it is the closest loose anchor for the cluster; however, there is no strong evidence that the items are true duplicates of it.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:36246 is the best representative only in a weak sense: it matches the common theme of broken imports/public API exports better than the more model-specific reports, but the cluster is not a coherent duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Different failures: position_ids buffer access vs Gemma-4 ZeRO3 from_pretrained loading." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both involve Qwen3 MoE loading regressions, but they target different model variants and failure modes." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Unrelated: slow import vs unrecognized model/config loading failure." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI escape output bug and a wrong docstring are unrelated." + }, + { + "left": "issue:44462", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer problems: repository tokenizer selection vs Kimi codec/regression handling." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to unsafe sys.modules access." + }, + { + "left": "issue:43994", + "right": "issue:45276", + "accept": false, + "reason": "Siglip2 inference corruption and resize_token_embeddings not updating embeddings are different code paths." + }, + { + "left": "issue:43531", + "right": "issue:45362", + "accept": false, + "reason": "Both mention Qwen, but one is sliding_window/MoE behavior and the other is chat crash; not the same bug." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols and unrelated modules." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "ImportError for Qwen2.5 VL image processor is not the same as missing HybridCache export." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Generation cache/chunked prefill issue is unrelated to removal of is_torch_fx_available." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "Loading report ANSI codes and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Qwen2.5 VL import error and DeepSpeed/BertModel IndexError are unrelated." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Load-balancing loss logic and LwDetrImageLoss AMP crash are different bugs." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids handling are unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Slow import and eos_token_id configuration inconsistency are unrelated." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Deepseek tokenizer regression is unrelated to resize_token_embeddings not updating output embeddings." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure and tokenizer protobuf error masking are different problems." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "Position_ids buffer bug is unrelated to the Chinese report about data filtering slowdown." + }, + { + "left": "issue:43441", + "right": "issue:43540", + "accept": false, + "reason": "FlashAttention failure for Ministral-3 and Qwen3OmniMoe video-input ValueError are unrelated." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve strict config handling, but they are different model configs and not clearly the same concrete bug." + }, + { + "left": "issue:41950", + "right": "issue:43596", + "accept": false, + "reason": "Video-classification pipeline image-processor lookup is unrelated to the ZeRO3/BertModel IndexError." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Wrong tokenizer decoder type and Deepseek tokenizer corruption are different tokenizer regressions." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mention of 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 OOM are unrelated." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "Stale indexer cache crash and mm_token_type_ids defaulting are different bugs." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MoE weight conversion and DeepSpeed ZeRO3 deque error are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and sam3_video vs sam3_tracker warning are related only by model family, not the same bug." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs handling and ANSI code rendering are unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model loading and sys.modules access 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": 13, + "review_unit_index": 30, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:42371", + "issue:42673", + "issue:43232", + "issue:43262", + "issue:43295", + "issue:43381", + "issue:43441", + "issue:43475", + "issue:43540", + "issue:43606", + "issue:43643", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43701", + "issue:43704", + "issue:43931", + "issue:44038", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44246", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44466", + "issue:44623", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:45003", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45230", + "issue:45278", + "issue:45292", + "issue:45310", + "issue:45335", + "issue:45356", + "issue:45381", + "issue:45397", + "issue:45459" + ], + "soft_pairs": [ + "issue:43262|issue:44246", + "issue:43295|issue:45292", + "issue:44060|issue:44077", + "issue:43475|issue:43540", + "issue:44466|issue:45335", + "issue:43653|issue:44162", + "issue:44368|issue:44977", + "issue:43673|issue:44734", + "issue:44933|issue:45459", + "issue:43441|issue:43606", + "issue:44869|issue:45356", + "issue:43232|issue:43673", + "issue:43931|issue:44368", + "issue:44297|issue:44623", + "issue:43673|issue:45278", + "issue:43646|issue:44162", + "issue:43381|issue:45292", + "issue:43381|issue:45335", + "issue:42673|issue:43704", + "issue:28282|issue:30990", + "issue:44361|issue:44749", + "issue:44077|issue:45003", + "issue:44749|issue:45310", + "issue:45230|issue:45397", + "issue:44038|issue:44623", + "issue:43475|issue:45381", + "issue:43475|issue:43643", + "issue:43701|issue:44749", + "issue:45081|issue:45103", + "issue:42371|issue:45092" + ], + "prepared_review_unit_hash": "6c5c97538c27fd62b4a323119318d6ed72662deb6204dfaacf3199a443abe445", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36151, + "estimated_input_tokens": 9038, + "estimated_eval_tokens": 18332 + }, + "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-era regressions across tokenizers, generation, multimodal inputs, and model-loading paths. Only one pair is a clear duplicate; the rest are related at a broad theme level but not the same underlying bug.", + "confidence": 0.88, + "canonical_issue_reason": "issue:43646 is the broadest representative of the cluster\u2019s main theme: general Transformers v5 breakage around model initialization and compatibility, while most other items are narrower, model-specific regressions.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best single issue to anchor this cluster because it is a generic upgrade-breakage report and captures the overarching v5 regression theme better than the more niche model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Different failures: audio processor chat-template sample-rate handling vs slow import performance." + }, + { + "left": "issue:43295", + "right": "issue:45292", + "accept": false, + "reason": "Different code paths: processor/tokenizer image handling regression vs token-embedding resize not propagating to output embeddings." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Both mention config/model semantics, but one is a tied-weights warning bug and the other is a post_init allowance issue for a different model class." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Different multimodal bugs: missing vision encoder attribute vs video-input validation error in another model." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both involve embeddings/tied weights, but one is serialization-dependent and the other is resize_token_embeddings not updating decoder embeddings." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Different tokenizer/model failures: BigBird tokenizer special-token handling vs ESM2 being broadly broken." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "A warning about tie_word_embeddings is unrelated to Qwen3.5 flash-attention generation breakage." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Both are generation/cache-related, but the concrete bugs differ: missing GenerationMixin cache vs wrong tensor indexing in serve continuation." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Different import/tokenizer issues: missing image_utils import vs protobuf decode error masking real tokenizer exceptions." + }, + { + "left": "issue:43441", + "right": "issue:43606", + "accept": false, + "reason": "Different model-specific regressions: FlashAttention failure for Ministral vs CPU offload device mismatch for bark-small." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer/audio edge cases: Whisper timestamp decode crash vs Kimi-K2.5 codec/fix_mistral_regex regression." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both touch generation internals, but one is sync_gpus/model_kwargs handling and the other is chunked_prefill cache availability." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Weight-shape mismatch on a specific VL model is not the same bug as a tied-weights warning in a Qwen3.5 LoRA workflow." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Both are save_pretrained-related, but one is tokenizer_config metadata mismatch while the other is processor file omissions." + }, + { + "left": "issue:43673", + "right": "issue:45278", + "accept": false, + "reason": "A generation cache regression is not the same as broad import errors after upgrading Transformers." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Both are broad breakages, but they affect different areas: custom model initialization vs an ESM2-specific regression." + }, + { + "left": "issue:43381", + "right": "issue:45292", + "accept": false, + "reason": "Gradient-checkpointing eval-mode behavior is unrelated to token embedding resizing." + }, + { + "left": "issue:43381", + "right": "issue:45335", + "accept": false, + "reason": "These are separate bugs: eval-mode gradient checkpointing vs resize_token_embeddings not updating decoder embeddings." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Same model, same symptom, same title: Qwen3ForCausalLM leaking VRAM across multiple dataloader threads." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "ImportError about missing PyTorch is unrelated to a Sentence Transformers loading hang." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "Different issues: a tokenizer AttributeError on tasks vs a general slowdown after upgrading Transformers." + }, + { + "left": "issue:44077", + "right": "issue:45003", + "accept": false, + "reason": "Optional post_init policy for patchtsmixer is unrelated to unsafe sys.modules access in modeling_utils." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "General preprocessing slowdown is not the same underlying bug as a Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "The first is a vague, underspecified report; the second is a specific gemma-4 zero3 from_pretrained failure." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "A Qwen3-VL-Moe transformers-5 compatibility bug is unrelated to missing files on processor save_pretrained." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Both are vision/video-related, but they target different models and different failure modes." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "A missing vision-encoder output attribute is not the same bug as trust_remote_code dropping fields from AutoConfig." + }, + { + "left": "issue:43701", + "right": "issue:44749", + "accept": false, + "reason": "Checkpoint resume key mismatch is unrelated to slow filtering after upgrade." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Both are AttributeErrors, but they arise in unrelated subsystems: tokenizer regex patching vs auto-docstring processing." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 settings guidance is unrelated to remote-code checkpoint incompatibility with v5 meta initialization." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet: the items are mostly separate Transformers v5-era regressions, and the only clearly duplicate pair marked true is the Qwen3ForCausalLM VRAM leak issues (42673/43704). The false soft-edge calls are conservative and generally distinguish different subsystems or failure modes without overclaiming." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 31, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:30990", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43475", + "issue:43479", + "issue:43525", + "issue:43673", + "issue:43784", + "issue:43824", + "issue:43873", + "issue:43976", + "issue:44038", + "issue:44060", + "issue:44079", + "issue:44164", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44373", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44734", + "issue:44792", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45356", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45478" + ], + "soft_pairs": [ + "issue:45375|issue:45478", + "issue:41628|issue:44933", + "issue:42994|issue:43525", + "issue:45310|issue:45375", + "issue:43475|issue:44661", + "issue:42222|issue:45200", + "issue:43873|issue:44945", + "issue:42831|issue:44222", + "issue:45362|issue:45375", + "issue:45310|issue:45397", + "issue:43232|issue:44188", + "issue:41628|issue:44351", + "issue:44222|issue:45310", + "issue:42994|issue:44164", + "issue:43232|issue:44792", + "issue:44038|issue:45310", + "issue:30990|issue:35141", + "issue:36010|issue:41628", + "issue:43377|issue:44242", + "issue:43479|issue:44079", + "issue:43673|issue:44188", + "issue:43479|issue:44869", + "issue:42898|issue:44568", + "issue:44964|issue:45137", + "issue:42175|issue:44933", + "issue:43976|issue:44933", + "issue:43784|issue:43824", + "issue:43278|issue:45137", + "issue:44623|issue:45310", + "issue:44734|issue:45103", + "issue:44188|issue:44373", + "issue:44060|issue:45125", + "issue:42898|issue:45356" + ], + "prepared_review_unit_hash": "734be342eceb723fb4502d3f31153d55c4c3cdcd6411d83841c8fa746a652cad", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37261, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are broadly heterogeneous; the high similarity scores mostly reflect shared library/model vocabulary rather than the same underlying defect. I would reject all soft-edge duplicate links.", + "confidence": 0.94, + "canonical_issue_reason": "45310 is the best single issue anchor: it is the earliest and most discussed report in the repeated Qwen3.5 MoE `from_pretrained` failure thread, and later 45478 is essentially the same title.", + "canonical_pr_reason": null, + "best_issue_reason": "Still only a partial representative, because the surrounding items span unrelated import, tokenizer, config, quantization, and generation bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same model family, but different failure mode: missing `deepstack_visual_indexes` vs a generic `from_pretrained` crash." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import problems, but they target different symbols/modules (`AutoImageProcessor` vs `image_utils`) and likely different code paths." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Unrelated bugs: quantized model saving failure vs missing `pad_token_id` on `Llama4Config`." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Both involve Qwen3.5 MoE, but one is a `from_pretrained` crash and the other is a config-field omission under `@strict`." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Different subsystems and symptoms: SAM3 vision encoder attribute error vs tokenizer-mapping/model-registration failure." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Different models and bugs: broken VitPose models vs Gemma 4 text-only fine-tuning token type defaults." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Different concrete problems: quantization/offloading behavior vs incorrect outputs under pipeline parallelism." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Both mention FP8, but one is an accuracy regression while the other is a save/load issue for MoE models." + }, + { + "left": "issue:45362", + "right": "issue:45375", + "accept": false, + "reason": "Different Qwen issues: chat crash for Qwen3.5-35B vs missing `deepstack_visual_indexes` in a config." + }, + { + "left": "issue:45310", + "right": "issue:45397", + "accept": false, + "reason": "Different model families and paths: Qwen3.5 MoE `from_pretrained` vs Gemma-4 Zero3 loading." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation kwargs cache bug vs attention-kernel divergence under `torch.compile`; not the same code-path failure." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they are for different missing exports (`AutoImageProcessor` vs `HybridCache`)." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Related model family, but one is FP8 save/load behavior and the other is a `from_pretrained` initialization error." + }, + { + "left": "issue:42994", + "right": "issue:44164", + "accept": false, + "reason": "Both involve serialization, but `quantized model saving failed` and `extra_state` handling are distinct bugs." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation cache logic bug vs a failing image-generation test for Janus; different underlying defects." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Same broad Qwen/VL area, but different model variant and symptom; not the same concrete bug." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Completely different areas: Sentence Transformers loading stall vs embedding resize/post-init reinitialization." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are namespace import regressions, but they concern different exported names and unrelated fixes." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "MIMI padding-mask inconsistency vs MoE load-balancing loss omission; different model behavior and code paths." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Both mention `None`, but one is multimodal config initialization and the other is `ModelOutput` key assignment." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "GenerationMixin cache availability vs attention-kernel branching under `torch.compile`; not the same bug." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Different components entirely: multimodal config defaults vs Whisper word-timestamp decoding crash." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions, but one is cleanup-space behavior and the other is missing BOS/EOS insertion." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Different domains: model loading for Phi-4 multimodal vs DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Packaging/backend dependency issue vs a missing import from `image_utils`; unrelated failures." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python-version compatibility regression vs missing import from `image_utils`; different root causes." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Both are import failures under newer transformers, but they affect different packages and missing symbols." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype regression in evaluation vs DeepSpeed ZeRO3 deque error; no shared code path." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Processor save-pretrained file omission vs Qwen3.5 MoE load failure; save path and model family differ." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Server KV-cache continuation crash vs auto-docstring annotation parsing crash; unrelated code paths." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Runtime attention-kernel divergence vs a docstring issue for `position_ids`; not the same defect." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Different model internals: incorrect tied-weights warning vs missing `_tp_plan` for tensor parallelism." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer-related regressions, but they describe different symptoms and different models/releases." + } + ] + }, + "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": 13, + "review_unit_index": 32, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:38175", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42898", + "issue:42994", + "issue:43295", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43824", + "issue:43874", + "issue:44077", + "issue:44206", + "issue:44222", + "issue:44242", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44448", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44568", + "issue:44623", + "issue:44779", + "issue:44871", + "issue:44913", + "issue:44977", + "issue:44991", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45276", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45459" + ], + "soft_pairs": [ + "issue:43723|issue:44568", + "issue:42898|issue:44779", + "issue:45137|issue:45276", + "issue:43874|issue:45092", + "issue:44077|issue:44242", + "issue:42898|issue:44448", + "issue:41628|issue:45459", + "issue:44222|issue:44297", + "issue:44442|issue:45459", + "issue:42898|issue:43295", + "issue:43479|issue:43644", + "issue:44222|issue:44623", + "issue:44206|issue:45103", + "issue:42831|issue:44623", + "issue:22355|issue:28282", + "issue:41628|issue:42757", + "issue:44297|issue:45310", + "issue:44483|issue:45406", + "issue:44222|issue:44484", + "issue:44263|issue:44360", + "issue:43723|issue:44977", + "issue:44263|issue:45092", + "issue:44514|issue:45103", + "issue:43479|issue:44913", + "issue:44295|issue:44623", + "issue:43723|issue:44871", + "issue:44261|issue:45092", + "issue:43723|issue:44991", + "issue:30990|issue:38175", + "issue:44373|issue:44485", + "issue:43723|issue:44442", + "issue:45092|issue:45357", + "issue:42886|issue:42994", + "issue:41628|issue:43824", + "issue:42831|issue:45310" + ], + "prepared_review_unit_hash": "01eb065c064023df022a1b2aa9c1a51620fc9ea362440a9a1c4f385826476729", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37412, + "estimated_input_tokens": 9353, + "estimated_eval_tokens": 18962 + }, + "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 regression reports, especially around tokenizer/processor loading and save/load behavior, plus several unrelated model-specific bugs. There are no PRs, and none of the soft pairs look like true duplicates of the same concrete fix.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43723 is the clearest umbrella report for the cluster\u2019s tokenizer-loading regressions in v5. It is broad enough to represent the shared load-path theme while still being a concrete user-facing failure.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43723 is the best representative issue because it targets the core AutoTokenizer.from_pretrained regression and overlaps conceptually with several nearby tokenizer-related reports without being tied to a single model family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but one is loading failure and the other is BOS/EOS handling; different code paths and symptoms." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "One is about clean_up_tokenization_spaces behavior, the other about Deepseek tokenizer outputs; same broad area, different bug." + }, + { + "left": "issue:45137", + "right": "issue:45276", + "accept": false, + "reason": "ZeRO3 deque IndexError and gemma4 resize_token_embeddings behavior are unrelated failures." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Different model families and different problems: missing image-processor method vs remote-code checkpoint/meta-init incompatibility." + }, + { + "left": "issue:44077", + "right": "issue:44242", + "accept": false, + "reason": "PatchTSMixer post_init validation and MoE load-balancing loss are distinct implementation issues." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Tokenizer cleanup behavior and Pegasus output differences are not the same concrete bug." + }, + { + "left": "issue:41628", + "right": "issue:45459", + "accept": false, + "reason": "AutoImageProcessor import failure and tokenizer protobuf error masking are separate import/error-handling issues." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "FP8 MoE save_pretrained failure is unrelated to tokenizer_class metadata mismatch on save." + }, + { + "left": "issue:44442", + "right": "issue:45459", + "accept": false, + "reason": "A specific tokenizer load failure is not the same as generic exception masking when protobuf is missing." + }, + { + "left": "issue:42898", + "right": "issue:43295", + "accept": false, + "reason": "clean_up_tokenization_spaces behavior and processor.tokenizer/image passing regression are different features." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Phi4MultimodalConfig default-init bug and junk non-persistent buffers are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "Saving FP8 MoE checkpoints and processor.save_pretrained missing files are different save-path bugs." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature extractor center-arg crash and auto-docstring annotation crash are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FineGrainedFP8 accuracy loss is not the same as processor serialization missing files." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Both are import errors, but one is a missing module path and the other is a missing PyTorch dependency; not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Different missing imports from different packages and symbols." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer save metadata mismatch and Qwen3.5 from_pretrained failure are different regressions." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat-completions request handling and Gemma4Processor _tokenizer attribute errors are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 checkpoint saving and max_shard_size defaults are not the same issue." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention DSA indexer, but the concrete operations and failures differ (torch.split vs missing ReLU)." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression and flash-attention generation bug are different code paths." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "GlmMoeDsaIndexer torch.split issue is unrelated to InternVL2 remote-code/meta-init incompatibility." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched processor chat-template crash and auto-docstring annotation crash are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Config default initialization and GPTNeoX rotary_pct reload bug are different problems." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "position_ids buffer read error and processor.save_pretrained missing files are not the same failure." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading failure and eos_token_id config mismatch are distinct." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA precision/config epsilon issue and remote-code meta-init incompatibility do not match." + }, + { + "left": "issue:43723", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer load regressions in v5, but one is a general AutoTokenizer failure and the other is a model-specific tokenizer load error; not enough evidence of one underlying bug." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence-Transformers loading hang and SigLIP2 zero probabilities are different model issues." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Docstring wording for position_ids and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "General AutoTokenizer loading regression and FastSpeech2ConformerTokenizer-specific load failure are related only at a broad level, not clearly the same bug." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Remote-code checkpoint incompatibility and incorrect visual encoder keys on save are different Qwen3.5 issues." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading and quantized model saving are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Missing AutoImageProcessor import and missing Qwen2_5_VLForConditionalGeneration import are separate symbol-resolution problems." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue and Qwen3.5 MoE from_pretrained error are unrelated 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": 13, + "review_unit_index": 33, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:29127", + "issue:30990", + "issue:33357", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43576", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:43976", + "issue:43992", + "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:45200", + "issue:45245", + "issue:45278", + "issue:45290" + ], + "soft_pairs": [ + "issue:43576|issue:43784", + "issue:42831|issue:44038", + "issue:43122|issue:44521", + "issue:42757|issue:45278", + "issue:44263|issue:44373", + "issue:42886|issue:43066", + "issue:44117|issue:44704", + "issue:30990|issue:33357", + "issue:43122|issue:44514", + "issue:44704|issue:45290", + "issue:43232|issue:45245", + "issue:42907|issue:44945", + "issue:42371|issue:44263", + "issue:43232|issue:44743", + "issue:44295|issue:44297", + "issue:43976|issue:44945", + "issue:39401|issue:44488", + "issue:42907|issue:43937", + "issue:43408|issue:43475", + "issue:44625|issue:44829", + "issue:29127|issue:30990", + "issue:41628|issue:45278", + "issue:44360|issue:44485", + "issue:43116|issue:45200", + "issue:43992|issue:44704", + "issue:39401|issue:44521", + "issue:43122|issue:44779", + "issue:44038|issue:44297", + "issue:44261|issue:44373", + "issue:42371|issue:42831", + "issue:44038|issue:44295", + "issue:36296|issue:43116", + "issue:42907|issue:43452", + "issue:44038|issue:44222", + "issue:43824|issue:44351" + ], + "prepared_review_unit_hash": "83fc9767f1046a89f06cff5b4fa719efb94b03d2bdb16051a372690ef0fa7426", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37673, + "estimated_input_tokens": 9419, + "estimated_eval_tokens": 19094 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous Transformers issues with no clear duplicate PRs; the only loose common thread is broad v5 migration/import regressions, but the soft pairs do not appear to share the same concrete bug.", + "confidence": 0.85, + "canonical_issue_reason": "Issue 45278 is the broadest and most representative report in the set, covering the general v5 upgrade/import-regression theme that overlaps with several other items.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45278 is the best umbrella representative because it captures the widest cluster theme (post-upgrade import failures) without overfitting to a single model or API surface.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Broken env command vs sentence-transformers import NameError; different code paths and symptoms." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "FineGrainedFP8 accuracy regression is not the same bug as the Qwen3-VL-Moe v5 issue." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer output differences vs multimodal assistant mask generation; unrelated failures." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "Single missing import from huggingface_hub is broader than, but not the same as, general import errors after upgrade." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "DSA indexer torch.split issue vs a docstring bug for position_ids; different underlying problems." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading failure is unrelated to wrong tokenizer decoder type in v5." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Tokenizer mapping returning None is not the same as AutoProcessor failing to pass kwargs to cached_file." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Stuck loading sentence-transformers vs MacOS bus error on CLIP; different failure modes." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "General tokenization change vs Qwen2_5_VL batched chat-template crash; not the same bug." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor cached_file kwargs bug is unrelated to assistant message tool-call handling in chat templates." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation kwarg sync bug vs category-count runtime error; no shared code path." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Dequantized model save failure vs incorrect pipeline-parallel output; different subsystems." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings guidance is unrelated to the GlmMoeDsaIndexer torch.split bug." + }, + { + "left": "issue:43232", + "right": "issue:44743", + "accept": false, + "reason": "Both are generation-related only at a high level; the concrete bugs differ." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Reading position_ids as a buffer and tokenizer_class metadata mismatch are separate issues." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version compatibility regression is not the same as pipeline parallelism output corruption." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 offset_mapping bug vs loading a specific community model; unrelated tokenizer/model issues." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Saving dequantized models differs from invalid GenerationConfig validation." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Model-type warning on SAM3 tracker instantiation is not the same as missing fpn_position_embeddings." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "num_labels propagation bug and flash_attention_3 training degeneration are unrelated." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "LayoutLMv3 error message clarity issue vs sentence-transformers loading hang; no duplicate evidence." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Specific AutoImageProcessor import error could be part of a broader trend, but this is not the same concrete issue." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA ReLU omission and GLM-5 RoPE implementation are distinct model/logic issues." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Example script multi-label output bug is unrelated to Gemma 4 mm_token_type_ids defaults." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Missing embed_tokens.weight in UMT5Encoder is not about AutoProcessor kwargs forwarding." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Wrong offset_mapping and zero assistant_masks are different tokenizer/template behaviors." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer behavior change in v5 is not the same as Deepseek incorrect results." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe bug and tokenizer save metadata mismatch are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "RMS norm epsilon precision discussion is not the same as a docstring typo for position_ids." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 API guidance and FineGrainedFP8 accuracy regression are unrelated." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Qwen3-VL-Moe bug is not the same as position_ids buffer read failure." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training bug and example-script classification output bug are different training paths." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Dequantized-model save failure is unrelated to gguf_file loading breakage." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe v5 bug is not the same as FP8 save_pretrained moe support." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Missing Qwen2_5_VLForConditionalGeneration export and missing HybridCache export are separate import errors." + } + ] + }, + "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": 13, + "review_unit_index": 34, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42757", + "issue:42907", + "issue:43064", + "issue:43116", + "issue:43122", + "issue:43278", + "issue:43441", + "issue:43450", + "issue:43493", + "issue:43550", + "issue:43673", + "issue:43784", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43937", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44075", + "issue:44222", + "issue:44291", + "issue:44351", + "issue:44485", + "issue:44779", + "issue:44912", + "issue:44933", + "issue:44936", + "issue:44945", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45083", + "issue:45216", + "issue:45278", + "issue:45405", + "issue:45446", + "issue:45478" + ], + "soft_pairs": [ + "issue:43122|issue:44977", + "issue:43278|issue:44945", + "issue:45216|issue:45478", + "issue:42757|issue:44351", + "issue:42907|issue:44222", + "issue:42222|issue:43441", + "issue:42907|issue:44912", + "issue:42673|issue:45072", + "issue:43784|issue:45446", + "issue:43064|issue:43673", + "issue:43784|issue:44933", + "issue:43550|issue:43784", + "issue:43937|issue:44485", + "issue:38617|issue:45278", + "issue:22355|issue:29127", + "issue:43116|issue:43493", + "issue:44075|issue:44936", + "issue:42371|issue:43874", + "issue:44222|issue:45478", + "issue:43976|issue:45446", + "issue:43116|issue:43825", + "issue:44038|issue:45478", + "issue:39401|issue:44779", + "issue:43931|issue:44945", + "issue:33453|issue:39401", + "issue:45083|issue:45446", + "issue:43937|issue:44977", + "issue:43827|issue:45446", + "issue:42673|issue:43906", + "issue:44291|issue:45071", + "issue:43450|issue:43986", + "issue:45405|issue:45446" + ], + "prepared_review_unit_hash": "fd50299196e2bd67bc94c385244fa8876ba851ce836d5294a7e87f1e9600cce5", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36851, + "estimated_input_tokens": 9213, + "estimated_eval_tokens": 18682 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated Transformers issues across tokenization, model loading, generation, and environment/import regressions. None of the soft pairs look like the same concrete bug/change closely enough to merge as duplicates.", + "confidence": 0.9, + "canonical_issue_reason": "issue:45216 is the strongest representative issue here: it is a clear, version-bounded regression with a concrete API (`save_pretrained`) and a focused model family, making it the best anchor for triage if one issue must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "Same as the canonical choice: it is specific, reproducible, and clearly scoped; the other issues are either different model families, different APIs, or broader environment problems.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Both are tokenizer-related, but they concern different models and symptoms: generic version-to-version tokenization drift vs Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:43278", + "right": "issue:44945", + "accept": false, + "reason": "Different failure modes and code paths: dtype changes between train/eval vs incorrect output under pipeline parallelism." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Same model family and same version range, but different APIs and symptoms (`save_pretrained` checkpoint corruption vs `from_pretrained` load error); not the same concrete bug." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different missing symbols from different modules; they do not share a specific underlying change." + }, + { + "left": "issue:42907", + "right": "issue:44222", + "accept": false, + "reason": "Both involve model save/load behavior, but one is dequantized Ministral/Devstral saving and the other is FP8 MoE save_pretrained; different mechanisms." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Both mention model breakage, but one is vitpose imports/broken models while the other is a Ministral-3 FlashAttention failure; not the same bug." + }, + { + "left": "issue:42907", + "right": "issue:44912", + "accept": false, + "reason": "Different quantization-related issues affecting different models and failure points; no clear shared code-path bug." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM multi-thread use is unrelated to dtype mismatch warnings in inference for different architectures." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Both are import/version problems, but they concern different symbols and different dependency checks; too broad to be the same bug." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Trainer optimizer-state corruption under FSDP2/PEFT is unrelated to missing generation cache in v5 chunked prefill." + }, + { + "left": "issue:43784", + "right": "issue:44933", + "accept": false, + "reason": "Both mention imports, but the missing names and affected modules differ; no evidence of a single underlying removal." + }, + { + "left": "issue:43550", + "right": "issue:43784", + "accept": false, + "reason": "Torch.compile/SDPA failure for Bamba is unrelated to an import-time NameError in sentence-transformers integration." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GenerationConfig validation for GLM-5 and RoPE implementation discussion are not the same concrete defect." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Both are import errors after version changes, but they reference different missing symbols and different upgrade paths." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "One is a missing module import for `transformers.onnx`; the other is a LayoutLMv3 error message clarity issue." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Multi-label classification returning empty results is unrelated to SigLIP2 implementation mismatch." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "SGD argument handling and trainer evaluate-after-train failure are different bugs with different scopes and code paths." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 settings guidance and a missing image-patch helper are unrelated issues." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen/MoE-related, but one is FP8 save_pretrained and the other is a from_pretrained load error; not the same fix." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility for Transformers 5.1.0 is unrelated to the flex_attention PyTorch version check bug." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Multi-label classification output bug and pipeline() translation-task messaging are distinct issues." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3-VL-Moe compatibility with Transformers 5.0 is not the same as Qwen3.5 Moe from_pretrained failure in 5.4.0." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer problems, but one is offset_mapping for Qwen3 tokenizer and the other is Deepseek tokenization correctness; different model/tokenizer behavior." + }, + { + "left": "issue:43931", + "right": "issue:44945", + "accept": false, + "reason": "Model weight shape mismatch on Qwen3-VL-30B is unrelated to incorrect output under pipeline parallelism." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "A tokenizer-loading regression and Qwen3 tokenizer offset_mapping bug are not the same underlying defect." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Unexpected helper length behavior in qwen3_omni_moe is unrelated to a PyTorch version check/import gating bug." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GLM-5 generation config validation and Qwen3.5 flash-attention generation failure are different model-specific issues." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing pipeline() after removals is unrelated to an import/version check bug in flex_attention." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM multi-threading is unrelated to a reproduction of another issue." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "Unexpected `_is_hf_initialized` argument during init_empty_weights is a distinct loading bug from PretrainedConfig type-checking breakage." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Video processor batched-shape bug and video-model loading crash without torchvision are different code paths." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "A dependency version bump to unreleased PEFT is a different problem from the flex_attention import/version check 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": 13, + "review_unit_index": 35, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42617", + "issue:42673", + "issue:42994", + "issue:43012", + "issue:43066", + "issue:43097", + "issue:43122", + "issue:43408", + "issue:43421", + "issue:43441", + "issue:43452", + "issue:43577", + "issue:43582", + "issue:43673", + "issue:43742", + "issue:43874", + "issue:43931", + "issue:43937", + "issue:43986", + "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:44987", + "issue:45003", + "issue:45071", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45341", + "issue:45459", + "issue:45464", + "issue:45478" + ], + "soft_pairs": [ + "issue:44484|issue:45310", + "issue:44829|issue:45216", + "issue:39401|issue:43421", + "issue:38617|issue:41628", + "issue:44117|issue:45081", + "issue:42673|issue:43582", + "issue:42673|issue:43577", + "issue:44410|issue:45310", + "issue:43408|issue:43742", + "issue:38617|issue:44220", + "issue:43937|issue:44496", + "issue:42371|issue:44261", + "issue:42175|issue:42222", + "issue:44483|issue:45464", + "issue:42617|issue:45341", + "issue:44933|issue:45278", + "issue:44484|issue:45478", + "issue:43066|issue:43122", + "issue:43673|issue:45341", + "issue:43097|issue:44493", + "issue:42222|issue:45459", + "issue:44410|issue:45478", + "issue:43986|issue:44484", + "issue:43441|issue:44829", + "issue:43874|issue:44261", + "issue:43012|issue:43408", + "issue:42222|issue:42994", + "issue:44263|issue:44485", + "issue:41628|issue:45071", + "issue:45003|issue:45341", + "issue:43097|issue:43452", + "issue:43986|issue:45341", + "issue:44117|issue:44987", + "issue:43931|issue:44410" + ], + "prepared_review_unit_hash": "06eeae27479a57baa601cb2f68554d46003037d71a6d4a4eca4edc7ac1bb048c", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37598, + "estimated_input_tokens": 9400, + "estimated_eval_tokens": 19056 + }, + "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 regressions and API/import/tokenizer bugs, not a set of true duplicates. The strongest common thread is broad import/API breakage around the v5 transition, but the individual reports target different code paths and symptoms.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 45278 is the best umbrella representative: it is broad, explicitly about multiple import errors after upgrading to 5.5.0, and matches the cluster\u2019s general v5 API-breakage theme better than the narrower model-specific reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45278 is the most suitable global representative because it is the broadest, most general regression report in the set and can stand in for the cluster\u2019s common import/API compatibility problem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5/v5.x regressions, but one is about `max_shard_size` behavior and the other is a `from_pretrained` model-loading error; different failure modes." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Both involve training/checkpoint behavior on v5, but one is flash-attention-induced degenerate training and the other is incorrect `save_pretrained` output for Qwen3.5; not the same bug." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Both are tokenizer-related, but one is a wrong `offset_mapping` bug and the other is runtime post-processor updates when special tokens change; different code paths." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different symbols (`layer_type_validation` vs `AutoImageProcessor`) and likely separate broken exports." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Both affect tokenizer loading, but one is a mapping-name/`from_pretrained` assumption and the other is a Mistral regex patch crash on a specific tokenizer object; not the same issue." + }, + { + "left": "issue:42673", + "right": "issue:43582", + "accept": false, + "reason": "One is a VRAM leak in multi-threaded dataloaders, the other is a TypeError in Apple Silicon warmup; unrelated runtime problems." + }, + { + "left": "issue:42673", + "right": "issue:43577", + "accept": false, + "reason": "Both mention model loading/runtime, but one is a VRAM leak and the other is dtype propagation for BLIP2 components; distinct bugs." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Both involve Qwen3.5/Qwen3-next style model loading, but one is missing projections in a layer and the other is a `from_pretrained` MoE loading error; not the same fix." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Both are model-loading errors, but one is a sam3_video/sam3_tracker type mismatch warning and the other is a MobileLLM key error; different causes." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "Both touch low-level preprocessing/import internals, but one is an import failure and the other is an fbank feature extraction issue; not duplicate." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "Both are model/config loading errors, but one is invalid GenerationConfig for GLM-5 and the other is an unrecognized model/config.json issue for Olmo-Hybrid; unrelated." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "Both mention TF32/precision, but one is about new API settings for TF32 behavior and the other is missing `rms_norm_eps` in MLA q_a_layernorm; different problems." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "One is about TensorFlow not being installed with a torch extra, the other is broken VitPose models; no shared underlying bug." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both mention chat/completions API behavior, but one is a v5.3 request acceptance issue and the other is streaming inference failure on Qwen3.5-0.8B; different endpoints/symptoms." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "One cannot run `3d_parallel.py`, the other is a testing_utils bug; no shared code-path." + }, + { + "left": "issue:44933", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related, but 44933 is a missing image_utils export while 45278 is a broad upgrade-related import-failure report; not the same concrete bug." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "Both concern Qwen3.5/v5.4 regressions, but one is about shard-size defaults and the other is a MoE `from_pretrained` error; separate issues." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both are tokenizer behavior regressions across v5, but one is decoder type selection and the other is changed tokenization output; related theme, not same bug." + }, + { + "left": "issue:43673", + "right": "issue:45341", + "accept": false, + "reason": "One is a GenerationMixin cache regression in chunked prefill, the other is a testing utility bug; unrelated." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Both mention v5 regressions and position-related behavior, but one is a removed config option and the other is unexpected position-id keys; not the same concrete change." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "One is broken VitPose models, the other is tokenizer error masking when protobuf is missing; different subsystems and fixes." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Both are Qwen3.5/Qwen3-next loading regressions, but one is missing layer projections and the other is a Qwen3.5 MoE `from_pretrained` failure; separate bugs." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "One is a missing torchvision dependency causing a confusing AutoProcessor crash, the other is a checkpoint shard-size question; unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "One is FlashAttention failure for Ministral-3, the other is degenerate training with flash_attention_3 in sequence classification; similar buzzwords but different concrete code paths." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "One is a missing method on GLM46VImageProcessorFast, the other is an MLA layernorm epsilon precision issue; distinct model bugs." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "One is a PyTorch warning when compiling bf16 models, the other is a sam3_video/sam3_tracker type warning; unrelated warnings." + }, + { + "left": "issue:42222", + "right": "issue:42994", + "accept": false, + "reason": "One is broken VitPose models, the other is quantized model saving failure; different functionality." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "One is about `torch.split()` return values in a specific indexer, the other is GLM-5 RoPE implementation; not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "Both are API/import compatibility issues in v5, but one is a missing `AutoImageProcessor` import and the other is `PreTrainedConfig` type checking; distinct symptoms and fixes." + }, + { + "left": "issue:45003", + "right": "issue:45341", + "accept": false, + "reason": "One is unsafe `sys.modules[]` access in modeling_utils, the other is a small testing_utils bug; no shared underlying problem." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "One is a removed config attribute warning, the other is a gguf_file path causing `from_pretrained` failures for tokenizer/model loading; separate regressions." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "One is a video-model crash without torchvision, the other is a testing_utils issue; unrelated." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Both involve tokenizer/model loading assumptions, but 44117 is a generic mapping-name None case while 44987 is a specific failure on `physical-intelligence/fast`; not clearly the same bug." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Both are Qwen-related model-loading issues, but one is weight-shape mismatch in Qwen3-VL and the other is missing projections in qwen3next; different model families and 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": 13, + "review_unit_index": 36, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:38617", + "issue:42757", + "issue:42886", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43335", + "issue:43352", + "issue:43381", + "issue:43408", + "issue:43502", + "issue:43531", + "issue:43550", + "issue:43582", + "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:44464", + "issue:44484", + "issue:44485", + "issue:44655", + "issue:44704", + "issue:44829", + "issue:45071", + "issue:45103", + "issue:45245", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45375" + ], + "soft_pairs": [ + "issue:43335|issue:45071", + "issue:43408|issue:44368", + "issue:43931|issue:44038", + "issue:43986|issue:45372", + "issue:44829|issue:45245", + "issue:43874|issue:44263", + "issue:43976|issue:45071", + "issue:44464|issue:45071", + "issue:43531|issue:45341", + "issue:43064|issue:44315", + "issue:38617|issue:42757", + "issue:44261|issue:44485", + "issue:44410|issue:45375", + "issue:44704|issue:45103", + "issue:43502|issue:43992", + "issue:44062|issue:44117", + "issue:43986|issue:44117", + "issue:38617|issue:44351", + "issue:43582|issue:45341", + "issue:44038|issue:44410", + "issue:43097|issue:43873", + "issue:43992|issue:44484", + "issue:43986|issue:45290", + "issue:43066|issue:43906", + "issue:38617|issue:43097", + "issue:43825|issue:44655", + "issue:43352|issue:44380", + "issue:43097|issue:43901", + "issue:43012|issue:43550", + "issue:43012|issue:44368", + "issue:42886|issue:43381", + "issue:43208|issue:43550" + ], + "prepared_review_unit_hash": "9a17454e8a2c2bad6455a46dc029d4ea5cb936f9750927ebc7f473caa016505c", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37264, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly unrelated Transformers regressions and API breakages rather than duplicates. I reject every soft edge because the paired issues affect different symbols, code paths, models, or failure modes. The best representative issue is 43873 because it is the broadest, most active runtime bug report in the set.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43873 is the broadest and most actively discussed bug report here, with multiple inbound refs and a clear runtime failure, so it is the best representative issue for the set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 has the strongest combination of scope, activity, and actionable bug detail; it is more representative than the narrow import/config regressions elsewhere in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "Different bugs: one is SwitchTransformers sparse-layer construction, the other is PretrainedConfig type-checking in v5.4.0." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Both mention warnings, but they concern unrelated model/config mismatches in different models and code paths." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Separate failures: Qwen3-VL-30B-A3B-Instruct weight-shape mismatch vs a Qwen3-VL-Moe issue; not the same concrete bug." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Both are processor-loading crashes, but one is about missing torchvision for video models and the other is a mistral_common import error for Gemma 4." + }, + { + "left": "issue:44829", + "right": "issue:45245", + "accept": false, + "reason": "Unrelated problems: flash_attention_3 training degeneration vs category-count overflow at 2^24." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Different components and symptoms: a missing image-processor method vs a torch.split return-value issue in GlmMoeDsaIndexer." + }, + { + "left": "issue:43976", + "right": "issue:45071", + "accept": false, + "reason": "These are different compatibility regressions: Python version support vs type-checking breakage in PretrainedConfig." + }, + { + "left": "issue:44464", + "right": "issue:45071", + "accept": false, + "reason": "Chunked generation with compiled forward is unrelated to PretrainedConfig type checking." + }, + { + "left": "issue:43531", + "right": "issue:45341", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to a testing_utils bug." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "Different training issues: FSDP2/PEFT optimizer-state corruption vs Liger Kernel not being applied with model_init." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different missing names from different modules and likely different root causes." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Different model bugs: missing rms_norm_eps precision issue vs GLM-5 RoPE implementation discussion." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "One is missing attention projections in qwen3next; the other is a missing config field in Qwen3_5MoeVisionConfig." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Both involve kwargs processing, but one is AutoProcessor forwarding args to cached_file and the other is an auto_docstring annotation crash." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Different loading problems: unwanted API requests despite local_files_only vs missing embed_tokens.weight in UMT5Encoder.from_pretrained." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "Tokenizers.AddedToken keyword duplication is unrelated to TOKENIZER_MAPPING_NAMES returning None." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Processor loading without torchvision is a different failure mode from tokenizer mapping assumptions in from_pretrained." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Both are import-name failures, but they concern different symbols (layer_type_validation vs HybridCache) and different release breaks." + }, + { + "left": "issue:43582", + "right": "issue:45341", + "accept": false, + "reason": "Apple Silicon caching_allocator_warmup TypeError is unrelated to the testing_utils bug." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Different Qwen-family issues: Qwen3-VL-Moe regression vs missing projections in qwen3next." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "tie_embeddings removal is a config/API change, while offloading with quantization is a runtime memory-management bug." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing embed_tokens.weight on load is unrelated to save_pretrained shard-size defaults." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "Video-model processor dependency crash and chat-template tool-call crash are separate code paths." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "The isolated reproduction is too vague to treat as the same concrete tokenizer-decoder bug as 43066." + }, + { + "left": "issue:38617", + "right": "issue:43097", + "accept": false, + "reason": "ImportError for layer_type_validation is unrelated to the tie_embeddings_and_encoder_decoder removal." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline translation-task messaging is unrelated to save_pretrained pipeline serialization." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Nemotron Flash Attention 2.0 support and GPT2 attention scaling under SDPA/FlashAttention are different backend/model issues." + }, + { + "left": "issue:43097", + "right": "issue:43901", + "accept": false, + "reason": "tie_embeddings removal and TextClassificationPipeline return_all_scores docs mismatch are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "A bfloat16 precision warning and a Bamba SDPA compile failure are different problems." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "The bfloat16 PyTorch warning is not the same as the tie_word_embeddings warning in Qwen3.5 LoRA fine-tuning." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading failure and eval-mode gradient checkpointing are unrelated." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training blockers and Bamba compile/SDPA failure are distinct model-specific bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 37, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42757", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43502", + "issue:43525", + "issue:43526", + "issue:43582", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43867", + "issue:43901", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44077", + "issue:44117", + "issue:44188", + "issue:44220", + "issue:44230", + "issue:44263", + "issue:44380", + "issue:44483", + "issue:44485", + "issue:44492", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:44792", + "issue:44938", + "issue:45216", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45440", + "issue:45479" + ], + "soft_pairs": [ + "issue:43937|issue:44792", + "issue:42907|issue:44655", + "issue:44380|issue:45479", + "issue:43525|issue:44117", + "issue:43352|issue:43976", + "issue:43064|issue:44380", + "issue:43208|issue:43526", + "issue:44483|issue:44514", + "issue:43618|issue:44380", + "issue:36683|issue:43582", + "issue:43618|issue:43761", + "issue:43012|issue:44683", + "issue:44483|issue:45290", + "issue:42757|issue:43824", + "issue:38617|issue:43502", + "issue:44038|issue:44230", + "issue:44483|issue:45381", + "issue:43299|issue:43867", + "issue:43901|issue:44655", + "issue:42994|issue:44655", + "issue:43756|issue:44485", + "issue:36683|issue:43475", + "issue:43867|issue:45216", + "issue:44220|issue:44655", + "issue:43352|issue:43937", + "issue:43066|issue:45381", + "issue:44077|issue:44380", + "issue:36683|issue:44077", + "issue:43064|issue:44492", + "issue:44263|issue:45440", + "issue:43976|issue:44938", + "issue:36683|issue:43525", + "issue:36010|issue:42757", + "issue:44188|issue:44380", + "issue:43618|issue:45216", + "issue:43992|issue:45310" + ], + "prepared_review_unit_hash": "d8c2867f22a20e8c80395750bc424a5d596692ed2152280b33e70769cb5b484c", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38119, + "estimated_input_tokens": 9530, + "estimated_eval_tokens": 19316 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of distinct Transformers regressions: import errors, save/load problems, model-specific forward bugs, and a few docs/API mismatches. The soft pairs share superficial wording only; none look like the same underlying bug/change.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical issue: the items span unrelated subsystems and failure modes, so there is no single bug that safely subsumes the rest.", + "canonical_pr_reason": null, + "best_issue_reason": "No strong global best issue; 44188 is the most active open bug, but it is still a narrow torch.compile attention-kernel regression rather than a representative umbrella issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43937", + "right": "issue:44792", + "accept": false, + "reason": "Different defects: GLM-5 GenerationConfig validation vs a Janus image-generation test failure." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Different save paths: dequantized model saving vs Pipeline.save_pretrained serialization." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Unrelated: GPT2 attention scaling/SDPA backend bug vs zero-loss classification bug across models." + }, + { + "left": "issue:43525", + "right": "issue:44117", + "accept": false, + "reason": "Different code paths: missing config attribute in Llama4 vs tokenizer mapping returning None." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Different class of issue: FlashAttention support for Nemotron vs Python-version compatibility for Transformers." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Different bugs: FSDP2/PEFT optimizer-state mismatch vs GPT2 attention scaling under SDPA/FlashAttention." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "Unrelated model bugs: xLSTM training failures vs BEiT image processor label reduction behavior." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Different layers: chat/completions API rejection vs Qwen2.5-VL chat-template crash on batched input." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "Different model/output regression vs GPT2 attention scaling bug." + }, + { + "left": "issue:36683", + "right": "issue:43582", + "accept": false, + "reason": "Unrelated: Gemma3 config attribute missing vs Apple Silicon caching allocator TypeError." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Same model family but different output fields and symptoms: missing attentions vs missing hidden_states." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "Different compile-related issues: bf16 warning noise vs flex_attention failing on torch>=2.9." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Different failures: API request validation vs assistant tool-call chat-template crash." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different symbols and packages; not the same missing-export bug." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Different regressions: missing configuration_utils import vs unwanted network calls despite local_files_only=True." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Different intent: Qwen3-VL-MoE inference bug vs fp8 support request for qwen3-vl/qwen3.5 moes." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "Unrelated: chat/completions API rejection vs Qwen2.5-VL video vision_position_ids bug." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Different loading failures: Qwen3VL regression vs sorted-state_dict load error." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mismatch vs serialization bug; return_all_scores documentation is unrelated to Pipeline.save_pretrained." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Different save failures: quantized model checkpointing vs pipeline serialization." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Different models and issues: Smollm3 RoPE-layer mismatch vs GLM-5 RoPE implementation discussion." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Unrelated model-specific attribute bugs: Gemma3Config vocab_size vs Sam3VisionEncoderOutput fpn_position_embeddings." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Different directions of state-dict issues: load failure with sorted keys vs incorrect saved checkpoint contents." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Unrelated audio feature extraction bug vs pipeline serialization bug." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Different surfaces: FlashAttention unsupported warning vs invalid GenerationConfig error." + }, + { + "left": "issue:43066", + "right": "issue:45381", + "accept": false, + "reason": "Different tokenizer/decoder bug vs Qwen2.5-VL video positional-id bug." + }, + { + "left": "issue:44077", + "right": "issue:44380", + "accept": false, + "reason": "Unrelated: patchtsmixer post_init validation vs GPT2 attention scaling backend bug." + }, + { + "left": "issue:36683", + "right": "issue:44077", + "accept": false, + "reason": "Different problems entirely: Gemma3 config attribute missing vs patchtsmixer post_init policy." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols from different modules." + }, + { + "left": "issue:44188", + "right": "issue:44380", + "accept": false, + "reason": "Different attention bugs: torch.compile branching divergence vs GPT2 attention scaling ignored by backends." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "Different regressions: CLIP attentions missing vs Qwen3.5 checkpoint save corruption." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different from_pretrained failures on different model families and causes." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "Different model implementations and symptoms: GlmMoeDsaIndexer split behavior vs DeepSeekV3MoE divergence." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Separate compatibility issues with different Python versions and failure modes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 38, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42548", + "issue:42890", + "issue:43010", + "issue:43064", + "issue:43065", + "issue:43232", + "issue:43352", + "issue:43502", + "issue:43575", + "issue:43618", + "issue:43644", + "issue:43723", + "issue:43867", + "issue:43931", + "issue:43976", + "issue:43992", + "issue:44062", + "issue:44075", + "issue:44077", + "issue:44112", + "issue:44222", + "issue:44242", + "issue:44246", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44387", + "issue:44484", + "issue:44556", + "issue:44749", + "issue:44857", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45125", + "issue:45278", + "issue:45341", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45440", + "issue:45478" + ], + "soft_pairs": [ + "issue:36683|issue:44242", + "issue:43010|issue:45278", + "issue:36683|issue:43352", + "issue:41669|issue:44246", + "issue:43352|issue:43931", + "issue:43867|issue:45375", + "issue:36683|issue:43064", + "issue:43992|issue:45478", + "issue:44938|issue:45071", + "issue:43867|issue:45357", + "issue:43010|issue:43976", + "issue:44938|issue:45381", + "issue:44360|issue:45440", + "issue:43618|issue:44077", + "issue:43644|issue:44938", + "issue:36296|issue:43575", + "issue:43867|issue:44484", + "issue:43618|issue:44857", + "issue:42890|issue:44964", + "issue:28282|issue:33453", + "issue:42890|issue:44112", + "issue:43618|issue:44977", + "issue:43502|issue:44062", + "issue:43010|issue:44075", + "issue:42890|issue:45341", + "issue:43723|issue:44556", + "issue:44387|issue:44556", + "issue:43010|issue:43232", + "issue:44222|issue:45125", + "issue:43010|issue:43065", + "issue:42548|issue:44351", + "issue:45125|issue:45478", + "issue:44355|issue:44749", + "issue:45125|issue:45375" + ], + "prepared_review_unit_hash": "acedf5bb454355d7c7e7b2cecbdb20b3594c4b165acbcafc2eb2e708f5f60810", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37299, + "estimated_input_tokens": 9325, + "estimated_eval_tokens": 18906 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a noisy mix of Transformers v5 regression reports around importing, loading, and model-specific failures. Most soft pairs are only superficially similar; the only plausible duplicate-like pair is the Qwen3.5 MoE from_pretrained/_tp_plan reports.", + "confidence": 0.72, + "canonical_issue_reason": "issue:45278 is the broadest and most representative issue in the set for the recurring post-upgrade import/load regressions, even though it is still fairly generic.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 best matches the cluster\u2019s dominant theme and can serve as the umbrella issue, but it is not a precise root-cause ticket.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Different bugs: Gemma3Config vocab_size missing vs load balancing loss for MoE routing." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Different areas: cache/layer update no_grad behavior vs broad import failures after upgrade." + }, + { + "left": "issue:36683", + "right": "issue:43352", + "accept": false, + "reason": "Unrelated model issues: Gemma3Config attribute error vs NemotronH flash-attention support guard." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": false, + "reason": "One is import-star performance, the other is slow import behavior; related topic but not the same concrete bug." + }, + { + "left": "issue:43352", + "right": "issue:43931", + "accept": false, + "reason": "Different model loading failures with different symptoms and likely different code paths." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Both are config/loading related, but one is state_dict sort/load failure and the other is a missing config field being dropped." + }, + { + "left": "issue:36683", + "right": "issue:43064", + "accept": false, + "reason": "Different problems: config attribute error vs FSDP2/PEFT optimizer-state mismatch." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Different model families and failure modes: missing embed_tokens.weight vs Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44938", + "right": "issue:45071", + "accept": false, + "reason": "Version-related, but Python 3.14 import failure is not the same as PretrainedConfig type-checking regression." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "Both involve loading/saving regressions, but the reported broken behavior and model specifics differ." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Different issues: cache/layer update semantics vs Python/version compatibility." + }, + { + "left": "issue:44938", + "right": "issue:45381", + "accept": false, + "reason": "Different bugs: Python 3.14 load failure vs Qwen2.5-VL video position-id regression." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "Completely different topics: DSA indexer/ReLU discussion vs DeepseekV3MoE remote implementation divergence." + }, + { + "left": "issue:43618", + "right": "issue:44077", + "accept": false, + "reason": "Different subjects: CLIPOutput attentions regression vs patchtsmixer post_init API restriction." + }, + { + "left": "issue:43644", + "right": "issue:44938", + "accept": false, + "reason": "Non-persistent buffer junk in v5 is unrelated to Python 3.14 load failure." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Both mention tensor parallelism/OOM, but one is a training bug and the other is model loading OOM for Qwen2-57B." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "State_dict loading error and max_shard_size default question are not the same underlying bug." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Different model/output regression vs AMP/CUDA crash in a loss module." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "Seed-related flaky tests and a model load failure are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "Both are import/loading complaints, but AutoModel missing PyTorch and tokenizer loading regression are different failures." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Two separate test failures with different causes: missing seed setup vs stale device override." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Different Qwen/CLIP generation and flash-attention issues; no shared concrete code-path." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "Local-files-only network leakage is unrelated to AddedToken argument handling." + }, + { + "left": "issue:43010", + "right": "issue:44075", + "accept": false, + "reason": "Different functionality: cache/layer update vs optimizer SGD args not being used." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "Both are test-related, but one is seeding flakes and the other is a different testing_utils bug." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Both involve loading after v5 upgrades, but tokenizer.from_pretrained regression and checkpoint reload compatibility are different problems." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization memory growth is unrelated to checkpoint reload compatibility." + }, + { + "left": "issue:43010", + "right": "issue:43232", + "accept": false, + "reason": "Both involve generation/cached kwargs semantics, but not the same bug or code path." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained for MoE is different from missing _tp_plan for tensor parallelism." + }, + { + "left": "issue:43010", + "right": "issue:43065", + "accept": false, + "reason": "Cache update semantics and Sam3PixelDecoder dummy Conv2d are unrelated." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but PreTrainedModel missing and HybridCache missing are different export/regression problems." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": true, + "reason": "Same model family and same from_pretrained failure theme; the missing _tp_plan for tensor parallelism plausibly explains the Qwen3.5 MoE load error after 5.4.0." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file errors are unrelated to the reported slowdown after upgrading from 4.57.3 to 5.3.0." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Both are Qwen3.5 MoE-related, but one is a tensor-parallelism loading error and the other is a config field being dropped by strict parsing." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft pair, issue:45125 vs issue:45478, is reasonably supported by the titles and looks mergeable as a single Qwen3.5 MoE from_pretrained / tensor-parallelism fix. The remaining pair verdicts are appropriately cautious given the limited evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 39, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:30990", + "issue:31795", + "issue:33357", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38175", + "issue:38617", + "issue:41628", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43012", + "issue:43232", + "issue:43299", + "issue:43502", + "issue:43526", + "issue:43576", + "issue:43673", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:44075", + "issue:44222", + "issue:44230", + "issue:44261", + "issue:44273", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44373", + "issue:44485", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44871", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45230", + "issue:45468" + ], + "soft_pairs": [ + "issue:30990|issue:31795", + "issue:43502|issue:44485", + "issue:43010|issue:44368", + "issue:44075|issue:44871", + "issue:44315|issue:44360", + "issue:42890|issue:44373", + "issue:38175|issue:43502", + "issue:43299|issue:44556", + "issue:43502|issue:44961", + "issue:44355|issue:44655", + "issue:44355|issue:45071", + "issue:44222|issue:44230", + "issue:42831|issue:43874", + "issue:42890|issue:43232", + "issue:42757|issue:43576", + "issue:33453|issue:34689", + "issue:33453|issue:36296", + "issue:43827|issue:44961", + "issue:43576|issue:43824", + "issue:43576|issue:45071", + "issue:43673|issue:44492", + "issue:38617|issue:43576", + "issue:33357|issue:33453", + "issue:44961|issue:45468", + "issue:41628|issue:42548", + "issue:31795|issue:38617", + "issue:43576|issue:44351", + "issue:44908|issue:44961", + "issue:36296|issue:43901", + "issue:44485|issue:44961", + "issue:44273|issue:45003", + "issue:36296|issue:43526", + "issue:36296|issue:43012", + "issue:41628|issue:44355", + "issue:44261|issue:44360", + "issue:44623|issue:45230", + "issue:43576|issue:44556" + ], + "prepared_review_unit_hash": "c782a04196530de05974b38e2e0810a48fb1258f5428c4a8bfeb5ce66104ffc6", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38069, + "estimated_input_tokens": 9518, + "estimated_eval_tokens": 19292 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No soft-edge duplicate pairs look like the same underlying bug/change. Most share only a broad subsystem or version context. I selected the most central, broadly referenced v5-regression report as the canonical issue.", + "confidence": 0.57, + "canonical_issue_reason": "issue:43576 is the broadest and most connected report here: it targets a concrete v5 CLI regression, has inbound references, and generalizes better than the more model-specific or symptom-specific issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43576 best represents this cluster because it is a central, user-facing v5 regression with external references and broader impact than the narrowly scoped import/model issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Different problems: model loading hang vs forward-docstring confusion." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Different areas: offline/download behavior vs GLM-5 RoPE implementation." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "Cache/no_grad warning issue is unrelated to tie_word_embeddings warning." + }, + { + "left": "issue:44075", + "right": "issue:44871", + "accept": false, + "reason": "Optimizer argument handling and Gemma eos_token_id mismatch are separate bugs." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel/model_init issue is unrelated to a DSA ReLU omission." + }, + { + "left": "issue:42890", + "right": "issue:44373", + "accept": false, + "reason": "Seed-related test flakiness and a position_ids docstring bug are not the same issue." + }, + { + "left": "issue:38175", + "right": "issue:43502", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to local_files_only network requests." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both are v5 loading regressions, but they concern different models and failure modes." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "Offline-request bug and an unrelated placeholder issue have no shared concrete defect." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled-Python-file errors and pipeline save_pretrained failures are different code paths." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file execution issues are not the same as PretrainedConfig type-checking regressions." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both mention FP8/MoE, but save_pretrained support and inference support are distinct changes." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy and a missing image-patch helper are unrelated defects." + }, + { + "left": "issue:42890", + "right": "issue:43232", + "accept": false, + "reason": "Test seed flakiness is unrelated to generation kwargs after sync_gpus." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Missing huggingface_hub import and the transformers env command are different breakages." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Both are model-loading regressions, but the models, symptoms, and likely causes differ." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "MacOS bus error during loading is unrelated to tensor-parallel training." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still mentioning pipeline() is unrelated to the placeholder issue." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "Broken env CLI command and a missing Qwen2_5_VL import are different failures." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "CLI env breakage and PretrainedConfig type-checking regression are distinct issues." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked-prefill cache bug is not the same as a typo in cache strategies." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "ImportError for layer_type_validation is unrelated to the env command regression." + }, + { + "left": "issue:33357", + "right": "issue:33453", + "accept": false, + "reason": "Different models and symptoms: CLIP bus error vs tokenizer-loading regression." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "Placeholder issue 'racoon' is not comparable to Gemma-4 audio positional encoding." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "AutoImageProcessor import break and PreTrainedModel import break are separate API surface issues." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Doc confusion in model.forward and an import error in configuration_utils are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:44351", + "accept": false, + "reason": "Env command breakage and HybridCache import failure are not the same concrete bug." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling is unrelated to the placeholder issue." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor-parallel training bug and text-classification docs mismatch are unrelated." + }, + { + "left": "issue:44485", + "right": "issue:44961", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion does not match the placeholder issue." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Lazy loading problem and unsafe sys.modules access are not the same defect." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training bug is unrelated to BeitImageProcessorFast reduce_labels behavior." + }, + { + "left": "issue:36296", + "right": "issue:43012", + "accept": false, + "reason": "Training bug and a bfloat16 compile warning are distinct issues." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Importing AutoImageProcessor and errors running compiled Python files are different problems." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "LayerNorm epsilon precision discussion is unrelated to the DSA ReLU issue." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing files on processor.save_pretrained and a vague bug report are not the same issue." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Env command regression and checkpoint reload incompatibility are different failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 13, + "review_unit_index": 40, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:34689", + "issue:37428", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43502", + "issue:43519", + "issue:43576", + "issue:43606", + "issue:43673", + "issue:43704", + "issue:43723", + "issue:43827", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44246", + "issue:44261", + "issue:44263", + "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:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45310", + "issue:45341", + "issue:45468", + "issue:45478" + ], + "soft_pairs": [ + "issue:41669|issue:43673", + "issue:44393|issue:45071", + "issue:44038|issue:45125", + "issue:44556|issue:45092", + "issue:42371|issue:44492", + "issue:42890|issue:44908", + "issue:44704|issue:44908", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:44297|issue:45230", + "issue:43576|issue:44908", + "issue:43352|issue:44393", + "issue:44908|issue:45071", + "issue:43976|issue:44393", + "issue:44295|issue:45230", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:44492|issue:44945", + "issue:41669|issue:44492", + "issue:44315|issue:44829", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:31795|issue:33453", + "issue:43827|issue:44908", + "issue:41669|issue:44908", + "issue:43723|issue:44393", + "issue:44655|issue:44861", + "issue:43576|issue:44273", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:41669|issue:43704", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:44273|issue:45071", + "issue:43704|issue:44485", + "issue:44485|issue:45468", + "issue:42371|issue:43704", + "issue:43502|issue:43519", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:44261|issue:45468", + "issue:43606|issue:45468", + "issue:42890|issue:43704" + ], + "prepared_review_unit_hash": "b13dc79d6f6d4b66782171a5760bc2a9704c1163d9b26bd9e462fe7a26bf81f8", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 48, + "serialized_chars": 41486, + "estimated_input_tokens": 10372, + "estimated_eval_tokens": 21000 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: several unrelated v5 loading/compatibility regressions are mixed together, with only a couple of clear near-duplicate-looking cases elsewhere in the full set. For the listed soft edges, none are the same concrete bug/change, so they should all be rejected.", + "confidence": 0.61, + "canonical_issue_reason": "issue:45310 is the best anchor for the cluster because it is a specific, actionable regression report and has a later exact-title duplicate (issue:45478) with the same Qwen3.5 MoE from_pretrained failure.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the strongest overall issue candidate: clear title, concrete versioned regression, and direct duplicate evidence make it the most useful representative of the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Different bugs: import-star performance/regression vs missing GenerationMixin cache in chunked_prefill." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Unrelated failures: Qwen3-VL 2D bbox output issue vs PretrainedConfig type-checking regression." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Both are Qwen/MoE-related, but one is a general v5 model bug and the other is specifically missing tensor-parallel planning." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both concern loading after upgrading to v5, but the reported failure modes and affected checkpoints differ; not enough to treat as the same bug." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 behavior settings and a cache-strategy typo are unrelated." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "A flaky integration test due to missing set_seed is unrelated to scheduler kwargs being ignored." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "Different code paths: AutoProcessor kwargs forwarding vs inverse_sqrt scheduler kwargs handling." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Import-time slowness and lazy-loading malfunction are related at a high level, but not the same concrete defect." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Wrong model-type warning vs Liger Kernel not applied under model_init are different issues." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save mismatch is unrelated to an empty generic bug report." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken env command and scheduler kwarg handling are different bugs." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support for Nemotron is unrelated to Qwen3-VL bounding-box output errors." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwarg plumbing and PretrainedConfig type checking are unrelated regressions." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility issue does not match a Qwen3-VL output bug." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Position_ids buffer access error is unrelated to a generic bug report." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star cleanup/performance and HybridCache import failure are different problems." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated: model import performance vs a testing_utils bug." + }, + { + "left": "issue:44492", + "right": "issue:44945", + "accept": false, + "reason": "Cache-strategy typo and pipeline-parallelism wrong output are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Import-star performance regression is not the same as a typo in cache strategy docs/code." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel application under model_init and flash_attention_3 degenerate training are different failures." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different issues: Qwen3-VL 2D bbox output vs Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "PatchTSMixer post_init policy and tied-weights key handling are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Documentation confusion about forward args is unrelated to tokenizer loading regression." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() and inverse_sqrt scheduler kwargs are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import performance regression and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44393", + "accept": false, + "reason": "Tokenizer loading in v5 is unrelated to Qwen3-VL bounding-box output errors." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Saving Pipeline objects and _tied_weights_keys attribute errors are different code paths." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Broken env command and lazy-loading malfunction are different bugs, even if both touch v5 behavior." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "DSA indexer ReLU omission is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "A generic bug report is not evidence of the same Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading failure and scheduler kwargs omission are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star performance issue and VRAM leak across dataloader threads are unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are different bugs." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Timestamp math in Qwen3VL is unrelated to inverse_sqrt scheduler kwargs." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Forward-arg documentation confusion is unrelated to a model-loading breakage for Llama 3.2 Vision Instruct." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Documentation confusion is unrelated to the flash-support import error." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel application and remote-code checkpoint incompatibility are different bugs." + }, + { + "left": "issue:44273", + "right": "issue:45071", + "accept": false, + "reason": "Lazy loading not working and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in dataloader threads and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Different model-specific implementation issues." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 control settings and VRAM leak are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only API requests and Qwen3VL timestamp calculation are different bugs." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation issue vs model-loading regression." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Documentation issue vs import error." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel integration and meta-init checkpoint incompatibility do not share the same fix." + }, + { + "left": "issue:44273", + "right": "issue:45071", + "accept": false, + "reason": "Lazy loading regression and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak and RoPE implementation bug are unrelated." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "RoPE implementation discussion and Gemma-4 audio positional encoding are different model bugs." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 behavior control and VRAM leak 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": 13, + "review_unit_index": 41, + "review_unit_count": 41, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-15354-362", + "nodes": [ + "issue:31515", + "issue:31795", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:38617", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43525", + "issue:43572", + "issue:43618", + "issue:44230", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45290", + "issue:45310", + "issue:45341" + ], + "soft_pairs": [ + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:44998|issue:45341", + "issue:44492|issue:44998", + "issue:43618|issue:44998", + "issue:44556|issue:44998", + "issue:43525|issue:44861", + "issue:43572|issue:44861", + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:31515|issue:36296", + "issue:31515|issue:31795", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:31515|issue:36683", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "d92b333e4d5b02c0d9bda377ed052741c259dba41c2944c5b37310c9f59096ff", + "component_budget": { + "node_count": 362, + "item_count": 362, + "soft_pair_count": 1351, + "serialized_chars": 697247, + "estimated_input_tokens": 174312, + "estimated_eval_tokens": 348880 + }, + "budget": { + "node_count": 22, + "item_count": 22, + "soft_pair_count": 17, + "serialized_chars": 17368, + "estimated_input_tokens": 4342, + "estimated_eval_tokens": 8940 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Only one soft match looks like the same underlying bug: the two tokenizer-v5 issues. The other pairs are either clearly unrelated or too broadly similar to safely merge.", + "confidence": 0.87, + "canonical_issue_reason": "issue #43066 is the more concrete duplicate candidate: it names the specific tokenizer-v5 decoder-type regression, while #42913 is broader and more generic.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #43066 is the best representative issue because it states the failure mode more precisely and is easier to map to a fix.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42913", + "right": "issue:43066", + "accept": true, + "reason": "Both describe tokenizer behavior regressions after the v4\u2192v5 transition; the decoder-type mismatch is a concrete instance of the broader behavior difference." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwarg handling and an unrelated joke title are not the same bug." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "One is a tied-weights attribute error; the other is a chat-template crash with tool calls. Different code paths." + }, + { + "left": "issue:44998", + "right": "issue:45341", + "accept": false, + "reason": "No meaningful technical overlap; the second is a testing_utils bug, not related to the first." + }, + { + "left": "issue:44492", + "right": "issue:44998", + "accept": false, + "reason": "A cache-strategy typo is unrelated to the other issue." + }, + { + "left": "issue:43618", + "right": "issue:44998", + "accept": false, + "reason": "CLIP attentions assignment and the other issue are unrelated." + }, + { + "left": "issue:44556", + "right": "issue:44998", + "accept": false, + "reason": "Checkpoint reload breakage after v4\u2192v5 upgrade is unrelated to the other item." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config and tied-weight-key crashing are different bugs." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is not the same as the tied-weights list crash." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Checkpoint loading slowness and an import error for layer_type_validation are unrelated." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 Qwen inference support and processor.save_pretrained missing files are different problems." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Loading slowdown and tensor-parallel training bug do not describe the same failure." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Model loading performance and forward() documentation confusion are unrelated." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen/from_pretrained, but one is FP8 support and the other is a specific loading error; not enough evidence of the same bug." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Checkpoint loading slowness and tokenizer loading regression are different issues." + }, + { + "left": "issue:31515", + "right": "issue:36683", + "accept": false, + "reason": "From_pretrained slowness and Gemma3Config missing vocab_size are not the same code-path bug." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching audio-model support and FP8 Qwen inference support are different feature gaps." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The result is grounded in the packet and stays conservative overall. The one accepted pair (42913/43066) is plausibly the same tokenizer-v5 regression area, and the other pairs are rejected with sufficiently distinct titles/code paths." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 13, + "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-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "db6226b155e14b2b3233f284f32bcf68a2025de80bab82695b6a0ffc8e520d33", + "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 different feature efforts with no concrete code-path overlap.", + "confidence": 0.99, + "canonical_issue_reason": "No canonical issue for deduplication: the issues are about different features (Flash Attention 2 vs GGUF) and should remain separate.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 26350 is the better representative only because it is older and has more discussion, but it is not a duplicate of issue 33260.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different feature requests with different underlying implementations and targets; they do not describe the same bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 13, + "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-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": "5bb02acfc37eb3af4a2f01ba76bc40e4269cea6fc0fe075d5c480f0399f5ecba", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4453, + "estimated_input_tokens": 1114, + "estimated_eval_tokens": 2484 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4453, + "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 translation-request issues built from the same template, but they are not the same underlying request: 27088 is specifically for Turkish, while the others are generic placeholder-language issues that likely represent different translations. No soft edges should be merged.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 27088 is the only concrete, language-specific request (Turkish) and is the most informative representative; the other issues are placeholder/template variants rather than the same request.", + "canonical_pr_reason": null, + "best_issue_reason": "27088 is the best issue to keep as the representative because it has a real target language and a clear, actionable description.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Same translation-issue template, but no evidence they target the same language or same request; the concrete Turkish request should not be merged with a generic placeholder issue." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "These are not the same underlying request: one is explicitly Turkish, the other is a generic placeholder with no matching concrete language evidence." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Template similarity only; the Turkish-specific request is distinct from a generic placeholder translation issue." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "They share the same template text, but there is no concrete evidence they refer to the same language or same translation task." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Identical placeholder wording is not enough to treat them as the same issue; these could be separate language requests." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Both are generic template issues, but there is no reliable sign they are the same underlying 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": 13, + "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-36817-13", + "nodes": [ + "issue:36817", + "issue:37015", + "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:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:37015|issue:42503", + "issue:37015|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42503|issue:45027", + "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:43837|issue:45177" + ], + "prepared_review_unit_hash": "6522e94e4c0f86ca7ab8c0caadbae3255daf5da088524b2e95fc195cf8d6376d", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 25, + "serialized_chars": 16008, + "estimated_input_tokens": 4002, + "estimated_eval_tokens": 8260 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 25, + "serialized_chars": 16008, + "estimated_input_tokens": 4002, + "estimated_eval_tokens": 8260 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are all model-add requests, but they target different model families and capabilities (NeoBERT, DEIMv2, Qwen3-TTS/ASR, audio, OCR, etc.), so there is no true duplicate cluster.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "If one issue has to stand in as a representative, 37015 is the most generic active model-add request, but it is still NeoBERT-specific and not a duplicate of the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different models (EuroBert vs DEIMv2); same broad request pattern, not the same change." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config support is unrelated to Qwen3-TTS support." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are distinct models and code paths." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT vs OpenAI weight-sparse transformer are different requested additions." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT and LFM2.5 Audio are different model families and tasks." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are separate model requests, not one duplicate." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT and Voxtral-4B-TTS-2603 are unrelated model additions." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are unrelated models and capabilities." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT models and Qwen3-ASR are different model targets." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT and Qwen3-TTS are distinct requests." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT models and BERT-like models with RoPE overlap only loosely; they are not the same concrete request." + }, + { + "left": "issue:42503", + "right": "issue:45027", + "accept": false, + "reason": "ModernVBERT and Voxtral-4B-TTS-2603 are different model additions." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like models with RoPE is a broad architecture request, not the same as adding Voxtral-4B-TTS-2603." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR share a family name but request different modalities and support code." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS support and Voxtral-4B-TTS-2603 are different TTS models." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS support and DeepSeek-OCR2 are unrelated model requests." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS support and the weight-sparse transformer request are different changes." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio are different audio model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio are different models and tasks." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR and EUPE are unrelated model requests." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR support and weight-sparse transformer support are unrelated changes." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio and SAM3-LiteText are different model additions." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Weight-sparse transformer support and EUPE are different model requests." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral-4B-TTS-2603 are different audio models with different support paths." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR and DeepSeek-OCR2 are unrelated model requests." + } + ] + }, + "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": 13, + "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-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": "70fdf236980254de59409fa702e043aa1e07799d1fc3d2502b8ee2f494114f9a", + "component_budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 8, + "serialized_chars": 6291, + "estimated_input_tokens": 1573, + "estimated_eval_tokens": 3402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These items do not look like duplicates of one another; they span separate models, tokenizer behavior, config typing, a typo, and a loss-kwargs bug. The soft-similarity links appear to be false positives from generic wording rather than the same underlying issue.", + "confidence": 0.95, + "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 topics: Llama4 normalization implementation vs ModernBERT config type annotation." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2Former ignore_value handling is unrelated to passing kwargs into a loss function." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Model ignore_value bug and tokenizer regex warning regression are separate code paths." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former loss/input handling is unrelated to a quantization-operation typo." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Different models and different bug types; no shared underlying defect." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Generic loss-kwargs forwarding bug does not match a config type-hint issue." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "Config annotation typo is unrelated to tokenizer regex warning behavior." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "ModernBERT norm_eps typing and the quoted typo concern unrelated text/metadata issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 13, + "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-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "6a0eb8748c86225f58425ad027663d3eb0336dee75c41622ce78c15f8adb3ebe", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated: one asks for block decoding, the other requests DeepSeek v3.2 support. No duplicate/canonical linkage is evident.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different requests with no shared code-path or concrete bug: block decoding vs model support. The titles and available metadata do not indicate 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": 8, + "component_count": 13, + "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-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "e2c0c4b82c116b7273f829adfbd0caf64439ed9e87359397098a9bfee7706770", + "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 are related only at a very broad level (custom trainer support), but they describe different problems: one is about `remove_unused_column` behavior/customizability in `Trainer`, the other is about FLOPS estimation with custom trainers. They should not be merged as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43598 is the broader Trainer customization request and is the better representative of the cluster\u2019s theme.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43598 is the most central/general item; issue 43600 is a narrower instrumentation/estimation concern.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Different underlying problems: one changes `remove_unused_column` handling, the other affects FLOPS estimation for custom trainers. Shared mention of custom trainers is too broad to treat as the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 13, + "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-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "88a7b4792ce402ae4af5da89cbf7163d0b5226f8a881d2cd100697521ce7d5f6", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1612, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are about different model families and different API registrations, so they should not be treated as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43684 is the broader registration request for Qwen3-Omni in AutoModel / AutoModelForConditionalGeneration; issue 44405 is a separate request for AutoModelForSequenceClassification support on Qwen3.5 (Qwen3_5Config). They do not describe the same missing behavior.", + "canonical_pr_reason": null, + "best_issue_reason": "43684 is the better representative issue because it is the more general model-registration gap and reads as a broader API support request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model families (Qwen3-Omni vs Qwen3.5) and different target classes (generation vs sequence classification); not the same underlying bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 13, + "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-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": "1381e3358c3150c27651a88d6d9bb7bbc7dbb2c3c50b6def3fe3018c65438829", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4255, + "estimated_input_tokens": 1064, + "estimated_eval_tokens": 2384 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4255, + "estimated_input_tokens": 1064, + "estimated_eval_tokens": 2384 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three issues share the same near-identical title (\u201chuggingface \u201d) and look like duplicates; the separate \u201cFett\u201d issue does not have enough evidence to join that set.", + "confidence": 0.74, + "canonical_issue_reason": "Issue 43845 is the earliest of the three matching \u201chuggingface \u201d reports and is the best representative of that duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "43845 is the strongest cluster representative because it is earliest and matches the other two huggingface-titled issues exactly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different title from the repeated \u201chuggingface \u201d reports; no body/detail evidence tying it to the same issue." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different title and no concrete evidence of the same underlying problem." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different title and no concrete evidence of the same underlying problem." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same title, very close timing, and no distinguishing details; likely duplicate reports of the same issue." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same title and no evidence of a different bug; appears to be a duplicate report." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same title and no evidence of a different underlying issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: 43845/43846/43859 share the exact title \"huggingface \" and 43835 is titled differently, so treating it as separate is conservative. The soft-edge verdicts also stay within the available evidence (title similarity and timing) without overclaiming body-level proof." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 13, + "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-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": "426c3b3dcd14703d4d423501c7242a122e28d643e629f5fa6b8b75bfc6a361de", + "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 items look like unrelated low-information/spam issues rather than reports of the same bug or request. There is no clear duplicate cluster to collapse.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are generic spam-labeled issues with no substantive body or shared concrete problem; similarity is only superficial." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Same as above: no evidence they describe the same underlying issue, only matching spam-like placeholder content." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam and the other is a generic documentation suggestion; too little content to indicate the same bug/change." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Different titles and no body detail; no concrete overlap beyond both being closed issues." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A documentation suggestion and a spam placeholder are not the same underlying issue." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "A generic doc request does not match a spam-like placeholder issue." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam-like placeholders, but there is no evidence they report the same specific problem." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "No shared concrete bug or request is visible; titles are unrelated." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "No substantive overlap or explicit linkage; reject as duplicate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 12, + "component_count": 13, + "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-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "b39e29abd403d6084e5fbf507a94a54c039ba44853f3adeeebb01feefc728ce4", + "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 are highly similar and share the same title, but the evidence only shows soft similarity. With no shared targets, filenames, or explicit linkage, they are best treated as closely related reports rather than confidently marked duplicates.", + "confidence": 0.81, + "canonical_issue_reason": "Issue #45145 is the better canonical candidate because it was created earlier and has an inbound reference, making it the more established thread.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45145 is the best representative for this cluster because it is the earlier report and has the inbound reference; there is no stronger signal favoring #45151.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "Same title and similar text, but the match is only soft_similarity with no shared targets, filenames, or explicit duplicate linkage. That is not strong enough to confidently treat them as duplicates." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster assessment is a bit overstated. The packet supports that these two issues are very similar and share the same title, but it does not strongly prove they are duplicates; the evidence is only soft_similarity, with no shared targets/filenames. Also, the best_issue_reason is not grounded because issue #45145 does not have slightly more discussion signal than #45151 (it has 0 vs 1). The canonical choice based on earlier creation and inbound reference is reasonable, but the duplicate/duplicate-report language should be more conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 13, + "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": "pull_request", + "component_index": 1, + "component_count": 23, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-13", + "nodes": [ + "pull_request:39895", + "pull_request: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:45435", + "pull_request:45454", + "pull_request:45489" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:45435", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45454", + "pull_request:43823|pull_request:45435", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:45435", + "pull_request:43995|pull_request:45213", + "pull_request:43995|pull_request:44827", + "pull_request:44827|pull_request:45489", + "pull_request:44827|pull_request:45170", + "pull_request:43823|pull_request:44827", + "pull_request:45213|pull_request:45435", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:44827|pull_request:45435", + "pull_request:45454|pull_request:45489", + "pull_request:43823|pull_request:45489", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "a0ff1721763883c73033f88928d07cfabab71abd617a051d7f6b67ecc47d6e46", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 23, + "serialized_chars": 37549, + "estimated_input_tokens": 9388, + "estimated_eval_tokens": 19032 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 23, + "serialized_chars": 37549, + "estimated_input_tokens": 9388, + "estimated_eval_tokens": 19032 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated PRs across model additions, docs, tests, and small fixes. The only clear duplicate pair is the two `fixed_cross_entropy` patches (#43251 and #43254), which both implement the same `nn.functional.cross_entropy` kwargs support in the same file/function.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43251 is the clearest canonical representative of the duplicate loss fix: it targets the explicit issue, edits the same `fixed_cross_entropy` path, and has the fuller patch/discussion. PR #43254 is a near-identical alternate implementation of the same change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43251 is the best overall representative of the cluster because it is the only strong duplicate anchor and the most complete version of that concrete fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Different changes: VideoPrism model/docs addition vs an executorch dynamic-shape export test." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Different artifacts and goals: processor robustness fixes vs adding MobileLLM model support." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Unrelated: cross-entropy kwargs fix vs new MobileLLM model code." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Different code paths: loss utility kwargs support vs Mistral4 test/model fixes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "Different areas: executorch export test vs Mistral4 model/test changes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:45435", + "accept": false, + "reason": "Different bugs: executorch dynamic-shape export testing vs Whisper tokenizer boundary fix." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Different scope: exportability test vs MobileLLM model addition." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45454", + "accept": false, + "reason": "Different model families and issues: MobileLLM addition vs Gemma4 text-only training behavior." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45435", + "accept": false, + "reason": "No shared underlying change; model addition vs Whisper tokenization bug." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "Different changes: MobileLLM model addition vs Falcon output-interface refactor." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45435", + "accept": false, + "reason": "Different code paths: Falcon refactor vs Whisper tokenizer boundary fix." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon model refactor is unrelated to the model-creation skill/meta PR." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Different model work: Falcon refactor vs Mistral4 test/model fixes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45489", + "accept": false, + "reason": "Related by theme but not the same change: Mistral4 test/model fixes vs Gemma3n/Gemma4 cache-sharing alignment." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Different underlying changes: Mistral4 fixes vs CLIP-like layrnorm\u2192layernorm renaming." + }, + { + "left": "pull_request:43823", + "right": "pull_request:44827", + "accept": false, + "reason": "Different model implementations and bugs; not mergeable as one PR." + }, + { + "left": "pull_request:45213", + "right": "pull_request:45435", + "accept": false, + "reason": "Meta model-creation skill PR is unrelated to Whisper tokenizer bug fix." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 fixes are unrelated to the model-creation skill/meta PR." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model addition is unrelated to the model-creation skill/meta PR." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45435", + "accept": false, + "reason": "Mistral4 fixes and Whisper tokenizer fix are different code paths and symptoms." + }, + { + "left": "pull_request:45454", + "right": "pull_request:45489", + "accept": false, + "reason": "Both touch Gemma-related code, but one is a text-only training fix and the other is cache-sharing alignment; different concrete changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45489", + "accept": false, + "reason": "Different models and bugs: MobileLLM addition vs Gemma3n/Gemma4 cache-sharing refactor." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Same underlying fix in the same function/file: both add supported kwargs to `fixed_cross_entropy` so they can be merged into one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft-edge pair, #43251 and #43254, is supported by shared issue target, same file/function, and the same concrete cross-entropy kwargs fix. The remaining pairs are reasonably rejected as distinct model additions, tests, refactors, or unrelated bug fixes." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 23, + "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": "1cd090f34516eec6dbd87701699b850d9038ade82307e3e8c2c96a810910e3ec", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs are about VibeVoice, but they target different deliverables: one is the base VibeVoice integration, while the other adds a separate realtime/acoustic-tokenizer path. They overlap on shared model plumbing, but they are not the same change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 40546 is the cleaner canonical VibeVoice implementation: it introduces the core model/docs/auto-class wiring without the extra realtime-specific tokenizer and generation changes.", + "best_issue_reason": null, + "best_pr_reason": "PR 40546 is the best representative artifact because it defines the foundational VibeVoice integration that the later realtime PR builds on.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Not a duplicate: 40546 implements core VibeVoice support, while 42781 adds VibeVoice Realtime plus acoustic tokenizer and generation changes. They share filenames because they touch the same subsystem, but they are different features and would not plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 23, + "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": "1c6b9da50922886a862667a2c8ff58e8fd7e1a5351127037699a33d21950c03a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4674, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are unrelated feature additions in different model families: TimesFM covariate forecasting vs. DINOv3 image classification support. They do not fix the same code-path problem and should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #41224 is the more self-contained and concrete change: it adds image-classification support for DINOv3 with accompanying docs/tests. PR #40755 is a separate, broader feature for TimesFM forecasting with covariates.", + "best_issue_reason": null, + "best_pr_reason": "PR #41224 is the best representative of the cluster only because it is the clearest single feature PR; however, the cluster itself is not a duplicate set and the two PRs should remain separate.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models and different functionality: TimesFM covariate forecasting vs DINOv3 image classification support. No shared bug or mergeable code-path 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": 4, + "component_count": 23, + "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-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "88e60f926a84fb13a881f1700f827def51f6a2034775286ab5e8f054384e362c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5929, + "estimated_input_tokens": 1483, + "estimated_eval_tokens": 3222 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5929, + "estimated_input_tokens": 1483, + "estimated_eval_tokens": 3222 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests are about adding DEIMv2 support to Transformers. PR #44339 is the more complete, later implementation and appears to supersede the smaller initial addition in #41356.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #44339 is the stronger canonical PR because it is the later, more complete DEIMv2 integration: it adds the model, loss, auto-mapping, conversion script, and related docs/tests, while #41356 is an earlier partial model/image-processor addition.", + "best_issue_reason": null, + "best_pr_reason": "PR #44339 is the best representative of the cluster because it most fully implements the DEIMv2 feature and includes the broader set of integration changes expected for a merged model addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": true, + "reason": "Same underlying feature addition for DEIMv2 support, with substantial overlap in model files, docs, and tests; #44339 looks like the expanded successor to the earlier partial PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target the same DEIMv2 issue, share several core files, and #44339 clearly adds broader integration pieces beyond #41356. The soft-edge verdict is conservative because it says the later PR 'looks like' an expanded successor rather than asserting a definitive relationship." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 23, + "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-41797-2", + "nodes": [ + "pull_request:41797", + "pull_request:45186" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186" + ], + "prepared_review_unit_hash": "587a88d1cde82753c3f1087a8edf5173c49e0f2afee9eab6bcd82177c06252cd", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6723, + "estimated_input_tokens": 1681, + "estimated_eval_tokens": 3618 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6723, + "estimated_input_tokens": 1681, + "estimated_eval_tokens": 3618 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two unrelated model-integration PRs (DeepSeek OCR vs Isaac). They share standard Transformers boilerplate and generated scaffolding, but not the same underlying bug or feature 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 models and different codepaths; overlap is only generic new-model integration files and docs, not a single mergeable change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 23, + "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-42166-2", + "nodes": [ + "pull_request:42166", + "pull_request:45426" + ], + "soft_pairs": [ + "pull_request:42166|pull_request:45426" + ], + "prepared_review_unit_hash": "c1dbd24520c660e240eec75dcd0520c46f84ef529d7e529ee5362239c6786dc5", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5407, + "estimated_input_tokens": 1352, + "estimated_eval_tokens": 2960 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5407, + "estimated_input_tokens": 1352, + "estimated_eval_tokens": 2960 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are unrelated feature PRs adding different models: InternVLFlash vs AXK1. They share some Transformers registry boilerplate, but not the same underlying bug or change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: #42166 and #45426 implement separate model integrations with different packages, configs, modeling files, and tests; shared auto-registration edits are incidental.", + "best_issue_reason": null, + "best_pr_reason": "If a single representative is needed, #42166 is the stronger model-addition PR because it includes a broader InternVLFlash integration surface (docs, auto mappings, model code, and tests), but it is still not a duplicate of #45426.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42166", + "right": "pull_request:45426", + "accept": false, + "reason": "Reject: they add different models and different codepaths; shared registry files alone are not enough to treat them as the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 23, + "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-42227-4", + "nodes": [ + "pull_request:42227", + "pull_request:43291", + "pull_request:43665", + "pull_request:44815" + ], + "soft_pairs": [ + "pull_request:42227|pull_request:43291", + "pull_request:42227|pull_request:43665", + "pull_request:42227|pull_request:44815", + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "1d63bd0a59ec46a4458c32edfef9aaf5fc4db188ce330ec3e2ef77a1d8cb4b26", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 10170, + "estimated_input_tokens": 2543, + "estimated_eval_tokens": 5342 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates overall: one fixes Whisper return-language plumbing, one changes Whisper tokenizer tests/timestamp decoding, one is a CLIP/ViT test-only edit, and one is an FP8 dequant/loading fix. The only superficially related pair is the two Whisper PRs, but they address different code paths and should not be merged as the same change.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42227 is the strongest anchor: it has an explicit issue link, a focused user-facing Whisper pipeline fix, and a clear implementation change with tests. The others are either test-only or unrelated model/quantization work.", + "best_issue_reason": null, + "best_pr_reason": "PR 42227 is the best representative of the cluster because it is the most concrete standalone bug fix and the only one tied to a tracked issue; the rest are not the same underlying change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42227", + "right": "pull_request:43291", + "accept": false, + "reason": "Both mention Whisper, but 42227 fixes ASR pipeline return-language propagation while 43291 changes tokenizer decode/timestamp test behavior; different code paths and not one mergeable fix." + }, + { + "left": "pull_request:42227", + "right": "pull_request:43665", + "accept": false, + "reason": "42227 is a Whisper runtime fix; 43665 only adds/edit tests for CLIP and ViT. Same broad repo area, not the same bug or change." + }, + { + "left": "pull_request:42227", + "right": "pull_request:44815", + "accept": false, + "reason": "42227 touches Whisper ASR; 44815 is a quantization/dequant/loading fix across model-loading and FP8 integration. Unrelated changes." + }, + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Whisper tokenizer decoding vs. CLIP/ViT test edits are unrelated; no shared concrete bug or code path." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Whisper decoding/test work and FP8 dequant/loading work solve different problems in different subsystems." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "A test-only CLIP/ViT change is not the same underlying bug/change as the FP8 dequant 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": 8, + "component_count": 23, + "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": "dd4160f5e4869084f26bdd0761b6e20b55b5195b46890d1b39d5af9c93681895", + "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 workflow-dependency upgrade PRs overlap on some GitHub Actions files, but they target different upgrade goals and do not look like the same change set.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "No clear duplicate PR here: PR #42975 is specifically about Node 24 compatibility for GitHub Actions, while PR #42976 is a broader 'latest versions' upgrade centered on docker/build-push-action and related workflow actions.", + "best_issue_reason": null, + "best_pr_reason": "PR #42975 is the better representative PR if one must be chosen because it has the clearest, more specific purpose and broader workflow-wide compatibility framing; PR #42976 looks like a separate dependency refresh.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Different underlying changes: one upgrades actions for Node 24 compatibility, the other updates actions to newer versions (notably docker/build-push-action). Shared workflow filenames alone are not enough to treat these as the same fix/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 9, + "component_count": 23, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-10", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:43838", + "pull_request:43973", + "pull_request:44601", + "pull_request:45157", + "pull_request:45283", + "pull_request:45490", + "pull_request:45532" + ], + "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:43448|pull_request:45532", + "pull_request:43451|pull_request:45490", + "pull_request:43451|pull_request:45532", + "pull_request:43838|pull_request:45283", + "pull_request:43973|pull_request:45283", + "pull_request:44601|pull_request:45532", + "pull_request:45157|pull_request:45532", + "pull_request:45283|pull_request:45532", + "pull_request:45490|pull_request:45532" + ], + "prepared_review_unit_hash": "e3a4576fc0e397eb2fadf1fb118853a2db34567eb308f2ab22c8bb21920550b1", + "component_budget": { + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 32077, + "estimated_input_tokens": 8020, + "estimated_eval_tokens": 16296 + }, + "budget": { + "node_count": 10, + "item_count": 10, + "soft_pair_count": 14, + "serialized_chars": 32077, + "estimated_input_tokens": 8020, + "estimated_eval_tokens": 16296 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "False-positive cluster: the PRs are mostly unrelated model additions or infrastructure work that only overlap in boilerplate docs/auto-registry files. There is no single underlying bug or change here.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the set mixes distinct model additions (ViT NEPA, Molmo, Molmo2, Qwen3-ASR, Lfm2 Audio, CTSM, SLANet) plus unrelated distributed/quantization/GGUF changes; shared files are incidental boilerplate.", + "best_issue_reason": null, + "best_pr_reason": "No PR is a suitable global representative; these are separate feature PRs touching overlapping registry/docs files but fixing/adding different things.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "ViT NEPA vs Molmo are different model additions; overlap is only in docs/auto registration boilerplate." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "ViT NEPA and Molmo2 are distinct model integrations, not the same code change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "ViT NEPA and CTSM are unrelated model-addition PRs sharing only registry/docs files." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are different model families with different files and logic; not one change." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo vs CTSM are unrelated model support PRs; same broad subsystem is not enough." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45532", + "accept": false, + "reason": "Molmo and SLANet are separate model additions; shared docs/auto files are incidental." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are different model integrations, not the same concrete bug or feature." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45532", + "accept": false, + "reason": "Molmo2 and SLANet are unrelated model support PRs; overlap is only registry scaffolding." + }, + { + "left": "pull_request:43838", + "right": "pull_request:45283", + "accept": false, + "reason": "Qwen3-ASR support and Qwen3.5 GGUF loading are different features in different code paths." + }, + { + "left": "pull_request:43973", + "right": "pull_request:45283", + "accept": false, + "reason": "Lfm2 Audio model support is unrelated to Qwen3.5 GGUF loading; only broad audio/LLM tooling overlap." + }, + { + "left": "pull_request:44601", + "right": "pull_request:45532", + "accept": false, + "reason": "Native pipeline-parallel support is infrastructure work, not the same change as SLANet model support." + }, + { + "left": "pull_request:45157", + "right": "pull_request:45532", + "accept": false, + "reason": "PrismML Bonsai GGUF quantization support and SLANet model support are unrelated changes." + }, + { + "left": "pull_request:45283", + "right": "pull_request:45532", + "accept": false, + "reason": "Qwen3.5 GGUF loading and SLANet model support do not fix the same concrete code-path problem." + }, + { + "left": "pull_request:45490", + "right": "pull_request:45532", + "accept": false, + "reason": "CTSM and SLANet are different model-addition PRs; they share only generic docs/registry 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": 10, + "component_count": 23, + "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-43488-3", + "nodes": [ + "pull_request:43488", + "pull_request:43532", + "pull_request:45476" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532", + "pull_request:43488|pull_request:45476", + "pull_request:43532|pull_request:45476" + ], + "prepared_review_unit_hash": "91c37c0ad45a1f46a680f8f323a0a6ca98ea550e434cdb54e01949a00fe8ecf6", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7464, + "estimated_input_tokens": 1866, + "estimated_eval_tokens": 3988 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7464, + "estimated_input_tokens": 1866, + "estimated_eval_tokens": 3988 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three unrelated open PRs that look like test/bot-infrastructure experiments rather than duplicates of the same fix. They share some filenames only because they all poke at repo testing/CI files, but the titles and diffs point to different purposes.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43532 is the broadest and most representative of the cluster: it touches multiple workflow and test files and has the most discussion activity, so it best captures the shared 'bot/CI test PR' theme.", + "best_issue_reason": null, + "best_pr_reason": "PR #43532 is the strongest cluster exemplar because it has the widest scope across CI/test infrastructure and is more informative than the tiny, highly synthetic changes in #43488 and #45476.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Different intents: #43488 is a repo-bot format check, while #43532 rewrites a self-comment CI workflow and related test utilities. Shared Vit test filename is incidental and not the same underlying change." + }, + { + "left": "pull_request:43488", + "right": "pull_request:45476", + "accept": false, + "reason": "#43488 changes setup/versioning and a test file for a bot-format check; #45476 adds a PR CI caller workflow and unrelated placeholder edits. They do not fix the same code-path problem." + }, + { + "left": "pull_request:43532", + "right": "pull_request:45476", + "accept": false, + "reason": "Both are CI-related, but they target different workflows and behaviors: #43532 modifies self-comment/scheduled/slack reporting logic, while #45476 adds a PR CI workflow caller and unrelated tokenization/test noise. Not mergeable as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 23, + "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": "46d53a5a505a20a476d557fa8d07d5b8cad0fbf79e57e86e14652007a57ec86c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs add different segmentation pipelines and their associated docs/tests. They share scaffolding files, but they target different code paths and model families, so they are related but 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:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Reject: these are separate feature PRs for different pipelines ('Promptable Concept Segmentation' vs 'Promptable Visual Segmentation'). They touch overlapping documentation and registration files, but the added pipeline modules, tests, and model integrations are different, so they do not look like one mergeable change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 23, + "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": "4400efa376c7dcbc6858f01c76aa7e101ef0f006777a7d1bb3274167fccaaa65", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4292, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate trainer refactor/extension PRs in the same file, but they change different code paths: gradient-accumulation loss scaling vs. signature-column filtering for custom trainers. Shared filename alone is not enough to treat them as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR for a duplicate cluster; the two PRs solve different trainer concerns. If one must be chosen as the closest representative, #43651 is more concrete because it changes the training-step loss scaling path directly.", + "best_issue_reason": null, + "best_pr_reason": "#43651 is the better standalone representative of this cluster because it introduces a focused training behavior change with an explicit helper and a concrete loss-scaling path. #43663 is a separate API/refactor for signature-column handling and is not the same change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different underlying changes in `trainer.py`: #43651 alters gradient accumulation loss normalization in `training_step`, while #43663 extracts `_get_signature_columns` for model input filtering. They do not fix the same bug or implement the same feature, and would not plausibly be merged as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 23, + "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": "c86cba35672572405f16aaae4b13227adea85732fa9f7ec589cb6bd44a0c13e5", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 5992, + "estimated_input_tokens": 1498, + "estimated_eval_tokens": 3252 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three PRs are small fixes in `src/transformers/cli/serve.py` around runtime type-annotation handling for `TypeAdapter` / CLI startup NameErrors. `43842` is the cleanest, most targeted fix; `43836` looks like a close variant of the same fix; `43656` appears related but broader and less clearly the same concrete change.", + "confidence": 0.82, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43842 is the most focused and direct fix: it avoids importing `TypeAdapter` at runtime and quotes the annotation under `TYPE_CHECKING`, which cleanly addresses the reported NameError when pydantic is absent.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 is the best representative of the cluster because it is narrowly scoped, directly tied to the runtime error, and less entangled with unrelated typing cleanups than 43656 or the broader refactor-like 43836.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Both mention `TypeAdapter` NameError in the same file, but the visible fixes differ enough that they do not clearly look like the same concrete change; 43656 also includes broader annotation cleanup, so I would not merge them as one PR." + }, + { + "left": "pull_request:43836", + "right": "pull_request:43842", + "accept": true, + "reason": "These appear to be overlapping fixes for the same `TypeAdapter` annotation/runtime-NameError issue in `serve.py`, and the changes look plausibly mergeable into a single PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: all three PRs touch `src/transformers/cli/serve.py` and are about the same `TypeAdapter`/startup NameError area. The softer edge decisions are also conservative enough: `43656` is plausibly broader and not clearly the same concrete change as `43842`, while `43836` and `43842` look mergeable as closely related fixes for the same bug in the same file." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 23, + "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-43757-3", + "nodes": [ + "pull_request:43757", + "pull_request:45500", + "pull_request:45506" + ], + "soft_pairs": [ + "pull_request:45500|pull_request:45506", + "pull_request:43757|pull_request:45500", + "pull_request:43757|pull_request:45506" + ], + "prepared_review_unit_hash": "7f6ef0b38d2a676600b5f113a3637f9f95d78e3df0afa91373be98f1fa40f423", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7755, + "estimated_input_tokens": 1939, + "estimated_eval_tokens": 4134 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7755, + "estimated_input_tokens": 1939, + "estimated_eval_tokens": 4134 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are closely related GPT-OSS GGUF-loading PRs, but only the two later PRs are true duplicates; the earliest one is a narrower partial fix with extra unrelated changes. The strongest representative is PR #45506.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45506 is the best canonical PR: it has the broadest and most complete GPT-OSS GGUF support, includes the relevant ggml mapping, loader changes, and tests, and it is a non-draft reviewed PR that effectively supersedes the earlier draft.", + "best_issue_reason": null, + "best_pr_reason": "PR #45506 is the best global representative because it appears to implement the intended full fix for GPT-OSS GGUF loading rather than just a fallback, and it aligns with the shared target issue and the later duplicate PR.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45500", + "right": "pull_request:45506", + "accept": true, + "reason": "Same underlying GPT-OSS GGUF loading change: same issue target, same title, overlapping files, and the later PR looks like a fuller iteration of the same fix that could plausibly be merged into one PR." + }, + { + "left": "pull_request:43757", + "right": "pull_request:45500", + "accept": false, + "reason": "Both touch GPT-OSS GGUF loading, but #43757 is a narrower fallback-based partial fix and also includes unrelated Grounding DINO changes, while #45500 is a broader full-support PR; they are related but not the same concrete change." + }, + { + "left": "pull_request:43757", + "right": "pull_request:45506", + "accept": false, + "reason": "#43757 only adds a fallback for an unsupported architecture and mixes in unrelated edits, while #45506 implements full GGUF support with mapping/test changes; they address the same bug family but are not the same mergeable code change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 23, + "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": 16, + "component_count": 23, + "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:44071|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44018|pull_request:44086", + "pull_request:44018|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44059|pull_request:44722", + "pull_request:44085|pull_request:44086", + "pull_request:44098|pull_request:44101", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:44059|pull_request:44071", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44059|pull_request:44068", + "pull_request:44073|pull_request:44101", + "pull_request:44018|pull_request:44059", + "pull_request:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", + "pull_request:44101|pull_request:44161", + "pull_request:44017|pull_request:44018", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request: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:44010|pull_request:44073", + "pull_request:44018|pull_request:44129", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:44071|pull_request:44129", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "0126593005e81b5e9f15af1ba1ebddbb46aacb2bdea8e9a9d32aba0126e2ab5d", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84895, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75096, + "estimated_input_tokens": 18774, + "estimated_eval_tokens": 37804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a family of model-specific refactors toward standardized output tracing. Most PRs target different architectures and should stay separate; only a few pairs within the same model family look like true duplicates/overlaps.", + "confidence": 0.84, + "canonical_issue_reason": "Issue #43979 is the shared umbrella tracker for the standardized output-tracing refactor across these PRs.", + "canonical_pr_reason": "PR #44722 is the strongest representative for the GPT-J/CodeGen slice: it explicitly targets #43979, touches the same concrete code paths, and is the broadest later iteration in that subfamily.", + "best_issue_reason": "#43979 is the best global issue anchor because all of these PRs are variations of that same tracking effort.", + "best_pr_reason": "#44722 is the best global PR representative because it covers the same decorator-based output-tracing change on the core GPT-J/CodeGen path and is the most comprehensive example in the overlapping set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different models and code paths (CVT/FNet vs GPT-J); sharing the umbrella issue is not enough to make them duplicates." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different model families and different implementations of the tracing refactor." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors on the same underlying code path, and could plausibly be merged into one PR." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet and EfficientNet are separate model implementations; same issue target only indicates a shared migration theme." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "Different models (EfficientNet vs GPT-J/CodeGen); not the same concrete bug or change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen vs EfficientNet are unrelated code paths despite the same tracking issue." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa are separate refactors with no shared code path." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "Different model families (GPT-J/CodeGen vs MGP-STR); same umbrella refactor but not the same fix." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are different implementations; no evidence of a single shared bug." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both PRs are GPT-Neo output-tracing refactors on the same model/file set, so they look like overlapping 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 paths, so these are separate PRs." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated model refactors." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen are different code paths; same theme only." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet vs GPT-J are different model implementations and not duplicates." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are separate model-specific output-tracing changes." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT are different code paths." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert/XLM are different models; no shared concrete change." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are separate implementations." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are different model paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT2 and MGP-STR are unrelated model refactors." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT2 output tracing is a separate code path from GPT-J/CodeGen." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are different models; the similarity is only thematic." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are distinct model implementations." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "SegFormer and GPT-J/CodeGen are unrelated code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "SegFormer and LongT5 are different model-specific refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "SegFormer and VisualBERT are separate implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different models, so this is not the same concrete change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBERT and Flaubert/XLM are distinct code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet and MPNet are separate model refactors." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44076", + "accept": false, + "reason": "MPT and ImageGPT are unrelated model implementations." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert/XLM are different models; same migration pattern only." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are separate code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet and GPT-Neo are different model families." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet and LongT5 are unrelated model refactors." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44129", + "accept": false, + "reason": "TextNet and SpeechT5 are different code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet and LongT5 are separate model implementations." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet and SegFormer are unrelated code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBERT and MPT are different model families." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBERT and VisualBERT are separate refactors." + }, + { + "left": "pull_request:44044", + "right": "44074", + "accept": false, + "reason": "DeBERTa and TextNet are different model implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Both touch the same GPT-J/CodeGen output-tracing change family and could be combined into one PR." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors on the same file, so they look like overlapping versions of the same fix." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J and SpeechT5 are unrelated model paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "CVT/FNet and RegNet are different models." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet and SpeechT5 are unrelated code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa and SpeechT5 are separate model refactors." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa and VITS are different implementations; only the tracing pattern is shared." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays grounded in the packet: issue #43979 is the clear umbrella tracker for many of these output-tracing refactors, and #44722 is a reasonable representative for the GPT-J/CodeGen subgroup. The soft-edge calls are conservative overall: the accepted pairs share the same model/file family and look mergeable into a single bugfix PR, while the rejected pairs mostly involve different model architectures/code paths and are not strong duplicate candidates." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 23, + "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": "bf24c3b5dd052e905bf132d3a6bb0a219e86a5bed6415e6a0a0b481f6a4c1e3d", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84895, + "estimated_input_tokens": 21224, + "estimated_eval_tokens": 42704 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17120, + "estimated_input_tokens": 4280, + "estimated_eval_tokens": 8816 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a set of model-specific PRs all moving individual architectures toward standardized output tracing/capture_outputs. They share a broad refactor theme, but they are not the same concrete change and should not be merged as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "No issue artifacts are present. If one PR must represent the cluster, 44129 is the strongest standalone candidate because it has an explicit issue target and a clearly scoped standardized output tracing refactor.", + "best_issue_reason": null, + "best_pr_reason": "44129 is the best single PR to keep as canonical representative: it is a focused refactor with an explicit linked issue, while the others are separate model-by-model implementations of the same general migration pattern.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Both are output-tracing migrations, but for different models and code paths (FocalNet vs ImageGPT). This is the same refactor pattern, not the same change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "VisualBert and TextNet are unrelated model implementations; the PRs share only the standardized output capture theme and do not fix the same concrete bug or change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "These target different architectures (MPNet vs VisualBert). Similar decorator/capture_outputs work is too broad to treat as a duplicate PR." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "MPNet and TextNet are separate model refactors. The overlap is only the output-tracing migration pattern, not a mergeable single change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert changes affect different model files and code paths. Shared standardized-output plumbing is not enough to call them duplicates." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 are unrelated model-specific PRs. They both touch output handling, but they are distinct refactors with different implementations and targets." + } + ] + }, + "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": 23, + "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: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": "1810dc89024bb4736c8db67097155b9cdb6729b9c26c379d4e778b08a7f16663", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 39, + "serialized_chars": 39787, + "estimated_input_tokens": 9947, + "estimated_eval_tokens": 20150 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 39, + "serialized_chars": 39787, + "estimated_input_tokens": 9947, + "estimated_eval_tokens": 20150 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are many separate model-specific refactors that share the same output-tracing theme, but they do not fix the same concrete bug or change the same code path. I would not merge any of them as duplicates across model families.", + "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:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models and files (`timm_backbone` vs `upernet`); same refactor pattern, not the same code-path change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Different subsystems (`timm_backbone` vs `vision_text_dual_encoder`); only the output-tracing refactor is shared." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model families (`timm_backbone` vs `univnet`); no shared underlying bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "`timm_backbone` and `falcon_mamba/mamba` are unrelated code paths; similarity is only in the refactor style." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "`timm_backbone` and `codegen` touch unrelated architectures and files; not the same concrete change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Different models (`timm_backbone` vs `rwkv`); shared output-capturing cleanup only." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "`mobilenet_v1` and `univnet` are unrelated implementations; not a duplicate bug fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families (`mobilenet_v1` vs `upernet`); no shared code-path problem." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "`mobilenet_v1` and `depth_anything` are separate model code paths; same refactor theme only." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "`mobilenet_v1` and `vision_encoder_decoder` are unrelated; not the same underlying change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different models (`mobilenet_v1` vs `speech_encoder_decoder`); no mergeable duplicate relationship." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "`vision_text_dual_encoder` and `univnet` are different model families; only the refactor pattern matches." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different files and model architectures (`vision_text_dual_encoder` vs `upernet`); not the same concrete fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "`vision_text_dual_encoder` and `falcon_mamba/mamba` are unrelated code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model families (`vision_text_dual_encoder` vs `codegen`); shared output-tracing refactor is too broad to be a duplicate." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "`vision_text_dual_encoder` and `depth_anything` modify different model stacks; not the same change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "`univnet` and `upernet` are unrelated; same style of refactor, not same bug or PR." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model families (`univnet` vs `falcon_mamba/mamba`); no shared concrete code path." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "`univnet` and `depth_anything` are separate changes despite similar output-tracing cleanup." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "`upernet` and `falcon_mamba/mamba` are different subsystems; not mergeable as one fix." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "`upernet` and `rwkv` are unrelated model implementations; only the refactor theme overlaps." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "`falcon_mamba/mamba` and `codegen` fix different model code paths; similarity is superficial." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Different models (`timm_backbone` vs `codegen`) and different files; not the same underlying bug/change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "`univnet` and `codegen` are unrelated; same output-tracing cleanup only." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "`upernet` and `codegen` are different code paths; not a duplicate change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Different model families (`depth_anything` vs `vision_encoder_decoder`); same refactor motif only." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "`depth_anything` and `speech_encoder_decoder` are separate code paths; not the same bug or feature." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "`depth_anything` and `superpoint` are unrelated model implementations." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "`depth_anything` and `rwkv` are distinct model families; no duplicate fix." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "`depth_anything` and `dpr` touch different model code paths; not mergeable as one PR." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "`vision_encoder_decoder` and `speech_encoder_decoder` are different wrappers and code paths; only the refactor pattern is shared." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "`vision_encoder_decoder` and `superpoint` are unrelated; not the same underlying change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "`vision_encoder_decoder` and `rwkv` are different model families; not duplicates." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "`vision_encoder_decoder` and `dpr` modify different code paths; similarity is only thematic." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "`speech_encoder_decoder` and `superpoint` are unrelated model code paths." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "`speech_encoder_decoder` and `rwkv` are separate models; not the same concrete fix." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "`speech_encoder_decoder` and `dpr` are different subsystems; no duplicate relationship." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "`superpoint` and `rwkv` are unrelated implementations; same refactor pattern only." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "`superpoint` and `dpr` touch different code paths; not the same bug/change." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "`rwkv` and `dpr` are different model families; do not collapse 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": 18, + "component_count": 23, + "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": "87479abdaf2a74f154d5b71d23bb4b43e11ac6a4ad5617e44a6d80e24385af86", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 11071, + "estimated_input_tokens": 2768, + "estimated_eval_tokens": 5792 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 11071, + "estimated_input_tokens": 2768, + "estimated_eval_tokens": 5792 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three open PRs that each add a different model integration (PenguinVL, DeepSeek-OCR-2, Voxtral TTS). They overlap only in shared Transformers boilerplate and auto-registry/doc files, not in the underlying model or code path, so 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:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "Different model additions with different model directories, configs, modeling code, and tests (PenguinVL vs Voxtral TTS). Shared registry/docs updates are expected for any new model and do not indicate the same change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "These implement unrelated model integrations (PenguinVL vs DeepSeek-OCR-2). The overlap is limited to generic auto-registration and docs plumbing, which is not enough to treat them as the same PR." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model implementations with separate codepaths and tests. Similar framework scaffolding is incidental, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 23, + "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": "3e6e27aa6a448edd5ef3ca66693e90ec03d598c522ff7f2bd67e3680357b7177", + "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": "These are related by theme (kernel/module fusion) but they do not look like duplicate PRs. One introduces a new low-level Module Fusion API, while the other adds n-to-1 kernel fusion through KernelConfig and integration points in modeling/integrations code.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45363 is the more representative cluster item because it implements the more concrete end-user feature set: KernelConfig-driven fusion wired into core loading/integration paths, plus an example. PR 44979 is a lower-level API scaffold for module fusion.", + "best_issue_reason": null, + "best_pr_reason": "PR 45363 is the best overall representative because it has the broader, more product-facing change set and clearer integration surface, whereas PR 44979 is primarily the foundational API layer.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Reject as duplicate: the PRs target different change scopes and code paths. 44979 adds a standalone Module Fusion API in a new file, while 45363 wires KernelConfig-based n-to-1 kernel fusion through modeling/integration code and an example. They may be complementary, but they are not the same concrete fix or mergeable duplicate." + } + ] + }, + "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": 23, + "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": "81a24774a51ba7b7ec74b2973a96490008e979b339ef8b5534b93f3f98409142", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4413, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4413, + "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 tests, so it is the more complete duplicate-candidate.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45317 is the stronger canonical PR: it fixes the same bug as #45086 but also includes test coverage and appears to be the more complete version of the fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45317 is the best overall representative because it addresses the same concrete bug with additional validation, while #45086 is a smaller earlier variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same code path, same AttributeError fix, same target issue, and the second PR is just a 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": 21, + "component_count": 23, + "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": "80316ef99041a814bb9552144ad0340fc485e79ef771d697f52377ec2c915992", + "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": "The two open PRs are related but not duplicates: one adds heterogeneous per-layer config support, while the other adds broader heterogeneous model/runtime support that builds on that foundation. They overlap in infrastructure, but they address different scopes and code paths.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader umbrella change: it includes cache/modeling/masking updates plus GPT OSS integration and tests, making it the clearest representative of the overall heterogeneous-model feature set.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the most complete and representative PR in this cluster, since it covers the end-to-end modeling/runtime support rather than just the config layer.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature work, but not the same concrete change. #45333 is config-only per-layer configuration support, while #45332 adds model/runtime handling on top of that. They should remain separate PRs and would not plausibly be merged into one duplicate fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 22, + "component_count": 23, + "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": "ee755e34959b05cc003c30ff28d3bc1159ee2c45e62a08e22bb0b8a1720a6b99", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5306, + "estimated_input_tokens": 1327, + "estimated_eval_tokens": 2910 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5306, + "estimated_input_tokens": 1327, + "estimated_eval_tokens": 2910 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are both typing-related PRs in transformers, but they address different scopes: one is a broad repo-wide type-checking sweep, the other is a focused typing cleanup around modeling_utils/PEFT. They are not the same underlying change.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45425 is the more self-contained change set: it adds typing protocols/aliases for modeling_utils and related PEFT integration, with a clear single purpose.", + "best_issue_reason": null, + "best_pr_reason": "PR 45425 is the best representative for the cluster because it has a narrower, coherent typing objective and is less of a sweeping repository-wide cleanup.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Both are typing-focused, but 45415 is a broad multi-file type-checking pass while 45425 is a targeted modeling_utils/PEFT typing refactor; they do not appear to fix the same concrete code-path problem and would not plausibly merge as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 23, + "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-45470-2", + "nodes": [ + "pull_request:45470", + "pull_request:45487" + ], + "soft_pairs": [ + "pull_request:45470|pull_request:45487" + ], + "prepared_review_unit_hash": "483cef7dedc5d0ddad970e5774ae026987915b01ccf43260587ac71f587d83b9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4777, + "estimated_input_tokens": 1195, + "estimated_eval_tokens": 2646 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4777, + "estimated_input_tokens": 1195, + "estimated_eval_tokens": 2646 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are not duplicates: one is a narrow test skip for SAM3 Lite Text flash-attn dispatch behavior, while the other is a multi-file model-parallel fix for AltCLIP/ChineseCLIP and related models. They touch different code paths and would not plausibly merge into one PR.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45487 is the stronger canonical PR because it contains the actual functional fix across model code, whereas PR 45470 only adjusts a test expectation/skip for a specific SAM3 Lite Text case.", + "best_issue_reason": null, + "best_pr_reason": "PR 45487 is the best representative artifact for the cluster since it addresses a concrete runtime bug and spans the substantive code changes; PR 45470 is only a test-level workaround.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45470", + "right": "pull_request:45487", + "accept": false, + "reason": "Different problems and code paths: 45470 skips a flash-attn composite-model test in sam3_lite_text, while 45487 fixes model-parallel token_type_ids/device handling and related modules in AltCLIP/ChineseCLIP. Not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/manifest.json b/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..c1f8a7559def9c332d4470fd2a9cc6a301043208 --- /dev/null +++ b/snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260420t180040z", + "artifacts": { + "hybrid": "snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-04-20T18:14:36Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260420T180040Z", + "variant": "hybrid" +} diff --git a/snapshots/20260420T180040Z/manifest.json b/snapshots/20260420T180040Z/manifest.json index 7406d20462cf6c11bdf4e6973ef4315e8b4d6c6c..0f3d4bece0ad0b9114808012584ada5da2de9293 100644 --- a/snapshots/20260420T180040Z/manifest.json +++ b/snapshots/20260420T180040Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 1741 }, "extracted_at": "2026-04-20T18:00:40Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260420t180040z", + "runs": { + "hybrid-model-20260420t180040z": { + "analysis_id": "hybrid-model-20260420t180040z", + "artifacts": { + "hybrid": "snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260420T180040Z/analysis-runs/hybrid-model-20260420t180040z/manifest.json", + "model": null, + "published_at": "2026-04-20T18:14:36Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260420T180040Z", "watermark": {